diff --git a/deployment/bin/deploy b/deployment/bin/deploy old mode 100755 new mode 100644 index 3e3c2038..5926564a --- a/deployment/bin/deploy +++ b/deployment/bin/deploy @@ -136,6 +136,15 @@ if [ "${BASH_SOURCE[0]}" = "${0}" ]; then setup_helm + # Install namespaces + + echo "Installing namespaces..." + + helm upgrade --install \ + pc-namespaces helm/pc-namespaces \ + -n pc-namespaces \ + --create-namespace + # Install cert-manager echo "Installing cert-manager..." @@ -143,7 +152,6 @@ if [ "${BASH_SOURCE[0]}" = "${0}" ]; then helm upgrade --install \ cert-manager \ --namespace pc \ - --create-namespace \ --version v1.6.0 \ --set installCRDs=true jetstack/cert-manager @@ -193,6 +201,24 @@ if [ "${BASH_SOURCE[0]}" = "${0}" ]; then --wait \ --timeout 2m0s + echo "=====================" + echo "==== Prometheus =====" + echo "=====================" + + echo "Deploying prometheus crd..." + kubectl apply -f helm/prometheus-crd --server-side + + echo "Deploying prometheus component..." + kubectl apply -f helm/pc-apis-prometheus + + echo "===========================" + echo "==== Overprovisioning =====" + echo "===========================" + + helm upgrade --install overprovisioning helm/overprovisioning \ + --kube-context "${KUBE_CONTEXT}" \ + --wait \ + ######################### # Deploy Azure Function # ######################### diff --git a/deployment/helm/deploy-values.template.yaml b/deployment/helm/deploy-values.template.yaml index bf50966c..dc92be2b 100644 --- a/deployment/helm/deploy-values.template.yaml +++ b/deployment/helm/deploy-values.template.yaml @@ -102,10 +102,12 @@ pcingress: path: "/stac(/|$)(.*)" name: "planetary-computer-stac" port: "80" + blockMetrics: true tiler: path: "/data(/|$)(.*)" name: "planetary-computer-tiler" port: "80" + blockMetrics: true cert: secretName: "pqe-tls-secret" diff --git a/deployment/helm/overprovisioning/Chart.yaml b/deployment/helm/overprovisioning/Chart.yaml new file mode 100644 index 00000000..fc425c2a --- /dev/null +++ b/deployment/helm/overprovisioning/Chart.yaml @@ -0,0 +1,6 @@ +apiVersion: v2 +name: planetary-computer-stac +description: A Helm chart for the Overprovisioning virtual-nodes auxiliary +type: application +version: 0.1.1 +appVersion: 0.1.0 diff --git a/deployment/helm/overprovisioning/templates/overprovisioning.yaml b/deployment/helm/overprovisioning/templates/overprovisioning.yaml new file mode 100644 index 00000000..42524219 --- /dev/null +++ b/deployment/helm/overprovisioning/templates/overprovisioning.yaml @@ -0,0 +1,118 @@ +apiVersion: v1 +kind: Namespace +metadata: + name: {{ .Values.namespace }} +--- +apiVersion: scheduling.k8s.io/v1 +kind: PriorityClass +metadata: + name: overprovisioning +value: -10 +globalDefault: false +description: "Priority class used by overprovisioning." +--- +kind: ServiceAccount +apiVersion: v1 +metadata: + name: cluster-proportional-autoscaler-overprovision + namespace: {{ .Values.namespace }} +--- +kind: ClusterRole +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: cluster-proportional-autoscaler-overprovision +rules: + - apiGroups: [""] + resources: ["nodes"] + verbs: ["list", "watch"] + - apiGroups: [""] + resources: ["replicationcontrollers/scale"] + verbs: ["get", "update"] + - apiGroups: ["extensions","apps"] + resources: ["deployments/scale", "replicasets/scale"] + verbs: ["get", "update"] + - apiGroups: [""] + resources: ["configmaps"] + verbs: ["get", "create"] +--- +kind: ClusterRoleBinding +apiVersion: rbac.authorization.k8s.io/v1 +metadata: + name: cluster-proportional-autoscaler-overprovision +subjects: + - kind: ServiceAccount + name: cluster-proportional-autoscaler-overprovision + namespace: {{ .Values.namespace }} +roleRef: + kind: ClusterRole + name: cluster-proportional-autoscaler-overprovision + apiGroup: rbac.authorization.k8s.io +--- +apiVersion: apps/v1 +kind: Deployment +metadata: + name: overprovisioning + namespace: {{ .Values.namespace }} +spec: + replicas: 1 + selector: + matchLabels: + run: overprovisioning + template: + metadata: + labels: + run: overprovisioning + spec: + priorityClassName: overprovisioning + terminationGracePeriodSeconds: 0 + containers: + - name: reserve-resources + image: registry.k8s.io/pause:3.9 + resources: + {{- toYaml .Values.overprovision.deployment.resources | nindent 10 }} +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: overprovisioning-autoscaler + namespace: {{ .Values.namespace }} +data: + linear: |- + { + "coresPerReplica": {{ .Values.overprovision.hpa.coresPerReplica }}, + "nodesPerReplica": {{ .Values.overprovision.hpa.nodesPerReplica }}, + "min": {{ .Values.overprovision.hpa.minPods }}, + "max": {{ .Values.overprovision.hpa.maxPods }}, + "preventSinglePointFailure": {{ .Values.overprovision.hpa.preventSinglePointFailure }}, + "includeUnschedulableNodes": {{ .Values.overprovision.hpa.includeUnschedulableNodes }} + } +--- +apiVersion: apps/v1 +kind: Deployment +metadata: + name: overprovisioning-autoscaler + namespace: {{ .Values.namespace }} + labels: + app: overprovisioning-autoscaler +spec: + selector: + matchLabels: + app: overprovisioning-autoscaler + replicas: 1 + template: + metadata: + labels: + app: overprovisioning-autoscaler + spec: + containers: + - image: registry.k8s.io/cluster-proportional-autoscaler-amd64:1.8.1 + name: autoscaler + command: + - /cluster-proportional-autoscaler + - --namespace={{ .Values.namespace }} + - --configmap=overprovisioning-autoscaler + - --default-params={"linear":{"coresPerReplica":8,"nodesPerReplica":4,"preventSinglePointFailure":false,"includeUnschedulableNodes":true}} + - --target=deployment/overprovisioning + - --logtostderr=true + - --v=2 + serviceAccountName: cluster-proportional-autoscaler-overprovision diff --git a/deployment/helm/overprovisioning/values.yaml b/deployment/helm/overprovisioning/values.yaml new file mode 100644 index 00000000..b58c903c --- /dev/null +++ b/deployment/helm/overprovisioning/values.yaml @@ -0,0 +1,18 @@ +environment: "staging" +namespace: "overprovisioning" + +overprovision: + + deployment: + resources: + requests: + memory: "512Mi" + cpu: "400m" + + hpa: + coresPerReplica: 8 + nodesPerReplica: 4 + minPods: 1 + maxPods: 3 + preventSinglePointFailure: false + includeUnschedulableNodes: true \ No newline at end of file diff --git a/deployment/helm/pc-apis-ingress/templates/ingress.yaml b/deployment/helm/pc-apis-ingress/templates/ingress.yaml index 15718cf3..3e8994a0 100644 --- a/deployment/helm/pc-apis-ingress/templates/ingress.yaml +++ b/deployment/helm/pc-apis-ingress/templates/ingress.yaml @@ -13,6 +13,12 @@ metadata: {{- with .Values.pcingress.ingress.annotations }} annotations: {{- toYaml . | nindent 4 }} + {{- if .Values.pcingress.services.stac.blockMetrics -}} + nginx.ingress.kubernetes.io/server-snippet: | + if ($request_uri = {{ appRootPath }}/metrics) { + return 403; + } + {{- end }} {{- end }} spec: tls: diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-alertmanager.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-alertmanager.yaml new file mode 100644 index 00000000..c318ce52 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-alertmanager.yaml @@ -0,0 +1,36 @@ +apiVersion: monitoring.coreos.com/v1 +kind: Alertmanager +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: main + namespace: monitoring +spec: + image: quay.io/prometheus/alertmanager:v0.25.0 + nodeSelector: + kubernetes.io/os: linux + podMetadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + replicas: 3 + resources: + limits: + cpu: 100m + memory: 100Mi + requests: + cpu: 4m + memory: 100Mi + securityContext: + fsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + serviceAccountName: alertmanager-main + version: 0.25.0 diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-networkPolicy.yaml new file mode 100644 index 00000000..d84f4770 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-networkPolicy.yaml @@ -0,0 +1,42 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 9093 + protocol: TCP + - port: 8080 + protocol: TCP + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: alertmanager + ports: + - port: 9094 + protocol: TCP + - port: 9094 + protocol: UDP + podSelector: + matchLabels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-podDisruptionBudget.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-podDisruptionBudget.yaml new file mode 100644 index 00000000..85cae780 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-podDisruptionBudget.yaml @@ -0,0 +1,19 @@ +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring +spec: + maxUnavailable: 1 + selector: + matchLabels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-prometheusRule.yaml new file mode 100644 index 00000000..534bca21 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-prometheusRule.yaml @@ -0,0 +1,139 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + prometheus: k8s + role: alert-rules + name: alertmanager-main-rules + namespace: monitoring +spec: + groups: + - name: alertmanager.rules + rules: + - alert: AlertmanagerFailedReload + annotations: + description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedreload + summary: Reloading an Alertmanager configuration has failed. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_config_last_reload_successful{job="alertmanager-main",namespace="monitoring"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: AlertmanagerMembersInconsistent + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} has only found {{ $value }} members of the {{$labels.job}} cluster. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagermembersinconsistent + summary: A member of an Alertmanager cluster has not found all other cluster members. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m]) + < on (namespace,service) group_left + count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="alertmanager-main",namespace="monitoring"}[5m])) + for: 15m + labels: + severity: critical + - alert: AlertmanagerFailedToSendAlerts + annotations: + description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerfailedtosendalerts + summary: An Alertmanager instance failed to send notifications. + expr: | + ( + rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring"}[5m]) + / + rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring"}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration. + expr: | + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m]) + / + rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration=~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterFailedToSendAlerts + annotations: + description: The minimum notification failure rate to {{ $labels.integration }} sent from any instance in the {{$labels.job}} cluster is {{ $value | humanizePercentage }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterfailedtosendalerts + summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration. + expr: | + min by (namespace,service, integration) ( + rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m]) + / + rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring", integration!~`.*`}[5m]) + ) + > 0.01 + for: 5m + labels: + severity: warning + - alert: AlertmanagerConfigInconsistent + annotations: + description: Alertmanager instances within the {{$labels.job}} cluster have different configurations. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerconfiginconsistent + summary: Alertmanager instances within the same cluster have different configurations. + expr: | + count by (namespace,service) ( + count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="alertmanager-main",namespace="monitoring"}) + ) + != 1 + for: 20m + labels: + severity: critical + - alert: AlertmanagerClusterDown + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have been up for less than half of the last 5m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclusterdown + summary: Half or more of the Alertmanager instances within the same cluster are down. + expr: | + ( + count by (namespace,service) ( + avg_over_time(up{job="alertmanager-main",namespace="monitoring"}[5m]) < 0.5 + ) + / + count by (namespace,service) ( + up{job="alertmanager-main",namespace="monitoring"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical + - alert: AlertmanagerClusterCrashlooping + annotations: + description: '{{ $value | humanizePercentage }} of Alertmanager instances within the {{$labels.job}} cluster have restarted at least 5 times in the last 10m.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/alertmanager/alertmanagerclustercrashlooping + summary: Half or more of the Alertmanager instances within the same cluster are crashlooping. + expr: | + ( + count by (namespace,service) ( + changes(process_start_time_seconds{job="alertmanager-main",namespace="monitoring"}[10m]) > 4 + ) + / + count by (namespace,service) ( + up{job="alertmanager-main",namespace="monitoring"} + ) + ) + >= 0.5 + for: 5m + labels: + severity: critical diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-secret.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-secret.yaml new file mode 100644 index 00000000..54dfb43f --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-secret.yaml @@ -0,0 +1,59 @@ +apiVersion: v1 +kind: Secret +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring +stringData: + alertmanager.yaml: |- + "global": + "resolve_timeout": "5m" + "inhibit_rules": + - "equal": + - "namespace" + - "alertname" + "source_matchers": + - "severity = critical" + "target_matchers": + - "severity =~ warning|info" + - "equal": + - "namespace" + - "alertname" + "source_matchers": + - "severity = warning" + "target_matchers": + - "severity = info" + - "equal": + - "namespace" + "source_matchers": + - "alertname = InfoInhibitor" + "target_matchers": + - "severity = info" + "receivers": + - "name": "Default" + - "name": "Watchdog" + - "name": "Critical" + - "name": "null" + "route": + "group_by": + - "namespace" + "group_interval": "5m" + "group_wait": "30s" + "receiver": "Default" + "repeat_interval": "12h" + "routes": + - "matchers": + - "alertname = Watchdog" + "receiver": "Watchdog" + - "matchers": + - "alertname = InfoInhibitor" + "receiver": "null" + - "matchers": + - "severity = critical" + "receiver": "Critical" +type: Opaque diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-service.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-service.yaml new file mode 100644 index 00000000..33c960d0 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-service.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring +spec: + ports: + - name: web + port: 9093 + targetPort: web + - name: reloader-web + port: 8080 + targetPort: reloader-web + selector: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + sessionAffinity: ClientIP diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-serviceAccount.yaml new file mode 100644 index 00000000..dc2eb85e --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-serviceAccount.yaml @@ -0,0 +1,12 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/alertmanager-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/alertmanager-serviceMonitor.yaml new file mode 100644 index 00000000..492a9f04 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/alertmanager-serviceMonitor.yaml @@ -0,0 +1,23 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.25.0 + name: alertmanager-main + namespace: monitoring +spec: + endpoints: + - interval: 30s + port: web + - interval: 30s + port: reloader-web + selector: + matchLabels: + app.kubernetes.io/component: alert-router + app.kubernetes.io/instance: main + app.kubernetes.io/name: alertmanager + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRole.yaml new file mode 100644 index 00000000..c7824058 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRole.yaml @@ -0,0 +1,17 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + name: blackbox-exporter +rules: +- apiGroups: + - authentication.k8s.io + resources: + - tokenreviews + verbs: + - create +- apiGroups: + - authorization.k8s.io + resources: + - subjectaccessreviews + verbs: + - create diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRoleBinding.yaml new file mode 100644 index 00000000..1247e61b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-clusterRoleBinding.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: blackbox-exporter +subjects: +- kind: ServiceAccount + name: blackbox-exporter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-configuration.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-configuration.yaml new file mode 100644 index 00000000..a7407954 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-configuration.yaml @@ -0,0 +1,51 @@ +apiVersion: v1 +data: + config.yml: |- + "modules": + "http_2xx": + "http": + "preferred_ip_protocol": "ip4" + "prober": "http" + "http_post_2xx": + "http": + "method": "POST" + "preferred_ip_protocol": "ip4" + "prober": "http" + "irc_banner": + "prober": "tcp" + "tcp": + "preferred_ip_protocol": "ip4" + "query_response": + - "send": "NICK prober" + - "send": "USER prober prober prober :prober" + - "expect": "PING :([^ ]+)" + "send": "PONG ${1}" + - "expect": "^:[^ ]+ 001" + "pop3s_banner": + "prober": "tcp" + "tcp": + "preferred_ip_protocol": "ip4" + "query_response": + - "expect": "^+OK" + "tls": true + "tls_config": + "insecure_skip_verify": false + "ssh_banner": + "prober": "tcp" + "tcp": + "preferred_ip_protocol": "ip4" + "query_response": + - "expect": "^SSH-2.0-" + "tcp_connect": + "prober": "tcp" + "tcp": + "preferred_ip_protocol": "ip4" +kind: ConfigMap +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter-configuration + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-deployment.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-deployment.yaml new file mode 100644 index 00000000..93cbae33 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-deployment.yaml @@ -0,0 +1,115 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring +spec: + replicas: 1 + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + template: + metadata: + annotations: + kubectl.kubernetes.io/default-container: blackbox-exporter + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + spec: + automountServiceAccountToken: true + containers: + - args: + - --config.file=/etc/blackbox_exporter/config.yml + - --web.listen-address=:19115 + image: quay.io/prometheus/blackbox-exporter:v0.24.0 + name: blackbox-exporter + ports: + - containerPort: 19115 + name: http + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 65534 + volumeMounts: + - mountPath: /etc/blackbox_exporter/ + name: config + readOnly: true + - args: + - --webhook-url=http://localhost:19115/-/reload + - --volume-dir=/etc/blackbox_exporter/ + image: jimmidyson/configmap-reload:v0.5.0 + name: module-configmap-reloader + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 65534 + terminationMessagePath: /dev/termination-log + terminationMessagePolicy: FallbackToLogsOnError + volumeMounts: + - mountPath: /etc/blackbox_exporter/ + name: config + readOnly: true + - args: + - --logtostderr + - --secure-listen-address=:9115 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 + - --upstream=http://127.0.0.1:19115/ + image: quay.io/brancz/kube-rbac-proxy:v0.14.2 + name: kube-rbac-proxy + ports: + - containerPort: 9115 + name: https + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsGroup: 65532 + runAsNonRoot: true + runAsUser: 65532 + nodeSelector: + kubernetes.io/os: linux + serviceAccountName: blackbox-exporter + volumes: + - configMap: + name: blackbox-exporter-configuration + name: config diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-networkPolicy.yaml new file mode 100644 index 00000000..bf15eb4f --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-networkPolicy.yaml @@ -0,0 +1,31 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 9115 + protocol: TCP + - port: 19115 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-service.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-service.yaml new file mode 100644 index 00000000..e9e0aaf8 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-service.yaml @@ -0,0 +1,22 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring +spec: + ports: + - name: https + port: 9115 + targetPort: https + - name: probe + port: 19115 + targetPort: http + selector: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceAccount.yaml new file mode 100644 index 00000000..dfd5ac36 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceMonitor.yaml new file mode 100644 index 00000000..64c78d27 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/blackboxExporter-serviceMonitor.yaml @@ -0,0 +1,24 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.24.0 + name: blackbox-exporter + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + path: /metrics + port: https + scheme: https + tlsConfig: + insecureSkipVerify: true + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: blackbox-exporter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/grafana-config.yaml b/deployment/helm/pc-apis-prometheus/grafana-config.yaml new file mode 100644 index 00000000..9c491c39 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-config.yaml @@ -0,0 +1,15 @@ +apiVersion: v1 +kind: Secret +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-config + namespace: monitoring +stringData: + grafana.ini: | + [date_formats] + default_timezone = UTC +type: Opaque diff --git a/deployment/helm/pc-apis-prometheus/grafana-dashboardDatasources.yaml b/deployment/helm/pc-apis-prometheus/grafana-dashboardDatasources.yaml new file mode 100644 index 00000000..ab12c33d --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-dashboardDatasources.yaml @@ -0,0 +1,27 @@ +apiVersion: v1 +kind: Secret +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-datasources + namespace: monitoring +stringData: + datasources.yaml: |- + { + "apiVersion": 1, + "datasources": [ + { + "access": "proxy", + "editable": false, + "name": "prometheus", + "orgId": 1, + "type": "prometheus", + "url": "http://prometheus-k8s.monitoring.svc:9090", + "version": 1 + } + ] + } +type: Opaque diff --git a/deployment/helm/pc-apis-prometheus/grafana-dashboardDefinitions.yaml b/deployment/helm/pc-apis-prometheus/grafana-dashboardDefinitions.yaml new file mode 100644 index 00000000..3cd8cda6 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-dashboardDefinitions.yaml @@ -0,0 +1,39076 @@ +apiVersion: v1 +items: +- apiVersion: v1 + data: + alertmanager-overview.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "current set of alerts stored in the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(alertmanager_alerts{namespace=~\"$namespace\",service=~\"$service\"}) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Alerts", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "rate of successful and invalid alerts received by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(alertmanager_alerts_received_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Received", + "refId": "A" + }, + { + "expr": "sum(rate(alertmanager_alerts_invalid_total{namespace=~\"$namespace\",service=~\"$service\"}[$__rate_interval])) by (namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Invalid", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Alerts receive rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Alerts", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "rate of successful and invalid notifications sent by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "integration", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(alertmanager_notifications_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Total", + "refId": "A" + }, + { + "expr": "sum(rate(alertmanager_notifications_failed_total{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (integration,namespace,service,instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Failed", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "$integration: Notifications Send Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "latency of notifications sent by the Alertmanager", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": "integration", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} 99th Percentile", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.50,\n sum(rate(alertmanager_notification_latency_seconds_bucket{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (le,namespace,service,instance)\n) \n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Median", + "refId": "B" + }, + { + "expr": "sum(rate(alertmanager_notification_latency_seconds_sum{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n/\nsum(rate(alertmanager_notification_latency_seconds_count{namespace=~\"$namespace\",service=~\"$service\", integration=\"$integration\"}[$__rate_interval])) by (namespace,service,instance)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Average", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "$integration: Notification Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Notifications", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "alertmanager-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "Prometheus", + "value": "Prometheus" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(alertmanager_alerts, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "service", + "multi": false, + "name": "service", + "options": [ + + ], + "query": "label_values(alertmanager_alerts, service)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "all", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": true, + "label": null, + "multi": false, + "name": "integration", + "options": [ + + ], + "query": "label_values(alertmanager_notifications_total{integration=~\".*\"}, integration)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Alertmanager / Overview", + "uid": "alertmanager-overview", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-alertmanager-overview + namespace: monitoring +- apiVersion: v1 + data: + apiserver.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.", + "datasource": null, + "description": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.", + "gridPos": { + "h": 2, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "mode": "markdown", + "span": 12, + "title": "Notice", + "type": "text" + } + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 4, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Availability (30d) > 99.000%", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": 3, + "description": "How much error budget is left looking at our 0.990% availability guarantees?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "errorbudget", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ErrorBudget (30d) > 99.000%", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "decimals": 3, + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "decimals": 3, + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Read Availability (30d)", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many read requests (LIST,GET) per second do the apiservers get by code?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/2../i", + "color": "#56A64B" + }, + { + "alias": "/3../i", + "color": "#F2CC0C" + }, + { + "alias": "/4../i", + "color": "#3274D9" + }, + { + "alias": "/5../i", + "color": "#E02F44" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ code }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Requests", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Errors", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many seconds is the 99th percentile for reading (LIST|GET) a given resource?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Read SLI - Duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 3, + "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?", + "format": "percentunit", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Write Availability (30d)", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "avg" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/2../i", + "color": "#56A64B" + }, + { + "alias": "/3../i", + "color": "#F2CC0C" + }, + { + "alias": "/4../i", + "color": "#3274D9" + }, + { + "alias": "/5../i", + "color": "#E02F44" + } + ], + "spaceLength": 10, + "span": 3, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ code }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Requests", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Errors", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ resource }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Write SLI - Duration", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Add Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Depth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 17, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"apiserver\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / API server", + "uid": "09ec8aa1e996d6ffcd6817bbaff4db1b", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-apiserver + namespace: monitoring +- apiVersion: v1 + data: + cluster-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "Value #G", + "value": "Value #G" + }, + { + "text": "Value #H", + "value": "Value #H" + }, + { + "text": "namespace", + "value": "namespace" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?orgId=1&refresh=30s&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth History", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 31 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 50 + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{namespace}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + { + "targetBlank": true, + "title": "What is TCP Retransmit?", + "url": "https://accedian.com/enterprises/blog/network-packet-loss-retransmissions-and-duplicate-acknowledgements/" + } + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of TCP Retransmits out of all sent segments", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 59 + }, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 2, + "links": [ + { + "targetBlank": true, + "title": "Why monitor SYN retransmits?", + "url": "https://github.com/prometheus/node_exporter/issues/1023#issuecomment-408128365" + } + ], + "minSpan": 24, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{instance}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of TCP SYN Retransmits out of all retransmits", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Cluster", + "uid": "ff635a025bcfea7bc3dd4f508990a3e9", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-cluster-total + namespace: monitoring +- apiVersion: v1 + data: + controller-manager.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"kube-controller-manager\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Add Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Depth", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} {{name}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Work Queue Latency", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-controller-manager\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Controller Manager", + "uid": "72e0e05bef5099e5f049b05fdc429ed4", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-controller-manager + namespace: monitoring +- apiVersion: v1 + data: + grafana-overview.json: |- + { + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "target": { + "limit": 100, + "matchAny": false, + "tags": [ + + ], + "type": "dashboard" + }, + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "id": 3085, + "iteration": 1631554945276, + "links": [ + + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "mappings": [ + + ], + "noValue": "0", + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 6, + "x": 0, + "y": 0 + }, + "id": 6, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": { + + }, + "textMode": "auto" + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "grafana_alerting_result_total{job=~\"$job\", instance=~\"$instance\", state=\"alerting\"}", + "instant": true, + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Firing Alerts", + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 6, + "x": 6, + "y": 0 + }, + "id": 8, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "mean" + ], + "fields": "", + "values": false + }, + "text": { + + }, + "textMode": "auto" + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "sum(grafana_stat_totals_dashboard{job=~\"$job\", instance=~\"$instance\"})", + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Dashboards", + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + "align": null, + "displayMode": "auto" + }, + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": null + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + + ] + }, + "gridPos": { + "h": 5, + "w": 12, + "x": 12, + "y": 0 + }, + "id": 10, + "options": { + "showHeader": true + }, + "pluginVersion": "8.1.3", + "targets": [ + { + "expr": "grafana_build_info{job=~\"$job\", instance=~\"$instance\"}", + "instant": true, + "interval": "", + "legendFormat": "", + "refId": "A" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Build Info", + "transformations": [ + { + "id": "labelsToFields", + "options": { + + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + "Time": true, + "Value": true, + "branch": true, + "container": true, + "goversion": true, + "namespace": true, + "pod": true, + "revision": true + }, + "indexByName": { + "Time": 7, + "Value": 11, + "branch": 4, + "container": 8, + "edition": 2, + "goversion": 6, + "instance": 1, + "job": 0, + "namespace": 9, + "pod": 10, + "revision": 5, + "version": 3 + }, + "renameByName": { + + } + } + } + ], + "type": "table" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ] + }, + "overrides": [ + + ] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 0, + "y": 5 + }, + "hiddenSeries": false, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.1.3", + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (status_code) (irate(grafana_http_request_duration_seconds_count{job=~\"$job\", instance=~\"$instance\"}[1m])) ", + "interval": "", + "legendFormat": "{{status_code}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeRegions": [ + + ], + "timeShift": null, + "title": "RPS", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "$$hashKey": "object:157", + "format": "reqps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:158", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ] + }, + "overrides": [ + + ] + }, + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 8, + "w": 12, + "x": 12, + "y": 5 + }, + "hiddenSeries": false, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "nullPointMode": "null", + "options": { + "alertThreshold": true + }, + "percentage": false, + "pluginVersion": "8.1.3", + "pointradius": 2, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "exemplar": true, + "expr": "histogram_quantile(0.99, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1", + "interval": "", + "legendFormat": "99th Percentile", + "refId": "A" + }, + { + "exemplar": true, + "expr": "histogram_quantile(0.50, sum(irate(grafana_http_request_duration_seconds_bucket{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) by (le)) * 1", + "interval": "", + "legendFormat": "50th Percentile", + "refId": "B" + }, + { + "exemplar": true, + "expr": "sum(irate(grafana_http_request_duration_seconds_sum{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval])) * 1 / sum(irate(grafana_http_request_duration_seconds_count{instance=~\"$instance\", job=~\"$job\"}[$__rate_interval]))", + "interval": "", + "legendFormat": "Average", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeRegions": [ + + ], + "timeShift": null, + "title": "Request Latency", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "$$hashKey": "object:210", + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "$$hashKey": "object:211", + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ], + "yaxis": { + "align": false, + "alignLevel": null + } + } + ], + "schemaVersion": 30, + "style": "dark", + "tags": [ + + ], + "templating": { + "list": [ + { + "current": { + "selected": true, + "text": "dev-cortex", + "value": "dev-cortex" + }, + "description": null, + "error": null, + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "queryValue": "", + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "type": "datasource" + }, + { + "allValue": ".*", + "current": { + "selected": false, + "text": [ + "default/grafana" + ], + "value": [ + "default/grafana" + ] + }, + "datasource": "$datasource", + "definition": "label_values(grafana_build_info, job)", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "job", + "options": [ + + ], + "query": { + "query": "label_values(grafana_build_info, job)", + "refId": "Billing Admin-job-Variable-Query" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".*", + "current": { + "selected": false, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "definition": "label_values(grafana_build_info, instance)", + "description": null, + "error": null, + "hide": 0, + "includeAll": true, + "label": null, + "multi": true, + "name": "instance", + "options": [ + + ], + "query": { + "query": "label_values(grafana_build_info, instance)", + "refId": "Billing Admin-instance-Variable-Query" + }, + "refresh": 1, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ] + }, + "timezone": "", + "title": "Grafana Overview", + "uid": "6be0s85Mk", + "version": 2 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-grafana-overview + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-cluster.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Requests Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Limits Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Requests Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Limits Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to workloads", + "linkUrl": "/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workloads", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to workloads", + "linkUrl": "/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Requests by Namespace", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Requests", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Namespace: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Namespace", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 19, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 20, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 21, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{namespace}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 22, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Namespace", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell", + "pattern": "namespace", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Cluster", + "uid": "efa86fd1d0c121a26444b636a3f509a8", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-cluster + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-multicluster.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "cluster:node_cpu:ratio_rate5m", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Requests Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"cpu\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Limits Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "1 - sum(:node_memory_MemAvailable_bytes:sum) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Requests Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 2, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\", resource=\"memory\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Limits Commitment", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/efa86fd1d0c121a26444b636a3f509a8/k8s-resources-cluster?var-datasource=$datasource&var-cluster=$__cell", + "pattern": "cluster", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"cpu\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Cluster", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/efa86fd1d0c121a26444b636a3f509a8/k8s-resources-cluster?var-datasource=$datasource&var-cluster=$__cell", + "pattern": "cluster", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\"}) by (cluster) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", resource=\"memory\"}) by (cluster)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Requests by Cluster", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Requests", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Multi-Cluster", + "uid": "b59e6c9f2fcbe2e16d77fc492374cc4f", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-multicluster + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "100px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation (from requests)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation (from limits)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation (from requests)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "format": "percentunit", + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})", + "format": "time_series", + "instant": true, + "intervalFactor": 2, + "refId": "A" + } + ], + "thresholds": "70,80", + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation (from limits)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "singlestat", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Headlines", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 17, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 18, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Namespace (Pods)", + "uid": "85a562078cdf77779eaa1add43ccec1e", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-namespace + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-node.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "max capacity", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "max capacity", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "max capacity", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "max capacity", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (w/o cache)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": true, + "name": "node", + "options": [ + + ], + "query": "label_values(kube_node_info{cluster=\"$cluster\"}, node)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Node (Pods)", + "uid": "200ac8fdbfbb74b39aff88118e4d1c2c", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-node + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-pod.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "requests", + "color": "#F2495C", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{container}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": true, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{container}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + { + "colorMode": "critical", + "fill": true, + "line": true, + "op": "gt", + "value": 0.25, + "yaxis": "left" + } + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Throttling", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Throttling", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{container}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage (WSS)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage (WSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Usage (RSS)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Cache)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Usage (Swap)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sum(container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sum(container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reads", + "legendLink": null, + "step": 10 + }, + { + "expr": "ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writes", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Reads", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Writes", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution(Pod - Read & Writes)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "decimals": -1, + "fill": 10, + "id": 14, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{container}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "IOPS(Reads+Writes)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 15, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{container}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "ThroughPut(Read+Write)", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution(Containers)", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 16, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "sort": { + "col": 4, + "desc": true + }, + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "IOPS(Reads)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "IOPS(Reads + Writes)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": -1, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Throughput(Read)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Throughput(Read + Write)", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Container", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "container", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\",device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Storage IO", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage IO - Distribution", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Pod", + "uid": "6581e46e4e5c7ba40a07646395ef7b23", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-pod + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-workload.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Pod: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Pod", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{pod}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}, workload)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Workload", + "uid": "a164a7f0339f99e89cea5cb47e9be617", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-workload + namespace: monitoring +- apiVersion: v1 + data: + k8s-resources-workloads-namespace.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 1, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}} - {{workload_type}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "CPU Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "CPU Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + { + "alias": "quota - requests", + "color": "#F2495C", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + }, + { + "alias": "quota - limits", + "color": "#FF9830", + "dashes": true, + "fill": 0, + "hiddenSeries": true, + "hideTooltip": true, + "legend": true, + "linewidth": 2, + "stack": false + } + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}} - {{workload_type}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - requests", + "legendLink": null, + "step": 10 + }, + { + "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "quota - limits", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Running Pods", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 0, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Memory Usage", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Requests %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Memory Limits", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "bytes" + }, + { + "alias": "Memory Limits %", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "percentunit" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(\n container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Quota", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory Quota", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Current Receive Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Transmit Bandwidth", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTargetBlank": false, + "linkTooltip": "Drill down to pods", + "linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Workload Type", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "workload_type", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Network Usage", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Network Usage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Received", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Container Bandwidth by Workload: Transmitted", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Container Bandwidth by Workload", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 13, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{workload}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": false, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Rate of Packets Dropped", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Compute Resources / Namespace (Workloads)", + "uid": "a87fb0d919ec0ea5f6543124e16c42a5", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-k8s-resources-workloads-namespace + namespace: monitoring +- apiVersion: v1 + data: + kubelet.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 0, + "y": 0 + }, + "id": 2, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "title": "Running Kubelets", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 4, + "y": 0 + }, + "id": 3, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Running Pods", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 8, + "y": 0 + }, + "id": 4, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Running Containers", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 12, + "y": 0 + }, + "id": 5, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\", state=\"actual_state_of_world\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Actual Volume Count", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 16, + "y": 0 + }, + "id": 6, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",state=\"desired_state_of_world\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Desired Volume Count", + "transparent": false, + "type": "stat" + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "links": [ + + ], + "mappings": [ + + ], + "thresholds": { + "mode": "absolute", + "steps": [ + + ] + }, + "unit": "none" + } + }, + "gridPos": { + "h": 7, + "w": 4, + "x": 20, + "y": 0 + }, + "id": 7, + "links": [ + + ], + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "textMode": "auto" + }, + "pluginVersion": "7", + "targets": [ + { + "expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "title": "Config Error Count", + "transparent": false, + "type": "stat" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 7 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_type}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 7 + }, + "id": 9, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_type}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation Error Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 14 + }, + "id": 10, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_type}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Operation duration 99th quantile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 21 + }, + "id": 11, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} pod", + "refId": "A" + }, + { + "expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 21 + }, + "id": 12, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} pod", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} worker", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pod Start Duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 28 + }, + "id": 13, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 28 + }, + "id": 14, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Error Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 35 + }, + "id": 15, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Storage Operation Duration 99th quantile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 42 + }, + "id": 16, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{operation_type}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Cgroup manager operation rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 42 + }, + "id": 17, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{operation_type}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Cgroup manager 99th quantile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Pod lifecycle event generator", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 0, + "y": 49 + }, + "id": 18, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 12, + "x": 12, + "y": 49 + }, + "id": 19, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist interval", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 56 + }, + "id": 20, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "PLEG relist duration", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 63 + }, + "id": 21, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "RPC Rate", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 24, + "x": 0, + "y": 70 + }, + "id": 22, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Request duration 99th quantile", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 0, + "y": 77 + }, + "id": 23, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 8, + "y": 77 + }, + "id": 24, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + "h": 7, + "w": 8, + "x": 16, + "y": 77 + }, + "id": 25, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\", metrics_path=\"/metrics\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics\",cluster=\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Kubelet", + "uid": "3138fa155d5915769fbded898ac09fd9", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-kubelet + namespace: monitoring +- apiVersion: v1 + data: + namespace-by-pod.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "pod", + "value": "pod" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "100%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Pod", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell", + "pattern": "pod", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 30 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 30 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 30 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Namespace (Pods)", + "uid": "8b7a8b326d7a6f1f04244066368c67af", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-namespace-by-pod + namespace: monitoring +- apiVersion: v1 + data: + namespace-by-workload.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ workload }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ workload }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "columns": [ + { + "text": "Time", + "value": "Time" + }, + { + "text": "Value #A", + "value": "Value #A" + }, + { + "text": "Value #B", + "value": "Value #B" + }, + { + "text": "Value #C", + "value": "Value #C" + }, + { + "text": "Value #D", + "value": "Value #D" + }, + { + "text": "Value #E", + "value": "Value #E" + }, + { + "text": "Value #F", + "value": "Value #F" + }, + { + "text": "Value #G", + "value": "Value #G" + }, + { + "text": "Value #H", + "value": "Value #H" + }, + { + "text": "workload", + "value": "workload" + } + ], + "datasource": "$datasource", + "fill": 1, + "fontSize": "90%", + "gridPos": { + "h": 9, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null as zero", + "renderer": "flot", + "scroll": true, + "showHeader": true, + "sort": { + "col": 0, + "desc": false + }, + "spaceLength": 10, + "span": 24, + "styles": [ + { + "alias": "Time", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Time", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Current Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Current Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Received", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #C", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Average Bandwidth Transmitted", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #D", + "thresholds": [ + + ], + "type": "number", + "unit": "Bps" + }, + { + "alias": "Rate of Received Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #E", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #F", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Received Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #G", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Rate of Transmitted Packets Dropped", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #H", + "thresholds": [ + + ], + "type": "number", + "unit": "pps" + }, + { + "alias": "Workload", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": true, + "linkTooltip": "Drill down", + "linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell", + "pattern": "workload", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + } + ], + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "C", + "step": 10 + }, + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "D", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "E", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "F", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "G", + "step": 10 + }, + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "H", + "step": 10 + } + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Status", + "type": "table" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 19 + }, + "id": 6, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 20 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ workload }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 20 + }, + "id": 8, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ workload }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 29 + }, + "id": 9, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 38 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 38 + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 39 + }, + "id": 12, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 40 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 40 + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 40 + }, + "id": 15, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 41 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 41 + }, + "id": 17, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{workload}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Namespace (Workload)", + "uid": "bbb2a765a623ae38130206c7d94a160f", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-namespace-by-workload + namespace: monitoring +- apiVersion: v1 + data: + node-cluster-rsrc-use.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "((\n instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n *\n instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}\n) != 0 )\n/ scalar(sum(instance:node_num_cpu:sum{job=\"node-exporter\", cluster=\"$cluster\"}))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{ instance }}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_load1_per_cpu:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1 per CPU)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance:node_memory_utilisation:ratio{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/ Receive/", + "stack": "A" + }, + { + "alias": "/ Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Saturation (Drops Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}\n / scalar(count(instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", cluster=\"$cluster\"}))\n) != 0\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}} {{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without (device) (\n max without (fstype, mountpoint) ((\n node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n -\n node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"}\n ) != 0)\n)\n/ scalar(sum(max without (fstype, mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", mountpoint!=\"\", cluster=\"$cluster\"})))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(node_time_seconds, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Node Exporter / USE Method / Cluster", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-node-cluster-rsrc-use + namespace: monitoring +- apiVersion: v1 + data: + node-rsrc-use.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_cpu_utilisation:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_load1_per_cpu:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Saturation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Saturation (Load1 per CPU)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_memory_utilisation:ratio{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Utilisation", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_vmstat_pgmajfault:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Major page Faults", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Saturation (Major Page Faults)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "rds", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/Receive/", + "stack": "A" + }, + { + "alias": "/Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_bytes_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Utilisation (Bytes Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/ Receive/", + "stack": "A" + }, + { + "alias": "/ Transmit/", + "stack": "B", + "transform": "negative-Y" + } + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance:node_network_receive_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Receive", + "refId": "A" + }, + { + "expr": "instance:node_network_transmit_drop_excluding_lo:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Transmit", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Saturation (Drops Receive/Transmit)", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "instance_device:node_disk_io_time_weighted_seconds:rate5m{job=\"node-exporter\", instance=\"$instance\", cluster=\"$cluster\"} != 0", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk IO Saturation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk IO", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": false, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(1 -\n (\n max without (mountpoint, fstype) (node_filesystem_avail_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n /\n max without (mountpoint, fstype) (node_filesystem_size_bytes{job=\"node-exporter\", fstype!=\"\", instance=\"$instance\", cluster=\"$cluster\"})\n ) != 0\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk Space Utilisation", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk Space", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(node_time_seconds, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_exporter_build_info{job=\"node-exporter\", cluster=\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Node Exporter / USE Method / Node", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-node-rsrc-use + namespace: monitoring +- apiVersion: v1 + data: + nodes-darwin.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "intervalFactor": 5, + "legendFormat": "{{cpu}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_load1{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "1m load average", + "refId": "A" + }, + { + "expr": "node_load5{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5m load average", + "refId": "B" + }, + { + "expr": "node_load15{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "15m load average", + "refId": "C" + }, + { + "expr": "count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Load Average", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Physical Memory", + "refId": "A" + }, + { + "expr": "(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"} +\n node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Memory Used", + "refId": "B" + }, + { + "expr": "(\n node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"} -\n node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "App Memory", + "refId": "C" + }, + { + "expr": "node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Wired Memory", + "refId": "D" + }, + { + "expr": "node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Compressed", + "refId": "E" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)" + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + } + }, + "gridPos": { + + }, + "id": 5, + "span": 3, + "targets": [ + { + "expr": "(\n (\n avg(node_memory_internal_bytes{job=\"node-exporter\", instance=\"$instance\"}) -\n avg(node_memory_purgeable_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_wired_bytes{job=\"node-exporter\", instance=\"$instance\"}) +\n avg(node_memory_compressed_bytes{job=\"node-exporter\", instance=\"$instance\"})\n ) /\n avg(node_memory_total_bytes{job=\"node-exporter\", instance=\"$instance\"})\n)\n*\n100\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Memory Usage", + "transparent": false, + "type": "gauge" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/ read| written/", + "yaxis": 1 + }, + { + "alias": "/ io time/", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} read", + "refId": "A" + }, + { + "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} written", + "refId": "B" + }, + { + "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "yellow", + "value": 0.8 + }, + { + "color": "red", + "value": 0.9 + } + ] + }, + "unit": "decbytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Mounted on" + }, + "properties": [ + { + "id": "custom.width", + "value": 260 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Size" + }, + "properties": [ + { + "id": "custom.width", + "value": 93 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used" + }, + "properties": [ + { + "id": "custom.width", + "value": 72 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Available" + }, + "properties": [ + { + "id": "custom.width", + "value": 88 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used, %" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "custom.displayMode", + "value": "gradient-gauge" + }, + { + "id": "max", + "value": 1 + }, + { + "id": "min", + "value": 0 + } + ] + } + ] + }, + "gridPos": { + + }, + "id": 7, + "span": 6, + "targets": [ + { + "expr": "max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + }, + { + "expr": "max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Disk Space Usage", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "Value #A": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "Value #B": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "mountpoint": { + "aggregations": [ + + ], + "operation": "groupby" + } + } + } + }, + { + "id": "merge", + "options": { + + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used", + "binary": { + "left": "Value #A (lastNotNull)", + "operator": "-", + "reducer": "sum", + "right": "Value #B (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used, %", + "binary": { + "left": "Used", + "operator": "/", + "reducer": "sum", + "right": "Value #A (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + + }, + "indexByName": { + + }, + "renameByName": { + "Value #A (lastNotNull)": "Size", + "Value #B (lastNotNull)": "Available", + "mountpoint": "Mounted on" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { + + }, + "sort": [ + { + "field": "Mounted on" + } + ] + } + } + ], + "transparent": false, + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network received (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network transmitted (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_uname_info{job=\"node-exporter\", sysname=\"Darwin\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Node Exporter / MacOS", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-nodes-darwin + namespace: monitoring +- apiVersion: v1 + data: + nodes.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 1, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "30s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n", + "format": "time_series", + "intervalFactor": 5, + "legendFormat": "{{cpu}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": 1, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "node_load1{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "1m load average", + "refId": "A" + }, + { + "expr": "node_load5{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5m load average", + "refId": "B" + }, + { + "expr": "node_load15{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "15m load average", + "refId": "C" + }, + { + "expr": "count(node_cpu_seconds_total{job=\"node-exporter\", instance=\"$instance\", mode=\"idle\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "logical cores", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Load Average", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "CPU", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}\n-\n node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory used", + "refId": "A" + }, + { + "expr": "node_memory_Buffers_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory buffers", + "refId": "B" + }, + { + "expr": "node_memory_Cached_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory cached", + "refId": "C" + }, + { + "expr": "node_memory_MemFree_bytes{job=\"node-exporter\", instance=\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "memory free", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory Usage", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "max": 100, + "min": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "rgba(50, 172, 45, 0.97)" + }, + { + "color": "rgba(237, 129, 40, 0.89)", + "value": 80 + }, + { + "color": "rgba(245, 54, 54, 0.9)", + "value": 90 + } + ] + }, + "unit": "percent" + } + }, + "gridPos": { + + }, + "id": 5, + "span": 3, + "targets": [ + { + "expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}) /\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Memory Usage", + "transparent": false, + "type": "gauge" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Memory", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + { + "alias": "/ read| written/", + "yaxis": 1 + }, + { + "alias": "/ io time/", + "yaxis": 2 + } + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} read", + "refId": "A" + }, + { + "expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} written", + "refId": "B" + }, + { + "expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device=~\"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}} io time", + "refId": "C" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Disk I/O", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "percentunit", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "datasource": "$datasource", + "fieldConfig": { + "defaults": { + "custom": { + + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green" + }, + { + "color": "yellow", + "value": 0.8 + }, + { + "color": "red", + "value": 0.9 + } + ] + }, + "unit": "decbytes" + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "Mounted on" + }, + "properties": [ + { + "id": "custom.width", + "value": 260 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Size" + }, + "properties": [ + { + "id": "custom.width", + "value": 93 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used" + }, + "properties": [ + { + "id": "custom.width", + "value": 72 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Available" + }, + "properties": [ + { + "id": "custom.width", + "value": 88 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "Used, %" + }, + "properties": [ + { + "id": "unit", + "value": "percentunit" + }, + { + "id": "custom.displayMode", + "value": "gradient-gauge" + }, + { + "id": "max", + "value": 1 + }, + { + "id": "min", + "value": 0 + } + ] + } + ] + }, + "gridPos": { + + }, + "id": 7, + "span": 6, + "targets": [ + { + "expr": "max by (mountpoint) (node_filesystem_size_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + }, + { + "expr": "max by (mountpoint) (node_filesystem_avail_bytes{job=\"node-exporter\", instance=\"$instance\", fstype!=\"\", mountpoint!=\"\"})\n", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "" + } + ], + "title": "Disk Space Usage", + "transformations": [ + { + "id": "groupBy", + "options": { + "fields": { + "Value #A": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "Value #B": { + "aggregations": [ + "lastNotNull" + ], + "operation": "aggregate" + }, + "mountpoint": { + "aggregations": [ + + ], + "operation": "groupby" + } + } + } + }, + { + "id": "merge", + "options": { + + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used", + "binary": { + "left": "Value #A (lastNotNull)", + "operator": "-", + "reducer": "sum", + "right": "Value #B (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "calculateField", + "options": { + "alias": "Used, %", + "binary": { + "left": "Used", + "operator": "/", + "reducer": "sum", + "right": "Value #A (lastNotNull)" + }, + "mode": "binary", + "reduce": { + "reducer": "sum" + } + } + }, + { + "id": "organize", + "options": { + "excludeByName": { + + }, + "indexByName": { + + }, + "renameByName": { + "Value #A (lastNotNull)": "Size", + "Value #B (lastNotNull)": "Available", + "mountpoint": "Mounted on" + } + } + }, + { + "id": "sortBy", + "options": { + "fields": { + + }, + "sort": [ + { + "field": "Mounted on" + } + ] + } + } + ], + "transparent": false, + "type": "table" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Disk", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network received (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Received", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "description": "Network transmitted (bits/s)", + "fill": 0, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval]) * 8", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{device}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Transmitted", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Network", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "node-exporter-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Instance", + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(node_uname_info{job=\"node-exporter\", sysname!=\"Darwin\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Node Exporter / Nodes", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-nodes + namespace: monitoring +- apiVersion: v1 + data: + persistentvolumesusage.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used Space", + "refId": "A" + }, + { + "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Free Space", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume Space Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume Space Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": true, + "current": true, + "max": true, + "min": true, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 9, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "Used inodes", + "refId": "A" + }, + { + "expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": " Free inodes", + "refId": "B" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Volume inodes Usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "rgba(50, 172, 45, 0.97)", + "rgba(237, 129, 40, 0.89)", + "rgba(245, 54, 54, 0.9)" + ], + "datasource": "$datasource", + "format": "percent", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": true, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 3, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "80, 90", + "title": "Volume inodes Usage", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "Namespace", + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\"}, namespace)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "PersistentVolumeClaim", + "multi": false, + "name": "volume", + "options": [ + + ], + "query": "label_values(kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", metrics_path=\"/metrics\", namespace=\"$namespace\"}, persistentvolumeclaim)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-7d", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Persistent Volumes", + "uid": "919b92a8e8041bd567af9edab12c840c", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-persistentvolumesusage + namespace: monitoring +- apiVersion: v1 + data: + pod-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "height": 9, + "id": 3, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "decimals": 0, + "format": "time_series", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "height": 9, + "id": 4, + "interval": null, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "minSpan": 12, + "nullPointMode": "connected", + "nullText": null, + "options": { + "fieldOptions": { + "calcs": [ + "last" + ], + "defaults": { + "max": 10000000000, + "min": 0, + "title": "$namespace: $pod", + "unit": "Bps" + }, + "mappings": [ + + ], + "override": { + + }, + "thresholds": [ + { + "color": "dark-green", + "index": 0, + "value": null + }, + { + "color": "dark-yellow", + "index": 1, + "value": 5000000000 + }, + { + "color": "dark-red", + "index": 2, + "value": 7000000000 + } + ], + "values": false + } + }, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 12, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))", + "format": "time_series", + "instant": null, + "intervalFactor": 1, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "type": "gauge", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "current" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 20 + }, + "id": 8, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 21 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 21 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 0, + "y": 32 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 10, + "w": 12, + "x": 12, + "y": 32 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "pod", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Pod", + "uid": "7a18067ce943a40ae25454675c19ff5c", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-pod-total + namespace: monitoring +- apiVersion: v1 + data: + prometheus-remote-write.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "60s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 2, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Highest Timestamp In vs. Highest Timestamp Sent", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "clamp_min(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate[5m]", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Timestamps", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) (rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate, in vs. succeeded or dropped [5m]", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Samples", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "minSpan": 6, + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Max Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Min Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Desired Shards", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Shards", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Shard Capacity", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Pending Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Shard Details", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "TSDB Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{consumer}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Remote Write Current Segment", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "none", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Segments", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Dropped Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 14, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Failed Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_retried_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Retried Samples", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 3, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Enqueue Retries", + "tooltip": { + "shared": true, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Misc. Rates", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "prometheus-mixin" + ], + "templating": { + "list": [ + { + "hide": 0, + "label": null, + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + "text": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "value": { + "selected": true, + "text": "All", + "value": "$__all" + } + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(prometheus_build_info{cluster=~\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "url", + "options": [ + + ], + "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-6h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "browser", + "title": "Prometheus / Remote Write", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-prometheus-remote-write + namespace: monitoring +- apiVersion: v1 + data: + prometheus.json: |- + { + "annotations": { + "list": [ + + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "links": [ + + ], + "refresh": "60s", + "rows": [ + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 1, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "styles": [ + { + "alias": "Time", + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "pattern": "Time", + "type": "hidden" + }, + { + "alias": "Count", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #A", + "thresholds": [ + + ], + "type": "hidden", + "unit": "short" + }, + { + "alias": "Uptime", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "Value #B", + "thresholds": [ + + ], + "type": "number", + "unit": "s" + }, + { + "alias": "Instance", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "instance", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Job", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "job", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "Version", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "link": false, + "linkTargetBlank": false, + "linkTooltip": "Drill down", + "linkUrl": "", + "pattern": "version", + "thresholds": [ + + ], + "type": "number", + "unit": "short" + }, + { + "alias": "", + "colorMode": null, + "colors": [ + + ], + "dateFormat": "YYYY-MM-DD HH:mm:ss", + "decimals": 2, + "pattern": "/.*/", + "thresholds": [ + + ], + "type": "string", + "unit": "short" + } + ], + "targets": [ + { + "expr": "count by (job, instance, version) (prometheus_build_info{job=~\"$job\", instance=~\"$instance\"})", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "A", + "step": 10 + }, + { + "expr": "max by (job, instance) (time() - process_start_time_seconds{job=~\"$job\", instance=~\"$instance\"})", + "format": "table", + "instant": true, + "intervalFactor": 2, + "legendFormat": "", + "refId": "B", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Prometheus Stats", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "transform": "table", + "type": "table", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Prometheus Stats", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 2, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(prometheus_target_sync_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m])) by (scrape_job) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{scrape_job}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Target Sync", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 3, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum(prometheus_sd_discovered_targets{job=~\"$job\",instance=~\"$instance\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "Targets", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Targets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Discovery", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "id": 4, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_target_interval_length_seconds_sum{job=~\"$job\",instance=~\"$instance\"}[5m]) / rate(prometheus_target_interval_length_seconds_count{job=~\"$job\",instance=~\"$instance\"}[5m]) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{interval}} configured", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Scrape Interval Duration", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 5, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_body_size_limit_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exceeded body size limit: {{job}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "exceeded sample limit: {{job}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_duplicate_timestamp_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "duplicate timestamp: {{job}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_bounds_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "out of bounds: {{job}}", + "legendLink": null, + "step": 10 + }, + { + "expr": "sum by (job) (rate(prometheus_target_scrapes_sample_out_of_order_total[1m]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "out of order: {{job}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scrape failures", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 6, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=~\"$job\",instance=~\"$instance\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{job}} {{instance}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Appended Samples", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Retrieval", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 7, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_series{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{job}} {{instance}} head series", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Head Series", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 8, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "prometheus_tsdb_head_chunks{job=~\"$job\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{job}} {{instance}} head chunks", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Head Chunks", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Storage", + "titleSize": "h6" + }, + { + "collapse": false, + "height": "250px", + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 9, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "rate(prometheus_engine_query_duration_seconds_count{job=~\"$job\",instance=~\"$instance\",slice=\"inner_eval\"}[5m])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{job}} {{instance}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Query Rate", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 10, + "id": 10, + "legend": { + "avg": false, + "current": false, + "max": false, + "min": false, + "show": true, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 0, + "links": [ + + ], + "nullPointMode": "null as zero", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "max by (slice) (prometheus_engine_query_duration_seconds{quantile=\"0.9\",job=~\"$job\",instance=~\"$instance\"}) * 1e3", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{slice}}", + "legendLink": null, + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Stage Duration", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ms", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": false + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Query", + "titleSize": "h6" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "prometheus-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [ + + ], + "query": "label_values(prometheus_build_info{job=\"prometheus-k8s\",namespace=\"monitoring\"}, job)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "current": { + "selected": true, + "text": "All", + "value": "$__all" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": "instance", + "multi": true, + "name": "instance", + "options": [ + + ], + "query": "label_values(prometheus_build_info{job=~\"$job\"}, instance)", + "refresh": 1, + "regex": "", + "sort": 2, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "utc", + "title": "Prometheus / Overview", + "uid": "", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-prometheus + namespace: monitoring +- apiVersion: v1 + data: + proxy.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rules Sync Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rule Sync Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "rate", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Programming Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 6, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Network Programming Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 11, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 12, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-proxy\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Proxy", + "uid": "632e265de029684c40b21cb76bca4f94", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-proxy + namespace: monitoring +- apiVersion: v1 + data: + scheduler.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + + ] + }, + "editable": false, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "refresh": "10s", + "rows": [ + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "cacheTimeout": null, + "colorBackground": false, + "colorValue": false, + "colors": [ + "#299c46", + "rgba(237, 129, 40, 0.89)", + "#d44a3a" + ], + "datasource": "$datasource", + "format": "none", + "gauge": { + "maxValue": 100, + "minValue": 0, + "show": false, + "thresholdLabels": false, + "thresholdMarkers": true + }, + "gridPos": { + + }, + "id": 2, + "interval": "1m", + "legend": { + "alignAsTable": true, + "rightSide": true + }, + "links": [ + + ], + "mappingType": 1, + "mappingTypes": [ + { + "name": "value to text", + "value": 1 + }, + { + "name": "range to text", + "value": 2 + } + ], + "maxDataPoints": 100, + "nullPointMode": "connected", + "nullText": null, + "postfix": "", + "postfixFontSize": "50%", + "prefix": "", + "prefixFontSize": "50%", + "rangeMaps": [ + { + "from": "null", + "text": "N/A", + "to": "null" + } + ], + "span": 2, + "sparkline": { + "fillColor": "rgba(31, 118, 189, 0.18)", + "full": false, + "lineColor": "rgb(31, 120, 193)", + "show": false + }, + "tableColumn": "", + "targets": [ + { + "expr": "sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "", + "refId": "A" + } + ], + "thresholds": "", + "title": "Up", + "tooltip": { + "shared": false + }, + "type": "singlestat", + "valueFontSize": "80%", + "valueMaps": [ + { + "op": "=", + "text": "N/A", + "value": "null" + } + ], + "valueName": "min" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 3, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} e2e", + "refId": "A" + }, + { + "expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} binding", + "refId": "B" + }, + { + "expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} volume", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scheduling Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 4, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 5, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} e2e", + "refId": "A" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} binding", + "refId": "B" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} scheduling algorithm", + "refId": "C" + }, + { + "expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{cluster}} {{instance}} volume", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Scheduling latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 5, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "2xx", + "refId": "A" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "3xx", + "refId": "B" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "4xx", + "refId": "C" + }, + { + "expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "5xx", + "refId": "D" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Kube API Request Rate", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "ops", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 6, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 8, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Post Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 7, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": true + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{verb}} {{url}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Get Request Latency 99th Quantile", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "s", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 8, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Memory", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 9, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "CPU usage", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "bytes", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 1, + "fillGradient": 0, + "gridPos": { + + }, + "id": 10, + "interval": "1m", + "legend": { + "alignAsTable": true, + "avg": false, + "current": false, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 1, + "links": [ + + ], + "nullPointMode": "null", + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 4, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}", + "format": "time_series", + "intervalFactor": 2, + "legendFormat": "{{instance}}", + "refId": "A" + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Goroutines", + "tooltip": { + "shared": false, + "sort": 0, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + }, + { + "format": "short", + "label": null, + "logBase": 1, + "max": null, + "min": null, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": false, + "title": "Dashboard Row", + "titleSize": "h6", + "type": "row" + } + ], + "schemaVersion": 14, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": "cluster", + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(up{job=\"kube-scheduler\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "instance", + "options": [ + + ], + "query": "label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)", + "refresh": 2, + "regex": "", + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Scheduler", + "uid": "2e6b6a3b4bddf1427b3a55aa1311c656", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-scheduler + namespace: monitoring +- apiVersion: v1 + data: + workload-total.json: |- + { + "__inputs": [ + + ], + "__requires": [ + + ], + "annotations": { + "list": [ + { + "builtIn": 1, + "datasource": "-- Grafana --", + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "type": "dashboard" + } + ] + }, + "editable": true, + "gnetId": null, + "graphTooltip": 0, + "hideControls": false, + "id": null, + "links": [ + + ], + "panels": [ + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 0 + }, + "id": 2, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Current Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 1 + }, + "id": 3, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ pod }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 1 + }, + "id": 4, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ pod }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Current Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 10 + }, + "id": 5, + "panels": [ + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 11 + }, + "id": 6, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ pod }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Received", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": true, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 11 + }, + "id": 7, + "legend": { + "alignAsTable": true, + "avg": false, + "current": true, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": true, + "show": true, + "sideWidth": null, + "sort": "current", + "sortDesc": true, + "total": false, + "values": true + }, + "lines": false, + "linewidth": 1, + "links": [ + + ], + "minSpan": 24, + "nullPointMode": "null", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 24, + "stack": false, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{ pod }}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Average Rate of Bytes Transmitted", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "series", + "name": null, + "show": false, + "values": [ + "current" + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Average Bandwidth", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": false, + "collapsed": false, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 11 + }, + "id": 8, + "panels": [ + + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Bandwidth HIstory", + "titleSize": "h6", + "type": "row" + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 12 + }, + "id": 9, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Receive Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 12 + }, + "id": 10, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Transmit Bandwidth", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "Bps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 21 + }, + "id": 11, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 22 + }, + "id": 12, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 22 + }, + "id": 13, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Packets", + "titleSize": "h6", + "type": "row" + }, + { + "collapse": true, + "collapsed": true, + "gridPos": { + "h": 1, + "w": 24, + "x": 0, + "y": 22 + }, + "id": 14, + "panels": [ + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 0, + "y": 23 + }, + "id": 15, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Received Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + }, + { + "aliasColors": { + + }, + "bars": false, + "dashLength": 10, + "dashes": false, + "datasource": "$datasource", + "fill": 2, + "fillGradient": 0, + "gridPos": { + "h": 9, + "w": 12, + "x": 12, + "y": 23 + }, + "id": 16, + "legend": { + "alignAsTable": false, + "avg": false, + "current": false, + "hideEmpty": true, + "hideZero": true, + "max": false, + "min": false, + "rightSide": false, + "show": true, + "sideWidth": null, + "total": false, + "values": false + }, + "lines": true, + "linewidth": 2, + "links": [ + + ], + "minSpan": 12, + "nullPointMode": "connected", + "paceLength": 10, + "percentage": false, + "pointradius": 5, + "points": false, + "renderer": "flot", + "repeat": null, + "seriesOverrides": [ + + ], + "spaceLength": 10, + "span": 12, + "stack": true, + "steppedLine": false, + "targets": [ + { + "expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n", + "format": "time_series", + "intervalFactor": 1, + "legendFormat": "{{pod}}", + "refId": "A", + "step": 10 + } + ], + "thresholds": [ + + ], + "timeFrom": null, + "timeShift": null, + "title": "Rate of Transmitted Packets Dropped", + "tooltip": { + "shared": true, + "sort": 2, + "value_type": "individual" + }, + "type": "graph", + "xaxis": { + "buckets": null, + "mode": "time", + "name": null, + "show": true, + "values": [ + + ] + }, + "yaxes": [ + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + }, + { + "format": "pps", + "label": null, + "logBase": 1, + "max": null, + "min": 0, + "show": true + } + ] + } + ], + "repeat": null, + "repeatIteration": null, + "repeatRowId": null, + "showTitle": true, + "title": "Errors", + "titleSize": "h6", + "type": "row" + } + ], + "refresh": "10s", + "rows": [ + + ], + "schemaVersion": 18, + "style": "dark", + "tags": [ + "kubernetes-mixin" + ], + "templating": { + "list": [ + { + "current": { + "text": "default", + "value": "default" + }, + "hide": 0, + "label": "Data Source", + "name": "datasource", + "options": [ + + ], + "query": "prometheus", + "refresh": 1, + "regex": "", + "type": "datasource" + }, + { + "allValue": null, + "current": { + + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "cluster", + "options": [ + + ], + "query": "label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)", + "refresh": 2, + "regex": "", + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": ".+", + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "kube-system", + "value": "kube-system" + }, + "datasource": "$datasource", + "definition": "label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)", + "hide": 0, + "includeAll": true, + "label": null, + "multi": false, + "name": "namespace", + "options": [ + + ], + "query": "label_values(container_network_receive_packets_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", cluster=\"$cluster\"}, namespace)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "", + "value": "" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "workload", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "deployment", + "value": "deployment" + }, + "datasource": "$datasource", + "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "type", + "options": [ + + ], + "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 0, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "query", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 0, + "includeAll": false, + "label": null, + "multi": false, + "name": "resolution", + "options": [ + { + "selected": false, + "text": "30s", + "value": "30s" + }, + { + "selected": true, + "text": "5m", + "value": "5m" + }, + { + "selected": false, + "text": "1h", + "value": "1h" + } + ], + "query": "30s,5m,1h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + }, + { + "allValue": null, + "auto": false, + "auto_count": 30, + "auto_min": "10s", + "current": { + "text": "5m", + "value": "5m" + }, + "datasource": "$datasource", + "hide": 2, + "includeAll": false, + "label": null, + "multi": false, + "name": "interval", + "options": [ + { + "selected": true, + "text": "4h", + "value": "4h" + } + ], + "query": "4h", + "refresh": 2, + "regex": "", + "skipUrlSync": false, + "sort": 1, + "tagValuesQuery": "", + "tags": [ + + ], + "tagsQuery": "", + "type": "interval", + "useTags": false + } + ] + }, + "time": { + "from": "now-1h", + "to": "now" + }, + "timepicker": { + "refresh_intervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "time_options": [ + "5m", + "15m", + "1h", + "6h", + "12h", + "24h", + "2d", + "7d", + "30d" + ] + }, + "timezone": "UTC", + "title": "Kubernetes / Networking / Workload", + "uid": "728bf77cc1166d2f3133bf25846876cc", + "version": 0 + } + kind: ConfigMap + metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboard-workload-total + namespace: monitoring +kind: ConfigMapList diff --git a/deployment/helm/pc-apis-prometheus/grafana-dashboardSources.yaml b/deployment/helm/pc-apis-prometheus/grafana-dashboardSources.yaml new file mode 100644 index 00000000..b3af416b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-dashboardSources.yaml @@ -0,0 +1,27 @@ +apiVersion: v1 +data: + dashboards.yaml: |- + { + "apiVersion": 1, + "providers": [ + { + "folder": "Default", + "folderUid": "", + "name": "0", + "options": { + "path": "/grafana-dashboard-definitions/0" + }, + "orgId": 1, + "type": "file" + } + ] + } +kind: ConfigMap +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana-dashboards + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/grafana-deployment.yaml b/deployment/helm/pc-apis-prometheus/grafana-deployment.yaml new file mode 100644 index 00000000..06f1ec69 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-deployment.yaml @@ -0,0 +1,250 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana + namespace: monitoring +spec: + replicas: 1 + selector: + matchLabels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + template: + metadata: + annotations: + checksum/grafana-config: 5c598ba58d9b65011bdbb3864138399a + checksum/grafana-dashboardproviders: c9c1743868aa1c3dab60d2c402e2dcf0 + checksum/grafana-datasources: 5ef0e6acaa5b4e8603740fbad440717d + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + spec: + automountServiceAccountToken: false + containers: + - env: [] + image: grafana/grafana:9.5.3 + name: grafana + ports: + - containerPort: 3000 + name: http + readinessProbe: + httpGet: + path: /api/health + port: http + resources: + limits: + cpu: 200m + memory: 200Mi + requests: + cpu: 100m + memory: 100Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + seccompProfile: + type: RuntimeDefault + volumeMounts: + - mountPath: /var/lib/grafana + name: grafana-storage + readOnly: false + - mountPath: /etc/grafana/provisioning/datasources + name: grafana-datasources + readOnly: false + - mountPath: /etc/grafana/provisioning/dashboards + name: grafana-dashboards + readOnly: false + - mountPath: /tmp + name: tmp-plugins + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/alertmanager-overview + name: grafana-dashboard-alertmanager-overview + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/apiserver + name: grafana-dashboard-apiserver + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/cluster-total + name: grafana-dashboard-cluster-total + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/controller-manager + name: grafana-dashboard-controller-manager + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/grafana-overview + name: grafana-dashboard-grafana-overview + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-cluster + name: grafana-dashboard-k8s-resources-cluster + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-multicluster + name: grafana-dashboard-k8s-resources-multicluster + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-namespace + name: grafana-dashboard-k8s-resources-namespace + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-node + name: grafana-dashboard-k8s-resources-node + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-pod + name: grafana-dashboard-k8s-resources-pod + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-workload + name: grafana-dashboard-k8s-resources-workload + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/k8s-resources-workloads-namespace + name: grafana-dashboard-k8s-resources-workloads-namespace + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/kubelet + name: grafana-dashboard-kubelet + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/namespace-by-pod + name: grafana-dashboard-namespace-by-pod + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/namespace-by-workload + name: grafana-dashboard-namespace-by-workload + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/node-cluster-rsrc-use + name: grafana-dashboard-node-cluster-rsrc-use + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/node-rsrc-use + name: grafana-dashboard-node-rsrc-use + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/nodes-darwin + name: grafana-dashboard-nodes-darwin + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/nodes + name: grafana-dashboard-nodes + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/persistentvolumesusage + name: grafana-dashboard-persistentvolumesusage + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/pod-total + name: grafana-dashboard-pod-total + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/prometheus-remote-write + name: grafana-dashboard-prometheus-remote-write + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/prometheus + name: grafana-dashboard-prometheus + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/proxy + name: grafana-dashboard-proxy + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/scheduler + name: grafana-dashboard-scheduler + readOnly: false + - mountPath: /grafana-dashboard-definitions/0/workload-total + name: grafana-dashboard-workload-total + readOnly: false + - mountPath: /etc/grafana + name: grafana-config + readOnly: false + nodeSelector: + kubernetes.io/os: linux + securityContext: + fsGroup: 65534 + runAsNonRoot: true + runAsUser: 65534 + serviceAccountName: grafana + volumes: + - emptyDir: {} + name: grafana-storage + - name: grafana-datasources + secret: + secretName: grafana-datasources + - configMap: + name: grafana-dashboards + name: grafana-dashboards + - emptyDir: + medium: Memory + name: tmp-plugins + - configMap: + name: grafana-dashboard-alertmanager-overview + name: grafana-dashboard-alertmanager-overview + - configMap: + name: grafana-dashboard-apiserver + name: grafana-dashboard-apiserver + - configMap: + name: grafana-dashboard-cluster-total + name: grafana-dashboard-cluster-total + - configMap: + name: grafana-dashboard-controller-manager + name: grafana-dashboard-controller-manager + - configMap: + name: grafana-dashboard-grafana-overview + name: grafana-dashboard-grafana-overview + - configMap: + name: grafana-dashboard-k8s-resources-cluster + name: grafana-dashboard-k8s-resources-cluster + - configMap: + name: grafana-dashboard-k8s-resources-multicluster + name: grafana-dashboard-k8s-resources-multicluster + - configMap: + name: grafana-dashboard-k8s-resources-namespace + name: grafana-dashboard-k8s-resources-namespace + - configMap: + name: grafana-dashboard-k8s-resources-node + name: grafana-dashboard-k8s-resources-node + - configMap: + name: grafana-dashboard-k8s-resources-pod + name: grafana-dashboard-k8s-resources-pod + - configMap: + name: grafana-dashboard-k8s-resources-workload + name: grafana-dashboard-k8s-resources-workload + - configMap: + name: grafana-dashboard-k8s-resources-workloads-namespace + name: grafana-dashboard-k8s-resources-workloads-namespace + - configMap: + name: grafana-dashboard-kubelet + name: grafana-dashboard-kubelet + - configMap: + name: grafana-dashboard-namespace-by-pod + name: grafana-dashboard-namespace-by-pod + - configMap: + name: grafana-dashboard-namespace-by-workload + name: grafana-dashboard-namespace-by-workload + - configMap: + name: grafana-dashboard-node-cluster-rsrc-use + name: grafana-dashboard-node-cluster-rsrc-use + - configMap: + name: grafana-dashboard-node-rsrc-use + name: grafana-dashboard-node-rsrc-use + - configMap: + name: grafana-dashboard-nodes-darwin + name: grafana-dashboard-nodes-darwin + - configMap: + name: grafana-dashboard-nodes + name: grafana-dashboard-nodes + - configMap: + name: grafana-dashboard-persistentvolumesusage + name: grafana-dashboard-persistentvolumesusage + - configMap: + name: grafana-dashboard-pod-total + name: grafana-dashboard-pod-total + - configMap: + name: grafana-dashboard-prometheus-remote-write + name: grafana-dashboard-prometheus-remote-write + - configMap: + name: grafana-dashboard-prometheus + name: grafana-dashboard-prometheus + - configMap: + name: grafana-dashboard-proxy + name: grafana-dashboard-proxy + - configMap: + name: grafana-dashboard-scheduler + name: grafana-dashboard-scheduler + - configMap: + name: grafana-dashboard-workload-total + name: grafana-dashboard-workload-total + - name: grafana-config + secret: + secretName: grafana-config diff --git a/deployment/helm/pc-apis-prometheus/grafana-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/grafana-networkPolicy.yaml new file mode 100644 index 00000000..62cf11cd --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-networkPolicy.yaml @@ -0,0 +1,29 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 3000 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/grafana-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/grafana-prometheusRule.yaml new file mode 100644 index 00000000..7572cf00 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-prometheusRule.yaml @@ -0,0 +1,33 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + prometheus: k8s + role: alert-rules + name: grafana-rules + namespace: monitoring +spec: + groups: + - name: GrafanaAlerts + rules: + - alert: GrafanaRequestsFailing + annotations: + message: '{{ $labels.namespace }}/{{ $labels.job }}/{{ $labels.handler }} is experiencing {{ $value | humanize }}% errors' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/grafana/grafanarequestsfailing + expr: | + 100 * namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query", status_code=~"5.."} + / ignoring (status_code) + sum without (status_code) (namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m{handler!~"/api/datasources/proxy/:id.*|/api/ds/query|/api/tsdb/query"}) + > 50 + for: 5m + labels: + severity: warning + - name: grafana_rules + rules: + - expr: | + sum by (namespace, job, handler, status_code) (rate(grafana_http_request_duration_seconds_count[5m])) + record: namespace_job_handler_statuscode:grafana_http_request_duration_seconds_count:rate5m diff --git a/deployment/helm/pc-apis-prometheus/grafana-service.yaml b/deployment/helm/pc-apis-prometheus/grafana-service.yaml new file mode 100644 index 00000000..1fad5b80 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-service.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana + namespace: monitoring +spec: + ports: + - name: http + port: 3000 + targetPort: http + selector: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/grafana-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/grafana-serviceAccount.yaml new file mode 100644 index 00000000..d0fa1790 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/grafana-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/grafana-serviceMonitor.yaml new file mode 100644 index 00000000..c64ad37b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/grafana-serviceMonitor.yaml @@ -0,0 +1,17 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: grafana + app.kubernetes.io/name: grafana + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 9.5.3 + name: grafana + namespace: monitoring +spec: + endpoints: + - interval: 15s + port: http + selector: + matchLabels: + app.kubernetes.io/name: grafana diff --git a/deployment/helm/pc-apis-prometheus/kubePrometheus-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/kubePrometheus-prometheusRule.yaml new file mode 100644 index 00000000..1356ee9d --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubePrometheus-prometheusRule.yaml @@ -0,0 +1,83 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-prometheus + app.kubernetes.io/part-of: kube-prometheus + prometheus: k8s + role: alert-rules + name: kube-prometheus-rules + namespace: monitoring +spec: + groups: + - name: general.rules + rules: + - alert: TargetDown + annotations: + description: '{{ printf "%.4g" $value }}% of the {{ $labels.job }}/{{ $labels.service }} targets in {{ $labels.namespace }} namespace are down.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/targetdown + summary: One or more targets are unreachable. + expr: 100 * (count(up == 0) BY (cluster, job, namespace, service) / count(up) BY (cluster, job, namespace, service)) > 10 + for: 10m + labels: + severity: warning + - alert: Watchdog + annotations: + description: | + This is an alert meant to ensure that the entire alerting pipeline is functional. + This alert is always firing, therefore it should always be firing in Alertmanager + and always fire against a receiver. There are integrations with various notification + mechanisms that send a notification when this alert is not firing. For example the + "DeadMansSnitch" integration in PagerDuty. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/watchdog + summary: An alert that should always be firing to certify that Alertmanager is working properly. + expr: vector(1) + labels: + severity: none + - alert: InfoInhibitor + annotations: + description: | + This is an alert that is used to inhibit info alerts. + By themselves, the info-level alerts are sometimes very noisy, but they are relevant when combined with + other alerts. + This alert fires whenever there's a severity="info" alert, and stops firing when another alert with a + severity of 'warning' or 'critical' starts firing on the same namespace. + This alert should be routed to a null receiver and configured to inhibit alerts with severity="info". + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/infoinhibitor + summary: Info-level alert inhibition. + expr: ALERTS{severity = "info"} == 1 unless on(namespace) ALERTS{alertname != "InfoInhibitor", severity =~ "warning|critical", alertstate="firing"} == 1 + labels: + severity: none + - name: node-network + rules: + - alert: NodeNetworkInterfaceFlapping + annotations: + description: Network interface "{{ $labels.device }}" changing its up status often on node-exporter {{ $labels.namespace }}/{{ $labels.pod }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/general/nodenetworkinterfaceflapping + summary: Network interface is often changing its status + expr: | + changes(node_network_up{job="node-exporter",device!~"veth.+"}[2m]) > 2 + for: 2m + labels: + severity: warning + - name: kube-prometheus-node-recording.rules + rules: + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[3m])) BY (instance) + record: instance:node_cpu:rate:sum + - expr: sum(rate(node_network_receive_bytes_total[3m])) BY (instance) + record: instance:node_network_receive_bytes:rate:sum + - expr: sum(rate(node_network_transmit_bytes_total[3m])) BY (instance) + record: instance:node_network_transmit_bytes:rate:sum + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) WITHOUT (cpu, mode) / ON(instance) GROUP_LEFT() count(sum(node_cpu_seconds_total) BY (instance, cpu)) BY (instance) + record: instance:node_cpu:ratio + - expr: sum(rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal"}[5m])) + record: cluster:node_cpu:sum_rate5m + - expr: cluster:node_cpu:sum_rate5m / count(sum(node_cpu_seconds_total) BY (instance, cpu)) + record: cluster:node_cpu:ratio + - name: kube-prometheus-general.rules + rules: + - expr: count without(instance, pod, node) (up == 1) + record: count:up1 + - expr: count without(instance, pod, node) (up == 0) + record: count:up0 diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRole.yaml new file mode 100644 index 00000000..146bfd4e --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRole.yaml @@ -0,0 +1,129 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics +rules: +- apiGroups: + - "" + resources: + - configmaps + - secrets + - nodes + - pods + - services + - serviceaccounts + - resourcequotas + - replicationcontrollers + - limitranges + - persistentvolumeclaims + - persistentvolumes + - namespaces + - endpoints + verbs: + - list + - watch +- apiGroups: + - apps + resources: + - statefulsets + - daemonsets + - deployments + - replicasets + verbs: + - list + - watch +- apiGroups: + - batch + resources: + - cronjobs + - jobs + verbs: + - list + - watch +- apiGroups: + - autoscaling + resources: + - horizontalpodautoscalers + verbs: + - list + - watch +- apiGroups: + - authentication.k8s.io + resources: + - tokenreviews + verbs: + - create +- apiGroups: + - authorization.k8s.io + resources: + - subjectaccessreviews + verbs: + - create +- apiGroups: + - policy + resources: + - poddisruptionbudgets + verbs: + - list + - watch +- apiGroups: + - certificates.k8s.io + resources: + - certificatesigningrequests + verbs: + - list + - watch +- apiGroups: + - discovery.k8s.io + resources: + - endpointslices + verbs: + - list + - watch +- apiGroups: + - storage.k8s.io + resources: + - storageclasses + - volumeattachments + verbs: + - list + - watch +- apiGroups: + - admissionregistration.k8s.io + resources: + - mutatingwebhookconfigurations + - validatingwebhookconfigurations + verbs: + - list + - watch +- apiGroups: + - networking.k8s.io + resources: + - networkpolicies + - ingressclasses + - ingresses + verbs: + - list + - watch +- apiGroups: + - coordination.k8s.io + resources: + - leases + verbs: + - list + - watch +- apiGroups: + - rbac.authorization.k8s.io + resources: + - clusterrolebindings + - clusterroles + - rolebindings + - roles + verbs: + - list + - watch diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRoleBinding.yaml new file mode 100644 index 00000000..a431e4a6 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-clusterRoleBinding.yaml @@ -0,0 +1,17 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: kube-state-metrics +subjects: +- kind: ServiceAccount + name: kube-state-metrics + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-deployment.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-deployment.yaml new file mode 100644 index 00000000..0e0a3ce9 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-deployment.yaml @@ -0,0 +1,108 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics + namespace: monitoring +spec: + replicas: 1 + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + template: + metadata: + annotations: + kubectl.kubernetes.io/default-container: kube-state-metrics + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + spec: + automountServiceAccountToken: true + containers: + - args: + - --host=127.0.0.1 + - --port=8081 + - --telemetry-host=127.0.0.1 + - --telemetry-port=8082 + image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.9.2 + name: kube-state-metrics + resources: + limits: + cpu: 100m + memory: 250Mi + requests: + cpu: 10m + memory: 190Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + - args: + - --logtostderr + - --secure-listen-address=:8443 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 + - --upstream=http://127.0.0.1:8081/ + image: quay.io/brancz/kube-rbac-proxy:v0.14.2 + name: kube-rbac-proxy-main + ports: + - containerPort: 8443 + name: https-main + resources: + limits: + cpu: 40m + memory: 40Mi + requests: + cpu: 20m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsGroup: 65532 + runAsNonRoot: true + runAsUser: 65532 + - args: + - --logtostderr + - --secure-listen-address=:9443 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 + - --upstream=http://127.0.0.1:8082/ + image: quay.io/brancz/kube-rbac-proxy:v0.14.2 + name: kube-rbac-proxy-self + ports: + - containerPort: 9443 + name: https-self + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsGroup: 65532 + runAsNonRoot: true + runAsUser: 65532 + nodeSelector: + kubernetes.io/os: linux + serviceAccountName: kube-state-metrics diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-networkPolicy.yaml new file mode 100644 index 00000000..e41b058b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-networkPolicy.yaml @@ -0,0 +1,31 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 8443 + protocol: TCP + - port: 9443 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-prometheusRule.yaml new file mode 100644 index 00000000..11bc9b61 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-prometheusRule.yaml @@ -0,0 +1,65 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + prometheus: k8s + role: alert-rules + name: kube-state-metrics-rules + namespace: monitoring +spec: + groups: + - name: kube-state-metrics + rules: + - alert: KubeStateMetricsListErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in list operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricslisterrors + summary: kube-state-metrics is experiencing errors in list operations. + expr: | + (sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsWatchErrors + annotations: + description: kube-state-metrics is experiencing errors at an elevated rate in watch operations. This is likely causing it to not be able to expose metrics about Kubernetes objects correctly or at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricswatcherrors + summary: kube-state-metrics is experiencing errors in watch operations. + expr: | + (sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m])) by (cluster) + / + sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])) by (cluster)) + > 0.01 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardingMismatch + annotations: + description: kube-state-metrics pods are running with different --total-shards configuration, some Kubernetes objects may be exposed multiple times or not exposed at all. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardingmismatch + summary: kube-state-metrics sharding is misconfigured. + expr: | + stdvar (kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) != 0 + for: 15m + labels: + severity: critical + - alert: KubeStateMetricsShardsMissing + annotations: + description: kube-state-metrics shards are missing, some Kubernetes objects are not being exposed. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kube-state-metrics/kubestatemetricsshardsmissing + summary: kube-state-metrics shards are missing. + expr: | + 2^max(kube_state_metrics_total_shards{job="kube-state-metrics"}) by (cluster) - 1 + - + sum( 2 ^ max by (cluster, shard_ordinal) (kube_state_metrics_shard_ordinal{job="kube-state-metrics"}) ) by (cluster) + != 0 + for: 15m + labels: + severity: critical diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-service.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-service.yaml new file mode 100644 index 00000000..55145cac --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-service.yaml @@ -0,0 +1,23 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics + namespace: monitoring +spec: + clusterIP: None + ports: + - name: https-main + port: 8443 + targetPort: https-main + - name: https-self + port: 9443 + targetPort: https-self + selector: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceAccount.yaml new file mode 100644 index 00000000..f34b1a8f --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceMonitor.yaml new file mode 100644 index 00000000..93ca4bd8 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubeStateMetrics-serviceMonitor.yaml @@ -0,0 +1,40 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.9.2 + name: kube-state-metrics + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + interval: 30s + metricRelabelings: + - action: drop + regex: kube_endpoint_address_not_ready|kube_endpoint_address_available + sourceLabels: + - __name__ + port: https-main + relabelings: + - action: labeldrop + regex: (pod|service|endpoint|namespace) + scheme: https + scrapeTimeout: 30s + tlsConfig: + insecureSkipVerify: true + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + port: https-self + scheme: https + tlsConfig: + insecureSkipVerify: true + jobLabel: app.kubernetes.io/name + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: kube-state-metrics + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-prometheusRule.yaml new file mode 100644 index 00000000..e62b2518 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-prometheusRule.yaml @@ -0,0 +1,1449 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/name: kube-prometheus + app.kubernetes.io/part-of: kube-prometheus + prometheus: k8s + role: alert-rules + name: kubernetes-monitoring-rules + namespace: monitoring +spec: + groups: + - name: kubernetes-apps + rules: + - alert: KubePodCrashLooping + annotations: + description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff").' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping + summary: Pod is crash looping. + expr: | + max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics"}[5m]) >= 1 + for: 15m + labels: + severity: warning + - alert: KubePodNotReady + annotations: + description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready + summary: Pod has been in a non-ready state for more than 15 minutes. + expr: | + sum by (namespace, pod, cluster) ( + max by(namespace, pod, cluster) ( + kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown|Failed"} + ) * on(namespace, pod, cluster) group_left(owner_kind) topk by(namespace, pod, cluster) ( + 1, max by(namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!="Job"}) + ) + ) > 0 + for: 15m + labels: + severity: warning + - alert: KubeDeploymentGenerationMismatch + annotations: + description: Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch + summary: Deployment generation mismatch due to possible roll-back + expr: | + kube_deployment_status_observed_generation{job="kube-state-metrics"} + != + kube_deployment_metadata_generation{job="kube-state-metrics"} + for: 15m + labels: + severity: warning + - alert: KubeDeploymentReplicasMismatch + annotations: + description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: | + ( + kube_deployment_spec_replicas{job="kube-state-metrics"} + > + kube_deployment_status_replicas_available{job="kube-state-metrics"} + ) and ( + changes(kube_deployment_status_replicas_updated{job="kube-state-metrics"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDeploymentRolloutStuck + annotations: + description: Rollout of deployment {{ $labels.namespace }}/{{ $labels.deployment }} is not progressing for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck + summary: Deployment rollout is not progressing. + expr: | + kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics"} + != 0 + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetReplicasMismatch + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch + summary: Deployment has not matched the expected number of replicas. + expr: | + ( + kube_statefulset_status_replicas_ready{job="kube-state-metrics"} + != + kube_statefulset_status_replicas{job="kube-state-metrics"} + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[10m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetGenerationMismatch + annotations: + description: StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch + summary: StatefulSet generation mismatch due to possible roll-back + expr: | + kube_statefulset_status_observed_generation{job="kube-state-metrics"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics"} + for: 15m + labels: + severity: warning + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout + summary: StatefulSet update has not been rolled out. + expr: | + ( + max without (revision) ( + kube_statefulset_status_current_revision{job="kube-state-metrics"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics"} + ) + * + ( + kube_statefulset_replicas{job="kube-state-metrics"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics"} + ) + ) and ( + changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeDaemonSetRolloutStuck + annotations: + description: DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck + summary: DaemonSet rollout is stuck. + expr: | + ( + ( + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} + ) or ( + kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} + != + 0 + ) or ( + kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} + ) or ( + kube_daemonset_status_number_available{job="kube-state-metrics"} + != + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} + ) + ) and ( + changes(kube_daemonset_status_updated_number_scheduled{job="kube-state-metrics"}[5m]) + == + 0 + ) + for: 15m + labels: + severity: warning + - alert: KubeContainerWaiting + annotations: + description: pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting + summary: Pod container waiting longer than 1 hour + expr: | + sum by (namespace, pod, container, cluster) (kube_pod_container_status_waiting_reason{job="kube-state-metrics"}) > 0 + for: 1h + labels: + severity: warning + - alert: KubeDaemonSetNotScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled + summary: DaemonSet pods are not scheduled. + expr: | + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0 + for: 10m + labels: + severity: warning + - alert: KubeDaemonSetMisScheduled + annotations: + description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled + summary: DaemonSet pods are misscheduled. + expr: | + kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeJobNotCompleted + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ "43200" | humanizeDuration }} to complete. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted + summary: Job did not complete in time + expr: | + time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics"} + and + kube_job_status_active{job="kube-state-metrics"} > 0) > 43200 + labels: + severity: warning + - alert: KubeJobFailed + annotations: + description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed + summary: Job failed to complete. + expr: | + kube_job_failed{job="kube-state-metrics"} > 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaReplicasMismatch + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch + summary: HPA has not matched desired number of replicas. + expr: | + (kube_horizontalpodautoscaler_status_desired_replicas{job="kube-state-metrics"} + != + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics"} + > + kube_horizontalpodautoscaler_spec_min_replicas{job="kube-state-metrics"}) + and + (kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics"} + < + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics"}) + and + changes(kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics"}[15m]) == 0 + for: 15m + labels: + severity: warning + - alert: KubeHpaMaxedOut + annotations: + description: HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout + summary: HPA is running at max replicas + expr: | + kube_horizontalpodautoscaler_status_current_replicas{job="kube-state-metrics"} + == + kube_horizontalpodautoscaler_spec_max_replicas{job="kube-state-metrics"} + for: 15m + labels: + severity: warning + - name: kubernetes-resources + rules: + - alert: KubeCPUOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: | + sum(namespace_cpu:kube_pod_container_resource_requests:sum{job="kube-state-metrics",}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeMemoryOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit + summary: Cluster has overcommitted memory resource requests. + expr: | + sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + and + (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0 + for: 10m + labels: + severity: warning + - alert: KubeCPUQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted CPU resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit + summary: Cluster has overcommitted CPU resource requests. + expr: | + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(cpu|requests.cpu)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="cpu", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeMemoryQuotaOvercommit + annotations: + description: Cluster {{ $labels.cluster }} has overcommitted memory resource requests for Namespaces. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit + summary: Cluster has overcommitted memory resource requests. + expr: | + sum(min without(resource) (kube_resourcequota{job="kube-state-metrics", type="hard", resource=~"(memory|requests.memory)"})) by (cluster) + / + sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) + > 1.5 + for: 5m + labels: + severity: warning + - alert: KubeQuotaAlmostFull + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull + summary: Namespace quota is going to be full. + expr: | + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 0.9 < 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaFullyUsed + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused + summary: Namespace quota is fully used. + expr: | + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + == 1 + for: 15m + labels: + severity: info + - alert: KubeQuotaExceeded + annotations: + description: Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded + summary: Namespace quota has exceeded the limits. + expr: | + kube_resourcequota{job="kube-state-metrics", type="used"} + / ignoring(instance, job, type) + (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0) + > 1 + for: 15m + labels: + severity: warning + - alert: CPUThrottlingHigh + annotations: + description: '{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh + summary: Processes experience elevated CPU throttling. + expr: | + sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace) + / + sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace) + > ( 25 / 100 ) + for: 15m + labels: + severity: info + - name: kubernetes-storage + rules: + - alert: KubePersistentVolumeFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: | + ( + kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_used_bytes{job="kubelet", metrics_path="/metrics"} > 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup + summary: PersistentVolume is filling up. + expr: | + ( + kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"} + / + kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_used_bytes{job="kubelet", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} only has {{ $value | humanizePercentage }} free inodes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: | + ( + kubelet_volume_stats_inodes_free{job="kubelet", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", metrics_path="/metrics"} + ) < 0.03 + and + kubelet_volume_stats_inodes_used{job="kubelet", metrics_path="/metrics"} > 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1m + labels: + severity: critical + - alert: KubePersistentVolumeInodesFillingUp + annotations: + description: Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to run out of inodes within four days. Currently {{ $value | humanizePercentage }} of its inodes are free. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup + summary: PersistentVolumeInodes are filling up. + expr: | + ( + kubelet_volume_stats_inodes_free{job="kubelet", metrics_path="/metrics"} + / + kubelet_volume_stats_inodes{job="kubelet", metrics_path="/metrics"} + ) < 0.15 + and + kubelet_volume_stats_inodes_used{job="kubelet", metrics_path="/metrics"} > 0 + and + predict_linear(kubelet_volume_stats_inodes_free{job="kubelet", metrics_path="/metrics"}[6h], 4 * 24 * 3600) < 0 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1 + unless on(namespace, persistentvolumeclaim) + kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1 + for: 1h + labels: + severity: warning + - alert: KubePersistentVolumeErrors + annotations: + description: The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeerrors + summary: PersistentVolume is having issues with provisioning. + expr: | + kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0 + for: 5m + labels: + severity: critical + - name: kubernetes-system + rules: + - alert: KubeVersionMismatch + annotations: + description: There are {{ $value }} different semantic versions of Kubernetes components running. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch + summary: Different semantic versions of Kubernetes components running. + expr: | + count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1 + for: 15m + labels: + severity: warning + - alert: KubeClientErrors + annotations: + description: Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors + summary: Kubernetes API server client is experiencing errors. + expr: | + (sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (cluster, instance, job, namespace) + / + sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (cluster, instance, job, namespace)) + > 0.01 + for: 15m + labels: + severity: warning + - name: kube-apiserver-slos + rules: + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: | + sum(apiserver_request:burnrate1h) > (14.40 * 0.01000) + and + sum(apiserver_request:burnrate5m) > (14.40 * 0.01000) + for: 2m + labels: + long: 1h + severity: critical + short: 5m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: | + sum(apiserver_request:burnrate6h) > (6.00 * 0.01000) + and + sum(apiserver_request:burnrate30m) > (6.00 * 0.01000) + for: 15m + labels: + long: 6h + severity: critical + short: 30m + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: | + sum(apiserver_request:burnrate1d) > (3.00 * 0.01000) + and + sum(apiserver_request:burnrate2h) > (3.00 * 0.01000) + for: 1h + labels: + long: 1d + severity: warning + short: 2h + - alert: KubeAPIErrorBudgetBurn + annotations: + description: The API server is burning too much error budget. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn + summary: The API server is burning too much error budget. + expr: | + sum(apiserver_request:burnrate3d) > (1.00 * 0.01000) + and + sum(apiserver_request:burnrate6h) > (1.00 * 0.01000) + for: 3h + labels: + long: 3d + severity: warning + short: 6h + - name: kubernetes-system-apiserver + rules: + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: | + apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800 + for: 5m + labels: + severity: warning + - alert: KubeClientCertificateExpiration + annotations: + description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration + summary: Client certificate is about to expire. + expr: | + apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400 + for: 5m + labels: + severity: critical + - alert: KubeAggregatedAPIErrors + annotations: + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors + summary: Kubernetes aggregated API has reported errors. + expr: | + sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m])) > 4 + labels: + severity: warning + - alert: KubeAggregatedAPIDown + annotations: + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown + summary: Kubernetes aggregated API is down. + expr: | + (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85 + for: 5m + labels: + severity: warning + - alert: KubeAPIDown + annotations: + description: KubeAPI has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapidown + summary: Target disappeared from Prometheus target discovery. + expr: | + absent(up{job="apiserver"} == 1) + for: 15m + labels: + severity: critical + - alert: KubeAPITerminatedRequests + annotations: + description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests + summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. + expr: | + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum(rate(apiserver_request_total{job="apiserver"}[10m])) + sum(rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 + for: 5m + labels: + severity: warning + - name: kubernetes-system-kubelet + rules: + - alert: KubeNodeNotReady + annotations: + description: '{{ $labels.node }} has been unready for more than 15 minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodenotready + summary: Node is not ready. + expr: | + kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0 + for: 15m + labels: + severity: warning + - alert: KubeNodeUnreachable + annotations: + description: '{{ $labels.node }} is unreachable and some workloads may be rescheduled.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodeunreachable + summary: Node is unreachable. + expr: | + (kube_node_spec_taint{job="kube-state-metrics",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="kube-state-metrics",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1 + for: 15m + labels: + severity: warning + - alert: KubeletTooManyPods + annotations: + description: Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods + summary: Kubelet is running at capacity. + expr: | + count by(cluster, node) ( + (kube_pod_status_phase{job="kube-state-metrics",phase="Running"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job="kube-state-metrics"}) + ) + / + max by(cluster, node) ( + kube_node_status_capacity{job="kube-state-metrics",resource="pods"} != 1 + ) > 0.95 + for: 15m + labels: + severity: info + - alert: KubeNodeReadinessFlapping + annotations: + description: The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping + summary: Node readiness status is flapping. + expr: | + sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2 + for: 15m + labels: + severity: warning + - alert: KubeletPlegDurationHigh + annotations: + description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletplegdurationhigh + summary: Kubelet Pod Lifecycle Event Generator is taking too long to relist. + expr: | + node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile="0.99"} >= 10 + for: 5m + labels: + severity: warning + - alert: KubeletPodStartUpLatencyHigh + annotations: + description: Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh + summary: Kubelet Pod startup latency is too high. + expr: | + histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60 + for: 15m + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: | + kubelet_certificate_manager_client_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletClientCertificateExpiration + annotations: + description: Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration + summary: Kubelet client certificate is about to expire. + expr: | + kubelet_certificate_manager_client_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: | + kubelet_certificate_manager_server_ttl_seconds < 604800 + labels: + severity: warning + - alert: KubeletServerCertificateExpiration + annotations: + description: Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration + summary: Kubelet server certificate is about to expire. + expr: | + kubelet_certificate_manager_server_ttl_seconds < 86400 + labels: + severity: critical + - alert: KubeletClientCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes). + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificaterenewalerrors + summary: Kubelet has failed to renew its client certificate. + expr: | + increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletServerCertificateRenewalErrors + annotations: + description: Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes). + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors + summary: Kubelet has failed to renew its server certificate. + expr: | + increase(kubelet_server_expiration_renew_errors[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: KubeletDown + annotations: + description: Kubelet has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletdown + summary: Target disappeared from Prometheus target discovery. + expr: | + absent(up{job="kubelet", metrics_path="/metrics"} == 1) + for: 15m + labels: + severity: critical + - name: kubernetes-system-scheduler + rules: + - alert: KubeSchedulerDown + annotations: + description: KubeScheduler has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeschedulerdown + summary: Target disappeared from Prometheus target discovery. + expr: | + absent(up{job="kube-scheduler"} == 1) + for: 15m + labels: + severity: critical + - name: kubernetes-system-controller-manager + rules: + - alert: KubeControllerManagerDown + annotations: + description: KubeControllerManager has disappeared from Prometheus target discovery. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown + summary: Target disappeared from Prometheus target discovery. + expr: | + absent(up{job="kube-controller-manager"} == 1) + for: 15m + labels: + severity: critical + - name: kube-apiserver-burnrate.rules + rules: + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1d])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1d])) + labels: + verb: read + record: apiserver_request:burnrate1d + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[1h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[1h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[1h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[1h])) + labels: + verb: read + record: apiserver_request:burnrate1h + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[2h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[2h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[2h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[2h])) + labels: + verb: read + record: apiserver_request:burnrate2h + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[30m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[30m])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[30m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[30m])) + labels: + verb: read + record: apiserver_request:burnrate30m + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[3d])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[3d])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[3d])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[3d])) + labels: + verb: read + record: apiserver_request:burnrate3d + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[5m])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[5m])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[5m])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: apiserver_request:burnrate5m + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + ( + ( + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope=~"resource|",le="1"}[6h])) + or + vector(0) + ) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="namespace",le="5"}[6h])) + + + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward",scope="cluster",le="30"}[6h])) + ) + ) + + + # errors + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[6h])) + labels: + verb: read + record: apiserver_request:burnrate6h + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1d])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d])) + labels: + verb: write + record: apiserver_request:burnrate1d + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[1h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[1h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h])) + labels: + verb: write + record: apiserver_request:burnrate1h + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[2h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[2h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h])) + labels: + verb: write + record: apiserver_request:burnrate2h + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[30m])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[30m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m])) + labels: + verb: write + record: apiserver_request:burnrate30m + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[3d])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[3d])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d])) + labels: + verb: write + record: apiserver_request:burnrate3d + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[5m])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: apiserver_request:burnrate5m + - expr: | + ( + ( + # too slow + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_count{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[6h])) + - + sum by (cluster) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward",le="1"}[6h])) + ) + + + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h])) + ) + / + sum by (cluster) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h])) + labels: + verb: write + record: apiserver_request:burnrate6h + - name: kube-apiserver-histogram.rules + rules: + - expr: | + histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: "0.99" + verb: read + record: cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_slo_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0 + labels: + quantile: "0.99" + verb: write + record: cluster_quantile:apiserver_request_slo_duration_seconds:histogram_quantile + - interval: 3m + name: kube-apiserver-availability.rules + rules: + - expr: | + avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30 + record: code_verb:apiserver_request_total:increase30d + - expr: | + sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"}) + labels: + verb: read + record: code:apiserver_request_total:increase30d + - expr: | + sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + labels: + verb: write + record: code:apiserver_request_total:increase30d + - expr: | + sum by (cluster, verb, scope) (increase(apiserver_request_slo_duration_seconds_count{job="apiserver"}[1h])) + record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h + - expr: | + sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d + - expr: | + sum by (cluster, verb, scope, le) (increase(apiserver_request_slo_duration_seconds_bucket[1h])) + record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h + - expr: | + sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase1h[30d]) * 24 * 30) + record: cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d + - expr: | + 1 - ( + ( + # write too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + ( + # read too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + ) + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d) + labels: + verb: all + record: apiserver_request:availability30d + - expr: | + 1 - ( + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"LIST|GET"}) + - + ( + # too slow + ( + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope=~"resource|",le="1"}) + or + vector(0) + ) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="namespace",le="5"}) + + + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"LIST|GET",scope="cluster",le="30"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="read"}) + labels: + verb: read + record: apiserver_request:availability30d + - expr: | + 1 - ( + ( + # too slow + sum by (cluster) (cluster_verb_scope:apiserver_request_slo_duration_seconds_count:increase30d{verb=~"POST|PUT|PATCH|DELETE"}) + - + sum by (cluster) (cluster_verb_scope_le:apiserver_request_slo_duration_seconds_bucket:increase30d{verb=~"POST|PUT|PATCH|DELETE",le="1"}) + ) + + + # errors + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0)) + ) + / + sum by (cluster) (code:apiserver_request_total:increase30d{verb="write"}) + labels: + verb: write + record: apiserver_request:availability30d + - expr: | + sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m])) + labels: + verb: read + record: code_resource:apiserver_request_total:rate5m + - expr: | + sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m])) + labels: + verb: write + record: code_resource:apiserver_request_total:rate5m + - expr: | + sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: | + sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: | + sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - expr: | + sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h])) + record: code_verb:apiserver_request_total:increase1h + - name: k8s.rules + rules: + - expr: | + sum by (cluster, namespace, pod, container) ( + irate(container_cpu_usage_seconds_total{job="kubelet", metrics_path="/metrics/cadvisor", image!=""}[5m]) + ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) ( + 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate + - expr: | + container_memory_working_set_bytes{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, + max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_working_set_bytes + - expr: | + container_memory_rss{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, + max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_rss + - expr: | + container_memory_cache{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, + max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_cache + - expr: | + container_memory_swap{job="kubelet", metrics_path="/metrics/cadvisor", image!=""} + * on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1, + max by(cluster, namespace, pod, node) (kube_pod_info{node!=""}) + ) + record: node_namespace_pod_container:container_memory_swap + - expr: | + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests + - expr: | + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="memory",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_requests:sum + - expr: | + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests + - expr: | + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_requests{resource="cpu",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_requests:sum + - expr: | + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits + - expr: | + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="memory",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_memory:kube_pod_container_resource_limits:sum + - expr: | + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} * on (namespace, pod, cluster) + group_left() max by (namespace, pod, cluster) ( + (kube_pod_status_phase{phase=~"Pending|Running"} == 1) + ) + record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits + - expr: | + sum by (namespace, cluster) ( + sum by (namespace, pod, cluster) ( + max by (namespace, pod, container, cluster) ( + kube_pod_container_resource_limits{resource="cpu",job="kube-state-metrics"} + ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) ( + kube_pod_status_phase{phase=~"Pending|Running"} == 1 + ) + ) + ) + record: namespace_cpu:kube_pod_container_resource_limits:sum + - expr: | + max by (cluster, namespace, workload, pod) ( + label_replace( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"}, + "replicaset", "$1", "owner_name", "(.*)" + ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) ( + 1, max by (replicaset, namespace, owner_name) ( + kube_replicaset_owner{job="kube-state-metrics"} + ) + ), + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: deployment + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: | + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: daemonset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: | + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: statefulset + record: namespace_workload_pod:kube_pod_owner:relabel + - expr: | + max by (cluster, namespace, workload, pod) ( + label_replace( + kube_pod_owner{job="kube-state-metrics", owner_kind="Job"}, + "workload", "$1", "owner_name", "(.*)" + ) + ) + labels: + workload_type: job + record: namespace_workload_pod:kube_pod_owner:relabel + - name: kube-scheduler.rules + rules: + - expr: | + histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.99" + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.99" + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.99" + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.9" + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.9" + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.9" + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.5" + record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.5" + record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod)) + labels: + quantile: "0.5" + record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile + - name: node.rules + rules: + - expr: | + topk by(cluster, namespace, pod) (1, + max by (cluster, node, namespace, pod) ( + label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)") + )) + record: 'node_namespace_pod:kube_pod_info:' + - expr: | + count by (cluster, node) ( + node_cpu_seconds_total{mode="idle",job="node-exporter"} + * on (namespace, pod) group_left(node) + topk by(namespace, pod) (1, node_namespace_pod:kube_pod_info:) + ) + record: node:node_num_cpu:sum + - expr: | + sum( + node_memory_MemAvailable_bytes{job="node-exporter"} or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + node_memory_Cached_bytes{job="node-exporter"} + + node_memory_MemFree_bytes{job="node-exporter"} + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) by (cluster) + record: :node_memory_MemAvailable_bytes:sum + - expr: | + avg by (cluster, node) ( + sum without (mode) ( + rate(node_cpu_seconds_total{mode!="idle",mode!="iowait",mode!="steal",job="node-exporter"}[5m]) + ) + ) + record: node:node_cpu_utilization:ratio_rate5m + - expr: | + avg by (cluster) ( + node:node_cpu_utilization:ratio_rate5m + ) + record: cluster:node_cpu:ratio_rate5m + - name: kubelet.rules + rules: + - expr: | + histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: "0.99" + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: "0.9" + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile + - expr: | + histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"}) + labels: + quantile: "0.5" + record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorApiserver.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorApiserver.yaml new file mode 100644 index 00000000..95f4e338 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorApiserver.yaml @@ -0,0 +1,75 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/name: apiserver + app.kubernetes.io/part-of: kube-prometheus + name: kube-apiserver + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + metricRelabelings: + - action: drop + regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds) + sourceLabels: + - __name__ + - action: drop + regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds) + sourceLabels: + - __name__ + - action: drop + regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers) + sourceLabels: + - __name__ + - action: drop + regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout) + sourceLabels: + - __name__ + - action: drop + regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total) + sourceLabels: + - __name__ + - action: drop + regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary) + sourceLabels: + - __name__ + - action: drop + regex: transformation_(transformation_latencies_microseconds|failures_total) + sourceLabels: + - __name__ + - action: drop + regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count) + sourceLabels: + - __name__ + - action: drop + regex: etcd_(debugging|disk|server).* + sourceLabels: + - __name__ + - action: drop + regex: apiserver_admission_controller_admission_latencies_seconds_.* + sourceLabels: + - __name__ + - action: drop + regex: apiserver_admission_step_admission_latencies_seconds_.* + sourceLabels: + - __name__ + - action: drop + regex: apiserver_request_duration_seconds_bucket;(0.15|0.25|0.3|0.35|0.4|0.45|0.6|0.7|0.8|0.9|1.25|1.5|1.75|2.5|3|3.5|4.5|6|7|8|9|15|25|30|50) + sourceLabels: + - __name__ + - le + port: https + scheme: https + tlsConfig: + caFile: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt + serverName: kubernetes + jobLabel: component + namespaceSelector: + matchNames: + - default + selector: + matchLabels: + component: apiserver + provider: kubernetes diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorCoreDNS.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorCoreDNS.yaml new file mode 100644 index 00000000..f3313d6d --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorCoreDNS.yaml @@ -0,0 +1,25 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/name: coredns + app.kubernetes.io/part-of: kube-prometheus + name: coredns + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 15s + metricRelabelings: + - action: drop + regex: coredns_cache_misses_total + sourceLabels: + - __name__ + port: metrics + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + k8s-app: kube-dns diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeControllerManager.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeControllerManager.yaml new file mode 100644 index 00000000..efd7135f --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeControllerManager.yaml @@ -0,0 +1,60 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/name: kube-controller-manager + app.kubernetes.io/part-of: kube-prometheus + name: kube-controller-manager + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + metricRelabelings: + - action: drop + regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds) + sourceLabels: + - __name__ + - action: drop + regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds) + sourceLabels: + - __name__ + - action: drop + regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers) + sourceLabels: + - __name__ + - action: drop + regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout) + sourceLabels: + - __name__ + - action: drop + regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total) + sourceLabels: + - __name__ + - action: drop + regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary) + sourceLabels: + - __name__ + - action: drop + regex: transformation_(transformation_latencies_microseconds|failures_total) + sourceLabels: + - __name__ + - action: drop + regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count) + sourceLabels: + - __name__ + - action: drop + regex: etcd_(debugging|disk|request|server).* + sourceLabels: + - __name__ + port: https-metrics + scheme: https + tlsConfig: + insecureSkipVerify: true + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + app.kubernetes.io/name: kube-controller-manager diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeScheduler.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeScheduler.yaml new file mode 100644 index 00000000..7fd84fc3 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubeScheduler.yaml @@ -0,0 +1,23 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/name: kube-scheduler + app.kubernetes.io/part-of: kube-prometheus + name: kube-scheduler + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + port: https-metrics + scheme: https + tlsConfig: + insecureSkipVerify: true + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + app.kubernetes.io/name: kube-scheduler diff --git a/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubelet.yaml b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubelet.yaml new file mode 100644 index 00000000..d0d2611f --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/kubernetesControlPlane-serviceMonitorKubelet.yaml @@ -0,0 +1,105 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/name: kubelet + app.kubernetes.io/part-of: kube-prometheus + name: kubelet + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + interval: 30s + metricRelabelings: + - action: drop + regex: kubelet_(pod_worker_latency_microseconds|pod_start_latency_microseconds|cgroup_manager_latency_microseconds|pod_worker_start_latency_microseconds|pleg_relist_latency_microseconds|pleg_relist_interval_microseconds|runtime_operations|runtime_operations_latency_microseconds|runtime_operations_errors|eviction_stats_age_microseconds|device_plugin_registration_count|device_plugin_alloc_latency_microseconds|network_plugin_operations_latency_microseconds) + sourceLabels: + - __name__ + - action: drop + regex: scheduler_(e2e_scheduling_latency_microseconds|scheduling_algorithm_predicate_evaluation|scheduling_algorithm_priority_evaluation|scheduling_algorithm_preemption_evaluation|scheduling_algorithm_latency_microseconds|binding_latency_microseconds|scheduling_latency_seconds) + sourceLabels: + - __name__ + - action: drop + regex: apiserver_(request_count|request_latencies|request_latencies_summary|dropped_requests|storage_data_key_generation_latencies_microseconds|storage_transformation_failures_total|storage_transformation_latencies_microseconds|proxy_tunnel_sync_latency_secs|longrunning_gauge|registered_watchers) + sourceLabels: + - __name__ + - action: drop + regex: kubelet_docker_(operations|operations_latency_microseconds|operations_errors|operations_timeout) + sourceLabels: + - __name__ + - action: drop + regex: reflector_(items_per_list|items_per_watch|list_duration_seconds|lists_total|short_watches_total|watch_duration_seconds|watches_total) + sourceLabels: + - __name__ + - action: drop + regex: etcd_(helper_cache_hit_count|helper_cache_miss_count|helper_cache_entry_count|object_counts|request_cache_get_latencies_summary|request_cache_add_latencies_summary|request_latencies_summary) + sourceLabels: + - __name__ + - action: drop + regex: transformation_(transformation_latencies_microseconds|failures_total) + sourceLabels: + - __name__ + - action: drop + regex: (admission_quota_controller_adds|admission_quota_controller_depth|admission_quota_controller_longest_running_processor_microseconds|admission_quota_controller_queue_latency|admission_quota_controller_unfinished_work_seconds|admission_quota_controller_work_duration|APIServiceOpenAPIAggregationControllerQueue1_adds|APIServiceOpenAPIAggregationControllerQueue1_depth|APIServiceOpenAPIAggregationControllerQueue1_longest_running_processor_microseconds|APIServiceOpenAPIAggregationControllerQueue1_queue_latency|APIServiceOpenAPIAggregationControllerQueue1_retries|APIServiceOpenAPIAggregationControllerQueue1_unfinished_work_seconds|APIServiceOpenAPIAggregationControllerQueue1_work_duration|APIServiceRegistrationController_adds|APIServiceRegistrationController_depth|APIServiceRegistrationController_longest_running_processor_microseconds|APIServiceRegistrationController_queue_latency|APIServiceRegistrationController_retries|APIServiceRegistrationController_unfinished_work_seconds|APIServiceRegistrationController_work_duration|autoregister_adds|autoregister_depth|autoregister_longest_running_processor_microseconds|autoregister_queue_latency|autoregister_retries|autoregister_unfinished_work_seconds|autoregister_work_duration|AvailableConditionController_adds|AvailableConditionController_depth|AvailableConditionController_longest_running_processor_microseconds|AvailableConditionController_queue_latency|AvailableConditionController_retries|AvailableConditionController_unfinished_work_seconds|AvailableConditionController_work_duration|crd_autoregistration_controller_adds|crd_autoregistration_controller_depth|crd_autoregistration_controller_longest_running_processor_microseconds|crd_autoregistration_controller_queue_latency|crd_autoregistration_controller_retries|crd_autoregistration_controller_unfinished_work_seconds|crd_autoregistration_controller_work_duration|crdEstablishing_adds|crdEstablishing_depth|crdEstablishing_longest_running_processor_microseconds|crdEstablishing_queue_latency|crdEstablishing_retries|crdEstablishing_unfinished_work_seconds|crdEstablishing_work_duration|crd_finalizer_adds|crd_finalizer_depth|crd_finalizer_longest_running_processor_microseconds|crd_finalizer_queue_latency|crd_finalizer_retries|crd_finalizer_unfinished_work_seconds|crd_finalizer_work_duration|crd_naming_condition_controller_adds|crd_naming_condition_controller_depth|crd_naming_condition_controller_longest_running_processor_microseconds|crd_naming_condition_controller_queue_latency|crd_naming_condition_controller_retries|crd_naming_condition_controller_unfinished_work_seconds|crd_naming_condition_controller_work_duration|crd_openapi_controller_adds|crd_openapi_controller_depth|crd_openapi_controller_longest_running_processor_microseconds|crd_openapi_controller_queue_latency|crd_openapi_controller_retries|crd_openapi_controller_unfinished_work_seconds|crd_openapi_controller_work_duration|DiscoveryController_adds|DiscoveryController_depth|DiscoveryController_longest_running_processor_microseconds|DiscoveryController_queue_latency|DiscoveryController_retries|DiscoveryController_unfinished_work_seconds|DiscoveryController_work_duration|kubeproxy_sync_proxy_rules_latency_microseconds|non_structural_schema_condition_controller_adds|non_structural_schema_condition_controller_depth|non_structural_schema_condition_controller_longest_running_processor_microseconds|non_structural_schema_condition_controller_queue_latency|non_structural_schema_condition_controller_retries|non_structural_schema_condition_controller_unfinished_work_seconds|non_structural_schema_condition_controller_work_duration|rest_client_request_latency_seconds|storage_operation_errors_total|storage_operation_status_count) + sourceLabels: + - __name__ + port: https-metrics + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + scheme: https + tlsConfig: + insecureSkipVerify: true + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + honorTimestamps: false + interval: 30s + metricRelabelings: + - action: drop + regex: container_(network_tcp_usage_total|network_udp_usage_total|tasks_state|cpu_load_average_10s) + sourceLabels: + - __name__ + - action: drop + regex: (container_spec_.*|container_file_descriptors|container_sockets|container_threads_max|container_threads|container_start_time_seconds|container_last_seen);; + sourceLabels: + - __name__ + - pod + - namespace + - action: drop + regex: (container_blkio_device_usage_total);.+ + sourceLabels: + - __name__ + - container + path: /metrics/cadvisor + port: https-metrics + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + scheme: https + tlsConfig: + insecureSkipVerify: true + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + interval: 30s + path: /metrics/probes + port: https-metrics + relabelings: + - action: replace + sourceLabels: + - __metrics_path__ + targetLabel: metrics_path + scheme: https + tlsConfig: + insecureSkipVerify: true + jobLabel: app.kubernetes.io/name + namespaceSelector: + matchNames: + - kube-system + selector: + matchLabels: + app.kubernetes.io/name: kubelet diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRole.yaml new file mode 100644 index 00000000..f8d8ed3e --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRole.yaml @@ -0,0 +1,23 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +rules: +- apiGroups: + - authentication.k8s.io + resources: + - tokenreviews + verbs: + - create +- apiGroups: + - authorization.k8s.io + resources: + - subjectaccessreviews + verbs: + - create diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRoleBinding.yaml new file mode 100644 index 00000000..544eba98 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-clusterRoleBinding.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: node-exporter +subjects: +- kind: ServiceAccount + name: node-exporter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-daemonset.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-daemonset.yaml new file mode 100644 index 00000000..3dd55747 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-daemonset.yaml @@ -0,0 +1,119 @@ +apiVersion: apps/v1 +kind: DaemonSet +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +spec: + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + template: + metadata: + annotations: + kubectl.kubernetes.io/default-container: node-exporter + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + spec: + automountServiceAccountToken: true + containers: + - args: + - --web.listen-address=127.0.0.1:9100 + - --path.sysfs=/host/sys + - --path.rootfs=/host/root + - --path.udev.data=/host/root/run/udev/data + - --no-collector.wifi + - --no-collector.hwmon + - --no-collector.btrfs + - --collector.filesystem.mount-points-exclude=^/(dev|proc|sys|run/k3s/containerd/.+|var/lib/docker/.+|var/lib/kubelet/pods/.+)($|/) + - --collector.netclass.ignored-devices=^(veth.*|[a-f0-9]{15})$ + - --collector.netdev.device-exclude=^(veth.*|[a-f0-9]{15})$ + image: quay.io/prometheus/node-exporter:v1.6.0 + name: node-exporter + resources: + limits: + cpu: 250m + memory: 180Mi + requests: + cpu: 102m + memory: 180Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + add: + - SYS_TIME + drop: + - ALL + readOnlyRootFilesystem: true + volumeMounts: + - mountPath: /host/sys + mountPropagation: HostToContainer + name: sys + readOnly: true + - mountPath: /host/root + mountPropagation: HostToContainer + name: root + readOnly: true + - args: + - --logtostderr + - --secure-listen-address=[$(IP)]:9100 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 + - --upstream=http://127.0.0.1:9100/ + env: + - name: IP + valueFrom: + fieldRef: + fieldPath: status.podIP + image: quay.io/brancz/kube-rbac-proxy:v0.14.2 + name: kube-rbac-proxy + ports: + - containerPort: 9100 + hostPort: 9100 + name: https + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsGroup: 65532 + runAsNonRoot: true + runAsUser: 65532 + hostNetwork: true + hostPID: true + nodeSelector: + kubernetes.io/os: linux + priorityClassName: system-cluster-critical + securityContext: + runAsNonRoot: true + runAsUser: 65534 + serviceAccountName: node-exporter + tolerations: + - operator: Exists + volumes: + - hostPath: + path: /sys + name: sys + - hostPath: + path: / + name: root + updateStrategy: + rollingUpdate: + maxUnavailable: 10% + type: RollingUpdate diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-networkPolicy.yaml new file mode 100644 index 00000000..32ccc2ad --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-networkPolicy.yaml @@ -0,0 +1,29 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 9100 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-prometheusRule.yaml new file mode 100644 index 00000000..839cc89d --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-prometheusRule.yaml @@ -0,0 +1,316 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + prometheus: k8s + role: alert-rules + name: node-exporter-rules + namespace: monitoring +spec: + groups: + - name: node-exporter + rules: + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 24 hours. + expr: | + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 15 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemSpaceFillingUp + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemspacefillingup + summary: Filesystem is predicted to run out of space within the next 4 hours. + expr: | + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 10 + and + predict_linear(node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 5% space left. + expr: | + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfSpace + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available space left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutofspace + summary: Filesystem has less than 3% space left. + expr: | + ( + node_filesystem_avail_bytes{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_size_bytes{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 30m + labels: + severity: critical + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 24 hours. + expr: | + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 40 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 24*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemFilesFillingUp + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left and is filling up fast. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemfilesfillingup + summary: Filesystem is predicted to run out of inodes within the next 4 hours. + expr: | + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 20 + and + predict_linear(node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""}[6h], 4*60*60) < 0 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 5% inodes left. + expr: | + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 5 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: warning + - alert: NodeFilesystemAlmostOutOfFiles + annotations: + description: Filesystem on {{ $labels.device }} at {{ $labels.instance }} has only {{ printf "%.2f" $value }}% available inodes left. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefilesystemalmostoutoffiles + summary: Filesystem has less than 3% inodes left. + expr: | + ( + node_filesystem_files_free{job="node-exporter",fstype!="",mountpoint!=""} / node_filesystem_files{job="node-exporter",fstype!="",mountpoint!=""} * 100 < 3 + and + node_filesystem_readonly{job="node-exporter",fstype!="",mountpoint!=""} == 0 + ) + for: 1h + labels: + severity: critical + - alert: NodeNetworkReceiveErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} receive errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworkreceiveerrs + summary: Network interface is reporting many receive errors. + expr: | + rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeNetworkTransmitErrs + annotations: + description: '{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf "%.0f" $value }} transmit errors in the last two minutes.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodenetworktransmiterrs + summary: Network interface is reporting many transmit errors. + expr: | + rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01 + for: 1h + labels: + severity: warning + - alert: NodeHighNumberConntrackEntriesUsed + annotations: + description: '{{ $value | humanizePercentage }} of conntrack entries are used.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodehighnumberconntrackentriesused + summary: Number of conntrack are getting close to the limit. + expr: | + (node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75 + labels: + severity: warning + - alert: NodeTextFileCollectorScrapeError + annotations: + description: Node Exporter text file collector failed to scrape. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodetextfilecollectorscrapeerror + summary: Node Exporter text file collector failed to scrape. + expr: | + node_textfile_scrape_error{job="node-exporter"} == 1 + labels: + severity: warning + - alert: NodeClockSkewDetected + annotations: + description: Clock on {{ $labels.instance }} is out of sync by more than 0.05s. Ensure NTP is configured correctly on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclockskewdetected + summary: Clock skew detected. + expr: | + ( + node_timex_offset_seconds{job="node-exporter"} > 0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) >= 0 + ) + or + ( + node_timex_offset_seconds{job="node-exporter"} < -0.05 + and + deriv(node_timex_offset_seconds{job="node-exporter"}[5m]) <= 0 + ) + for: 10m + labels: + severity: warning + - alert: NodeClockNotSynchronising + annotations: + description: Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodeclocknotsynchronising + summary: Clock not synchronising. + expr: | + min_over_time(node_timex_sync_status{job="node-exporter"}[5m]) == 0 + and + node_timex_maxerror_seconds{job="node-exporter"} >= 16 + for: 10m + labels: + severity: warning + - alert: NodeRAIDDegraded + annotations: + description: RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddegraded + summary: RAID Array is degraded + expr: | + node_md_disks_required{job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} - ignoring (state) (node_md_disks{state="active",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}) > 0 + for: 15m + labels: + severity: critical + - alert: NodeRAIDDiskFailure + annotations: + description: At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/noderaiddiskfailure + summary: Failed device in RAID array + expr: | + node_md_disks{state="failed",job="node-exporter",device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"} > 0 + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: | + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 70 + ) + for: 15m + labels: + severity: warning + - alert: NodeFileDescriptorLimit + annotations: + description: File descriptors limit at {{ $labels.instance }} is currently at {{ printf "%.2f" $value }}%. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/node/nodefiledescriptorlimit + summary: Kernel is predicted to exhaust file descriptors limit soon. + expr: | + ( + node_filefd_allocated{job="node-exporter"} * 100 / node_filefd_maximum{job="node-exporter"} > 90 + ) + for: 15m + labels: + severity: critical + - name: node-exporter.rules + rules: + - expr: | + count without (cpu, mode) ( + node_cpu_seconds_total{job="node-exporter",mode="idle"} + ) + record: instance:node_num_cpu:sum + - expr: | + 1 - avg without (cpu) ( + sum without (mode) (rate(node_cpu_seconds_total{job="node-exporter", mode=~"idle|iowait|steal"}[5m])) + ) + record: instance:node_cpu_utilisation:rate5m + - expr: | + ( + node_load1{job="node-exporter"} + / + instance:node_num_cpu:sum{job="node-exporter"} + ) + record: instance:node_load1_per_cpu:ratio + - expr: | + 1 - ( + ( + node_memory_MemAvailable_bytes{job="node-exporter"} + or + ( + node_memory_Buffers_bytes{job="node-exporter"} + + + node_memory_Cached_bytes{job="node-exporter"} + + + node_memory_MemFree_bytes{job="node-exporter"} + + + node_memory_Slab_bytes{job="node-exporter"} + ) + ) + / + node_memory_MemTotal_bytes{job="node-exporter"} + ) + record: instance:node_memory_utilisation:ratio + - expr: | + rate(node_vmstat_pgmajfault{job="node-exporter"}[5m]) + record: instance:node_vmstat_pgmajfault:rate5m + - expr: | + rate(node_disk_io_time_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_seconds:rate5m + - expr: | + rate(node_disk_io_time_weighted_seconds_total{job="node-exporter", device=~"(/dev/)?(mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|md.+|dasd.+)"}[5m]) + record: instance_device:node_disk_io_time_weighted_seconds:rate5m + - expr: | + sum without (device) ( + rate(node_network_receive_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_bytes_excluding_lo:rate5m + - expr: | + sum without (device) ( + rate(node_network_transmit_bytes_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_bytes_excluding_lo:rate5m + - expr: | + sum without (device) ( + rate(node_network_receive_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_receive_drop_excluding_lo:rate5m + - expr: | + sum without (device) ( + rate(node_network_transmit_drop_total{job="node-exporter", device!="lo"}[5m]) + ) + record: instance:node_network_transmit_drop_excluding_lo:rate5m diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-service.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-service.yaml new file mode 100644 index 00000000..fe42b4ff --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-service.yaml @@ -0,0 +1,20 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +spec: + clusterIP: None + ports: + - name: https + port: 9100 + targetPort: https + selector: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-serviceAccount.yaml new file mode 100644 index 00000000..99f8183b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/nodeExporter-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/nodeExporter-serviceMonitor.yaml new file mode 100644 index 00000000..dae649fb --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/nodeExporter-serviceMonitor.yaml @@ -0,0 +1,31 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 1.6.0 + name: node-exporter + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 15s + port: https + relabelings: + - action: replace + regex: (.*) + replacement: $1 + sourceLabels: + - __meta_kubernetes_pod_node_name + targetLabel: instance + scheme: https + tlsConfig: + insecureSkipVerify: true + jobLabel: app.kubernetes.io/name + selector: + matchLabels: + app.kubernetes.io/component: exporter + app.kubernetes.io/name: node-exporter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheus-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/prometheus-clusterRole.yaml new file mode 100644 index 00000000..5b67f6ea --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-clusterRole.yaml @@ -0,0 +1,21 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s +rules: +- apiGroups: + - "" + resources: + - nodes/metrics + verbs: + - get +- nonResourceURLs: + - /metrics + verbs: + - get diff --git a/deployment/helm/pc-apis-prometheus/prometheus-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/prometheus-clusterRoleBinding.yaml new file mode 100644 index 00000000..343a6675 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-clusterRoleBinding.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-k8s +subjects: +- kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheus-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/prometheus-networkPolicy.yaml new file mode 100644 index 00000000..3314f6ac --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-networkPolicy.yaml @@ -0,0 +1,47 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 9090 + protocol: TCP + - port: 8080 + protocol: TCP + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus-adapter + ports: + - port: 9090 + protocol: TCP + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: grafana + ports: + - port: 9090 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/prometheus-podDisruptionBudget.yaml b/deployment/helm/pc-apis-prometheus/prometheus-podDisruptionBudget.yaml new file mode 100644 index 00000000..e22644e2 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-podDisruptionBudget.yaml @@ -0,0 +1,19 @@ +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring +spec: + minAvailable: 1 + selector: + matchLabels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheus-prometheus.yaml b/deployment/helm/pc-apis-prometheus/prometheus-prometheus.yaml new file mode 100644 index 00000000..2939d0cc --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-prometheus.yaml @@ -0,0 +1,48 @@ +apiVersion: monitoring.coreos.com/v1 +kind: Prometheus +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: k8s + namespace: monitoring +spec: + alerting: + alertmanagers: + - apiVersion: v2 + name: alertmanager-main + namespace: monitoring + port: web + enableFeatures: [] + externalLabels: {} + image: quay.io/prometheus/prometheus:v2.44.0 + nodeSelector: + kubernetes.io/os: linux + podMetadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + podMonitorNamespaceSelector: {} + podMonitorSelector: {} + probeNamespaceSelector: {} + probeSelector: {} + replicas: 2 + resources: + requests: + memory: 400Mi + ruleNamespaceSelector: {} + ruleSelector: {} + securityContext: + fsGroup: 2000 + runAsNonRoot: true + runAsUser: 1000 + serviceAccountName: prometheus-k8s + serviceMonitorNamespaceSelector: {} + serviceMonitorSelector: {} + version: 2.44.0 diff --git a/deployment/helm/pc-apis-prometheus/prometheus-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/prometheus-prometheusRule.yaml new file mode 100644 index 00000000..a32b0cee --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-prometheusRule.yaml @@ -0,0 +1,290 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + prometheus: k8s + role: alert-rules + name: prometheus-k8s-prometheus-rules + namespace: monitoring +spec: + groups: + - name: prometheus + rules: + - alert: PrometheusBadConfig + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to reload its configuration. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusbadconfig + summary: Failed Prometheus configuration reload. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_config_last_reload_successful{job="prometheus-k8s",namespace="monitoring"}[5m]) == 0 + for: 10m + labels: + severity: critical + - alert: PrometheusSDRefreshFailure + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to refresh SD with mechanism {{$labels.mechanism}}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheussdrefreshfailure + summary: Failed Prometheus SD refresh. + expr: | + increase(prometheus_sd_refresh_failures_total{job="prometheus-k8s",namespace="monitoring"}[10m]) > 0 + for: 20m + labels: + severity: warning + - alert: PrometheusNotificationQueueRunningFull + annotations: + description: Alert notification queue of Prometheus {{$labels.namespace}}/{{$labels.pod}} is running full. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotificationqueuerunningfull + summary: Prometheus alert notification queue predicted to run full in less than 30m. + expr: | + # Without min_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + predict_linear(prometheus_notifications_queue_length{job="prometheus-k8s",namespace="monitoring"}[5m], 60 * 30) + > + min_over_time(prometheus_notifications_queue_capacity{job="prometheus-k8s",namespace="monitoring"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToSomeAlertmanagers + annotations: + description: '{{ printf "%.1f" $value }}% errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to Alertmanager {{$labels.alertmanager}}.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstosomealertmanagers + summary: Prometheus has encountered more than 1% errors sending alerts to a specific Alertmanager. + expr: | + ( + rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring"}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring"}[5m]) + ) + * 100 + > 1 + for: 15m + labels: + severity: warning + - alert: PrometheusNotConnectedToAlertmanagers + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not connected to any Alertmanagers. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotconnectedtoalertmanagers + summary: Prometheus is not connected to any Alertmanagers. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + max_over_time(prometheus_notifications_alertmanagers_discovered{job="prometheus-k8s",namespace="monitoring"}[5m]) < 1 + for: 10m + labels: + severity: warning + - alert: PrometheusTSDBReloadsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} reload failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbreloadsfailing + summary: Prometheus has issues reloading blocks from disk. + expr: | + increase(prometheus_tsdb_reloads_failures_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusTSDBCompactionsFailing + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has detected {{$value | humanize}} compaction failures over the last 3h. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustsdbcompactionsfailing + summary: Prometheus has issues compacting blocks. + expr: | + increase(prometheus_tsdb_compactions_failed_total{job="prometheus-k8s",namespace="monitoring"}[3h]) > 0 + for: 4h + labels: + severity: warning + - alert: PrometheusNotIngestingSamples + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is not ingesting samples. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusnotingestingsamples + summary: Prometheus is not ingesting samples. + expr: | + ( + rate(prometheus_tsdb_head_samples_appended_total{job="prometheus-k8s",namespace="monitoring"}[5m]) <= 0 + and + ( + sum without(scrape_job) (prometheus_target_metadata_cache_entries{job="prometheus-k8s",namespace="monitoring"}) > 0 + or + sum without(rule_group) (prometheus_rule_group_rules{job="prometheus-k8s",namespace="monitoring"}) > 0 + ) + ) + for: 10m + labels: + severity: warning + - alert: PrometheusDuplicateTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with different values but duplicated timestamp. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusduplicatetimestamps + summary: Prometheus is dropping samples with duplicate timestamps. + expr: | + rate(prometheus_target_scrapes_sample_duplicate_timestamp_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusOutOfOrderTimestamps + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} is dropping {{ printf "%.4g" $value }} samples/s with timestamps arriving out of order. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusoutofordertimestamps + summary: Prometheus drops samples with out-of-order timestamps. + expr: | + rate(prometheus_target_scrapes_sample_out_of_order_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusRemoteStorageFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} failed to send {{ printf "%.1f" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }} + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotestoragefailures + summary: Prometheus fails to send samples to remote storage. + expr: | + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m])) + / + ( + (rate(prometheus_remote_storage_failed_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job="prometheus-k8s",namespace="monitoring"}[5m])) + + + (rate(prometheus_remote_storage_succeeded_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m]) or rate(prometheus_remote_storage_samples_total{job="prometheus-k8s",namespace="monitoring"}[5m])) + ) + ) + * 100 + > 1 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteBehind + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write is {{ printf "%.1f" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritebehind + summary: Prometheus remote write is behind. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job="prometheus-k8s",namespace="monitoring"}[5m]) + - ignoring(remote_name, url) group_right + max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job="prometheus-k8s",namespace="monitoring"}[5m]) + ) + > 120 + for: 15m + labels: + severity: critical + - alert: PrometheusRemoteWriteDesiredShards + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance="%s",job="prometheus-k8s",namespace="monitoring"}` $labels.instance | query | first | value }}. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusremotewritedesiredshards + summary: Prometheus remote write desired shards calculation wants to run more than configured max shards. + expr: | + # Without max_over_time, failed scrapes could create false negatives, see + # https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details. + ( + max_over_time(prometheus_remote_storage_shards_desired{job="prometheus-k8s",namespace="monitoring"}[5m]) + > + max_over_time(prometheus_remote_storage_shards_max{job="prometheus-k8s",namespace="monitoring"}[5m]) + ) + for: 15m + labels: + severity: warning + - alert: PrometheusRuleFailures + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to evaluate {{ printf "%.0f" $value }} rules in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusrulefailures + summary: Prometheus is failing rule evaluations. + expr: | + increase(prometheus_rule_evaluation_failures_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: critical + - alert: PrometheusMissingRuleEvaluations + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has missed {{ printf "%.0f" $value }} rule group evaluations in the last 5m. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusmissingruleevaluations + summary: Prometheus is missing rule evaluations due to slow rule group evaluation. + expr: | + increase(prometheus_rule_group_iterations_missed_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because the number of targets exceeded the configured target_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetlimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the targets limit. + expr: | + increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusLabelLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has dropped {{ printf "%.0f" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuslabellimithit + summary: Prometheus has dropped targets because some scrape configs have exceeded the labels limit. + expr: | + increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeBodySizeLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured body_size_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapebodysizelimithit + summary: Prometheus has dropped some targets that exceeded body size limit. + expr: | + increase(prometheus_target_scrapes_exceeded_body_size_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusScrapeSampleLimitHit + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed {{ printf "%.0f" $value }} scrapes in the last 5m because some targets exceeded the configured sample_limit. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheusscrapesamplelimithit + summary: Prometheus has failed scrapes that have exceeded the configured sample limit. + expr: | + increase(prometheus_target_scrapes_exceeded_sample_limit_total{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0 + for: 15m + labels: + severity: warning + - alert: PrometheusTargetSyncFailure + annotations: + description: '{{ printf "%.0f" $value }} targets in Prometheus {{$labels.namespace}}/{{$labels.pod}} have failed to sync because invalid configuration was supplied.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheustargetsyncfailure + summary: Prometheus has failed to sync targets. + expr: | + increase(prometheus_target_sync_failed_total{job="prometheus-k8s",namespace="monitoring"}[30m]) > 0 + for: 5m + labels: + severity: critical + - alert: PrometheusHighQueryLoad + annotations: + description: Prometheus {{$labels.namespace}}/{{$labels.pod}} query API has less than 20% available capacity in its query engine for the last 15 minutes. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheushighqueryload + summary: Prometheus is reaching its maximum capacity serving concurrent requests. + expr: | + avg_over_time(prometheus_engine_queries{job="prometheus-k8s",namespace="monitoring"}[5m]) / max_over_time(prometheus_engine_queries_concurrent_max{job="prometheus-k8s",namespace="monitoring"}[5m]) > 0.8 + for: 15m + labels: + severity: warning + - alert: PrometheusErrorSendingAlertsToAnyAlertmanager + annotations: + description: '{{ printf "%.1f" $value }}% minimum errors while sending alerts from Prometheus {{$labels.namespace}}/{{$labels.pod}} to any Alertmanager.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus/prometheuserrorsendingalertstoanyalertmanager + summary: Prometheus encounters more than 3% errors sending alerts to any Alertmanager. + expr: | + min without (alertmanager) ( + rate(prometheus_notifications_errors_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m]) + / + rate(prometheus_notifications_sent_total{job="prometheus-k8s",namespace="monitoring",alertmanager!~``}[5m]) + ) + * 100 + > 3 + for: 15m + labels: + severity: critical diff --git a/deployment/helm/pc-apis-prometheus/prometheus-roleBindingConfig.yaml b/deployment/helm/pc-apis-prometheus/prometheus-roleBindingConfig.yaml new file mode 100644 index 00000000..f3b16311 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-roleBindingConfig.yaml @@ -0,0 +1,19 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s-config + namespace: monitoring +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: prometheus-k8s-config +subjects: +- kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheus-roleBindingSpecificNamespaces.yaml b/deployment/helm/pc-apis-prometheus/prometheus-roleBindingSpecificNamespaces.yaml new file mode 100644 index 00000000..bd909604 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-roleBindingSpecificNamespaces.yaml @@ -0,0 +1,79 @@ +apiVersion: rbac.authorization.k8s.io/v1 +items: +- apiVersion: rbac.authorization.k8s.io/v1 + kind: RoleBinding + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: default + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: prometheus-k8s + subjects: + - kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring +- apiVersion: rbac.authorization.k8s.io/v1 + kind: RoleBinding + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: kube-system + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: prometheus-k8s + subjects: + - kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring +- apiVersion: rbac.authorization.k8s.io/v1 + kind: RoleBinding + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: prometheus-k8s + subjects: + - kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring +- apiVersion: rbac.authorization.k8s.io/v1 + kind: RoleBinding + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: pc + roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: prometheus-k8s + subjects: + - kind: ServiceAccount + name: prometheus-k8s + namespace: monitoring +kind: RoleBindingList diff --git a/deployment/helm/pc-apis-prometheus/prometheus-roleConfig.yaml b/deployment/helm/pc-apis-prometheus/prometheus-roleConfig.yaml new file mode 100644 index 00000000..c8828f6b --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-roleConfig.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: Role +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s-config + namespace: monitoring +rules: +- apiGroups: + - "" + resources: + - configmaps + verbs: + - get diff --git a/deployment/helm/pc-apis-prometheus/prometheus-roleSpecificNamespaces.yaml b/deployment/helm/pc-apis-prometheus/prometheus-roleSpecificNamespaces.yaml new file mode 100644 index 00000000..6e907b58 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-roleSpecificNamespaces.yaml @@ -0,0 +1,155 @@ +apiVersion: rbac.authorization.k8s.io/v1 +items: +- apiVersion: rbac.authorization.k8s.io/v1 + kind: Role + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: default + rules: + - apiGroups: + - "" + resources: + - services + - endpoints + - pods + verbs: + - get + - list + - watch + - apiGroups: + - extensions + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- apiVersion: rbac.authorization.k8s.io/v1 + kind: Role + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: kube-system + rules: + - apiGroups: + - "" + resources: + - services + - endpoints + - pods + verbs: + - get + - list + - watch + - apiGroups: + - extensions + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- apiVersion: rbac.authorization.k8s.io/v1 + kind: Role + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring + rules: + - apiGroups: + - "" + resources: + - services + - endpoints + - pods + verbs: + - get + - list + - watch + - apiGroups: + - extensions + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- apiVersion: rbac.authorization.k8s.io/v1 + kind: Role + metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: pc + rules: + - apiGroups: + - "" + resources: + - services + - endpoints + - pods + verbs: + - get + - list + - watch + - apiGroups: + - extensions + resources: + - ingresses + verbs: + - get + - list + - watch + - apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +kind: RoleList diff --git a/deployment/helm/pc-apis-prometheus/prometheus-service.yaml b/deployment/helm/pc-apis-prometheus/prometheus-service.yaml new file mode 100644 index 00000000..50fffbc7 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-service.yaml @@ -0,0 +1,25 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring +spec: + ports: + - name: web + port: 9090 + targetPort: web + - name: reloader-web + port: 8080 + targetPort: reloader-web + selector: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + sessionAffinity: ClientIP diff --git a/deployment/helm/pc-apis-prometheus/prometheus-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/prometheus-serviceAccount.yaml new file mode 100644 index 00000000..f2ac3c9e --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-serviceAccount.yaml @@ -0,0 +1,12 @@ +apiVersion: v1 +automountServiceAccountToken: true +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheus-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/prometheus-serviceMonitor.yaml new file mode 100644 index 00000000..8eded28c --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheus-serviceMonitor.yaml @@ -0,0 +1,23 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 2.44.0 + name: prometheus-k8s + namespace: monitoring +spec: + endpoints: + - interval: 30s + port: web + - interval: 30s + port: reloader-web + selector: + matchLabels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-apiService.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-apiService.yaml new file mode 100644 index 00000000..bf17b251 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-apiService.yaml @@ -0,0 +1,18 @@ +apiVersion: apiregistration.k8s.io/v1 +kind: APIService +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: v1beta1.metrics.k8s.io +spec: + group: metrics.k8s.io + groupPriorityMinimum: 100 + insecureSkipTLSVerify: true + service: + name: prometheus-adapter + namespace: monitoring + version: v1beta1 + versionPriority: 100 diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRole.yaml new file mode 100644 index 00000000..57e49253 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRole.yaml @@ -0,0 +1,22 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +rules: +- apiGroups: + - "" + resources: + - nodes + - namespaces + - pods + - services + verbs: + - get + - list + - watch diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleAggregatedMetricsReader.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleAggregatedMetricsReader.yaml new file mode 100644 index 00000000..b1f31754 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleAggregatedMetricsReader.yaml @@ -0,0 +1,23 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + rbac.authorization.k8s.io/aggregate-to-admin: "true" + rbac.authorization.k8s.io/aggregate-to-edit: "true" + rbac.authorization.k8s.io/aggregate-to-view: "true" + name: system:aggregated-metrics-reader + namespace: monitoring +rules: +- apiGroups: + - metrics.k8s.io + resources: + - pods + - nodes + verbs: + - get + - list + - watch diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBinding.yaml new file mode 100644 index 00000000..749fc66a --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBinding.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-adapter +subjects: +- kind: ServiceAccount + name: prometheus-adapter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBindingDelegator.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBindingDelegator.yaml new file mode 100644 index 00000000..eb8fc9e7 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleBindingDelegator.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: resource-metrics:system:auth-delegator + namespace: monitoring +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:auth-delegator +subjects: +- kind: ServiceAccount + name: prometheus-adapter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleServerResources.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleServerResources.yaml new file mode 100644 index 00000000..73d78b06 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-clusterRoleServerResources.yaml @@ -0,0 +1,17 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: resource-metrics-server-resources + namespace: monitoring +rules: +- apiGroups: + - metrics.k8s.io + resources: + - '*' + verbs: + - '*' diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-configMap.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-configMap.yaml new file mode 100644 index 00000000..a1690bb6 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-configMap.yaml @@ -0,0 +1,69 @@ +apiVersion: v1 +data: + config.yaml: |- + "resourceRules": + "cpu": + "containerLabel": "container" + "containerQuery": | + sum by (<<.GroupBy>>) ( + irate ( + container_cpu_usage_seconds_total{<<.LabelMatchers>>,container!="",pod!=""}[120s] + ) + ) + "nodeQuery": | + sum by (<<.GroupBy>>) ( + 1 - irate( + node_cpu_seconds_total{mode="idle"}[60s] + ) + * on(namespace, pod) group_left(node) ( + node_namespace_pod:kube_pod_info:{<<.LabelMatchers>>} + ) + ) + or sum by (<<.GroupBy>>) ( + 1 - irate( + windows_cpu_time_total{mode="idle", job="windows-exporter",<<.LabelMatchers>>}[4m] + ) + ) + "resources": + "overrides": + "namespace": + "resource": "namespace" + "node": + "resource": "node" + "pod": + "resource": "pod" + "memory": + "containerLabel": "container" + "containerQuery": | + sum by (<<.GroupBy>>) ( + container_memory_working_set_bytes{<<.LabelMatchers>>,container!="",pod!=""} + ) + "nodeQuery": | + sum by (<<.GroupBy>>) ( + node_memory_MemTotal_bytes{job="node-exporter",<<.LabelMatchers>>} + - + node_memory_MemAvailable_bytes{job="node-exporter",<<.LabelMatchers>>} + ) + or sum by (<<.GroupBy>>) ( + windows_cs_physical_memory_bytes{job="windows-exporter",<<.LabelMatchers>>} + - + windows_memory_available_bytes{job="windows-exporter",<<.LabelMatchers>>} + ) + "resources": + "overrides": + "instance": + "resource": "node" + "namespace": + "resource": "namespace" + "pod": + "resource": "pod" + "window": "5m" +kind: ConfigMap +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: adapter-config + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-customMetrics.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-customMetrics.yaml new file mode 100644 index 00000000..7fde1612 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-customMetrics.yaml @@ -0,0 +1,286 @@ +apiVersion: v1 +kind: ServiceAccount +metadata: + labels: + app: prometheus-adapter + name: custom-metrics-prometheus-adapter + namespace: monitoring +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-system-auth-delegator +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: system:auth-delegator +subjects: +- kind: ServiceAccount + name: custom-metrics-prometheus-adapter + namespace: monitoring +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-resource-reader +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-adapter-resource-reader +subjects: +- kind: ServiceAccount + name: custom-metrics-prometheus-adapter + namespace: monitoring +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-resource-reader +rules: +- apiGroups: + - "" + resources: + - namespaces + - pods + - services + - configmaps + verbs: + - get + - list + - watch +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-auth-reader + namespace: kube-system +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: extension-apiserver-authentication-reader +subjects: +- kind: ServiceAccount + name: custom-metrics-prometheus-adapter + namespace: monitoring +--- +apiVersion: v1 +kind: ConfigMap +metadata: + name: custom-metrics-prometheus-adapter + namespace: monitoring + labels: + app: prometheus-adapter +data: + config.yaml: | + rules: + - seriesQuery: 'http_requests_total{namespace!="",pod!=""}' + resources: + overrides: + namespace: + resource: namespace + pod: + resource: pod + name: + matches: "^(.*)_total" + as: "${1}_per_minute" + metricsQuery: 'sum(rate(<<.Series>>{<<.LabelMatchers>>}[20s])) by (<<.GroupBy>>)' + resourceRules: + cpu: + containerQuery: sum(rate(container_cpu_usage_seconds_total{<<.LabelMatchers>>, container_label_io_kubernetes_container_name!=""}[3m])) by (<<.GroupBy>>) + nodeQuery: sum(rate(container_cpu_usage_seconds_total{<<.LabelMatchers>>, id='/'}[3m])) by (<<.GroupBy>>) by (<<.GroupBy>>) + resources: + overrides: + container_label_io_kubernetes_pod_namespace: + resource: namespace + node: + resource: node + container_label_io_kubernetes_pod_name: + resource: pod + containerLabel: container_label_io_kubernetes_container_name + memory: + containerQuery: sum(container_memory_working_set_bytes{<<.LabelMatchers>>, container_label_io_kubernetes_container_name!=""}) by (<<.GroupBy>>) + nodeQuery: sum(container_memory_working_set_bytes{<<.LabelMatchers>>,id='/'}) by (<<.GroupBy>>) + resources: + overrides: + container_label_io_kubernetes_pod_namespace: + resource: namespace + node: + resource: node + container_label_io_kubernetes_pod_name: + resource: pod + containerLabel: container_label_io_kubernetes_container_name + window: 3m +--- +apiVersion: apps/v1 +kind: Deployment +metadata: + name: custom-metrics-prometheus-adapter + namespace: monitoring +spec: + replicas: 1 + selector: + matchLabels: + app: prometheus-adapter + template: + metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter + annotations: + checksum/config: 4b70a56e35e56c8038b94f63f0515e79f22bd49456902c2f3c3d2dd9b2474ece + spec: + serviceAccountName: custom-metrics-prometheus-adapter + containers: + - name: prometheus-adapter + image: "directxman12/k8s-prometheus-adapter-amd64:v0.8.4" + imagePullPolicy: IfNotPresent + args: + - /adapter + - --secure-port=6443 + - --cert-dir=/tmp/cert + - --logtostderr=true + - --prometheus-url=http://prometheus-operated.monitoring.svc:9090 + - --metrics-relist-interval=1m + - --v=4 + - --config=/etc/adapter/config.yaml + ports: + - containerPort: 6443 + name: https + livenessProbe: + httpGet: + path: /healthz + port: https + scheme: HTTPS + initialDelaySeconds: 30 + timeoutSeconds: 5 + readinessProbe: + httpGet: + path: /healthz + port: https + scheme: HTTPS + initialDelaySeconds: 30 + timeoutSeconds: 5 + resources: + limits: + cpu: 100m + memory: 128Mi + requests: + cpu: 100m + memory: 128Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: ["all"] + readOnlyRootFilesystem: true + runAsNonRoot: true + runAsUser: 10001 + volumeMounts: + - mountPath: /etc/adapter/ + name: config + readOnly: true + - mountPath: /tmp + name: tmp + volumes: + - name: config + configMap: + name: custom-metrics-prometheus-adapter + - name: tmp + emptyDir: {} +--- +apiVersion: v1 +kind: Service +metadata: + name: custom-metrics-prometheus-adapter + namespace: monitoring + labels: + app: prometheus-adapter +spec: + ports: + - port: 443 + protocol: TCP + targetPort: https + selector: + app: prometheus-adapter + type: ClusterIP +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-server-resources +rules: +- apiGroups: + - custom.metrics.k8s.io + resources: ["*"] + verbs: ["*"] +--- +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app: prometheus-adapter + name: prometheus-adapter-hpa-controller +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-adapter-server-resources +subjects: +- kind: ServiceAccount + name: custom-metrics-prometheus-adapter + namespace: monitoring +--- +apiVersion: apiregistration.k8s.io/v1 +kind: APIService +metadata: + name: v1beta1.custom.metrics.k8s.io + labels: + app: prometheus-adapter +spec: + service: + name: custom-metrics-prometheus-adapter + namespace: monitoring + group: custom.metrics.k8s.io + version: v1beta1 + insecureSkipTLSVerify: true + groupPriorityMinimum: 100 + versionPriority: 100 +--- +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + name: custom-metrics-prometheus-adapter + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app: prometheus-adapter + ports: + - port: 9090 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: prometheus + app.kubernetes.io/instance: k8s + app.kubernetes.io/name: prometheus + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-deployment.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-deployment.yaml new file mode 100644 index 00000000..ac196193 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-deployment.yaml @@ -0,0 +1,99 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +spec: + replicas: 2 + selector: + matchLabels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + strategy: + rollingUpdate: + maxSurge: 1 + maxUnavailable: 1 + template: + metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + spec: + automountServiceAccountToken: true + containers: + - args: + - --cert-dir=/var/run/serving-cert + - --config=/etc/adapter/config.yaml + - --logtostderr=true + - --metrics-relist-interval=1m + - --prometheus-url=http://prometheus-k8s.monitoring.svc:9090/ + - --secure-port=6443 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_CBC_SHA,TLS_ECDHE_RSA_WITH_AES_256_CBC_SHA,TLS_ECDHE_ECDSA_WITH_AES_256_CBC_SHA,TLS_RSA_WITH_AES_128_GCM_SHA256,TLS_RSA_WITH_AES_256_GCM_SHA384,TLS_RSA_WITH_AES_128_CBC_SHA,TLS_RSA_WITH_AES_256_CBC_SHA + image: registry.k8s.io/prometheus-adapter/prometheus-adapter:v0.10.0 + livenessProbe: + failureThreshold: 5 + httpGet: + path: /livez + port: https + scheme: HTTPS + periodSeconds: 5 + name: prometheus-adapter + ports: + - containerPort: 6443 + name: https + readinessProbe: + failureThreshold: 5 + httpGet: + path: /readyz + port: https + scheme: HTTPS + periodSeconds: 5 + resources: + limits: + cpu: 250m + memory: 180Mi + requests: + cpu: 102m + memory: 180Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + startupProbe: + failureThreshold: 18 + httpGet: + path: /livez + port: https + scheme: HTTPS + periodSeconds: 10 + volumeMounts: + - mountPath: /tmp + name: tmpfs + readOnly: false + - mountPath: /var/run/serving-cert + name: volume-serving-cert + readOnly: false + - mountPath: /etc/adapter + name: config + readOnly: false + nodeSelector: + kubernetes.io/os: linux + serviceAccountName: prometheus-adapter + volumes: + - emptyDir: {} + name: tmpfs + - emptyDir: {} + name: volume-serving-cert + - configMap: + name: adapter-config + name: config diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-networkPolicy.yaml new file mode 100644 index 00000000..29a11fd5 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-networkPolicy.yaml @@ -0,0 +1,23 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +spec: + egress: + - {} + ingress: + - {} + podSelector: + matchLabels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-podDisruptionBudget.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-podDisruptionBudget.yaml new file mode 100644 index 00000000..033fcaaf --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-podDisruptionBudget.yaml @@ -0,0 +1,17 @@ +apiVersion: policy/v1 +kind: PodDisruptionBudget +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +spec: + minAvailable: 1 + selector: + matchLabels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-roleBindingAuthReader.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-roleBindingAuthReader.yaml new file mode 100644 index 00000000..5d0d9036 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-roleBindingAuthReader.yaml @@ -0,0 +1,18 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: RoleBinding +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: resource-metrics-auth-reader + namespace: kube-system +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: Role + name: extension-apiserver-authentication-reader +subjects: +- kind: ServiceAccount + name: prometheus-adapter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-service.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-service.yaml new file mode 100644 index 00000000..c9848286 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-service.yaml @@ -0,0 +1,19 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +spec: + ports: + - name: https + port: 443 + targetPort: 6443 + selector: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceAccount.yaml new file mode 100644 index 00000000..bb1058b7 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceMonitor.yaml new file mode 100644 index 00000000..d8941459 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusAdapter-serviceMonitor.yaml @@ -0,0 +1,28 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.10.0 + name: prometheus-adapter + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + interval: 30s + metricRelabelings: + - action: drop + regex: (apiserver_client_certificate_.*|apiserver_envelope_.*|apiserver_flowcontrol_.*|apiserver_storage_.*|apiserver_webhooks_.*|workqueue_.*) + sourceLabels: + - __name__ + port: https + scheme: https + tlsConfig: + insecureSkipVerify: true + selector: + matchLabels: + app.kubernetes.io/component: metrics-adapter + app.kubernetes.io/name: prometheus-adapter + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRole.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRole.yaml new file mode 100644 index 00000000..70270455 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRole.yaml @@ -0,0 +1,99 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRole +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator +rules: +- apiGroups: + - monitoring.coreos.com + resources: + - alertmanagers + - alertmanagers/finalizers + - alertmanagers/status + - alertmanagerconfigs + - prometheuses + - prometheuses/finalizers + - prometheuses/status + - prometheusagents + - prometheusagents/finalizers + - prometheusagents/status + - thanosrulers + - thanosrulers/finalizers + - thanosrulers/status + - scrapeconfigs + - servicemonitors + - podmonitors + - probes + - prometheusrules + verbs: + - '*' +- apiGroups: + - apps + resources: + - statefulsets + verbs: + - '*' +- apiGroups: + - "" + resources: + - configmaps + - secrets + verbs: + - '*' +- apiGroups: + - "" + resources: + - pods + verbs: + - list + - delete +- apiGroups: + - "" + resources: + - services + - services/finalizers + - endpoints + verbs: + - get + - create + - update + - delete +- apiGroups: + - "" + resources: + - nodes + verbs: + - list + - watch +- apiGroups: + - "" + resources: + - namespaces + verbs: + - get + - list + - watch +- apiGroups: + - networking.k8s.io + resources: + - ingresses + verbs: + - get + - list + - watch +- apiGroups: + - authentication.k8s.io + resources: + - tokenreviews + verbs: + - create +- apiGroups: + - authorization.k8s.io + resources: + - subjectaccessreviews + verbs: + - create diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRoleBinding.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRoleBinding.yaml new file mode 100644 index 00000000..a375f5d6 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-clusterRoleBinding.yaml @@ -0,0 +1,17 @@ +apiVersion: rbac.authorization.k8s.io/v1 +kind: ClusterRoleBinding +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator +roleRef: + apiGroup: rbac.authorization.k8s.io + kind: ClusterRole + name: prometheus-operator +subjects: +- kind: ServiceAccount + name: prometheus-operator + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-deployment.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-deployment.yaml new file mode 100644 index 00000000..4cf7a6d5 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-deployment.yaml @@ -0,0 +1,84 @@ +apiVersion: apps/v1 +kind: Deployment +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator + namespace: monitoring +spec: + replicas: 1 + selector: + matchLabels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + template: + metadata: + annotations: + kubectl.kubernetes.io/default-container: prometheus-operator + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + spec: + automountServiceAccountToken: true + containers: + - args: + - --kubelet-service=kube-system/kubelet + - --prometheus-config-reloader=quay.io/prometheus-operator/prometheus-config-reloader:v0.66.0 + image: quay.io/prometheus-operator/prometheus-operator:v0.66.0 + name: prometheus-operator + ports: + - containerPort: 8080 + name: http + resources: + limits: + cpu: 200m + memory: 200Mi + requests: + cpu: 100m + memory: 100Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + - args: + - --logtostderr + - --secure-listen-address=:8443 + - --tls-cipher-suites=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_ECDSA_WITH_AES_128_GCM_SHA256,TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_ECDSA_WITH_AES_256_GCM_SHA384,TLS_ECDHE_RSA_WITH_CHACHA20_POLY1305,TLS_ECDHE_ECDSA_WITH_CHACHA20_POLY1305 + - --upstream=http://127.0.0.1:8080/ + image: quay.io/brancz/kube-rbac-proxy:v0.14.2 + name: kube-rbac-proxy + ports: + - containerPort: 8443 + name: https + resources: + limits: + cpu: 20m + memory: 40Mi + requests: + cpu: 10m + memory: 20Mi + securityContext: + allowPrivilegeEscalation: false + capabilities: + drop: + - ALL + readOnlyRootFilesystem: true + runAsGroup: 65532 + runAsNonRoot: true + runAsUser: 65532 + nodeSelector: + kubernetes.io/os: linux + securityContext: + runAsNonRoot: true + runAsUser: 65534 + seccompProfile: + type: RuntimeDefault + serviceAccountName: prometheus-operator diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-networkPolicy.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-networkPolicy.yaml new file mode 100644 index 00000000..8b7c944a --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-networkPolicy.yaml @@ -0,0 +1,29 @@ +apiVersion: networking.k8s.io/v1 +kind: NetworkPolicy +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator + namespace: monitoring +spec: + egress: + - {} + ingress: + - from: + - podSelector: + matchLabels: + app.kubernetes.io/name: prometheus + ports: + - port: 8443 + protocol: TCP + podSelector: + matchLabels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + policyTypes: + - Egress + - Ingress diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-prometheusRule.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-prometheusRule.yaml new file mode 100644 index 00000000..5e1e9f3d --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-prometheusRule.yaml @@ -0,0 +1,100 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + prometheus: k8s + role: alert-rules + name: prometheus-operator-rules + namespace: monitoring +spec: + groups: + - name: prometheus-operator + rules: + - alert: PrometheusOperatorListErrors + annotations: + description: Errors while performing List operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorlisterrors + summary: Errors while performing list operations in controller. + expr: | + (sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[10m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_list_operations_total{job="prometheus-operator",namespace="monitoring"}[10m]))) > 0.4 + for: 15m + labels: + severity: warning + - alert: PrometheusOperatorWatchErrors + annotations: + description: Errors while performing watch operations in controller {{$labels.controller}} in {{$labels.namespace}} namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorwatcherrors + summary: Errors while performing watch operations in controller. + expr: | + (sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_failed_total{job="prometheus-operator",namespace="monitoring"}[5m])) / sum by (cluster,controller,namespace) (rate(prometheus_operator_watch_operations_total{job="prometheus-operator",namespace="monitoring"}[5m]))) > 0.4 + for: 15m + labels: + severity: warning + - alert: PrometheusOperatorSyncFailed + annotations: + description: Controller {{ $labels.controller }} in {{ $labels.namespace }} namespace fails to reconcile {{ $value }} objects. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorsyncfailed + summary: Last controller reconciliation failed + expr: | + min_over_time(prometheus_operator_syncs{status="failed",job="prometheus-operator",namespace="monitoring"}[5m]) > 0 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorReconcileErrors + annotations: + description: '{{ $value | humanizePercentage }} of reconciling operations failed for {{ $labels.controller }} controller in {{ $labels.namespace }} namespace.' + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorreconcileerrors + summary: Errors while reconciling controller. + expr: | + (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]))) / (sum by (cluster,controller,namespace) (rate(prometheus_operator_reconcile_operations_total{job="prometheus-operator",namespace="monitoring"}[5m]))) > 0.1 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorNodeLookupErrors + annotations: + description: Errors while reconciling Prometheus in {{ $labels.namespace }} Namespace. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornodelookuperrors + summary: Errors while reconciling Prometheus. + expr: | + rate(prometheus_operator_node_address_lookup_errors_total{job="prometheus-operator",namespace="monitoring"}[5m]) > 0.1 + for: 10m + labels: + severity: warning + - alert: PrometheusOperatorNotReady + annotations: + description: Prometheus operator in {{ $labels.namespace }} namespace isn't ready to reconcile {{ $labels.controller }} resources. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatornotready + summary: Prometheus operator not ready + expr: | + min by (cluster,controller,namespace) (max_over_time(prometheus_operator_ready{job="prometheus-operator",namespace="monitoring"}[5m]) == 0) + for: 5m + labels: + severity: warning + - alert: PrometheusOperatorRejectedResources + annotations: + description: Prometheus operator in {{ $labels.namespace }} namespace rejected {{ printf "%0.0f" $value }} {{ $labels.controller }}/{{ $labels.resource }} resources. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/prometheusoperatorrejectedresources + summary: Resources rejected by Prometheus operator + expr: | + min_over_time(prometheus_operator_managed_resources{state="rejected",job="prometheus-operator",namespace="monitoring"}[5m]) > 0 + for: 5m + labels: + severity: warning + - name: config-reloaders + rules: + - alert: ConfigReloaderSidecarErrors + annotations: + description: |- + Errors encountered while the {{$labels.pod}} config-reloader sidecar attempts to sync config in {{$labels.namespace}} namespace. + As a result, configuration for service running in {{$labels.pod}} may be stale and cannot be updated anymore. + runbook_url: https://runbooks.prometheus-operator.dev/runbooks/prometheus-operator/configreloadersidecarerrors + summary: config-reloader sidecar has not had a successful reload for 10m + expr: | + max_over_time(reloader_last_reload_successful{namespace=~".+"}[5m]) == 0 + for: 10m + labels: + severity: warning diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-service.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-service.yaml new file mode 100644 index 00000000..5f11f684 --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-service.yaml @@ -0,0 +1,20 @@ +apiVersion: v1 +kind: Service +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator + namespace: monitoring +spec: + clusterIP: None + ports: + - name: https + port: 8443 + targetPort: https + selector: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceAccount.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceAccount.yaml new file mode 100644 index 00000000..568e30ca --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceAccount.yaml @@ -0,0 +1,11 @@ +apiVersion: v1 +automountServiceAccountToken: false +kind: ServiceAccount +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator + namespace: monitoring diff --git a/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceMonitor.yaml b/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceMonitor.yaml new file mode 100644 index 00000000..b8fb5cab --- /dev/null +++ b/deployment/helm/pc-apis-prometheus/prometheusOperator-serviceMonitor.yaml @@ -0,0 +1,24 @@ +apiVersion: monitoring.coreos.com/v1 +kind: ServiceMonitor +metadata: + labels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 + name: prometheus-operator + namespace: monitoring +spec: + endpoints: + - bearerTokenFile: /var/run/secrets/kubernetes.io/serviceaccount/token + honorLabels: true + port: https + scheme: https + tlsConfig: + insecureSkipVerify: true + selector: + matchLabels: + app.kubernetes.io/component: controller + app.kubernetes.io/name: prometheus-operator + app.kubernetes.io/part-of: kube-prometheus + app.kubernetes.io/version: 0.66.0 diff --git a/deployment/helm/pc-namespaces/Chart.yaml b/deployment/helm/pc-namespaces/Chart.yaml new file mode 100644 index 00000000..00803cd6 --- /dev/null +++ b/deployment/helm/pc-namespaces/Chart.yaml @@ -0,0 +1,6 @@ +apiVersion: v2 +name: pc-namespaces +description: A Helm chart for the namespaces of Planetary Computer APIs +type: application +version: 0.1.0 +appVersion: 0.1.0 diff --git a/deployment/helm/pc-namespaces/templates/namespace.yaml b/deployment/helm/pc-namespaces/templates/namespace.yaml new file mode 100644 index 00000000..013a00a8 --- /dev/null +++ b/deployment/helm/pc-namespaces/templates/namespace.yaml @@ -0,0 +1,9 @@ +apiVersion: v1 +kind: Namespace +metadata: + name: monitoring +--- +apiVersion: v1 +kind: Namespace +metadata: + name: pc diff --git a/deployment/helm/prometheus-crd/0alertmanagerConfigCustomResourceDefinition.yaml b/deployment/helm/prometheus-crd/0alertmanagerConfigCustomResourceDefinition.yaml new file mode 100644 index 00000000..97bde9e7 --- /dev/null +++ b/deployment/helm/prometheus-crd/0alertmanagerConfigCustomResourceDefinition.yaml @@ -0,0 +1,3401 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.11.1 + creationTimestamp: null + name: alertmanagerconfigs.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: AlertmanagerConfig + listKind: AlertmanagerConfigList + plural: alertmanagerconfigs + shortNames: + - amcfg + singular: alertmanagerconfig + scope: Namespaced + versions: + - name: v1alpha1 + schema: + openAPIV3Schema: + description: AlertmanagerConfig defines a namespaced AlertmanagerConfig to be aggregated across multiple namespaces configuring one Alertmanager cluster. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: AlertmanagerConfigSpec is a specification of the desired behavior of the Alertmanager configuration. By definition, the Alertmanager configuration only applies to alerts for which the `namespace` label is equal to the namespace of the AlertmanagerConfig resource. + properties: + inhibitRules: + description: List of inhibition rules. The rules will only apply to alerts matching the resource's namespace. + items: + description: InhibitRule defines an inhibition rule that allows to mute alerts when other alerts are already firing. See https://prometheus.io/docs/alerting/latest/configuration/#inhibit_rule + properties: + equal: + description: Labels that must have an equal value in the source and target alert for the inhibition to take effect. + items: + type: string + type: array + sourceMatch: + description: Matchers for which one or more alerts have to exist for the inhibition to take effect. The operator enforces that the alert matches the resource's namespace. + items: + description: Matcher defines how to match on alert's labels. + properties: + matchType: + description: Match operation available with AlertManager >= v0.22.0 and takes precedence over Regex (deprecated) if non-empty. + enum: + - '!=' + - = + - =~ + - '!~' + type: string + name: + description: Label to match. + minLength: 1 + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). Deprecated as of AlertManager >= v0.22.0 where a user should use MatchType instead. + type: boolean + value: + description: Label value to match. + type: string + required: + - name + type: object + type: array + targetMatch: + description: Matchers that have to be fulfilled in the alerts to be muted. The operator enforces that the alert matches the resource's namespace. + items: + description: Matcher defines how to match on alert's labels. + properties: + matchType: + description: Match operation available with AlertManager >= v0.22.0 and takes precedence over Regex (deprecated) if non-empty. + enum: + - '!=' + - = + - =~ + - '!~' + type: string + name: + description: Label to match. + minLength: 1 + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). Deprecated as of AlertManager >= v0.22.0 where a user should use MatchType instead. + type: boolean + value: + description: Label value to match. + type: string + required: + - name + type: object + type: array + type: object + type: array + muteTimeIntervals: + description: List of MuteTimeInterval specifying when the routes should be muted. + items: + description: MuteTimeInterval specifies the periods in time when notifications will be muted + properties: + name: + description: Name of the time interval + type: string + timeIntervals: + description: TimeIntervals is a list of TimeInterval + items: + description: TimeInterval describes intervals of time + properties: + daysOfMonth: + description: DaysOfMonth is a list of DayOfMonthRange + items: + description: DayOfMonthRange is an inclusive range of days of the month beginning at 1 + properties: + end: + description: End of the inclusive range + maximum: 31 + minimum: -31 + type: integer + start: + description: Start of the inclusive range + maximum: 31 + minimum: -31 + type: integer + type: object + type: array + months: + description: Months is a list of MonthRange + items: + description: MonthRange is an inclusive range of months of the year beginning in January Months can be specified by name (e.g 'January') by numerical month (e.g '1') or as an inclusive range (e.g 'January:March', '1:3', '1:March') + pattern: ^((?i)january|february|march|april|may|june|july|august|september|october|november|december|[1-12])(?:((:((?i)january|february|march|april|may|june|july|august|september|october|november|december|[1-12]))$)|$) + type: string + type: array + times: + description: Times is a list of TimeRange + items: + description: TimeRange defines a start and end time in 24hr format + properties: + endTime: + description: EndTime is the end time in 24hr format. + pattern: ^((([01][0-9])|(2[0-3])):[0-5][0-9])$|(^24:00$) + type: string + startTime: + description: StartTime is the start time in 24hr format. + pattern: ^((([01][0-9])|(2[0-3])):[0-5][0-9])$|(^24:00$) + type: string + type: object + type: array + weekdays: + description: Weekdays is a list of WeekdayRange + items: + description: WeekdayRange is an inclusive range of days of the week beginning on Sunday Days can be specified by name (e.g 'Sunday') or as an inclusive range (e.g 'Monday:Friday') + pattern: ^((?i)sun|mon|tues|wednes|thurs|fri|satur)day(?:((:(sun|mon|tues|wednes|thurs|fri|satur)day)$)|$) + type: string + type: array + years: + description: Years is a list of YearRange + items: + description: YearRange is an inclusive range of years + pattern: ^2\d{3}(?::2\d{3}|$) + type: string + type: array + type: object + type: array + type: object + type: array + receivers: + description: List of receivers. + items: + description: Receiver defines one or more notification integrations. + properties: + emailConfigs: + description: List of Email configurations. + items: + description: EmailConfig configures notifications via Email. + properties: + authIdentity: + description: The identity to use for authentication. + type: string + authPassword: + description: The secret's key that contains the password to use for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + authSecret: + description: The secret's key that contains the CRAM-MD5 secret. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + authUsername: + description: The username to use for authentication. + type: string + from: + description: The sender address. + type: string + headers: + description: Further headers email header key/value pairs. Overrides any headers previously set by the notification implementation. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + minLength: 1 + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + hello: + description: The hostname to identify to the SMTP server. + type: string + html: + description: The HTML body of the email notification. + type: string + requireTLS: + description: The SMTP TLS requirement. Note that Go does not support unencrypted connections to remote SMTP endpoints. + type: boolean + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + smarthost: + description: The SMTP host and port through which emails are sent. E.g. example.com:25 + type: string + text: + description: The text body of the email notification. + type: string + tlsConfig: + description: TLS configuration + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + to: + description: The email address to send notifications to. + type: string + type: object + type: array + name: + description: Name of the receiver. Must be unique across all items from the list. + minLength: 1 + type: string + opsgenieConfigs: + description: List of OpsGenie configurations. + items: + description: OpsGenieConfig configures notifications via OpsGenie. See https://prometheus.io/docs/alerting/latest/configuration/#opsgenie_config + properties: + actions: + description: Comma separated list of actions that will be available for the alert. + type: string + apiKey: + description: The secret's key that contains the OpsGenie API key. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiURL: + description: The URL to send OpsGenie API requests to. + type: string + description: + description: Description of the incident. + type: string + details: + description: A set of arbitrary key/value pairs that provide further detail about the incident. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + minLength: 1 + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + entity: + description: Optional field that can be used to specify which domain alert is related to. + type: string + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: Alert text limited to 130 characters. + type: string + note: + description: Additional alert note. + type: string + priority: + description: Priority level of alert. Possible values are P1, P2, P3, P4, and P5. + type: string + responders: + description: List of responders responsible for notifications. + items: + description: OpsGenieConfigResponder defines a responder to an incident. One of `id`, `name` or `username` has to be defined. + properties: + id: + description: ID of the responder. + type: string + name: + description: Name of the responder. + type: string + type: + description: Type of responder. + enum: + - team + - teams + - user + - escalation + - schedule + minLength: 1 + type: string + username: + description: Username of the responder. + type: string + required: + - type + type: object + type: array + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + source: + description: Backlink to the sender of the notification. + type: string + tags: + description: Comma separated list of tags attached to the notifications. + type: string + updateAlerts: + description: Whether to update message and description of the alert in OpsGenie if it already exists By default, the alert is never updated in OpsGenie, the new message only appears in activity log. + type: boolean + type: object + type: array + pagerdutyConfigs: + description: List of PagerDuty configurations. + items: + description: PagerDutyConfig configures notifications via PagerDuty. See https://prometheus.io/docs/alerting/latest/configuration/#pagerduty_config + properties: + class: + description: The class/type of the event. + type: string + client: + description: Client identification. + type: string + clientURL: + description: Backlink to the sender of notification. + type: string + component: + description: The part or component of the affected system that is broken. + type: string + description: + description: Description of the incident. + type: string + details: + description: Arbitrary key/value pairs that provide further detail about the incident. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + minLength: 1 + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + group: + description: A cluster or grouping of sources. + type: string + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + pagerDutyImageConfigs: + description: A list of image details to attach that provide further detail about an incident. + items: + description: PagerDutyImageConfig attaches images to an incident + properties: + alt: + description: Alt is the optional alternative text for the image. + type: string + href: + description: Optional URL; makes the image a clickable link. + type: string + src: + description: Src of the image being attached to the incident + type: string + type: object + type: array + pagerDutyLinkConfigs: + description: A list of link details to attach that provide further detail about an incident. + items: + description: PagerDutyLinkConfig attaches text links to an incident + properties: + alt: + description: Text that describes the purpose of the link, and can be used as the link's text. + type: string + href: + description: Href is the URL of the link to be attached + type: string + type: object + type: array + routingKey: + description: The secret's key that contains the PagerDuty integration key (when using Events API v2). Either this field or `serviceKey` needs to be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + serviceKey: + description: The secret's key that contains the PagerDuty service key (when using integration type "Prometheus"). Either this field or `routingKey` needs to be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + severity: + description: Severity of the incident. + type: string + url: + description: The URL to send requests to. + type: string + type: object + type: array + pushoverConfigs: + description: List of Pushover configurations. + items: + description: PushoverConfig configures notifications via Pushover. See https://prometheus.io/docs/alerting/latest/configuration/#pushover_config + properties: + expire: + description: How long your notification will continue to be retried for, unless the user acknowledges the notification. + pattern: ^(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?$ + type: string + html: + description: Whether notification message is HTML or plain text. + type: boolean + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: Notification message. + type: string + priority: + description: Priority, see https://pushover.net/api#priority + type: string + retry: + description: How often the Pushover servers will send the same notification to the user. Must be at least 30 seconds. + pattern: ^(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?$ + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + sound: + description: The name of one of the sounds supported by device clients to override the user's default sound choice + type: string + title: + description: Notification title. + type: string + token: + description: The secret's key that contains the registered application's API token, see https://pushover.net/apps. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + url: + description: A supplementary URL shown alongside the message. + type: string + urlTitle: + description: A title for supplementary URL, otherwise just the URL is shown + type: string + userKey: + description: The secret's key that contains the recipient user's user key. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + type: array + slackConfigs: + description: List of Slack configurations. + items: + description: SlackConfig configures notifications via Slack. See https://prometheus.io/docs/alerting/latest/configuration/#slack_config + properties: + actions: + description: A list of Slack actions that are sent with each notification. + items: + description: SlackAction configures a single Slack action that is sent with each notification. See https://api.slack.com/docs/message-attachments#action_fields and https://api.slack.com/docs/message-buttons for more information. + properties: + confirm: + description: SlackConfirmationField protect users from destructive actions or particularly distinguished decisions by asking them to confirm their button click one more time. See https://api.slack.com/docs/interactive-message-field-guide#confirmation_fields for more information. + properties: + dismissText: + type: string + okText: + type: string + text: + minLength: 1 + type: string + title: + type: string + required: + - text + type: object + name: + type: string + style: + type: string + text: + minLength: 1 + type: string + type: + minLength: 1 + type: string + url: + type: string + value: + type: string + required: + - text + - type + type: object + type: array + apiURL: + description: The secret's key that contains the Slack webhook URL. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + callbackId: + type: string + channel: + description: The channel or user to send notifications to. + type: string + color: + type: string + fallback: + type: string + fields: + description: A list of Slack fields that are sent with each notification. + items: + description: SlackField configures a single Slack field that is sent with each notification. Each field must contain a title, value, and optionally, a boolean value to indicate if the field is short enough to be displayed next to other fields designated as short. See https://api.slack.com/docs/message-attachments#fields for more information. + properties: + short: + type: boolean + title: + minLength: 1 + type: string + value: + minLength: 1 + type: string + required: + - title + - value + type: object + type: array + footer: + type: string + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + iconEmoji: + type: string + iconURL: + type: string + imageURL: + type: string + linkNames: + type: boolean + mrkdwnIn: + items: + type: string + type: array + pretext: + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + shortFields: + type: boolean + text: + type: string + thumbURL: + type: string + title: + type: string + titleLink: + type: string + username: + type: string + type: object + type: array + snsConfigs: + description: List of SNS configurations + items: + description: SNSConfig configures notifications via AWS SNS. See https://prometheus.io/docs/alerting/latest/configuration/#sns_configs + properties: + apiURL: + description: The SNS API URL i.e. https://sns.us-east-2.amazonaws.com. If not specified, the SNS API URL from the SNS SDK will be used. + type: string + attributes: + additionalProperties: + type: string + description: SNS message attributes. + type: object + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: The message content of the SNS notification. + type: string + phoneNumber: + description: Phone number if message is delivered via SMS in E.164 format. If you don't specify this value, you must specify a value for the TopicARN or TargetARN. + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + sigv4: + description: Configures AWS's Signature Verification 4 signing process to sign requests. + properties: + accessKey: + description: AccessKey is the AWS API key. If not specified, the environment variable `AWS_ACCESS_KEY_ID` is used. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + profile: + description: Profile is the named AWS profile used to authenticate. + type: string + region: + description: Region is the AWS region. If blank, the region from the default credentials chain used. + type: string + roleArn: + description: RoleArn is the named AWS profile used to authenticate. + type: string + secretKey: + description: SecretKey is the AWS API secret. If not specified, the environment variable `AWS_SECRET_ACCESS_KEY` is used. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + subject: + description: Subject line when the message is delivered to email endpoints. + type: string + targetARN: + description: The mobile platform endpoint ARN if message is delivered via mobile notifications. If you don't specify this value, you must specify a value for the topic_arn or PhoneNumber. + type: string + topicARN: + description: SNS topic ARN, i.e. arn:aws:sns:us-east-2:698519295917:My-Topic If you don't specify this value, you must specify a value for the PhoneNumber or TargetARN. + type: string + type: object + type: array + telegramConfigs: + description: List of Telegram configurations. + items: + description: TelegramConfig configures notifications via Telegram. See https://prometheus.io/docs/alerting/latest/configuration/#telegram_config + properties: + apiURL: + description: The Telegram API URL i.e. https://api.telegram.org. If not specified, default API URL will be used. + type: string + botToken: + description: Telegram bot token The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + chatID: + description: The Telegram chat ID. + format: int64 + type: integer + disableNotifications: + description: Disable telegram notifications + type: boolean + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: Message template + type: string + parseMode: + description: Parse mode for telegram message + enum: + - MarkdownV2 + - Markdown + - HTML + type: string + sendResolved: + description: Whether to notify about resolved alerts. + type: boolean + type: object + type: array + victoropsConfigs: + description: List of VictorOps configurations. + items: + description: VictorOpsConfig configures notifications via VictorOps. See https://prometheus.io/docs/alerting/latest/configuration/#victorops_config + properties: + apiKey: + description: The secret's key that contains the API key to use when talking to the VictorOps API. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiUrl: + description: The VictorOps API URL. + type: string + customFields: + description: Additional custom fields for notification. + items: + description: KeyValue defines a (key, value) tuple. + properties: + key: + description: Key of the tuple. + minLength: 1 + type: string + value: + description: Value of the tuple. + type: string + required: + - key + - value + type: object + type: array + entityDisplayName: + description: Contains summary of the alerted problem. + type: string + httpConfig: + description: The HTTP client's configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + messageType: + description: Describes the behavior of the alert (CRITICAL, WARNING, INFO). + type: string + monitoringTool: + description: The monitoring tool the state message is from. + type: string + routingKey: + description: A key used to map the alert to a team. + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + stateMessage: + description: Contains long explanation of the alerted problem. + type: string + type: object + type: array + webhookConfigs: + description: List of webhook configurations. + items: + description: WebhookConfig configures notifications via a generic receiver supporting the webhook payload. See https://prometheus.io/docs/alerting/latest/configuration/#webhook_config + properties: + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + maxAlerts: + description: Maximum number of alerts to be sent per webhook message. When 0, all alerts are included. + format: int32 + minimum: 0 + type: integer + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + url: + description: The URL to send HTTP POST requests to. `urlSecret` takes precedence over `url`. One of `urlSecret` and `url` should be defined. + type: string + urlSecret: + description: The secret's key that contains the webhook URL to send HTTP requests to. `urlSecret` takes precedence over `url`. One of `urlSecret` and `url` should be defined. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + type: object + type: array + wechatConfigs: + description: List of WeChat configurations. + items: + description: WeChatConfig configures notifications via WeChat. See https://prometheus.io/docs/alerting/latest/configuration/#wechat_config + properties: + agentID: + type: string + apiSecret: + description: The secret's key that contains the WeChat API key. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + apiURL: + description: The WeChat API URL. + type: string + corpID: + description: The corp id for authentication. + type: string + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the AlertmanagerConfig object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + message: + description: API request data as defined by the WeChat API. + type: string + messageType: + type: string + sendResolved: + description: Whether or not to notify about resolved alerts. + type: boolean + toParty: + type: string + toTag: + type: string + toUser: + type: string + type: object + type: array + required: + - name + type: object + type: array + route: + description: The Alertmanager route definition for alerts matching the resource's namespace. If present, it will be added to the generated Alertmanager configuration as a first-level route. + properties: + activeTimeIntervals: + description: ActiveTimeIntervals is a list of MuteTimeInterval names when this route should be active. + items: + type: string + type: array + continue: + description: Boolean indicating whether an alert should continue matching subsequent sibling nodes. It will always be overridden to true for the first-level route by the Prometheus operator. + type: boolean + groupBy: + description: List of labels to group by. Labels must not be repeated (unique list). Special label "..." (aggregate by all possible labels), if provided, must be the only element in the list. + items: + type: string + type: array + groupInterval: + description: 'How long to wait before sending an updated notification. Must match the regular expression`^(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?$` Example: "5m"' + type: string + groupWait: + description: 'How long to wait before sending the initial notification. Must match the regular expression`^(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?$` Example: "30s"' + type: string + matchers: + description: 'List of matchers that the alert''s labels should match. For the first level route, the operator removes any existing equality and regexp matcher on the `namespace` label and adds a `namespace: ` matcher.' + items: + description: Matcher defines how to match on alert's labels. + properties: + matchType: + description: Match operation available with AlertManager >= v0.22.0 and takes precedence over Regex (deprecated) if non-empty. + enum: + - '!=' + - = + - =~ + - '!~' + type: string + name: + description: Label to match. + minLength: 1 + type: string + regex: + description: Whether to match on equality (false) or regular-expression (true). Deprecated as of AlertManager >= v0.22.0 where a user should use MatchType instead. + type: boolean + value: + description: Label value to match. + type: string + required: + - name + type: object + type: array + muteTimeIntervals: + description: 'Note: this comment applies to the field definition above but appears below otherwise it gets included in the generated manifest. CRD schema doesn''t support self-referential types for now (see https://github.com/kubernetes/kubernetes/issues/62872). We have to use an alternative type to circumvent the limitation. The downside is that the Kube API can''t validate the data beyond the fact that it is a valid JSON representation. MuteTimeIntervals is a list of MuteTimeInterval names that will mute this route when matched,' + items: + type: string + type: array + receiver: + description: Name of the receiver for this route. If not empty, it should be listed in the `receivers` field. + type: string + repeatInterval: + description: 'How long to wait before repeating the last notification. Must match the regular expression`^(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?$` Example: "4h"' + type: string + routes: + description: Child routes. + items: + x-kubernetes-preserve-unknown-fields: true + type: array + type: object + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/deployment/helm/prometheus-crd/0alertmanagerCustomResourceDefinition.yaml b/deployment/helm/prometheus-crd/0alertmanagerCustomResourceDefinition.yaml new file mode 100644 index 00000000..f800bebf --- /dev/null +++ b/deployment/helm/prometheus-crd/0alertmanagerCustomResourceDefinition.yaml @@ -0,0 +1,4635 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.11.1 + creationTimestamp: null + name: alertmanagers.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: Alertmanager + listKind: AlertmanagerList + plural: alertmanagers + shortNames: + - am + singular: alertmanager + scope: Namespaced + versions: + - additionalPrinterColumns: + - description: The version of Alertmanager + jsonPath: .spec.version + name: Version + type: string + - description: The number of desired replicas + jsonPath: .spec.replicas + name: Replicas + type: integer + - description: The number of ready replicas + jsonPath: .status.availableReplicas + name: Ready + type: integer + - jsonPath: .status.conditions[?(@.type == 'Reconciled')].status + name: Reconciled + type: string + - jsonPath: .status.conditions[?(@.type == 'Available')].status + name: Available + type: string + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + - description: Whether the resource reconciliation is paused or not + jsonPath: .status.paused + name: Paused + priority: 1 + type: boolean + name: v1 + schema: + openAPIV3Schema: + description: Alertmanager describes an Alertmanager cluster. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: 'Specification of the desired behavior of the Alertmanager cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + additionalPeers: + description: AdditionalPeers allows injecting a set of additional Alertmanagers to peer with to form a highly available cluster. + items: + type: string + type: array + affinity: + description: If specified, the pod's scheduling constraints. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + properties: + preference: + description: A node selector term, associated with the corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + type: array + required: + - nodeSelectorTerms + type: object + x-kubernetes-map-type: atomic + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + alertmanagerConfigMatcherStrategy: + description: The AlertmanagerConfigMatcherStrategy defines how AlertmanagerConfig objects match the alerts. In the future more options may be added. + properties: + type: + default: OnNamespace + description: If set to `OnNamespace`, the operator injects a label matcher matching the namespace of the AlertmanagerConfig object for all its routes and inhibition rules. `None` will not add any additional matchers other than the ones specified in the AlertmanagerConfig. Default is `OnNamespace`. + enum: + - OnNamespace + - None + type: string + type: object + alertmanagerConfigNamespaceSelector: + description: Namespaces to be selected for AlertmanagerConfig discovery. If nil, only check own namespace. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + alertmanagerConfigSelector: + description: AlertmanagerConfigs to be selected for to merge and configure Alertmanager with. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + alertmanagerConfiguration: + description: 'EXPERIMENTAL: alertmanagerConfiguration specifies the configuration of Alertmanager. If defined, it takes precedence over the `configSecret` field. This field may change in future releases.' + properties: + global: + description: Defines the global parameters of the Alertmanager configuration. + properties: + httpConfig: + description: HTTP client configuration. + properties: + authorization: + description: Authorization header configuration for the client. This is mutually exclusive with BasicAuth and is only available starting from Alertmanager v0.22+. + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth for the client. This is mutually exclusive with Authorization. If both are defined, BasicAuth takes precedence. + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: The secret's key that contains the bearer token to be used by the client for authentication. The secret needs to be in the same namespace as the Alertmanager object and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + followRedirects: + description: FollowRedirects specifies whether the client should follow HTTP 3xx redirects. + type: boolean + oauth2: + description: OAuth2 client credentials used to fetch a token for the targets. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + proxyURL: + description: Optional proxy URL. + type: string + tlsConfig: + description: TLS configuration for the client. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + opsGenieApiKey: + description: The default OpsGenie API Key. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + opsGenieApiUrl: + description: The default OpsGenie API URL. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + pagerdutyUrl: + description: The default Pagerduty URL. + type: string + resolveTimeout: + description: ResolveTimeout is the default value used by alertmanager if the alert does not include EndsAt, after this time passes it can declare the alert as resolved if it has not been updated. This has no impact on alerts from Prometheus, as they always include EndsAt. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + slackApiUrl: + description: The default Slack API URL. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + smtp: + description: Configures global SMTP parameters. + properties: + authIdentity: + description: SMTP Auth using PLAIN + type: string + authPassword: + description: SMTP Auth using LOGIN and PLAIN. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + authSecret: + description: SMTP Auth using CRAM-MD5. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + authUsername: + description: SMTP Auth using CRAM-MD5, LOGIN and PLAIN. If empty, Alertmanager doesn't authenticate to the SMTP server. + type: string + from: + description: The default SMTP From header field. + type: string + hello: + description: The default hostname to identify to the SMTP server. + type: string + requireTLS: + description: The default SMTP TLS requirement. Note that Go does not support unencrypted connections to remote SMTP endpoints. + type: boolean + smartHost: + description: The default SMTP smarthost used for sending emails. + properties: + host: + description: Defines the host's address, it can be a DNS name or a literal IP address. + minLength: 1 + type: string + port: + description: Defines the host's port, it can be a literal port number or a port name. + minLength: 1 + type: string + required: + - host + - port + type: object + type: object + type: object + name: + description: The name of the AlertmanagerConfig resource which is used to generate the Alertmanager configuration. It must be defined in the same namespace as the Alertmanager object. The operator will not enforce a `namespace` label for routes and inhibition rules. + minLength: 1 + type: string + templates: + description: Custom notification templates. + items: + description: SecretOrConfigMap allows to specify data as a Secret or ConfigMap. Fields are mutually exclusive. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + type: array + type: object + automountServiceAccountToken: + description: 'AutomountServiceAccountToken indicates whether a service account token should be automatically mounted in the pod. If the service account has `automountServiceAccountToken: true`, set the field to `false` to opt out of automounting API credentials.' + type: boolean + baseImage: + description: 'Base image that is used to deploy pods, without tag. Deprecated: use ''image'' instead' + type: string + clusterAdvertiseAddress: + description: 'ClusterAdvertiseAddress is the explicit address to advertise in cluster. Needs to be provided for non RFC1918 [1] (public) addresses. [1] RFC1918: https://tools.ietf.org/html/rfc1918' + type: string + clusterGossipInterval: + description: Interval between gossip attempts. + pattern: ^(0|(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + clusterPeerTimeout: + description: Timeout for cluster peering. + pattern: ^(0|(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + clusterPushpullInterval: + description: Interval between pushpull attempts. + pattern: ^(0|(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + configMaps: + description: ConfigMaps is a list of ConfigMaps in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. Each ConfigMap is added to the StatefulSet definition as a volume named `configmap-`. The ConfigMaps are mounted into `/etc/alertmanager/configmaps/` in the 'alertmanager' container. + items: + type: string + type: array + configSecret: + description: "ConfigSecret is the name of a Kubernetes Secret in the same namespace as the Alertmanager object, which contains the configuration for this Alertmanager instance. If empty, it defaults to `alertmanager-`. \n The Alertmanager configuration should be available under the `alertmanager.yaml` key. Additional keys from the original secret are copied to the generated secret and mounted into the `/etc/alertmanager/config` directory in the `alertmanager` container. \n If either the secret or the `alertmanager.yaml` key is missing, the operator provisions a minimal Alertmanager configuration with one empty receiver (effectively dropping alert notifications)." + type: string + containers: + description: 'Containers allows injecting additional containers. This is meant to allow adding an authentication proxy to an Alertmanager pod. Containers described here modify an operator generated container if they share the same name and modifications are done via a strategic merge patch. The current container names are: `alertmanager` and `config-reloader`. Overriding containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The container image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The container image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['''']`, `metadata.annotations['''']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + description: 'Container image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The Pod''s termination grace period countdown begins before the PreStop hook is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period (unless delayed by finalizers). Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Modifying this array with strategic merge patch may corrupt the data. For more information See https://github.com/kubernetes/kubernetes/issues/108255. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resizePolicy: + description: Resources resize policy for the container. + items: + description: ContainerResizePolicy represents resource resize policy for the container. + properties: + resourceName: + description: 'Name of the resource to which this resource resize policy applies. Supported values: cpu, memory.' + type: string + restartPolicy: + description: Restart policy to apply when specified resource is resized. If not specified, it defaults to NotRequired. + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the container should be run with. If set, the fields of SecurityContext override the equivalent fields of PodSecurityContext. More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN Note that this field cannot be set when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. Note that this field cannot be set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. Note that this field cannot be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. If seccomp options are provided at both the pod & container level, the container options override the pod options. Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile will be applied. Valid options are: \n Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should be run as a 'Host Process' container. This field is alpha-level and will only be honored by components that enable the WindowsHostProcessContainers feature flag. Setting this field without the feature flag will result in errors when validating the Pod. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + externalUrl: + description: The external URL the Alertmanager instances will be available under. This is necessary to generate correct URLs. This is necessary if Alertmanager is not served from root of a DNS name. + type: string + forceEnableClusterMode: + description: ForceEnableClusterMode ensures Alertmanager does not deactivate the cluster mode when running with a single replica. Use case is e.g. spanning an Alertmanager cluster across Kubernetes clusters with a single replica in each. + type: boolean + hostAliases: + description: Pods' hostAliases configuration + items: + description: HostAlias holds the mapping between IP and hostnames that will be injected as an entry in the pod's hosts file. + properties: + hostnames: + description: Hostnames for the above IP address. + items: + type: string + type: array + ip: + description: IP address of the host file entry. + type: string + required: + - hostnames + - ip + type: object + type: array + x-kubernetes-list-map-keys: + - ip + x-kubernetes-list-type: map + image: + description: Image if specified has precedence over baseImage, tag and sha combinations. Specifying the version is still necessary to ensure the Prometheus Operator knows what version of Alertmanager is being configured. + type: string + imagePullPolicy: + description: Image pull policy for the 'alertmanager', 'init-config-reloader' and 'config-reloader' containers. See https://kubernetes.io/docs/concepts/containers/images/#image-pull-policy for more details. + enum: + - "" + - Always + - Never + - IfNotPresent + type: string + imagePullSecrets: + description: An optional list of references to secrets in the same namespace to use for pulling prometheus and alertmanager images from registries see http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod + items: + description: LocalObjectReference contains enough information to let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + type: array + initContainers: + description: 'InitContainers allows adding initContainers to the pod definition. Those can be used to e.g. fetch secrets for injection into the Alertmanager configuration from external sources. Any errors during the execution of an initContainer will lead to a restart of the Pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ InitContainers described here modify an operator generated init containers if they share the same name and modifications are done via a strategic merge patch. The current init container name is: `init-config-reloader`. Overriding init containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice.' + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The container image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The container image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['''']`, `metadata.annotations['''']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + description: 'Container image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The Pod''s termination grace period countdown begins before the PreStop hook is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period (unless delayed by finalizers). Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Modifying this array with strategic merge patch may corrupt the data. For more information See https://github.com/kubernetes/kubernetes/issues/108255. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resizePolicy: + description: Resources resize policy for the container. + items: + description: ContainerResizePolicy represents resource resize policy for the container. + properties: + resourceName: + description: 'Name of the resource to which this resource resize policy applies. Supported values: cpu, memory.' + type: string + restartPolicy: + description: Restart policy to apply when specified resource is resized. If not specified, it defaults to NotRequired. + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the container should be run with. If set, the fields of SecurityContext override the equivalent fields of PodSecurityContext. More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN Note that this field cannot be set when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. Note that this field cannot be set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. Note that this field cannot be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. If seccomp options are provided at both the pod & container level, the container options override the pod options. Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile will be applied. Valid options are: \n Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should be run as a 'Host Process' container. This field is alpha-level and will only be honored by components that enable the WindowsHostProcessContainers feature flag. Setting this field without the feature flag will result in errors when validating the Pod. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + listenLocal: + description: ListenLocal makes the Alertmanager server listen on loopback, so that it does not bind against the Pod IP. Note this is only for the Alertmanager UI, not the gossip communication. + type: boolean + logFormat: + description: Log format for Alertmanager to be configured with. + enum: + - "" + - logfmt + - json + type: string + logLevel: + description: Log level for Alertmanager to be configured with. + enum: + - "" + - debug + - info + - warn + - error + type: string + minReadySeconds: + description: Minimum number of seconds for which a newly created pod should be ready without any of its container crashing for it to be considered available. Defaults to 0 (pod will be considered available as soon as it is ready) This is an alpha field from kubernetes 1.22 until 1.24 which requires enabling the StatefulSetMinReadySeconds feature gate. + format: int32 + type: integer + nodeSelector: + additionalProperties: + type: string + description: Define which Nodes the Pods are scheduled on. + type: object + paused: + description: If set to true all actions on the underlying managed objects are not goint to be performed, except for delete actions. + type: boolean + podMetadata: + description: PodMetadata configures Labels and Annotations which are propagated to the alertmanager pods. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + portName: + default: web + description: Port name used for the pods and governing service. Defaults to `web`. + type: string + priorityClassName: + description: Priority class assigned to the Pods + type: string + replicas: + description: Size is the expected size of the alertmanager cluster. The controller will eventually make the size of the running cluster equal to the expected size. + format: int32 + type: integer + resources: + description: Define resources requests and limits for single Pods. + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + retention: + default: 120h + description: Time duration Alertmanager shall retain data for. Default is '120h', and must match the regular expression `[0-9]+(ms|s|m|h)` (milliseconds seconds minutes hours). + pattern: ^(0|(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + routePrefix: + description: The route prefix Alertmanager registers HTTP handlers for. This is useful, if using ExternalURL and a proxy is rewriting HTTP routes of a request, and the actual ExternalURL is still true, but the server serves requests under a different route prefix. For example for use with `kubectl proxy`. + type: string + secrets: + description: Secrets is a list of Secrets in the same namespace as the Alertmanager object, which shall be mounted into the Alertmanager Pods. Each Secret is added to the StatefulSet definition as a volume named `secret-`. The Secrets are mounted into `/etc/alertmanager/secrets/` in the 'alertmanager' container. + items: + type: string + type: array + securityContext: + description: SecurityContext holds pod-level security attributes and common container settings. This defaults to the default PodSecurityContext. + properties: + fsGroup: + description: "A special supplemental group that applies to all containers in a pod. Some volume types allow the Kubelet to change the ownership of that volume to be owned by the pod: \n 1. The owning GID will be the FSGroup 2. The setgid bit is set (new files created in the volume will be owned by FSGroup) 3. The permission bits are OR'd with rw-rw---- \n If unset, the Kubelet will not modify the ownership and permissions of any volume. Note that this field cannot be set when spec.os.name is windows." + format: int64 + type: integer + fsGroupChangePolicy: + description: 'fsGroupChangePolicy defines behavior of changing ownership and permission of the volume before being exposed inside Pod. This field will only apply to volume types which support fsGroup based ownership(and permissions). It will have no effect on ephemeral volume types such as: secret, configmaps and emptydir. Valid values are "OnRootMismatch" and "Always". If not specified, "Always" is used. Note that this field cannot be set when spec.os.name is windows.' + type: string + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to all containers. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in SecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence for that container. Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by the containers in this pod. Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile will be applied. Valid options are: \n Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied." + type: string + required: + - type + type: object + supplementalGroups: + description: A list of groups applied to the first process run in each container, in addition to the container's primary GID, the fsGroup (if specified), and group memberships defined in the container image for the uid of the container process. If unspecified, no additional groups are added to any container. Note that group memberships defined in the container image for the uid of the container process are still effective, even if they are not included in this list. Note that this field cannot be set when spec.os.name is windows. + items: + format: int64 + type: integer + type: array + sysctls: + description: Sysctls hold a list of namespaced sysctls used for the pod. Pods with unsupported sysctls (by the container runtime) might fail to launch. Note that this field cannot be set when spec.os.name is windows. + items: + description: Sysctl defines a kernel parameter to be set + properties: + name: + description: Name of a property to set + type: string + value: + description: Value of a property to set + type: string + required: + - name + - value + type: object + type: array + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options within a container's SecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should be run as a 'Host Process' container. This field is alpha-level and will only be honored by components that enable the WindowsHostProcessContainers feature flag. Setting this field without the feature flag will result in errors when validating the Pod. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + serviceAccountName: + description: ServiceAccountName is the name of the ServiceAccount to use to run the Prometheus Pods. + type: string + sha: + description: 'SHA of Alertmanager container image to be deployed. Defaults to the value of `version`. Similar to a tag, but the SHA explicitly deploys an immutable container image. Version and Tag are ignored if SHA is set. Deprecated: use ''image'' instead. The image digest can be specified as part of the image URL.' + type: string + storage: + description: Storage is the definition of how storage will be used by the Alertmanager instances. + properties: + disableMountSubPath: + description: '*Deprecated: subPath usage will be removed in a future release.*' + type: boolean + emptyDir: + description: 'EmptyDirVolumeSource to be used by the StatefulSet. If specified, it takes precedence over `ephemeral` and `volumeClaimTemplate`. More info: https://kubernetes.io/docs/concepts/storage/volumes/#emptydir' + properties: + medium: + description: 'medium represents what type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'sizeLimit is the total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + description: 'EphemeralVolumeSource to be used by the StatefulSet. This is a beta field in k8s 1.21 and GA in 1.15. For lower versions, starting with k8s 1.19, it requires enabling the GenericEphemeralVolume feature gate. More info: https://kubernetes.io/docs/concepts/storage/ephemeral-volumes/#generic-ephemeral-volumes' + properties: + volumeClaimTemplate: + description: "Will be used to create a stand-alone PVC to provision the volume. The pod in which this EphemeralVolumeSource is embedded will be the owner of the PVC, i.e. the PVC will be deleted together with the pod. The name of the PVC will be `-` where `` is the name from the `PodSpec.Volumes` array entry. Pod validation will reject the pod if the concatenated name is not valid for a PVC (for example, too long). \n An existing PVC with that name that is not owned by the pod will *not* be used for the pod to avoid using an unrelated volume by mistake. Starting the pod is then blocked until the unrelated PVC is removed. If such a pre-created PVC is meant to be used by the pod, the PVC has to updated with an owner reference to the pod once the pod exists. Normally this should not be necessary, but it may be useful when manually reconstructing a broken cluster. \n This field is read-only and no changes will be made by Kubernetes to the PVC after it has been created. \n Required, must not be nil." + properties: + metadata: + description: May contain labels and annotations that will be copied into the PVC when creating it. No other fields are allowed and will be rejected during validation. + type: object + spec: + description: The specification for the PersistentVolumeClaim. The entire content is copied unchanged into the PVC that gets created from this template. The same fields as in a PersistentVolumeClaim are also valid here. + properties: + accessModes: + description: 'accessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'dataSource field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) * An existing PVC (PersistentVolumeClaim) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. When the AnyVolumeDataSource feature gate is enabled, dataSource contents will be copied to dataSourceRef, and dataSourceRef contents will be copied to dataSource when dataSourceRef.namespace is not specified. If the namespace is specified, then dataSourceRef will not be copied to dataSource.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + description: 'dataSourceRef specifies the object from which to populate the volume with data, if a non-empty volume is desired. This may be any object from a non-empty API group (non core object) or a PersistentVolumeClaim object. When this field is specified, volume binding will only succeed if the type of the specified object matches some installed volume populator or dynamic provisioner. This field will replace the functionality of the dataSource field and as such if both fields are non-empty, they must have the same value. For backwards compatibility, when namespace isn''t specified in dataSourceRef, both fields (dataSource and dataSourceRef) will be set to the same value automatically if one of them is empty and the other is non-empty. When namespace is specified in dataSourceRef, dataSource isn''t set to the same value and must be empty. There are three important differences between dataSource and dataSourceRef: * While dataSource only allows two specific types of objects, dataSourceRef allows any non-core object, as well as PersistentVolumeClaim objects. * While dataSource ignores disallowed values (dropping them), dataSourceRef preserves all values, and generates an error if a disallowed value is specified. * While dataSource only allows local objects, dataSourceRef allows objects in any namespaces. (Beta) Using this field requires the AnyVolumeDataSource feature gate to be enabled. (Alpha) Using the namespace field of dataSourceRef requires the CrossNamespaceVolumeDataSource feature gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + namespace: + description: Namespace is the namespace of resource being referenced Note that when a namespace is specified, a gateway.networking.k8s.io/ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. (Alpha) This field requires the CrossNamespaceVolumeDataSource feature gate to be enabled. + type: string + required: + - kind + - name + type: object + resources: + description: 'resources represents the minimum resources the volume should have. If RecoverVolumeExpansionFailure feature is enabled users are allowed to specify resource requirements that are lower than previous value but must still be higher than capacity recorded in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: selector is a label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + description: 'storageClassName is the name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: volumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + required: + - spec + type: object + type: object + volumeClaimTemplate: + description: Defines the PVC spec to be used by the Prometheus StatefulSets. The easiest way to use a volume that cannot be automatically provisioned is to use a label selector alongside manually created PersistentVolumes. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + description: EmbeddedMetadata contains metadata relevant to an EmbeddedResource. + properties: + annotations: + additionalProperties: + type: string + description: 'Annotations is an unstructured key value map stored with a resource that may be set by external tools to store and retrieve arbitrary metadata. They are not queryable and should be preserved when modifying objects. More info: http://kubernetes.io/docs/user-guide/annotations' + type: object + labels: + additionalProperties: + type: string + description: 'Map of string keys and values that can be used to organize and categorize (scope and select) objects. May match selectors of replication controllers and services. More info: http://kubernetes.io/docs/user-guide/labels' + type: object + name: + description: 'Name must be unique within a namespace. Is required when creating resources, although some resources may allow a client to request the generation of an appropriate name automatically. Name is primarily intended for creation idempotence and configuration definition. Cannot be updated. More info: http://kubernetes.io/docs/user-guide/identifiers#names' + type: string + type: object + spec: + description: 'Defines the desired characteristics of a volume requested by a pod author. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + accessModes: + description: 'accessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'dataSource field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) * An existing PVC (PersistentVolumeClaim) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. When the AnyVolumeDataSource feature gate is enabled, dataSource contents will be copied to dataSourceRef, and dataSourceRef contents will be copied to dataSource when dataSourceRef.namespace is not specified. If the namespace is specified, then dataSourceRef will not be copied to dataSource.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + description: 'dataSourceRef specifies the object from which to populate the volume with data, if a non-empty volume is desired. This may be any object from a non-empty API group (non core object) or a PersistentVolumeClaim object. When this field is specified, volume binding will only succeed if the type of the specified object matches some installed volume populator or dynamic provisioner. This field will replace the functionality of the dataSource field and as such if both fields are non-empty, they must have the same value. For backwards compatibility, when namespace isn''t specified in dataSourceRef, both fields (dataSource and dataSourceRef) will be set to the same value automatically if one of them is empty and the other is non-empty. When namespace is specified in dataSourceRef, dataSource isn''t set to the same value and must be empty. There are three important differences between dataSource and dataSourceRef: * While dataSource only allows two specific types of objects, dataSourceRef allows any non-core object, as well as PersistentVolumeClaim objects. * While dataSource ignores disallowed values (dropping them), dataSourceRef preserves all values, and generates an error if a disallowed value is specified. * While dataSource only allows local objects, dataSourceRef allows objects in any namespaces. (Beta) Using this field requires the AnyVolumeDataSource feature gate to be enabled. (Alpha) Using the namespace field of dataSourceRef requires the CrossNamespaceVolumeDataSource feature gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + namespace: + description: Namespace is the namespace of resource being referenced Note that when a namespace is specified, a gateway.networking.k8s.io/ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. (Alpha) This field requires the CrossNamespaceVolumeDataSource feature gate to be enabled. + type: string + required: + - kind + - name + type: object + resources: + description: 'resources represents the minimum resources the volume should have. If RecoverVolumeExpansionFailure feature is enabled users are allowed to specify resource requirements that are lower than previous value but must still be higher than capacity recorded in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: selector is a label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + description: 'storageClassName is the name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: volumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + status: + description: '*Deprecated: this field is never set.*' + properties: + accessModes: + description: 'accessModes contains the actual access modes the volume backing the PVC has. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + allocatedResources: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: allocatedResources is the storage resource within AllocatedResources tracks the capacity allocated to a PVC. It may be larger than the actual capacity when a volume expansion operation is requested. For storage quota, the larger value from allocatedResources and PVC.spec.resources is used. If allocatedResources is not set, PVC.spec.resources alone is used for quota calculation. If a volume expansion capacity request is lowered, allocatedResources is only lowered if there are no expansion operations in progress and if the actual volume capacity is equal or lower than the requested capacity. This is an alpha field and requires enabling RecoverVolumeExpansionFailure feature. + type: object + capacity: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: capacity represents the actual resources of the underlying volume. + type: object + conditions: + description: conditions is the current Condition of persistent volume claim. If underlying persistent volume is being resized then the Condition will be set to 'ResizeStarted'. + items: + description: PersistentVolumeClaimCondition contains details about state of pvc + properties: + lastProbeTime: + description: lastProbeTime is the time we probed the condition. + format: date-time + type: string + lastTransitionTime: + description: lastTransitionTime is the time the condition transitioned from one status to another. + format: date-time + type: string + message: + description: message is the human-readable message indicating details about last transition. + type: string + reason: + description: reason is a unique, this should be a short, machine understandable string that gives the reason for condition's last transition. If it reports "ResizeStarted" that means the underlying persistent volume is being resized. + type: string + status: + type: string + type: + description: PersistentVolumeClaimConditionType is a valid value of PersistentVolumeClaimCondition.Type + type: string + required: + - status + - type + type: object + type: array + phase: + description: phase represents the current phase of PersistentVolumeClaim. + type: string + resizeStatus: + description: resizeStatus stores status of resize operation. ResizeStatus is not set by default but when expansion is complete resizeStatus is set to empty string by resize controller or kubelet. This is an alpha field and requires enabling RecoverVolumeExpansionFailure feature. + type: string + type: object + type: object + type: object + tag: + description: 'Tag of Alertmanager container image to be deployed. Defaults to the value of `version`. Version is ignored if Tag is set. Deprecated: use ''image'' instead. The image tag can be specified as part of the image URL.' + type: string + tolerations: + description: If specified, the pod's tolerations. + items: + description: The pod this Toleration is attached to tolerates any taint that matches the triple using the matching operator . + properties: + effect: + description: Effect indicates the taint effect to match. Empty means match all taint effects. When specified, allowed values are NoSchedule, PreferNoSchedule and NoExecute. + type: string + key: + description: Key is the taint key that the toleration applies to. Empty means match all taint keys. If the key is empty, operator must be Exists; this combination means to match all values and all keys. + type: string + operator: + description: Operator represents a key's relationship to the value. Valid operators are Exists and Equal. Defaults to Equal. Exists is equivalent to wildcard for value, so that a pod can tolerate all taints of a particular category. + type: string + tolerationSeconds: + description: TolerationSeconds represents the period of time the toleration (which must be of effect NoExecute, otherwise this field is ignored) tolerates the taint. By default, it is not set, which means tolerate the taint forever (do not evict). Zero and negative values will be treated as 0 (evict immediately) by the system. + format: int64 + type: integer + value: + description: Value is the taint value the toleration matches to. If the operator is Exists, the value should be empty, otherwise just a regular string. + type: string + type: object + type: array + topologySpreadConstraints: + description: If specified, the pod's topology spread constraints. + items: + description: TopologySpreadConstraint specifies how to spread matching pods among the given topology. + properties: + labelSelector: + description: LabelSelector is used to find matching pods. Pods that match this label selector are counted to determine the number of pods in their corresponding topology domain. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + matchLabelKeys: + description: "MatchLabelKeys is a set of pod label keys to select the pods over which spreading will be calculated. The keys are used to lookup values from the incoming pod labels, those key-value labels are ANDed with labelSelector to select the group of existing pods over which spreading will be calculated for the incoming pod. The same key is forbidden to exist in both MatchLabelKeys and LabelSelector. MatchLabelKeys cannot be set when LabelSelector isn't set. Keys that don't exist in the incoming pod labels will be ignored. A null or empty list means only match against labelSelector. \n This is a beta field and requires the MatchLabelKeysInPodTopologySpread feature gate to be enabled (enabled by default)." + items: + type: string + type: array + x-kubernetes-list-type: atomic + maxSkew: + description: 'MaxSkew describes the degree to which pods may be unevenly distributed. When `whenUnsatisfiable=DoNotSchedule`, it is the maximum permitted difference between the number of matching pods in the target topology and the global minimum. The global minimum is the minimum number of matching pods in an eligible domain or zero if the number of eligible domains is less than MinDomains. For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 2/2/1: In this case, the global minimum is 1. | zone1 | zone2 | zone3 | | P P | P P | P | - if MaxSkew is 1, incoming pod can only be scheduled to zone3 to become 2/2/2; scheduling it onto zone1(zone2) would make the ActualSkew(3-1) on zone1(zone2) violate MaxSkew(1). - if MaxSkew is 2, incoming pod can be scheduled onto any zone. When `whenUnsatisfiable=ScheduleAnyway`, it is used to give higher precedence to topologies that satisfy it. It''s a required field. Default value is 1 and 0 is not allowed.' + format: int32 + type: integer + minDomains: + description: "MinDomains indicates a minimum number of eligible domains. When the number of eligible domains with matching topology keys is less than minDomains, Pod Topology Spread treats \"global minimum\" as 0, and then the calculation of Skew is performed. And when the number of eligible domains with matching topology keys equals or greater than minDomains, this value has no effect on scheduling. As a result, when the number of eligible domains is less than minDomains, scheduler won't schedule more than maxSkew Pods to those domains. If value is nil, the constraint behaves as if MinDomains is equal to 1. Valid values are integers greater than 0. When value is not nil, WhenUnsatisfiable must be DoNotSchedule. \n For example, in a 3-zone cluster, MaxSkew is set to 2, MinDomains is set to 5 and pods with the same labelSelector spread as 2/2/2: | zone1 | zone2 | zone3 | | P P | P P | P P | The number of domains is less than 5(MinDomains), so \"global minimum\" is treated as 0. In this situation, new pod with the same labelSelector cannot be scheduled, because computed skew will be 3(3 - 0) if new Pod is scheduled to any of the three zones, it will violate MaxSkew. \n This is a beta field and requires the MinDomainsInPodTopologySpread feature gate to be enabled (enabled by default)." + format: int32 + type: integer + nodeAffinityPolicy: + description: "NodeAffinityPolicy indicates how we will treat Pod's nodeAffinity/nodeSelector when calculating pod topology spread skew. Options are: - Honor: only nodes matching nodeAffinity/nodeSelector are included in the calculations. - Ignore: nodeAffinity/nodeSelector are ignored. All nodes are included in the calculations. \n If this value is nil, the behavior is equivalent to the Honor policy. This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag." + type: string + nodeTaintsPolicy: + description: "NodeTaintsPolicy indicates how we will treat node taints when calculating pod topology spread skew. Options are: - Honor: nodes without taints, along with tainted nodes for which the incoming pod has a toleration, are included. - Ignore: node taints are ignored. All nodes are included. \n If this value is nil, the behavior is equivalent to the Ignore policy. This is a beta-level feature default enabled by the NodeInclusionPolicyInPodTopologySpread feature flag." + type: string + topologyKey: + description: TopologyKey is the key of node labels. Nodes that have a label with this key and identical values are considered to be in the same topology. We consider each as a "bucket", and try to put balanced number of pods into each bucket. We define a domain as a particular instance of a topology. Also, we define an eligible domain as a domain whose nodes meet the requirements of nodeAffinityPolicy and nodeTaintsPolicy. e.g. If TopologyKey is "kubernetes.io/hostname", each Node is a domain of that topology. And, if TopologyKey is "topology.kubernetes.io/zone", each zone is a domain of that topology. It's a required field. + type: string + whenUnsatisfiable: + description: 'WhenUnsatisfiable indicates how to deal with a pod if it doesn''t satisfy the spread constraint. - DoNotSchedule (default) tells the scheduler not to schedule it. - ScheduleAnyway tells the scheduler to schedule the pod in any location, but giving higher precedence to topologies that would help reduce the skew. A constraint is considered "Unsatisfiable" for an incoming pod if and only if every possible node assignment for that pod would violate "MaxSkew" on some topology. For example, in a 3-zone cluster, MaxSkew is set to 1, and pods with the same labelSelector spread as 3/1/1: | zone1 | zone2 | zone3 | | P P P | P | P | If WhenUnsatisfiable is set to DoNotSchedule, incoming pod can only be scheduled to zone2(zone3) to become 3/2/1(3/1/2) as ActualSkew(2-1) on zone2(zone3) satisfies MaxSkew(1). In other words, the cluster can still be imbalanced, but scheduler won''t make it *more* imbalanced. It''s a required field.' + type: string + required: + - maxSkew + - topologyKey + - whenUnsatisfiable + type: object + type: array + version: + description: Version the cluster should be on. + type: string + volumeMounts: + description: VolumeMounts allows configuration of additional VolumeMounts on the output StatefulSet definition. VolumeMounts specified will be appended to other VolumeMounts in the alertmanager container, that are generated as a result of StorageSpec objects. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + volumes: + description: Volumes allows configuration of additional volumes on the output StatefulSet definition. Volumes specified will be appended to other volumes that are generated as a result of StorageSpec objects. + items: + description: Volume represents a named volume in a pod that may be accessed by any container in the pod. + properties: + awsElasticBlockStore: + description: 'awsElasticBlockStore represents an AWS Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + properties: + fsType: + description: 'fsType is the filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'partition is the partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty).' + format: int32 + type: integer + readOnly: + description: 'readOnly value true will force the readOnly setting in VolumeMounts. More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: boolean + volumeID: + description: 'volumeID is unique ID of the persistent disk resource in AWS (Amazon EBS volume). More info: https://kubernetes.io/docs/concepts/storage/volumes#awselasticblockstore' + type: string + required: + - volumeID + type: object + azureDisk: + description: azureDisk represents an Azure Data Disk mount on the host and bind mount to the pod. + properties: + cachingMode: + description: 'cachingMode is the Host Caching mode: None, Read Only, Read Write.' + type: string + diskName: + description: diskName is the Name of the data disk in the blob storage + type: string + diskURI: + description: diskURI is the URI of data disk in the blob storage + type: string + fsType: + description: fsType is Filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + kind: + description: 'kind expected values are Shared: multiple blob disks per storage account Dedicated: single blob disk per storage account Managed: azure managed data disk (only in managed availability set). defaults to shared' + type: string + readOnly: + description: readOnly Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + required: + - diskName + - diskURI + type: object + azureFile: + description: azureFile represents an Azure File Service mount on the host and bind mount to the pod. + properties: + readOnly: + description: readOnly defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretName: + description: secretName is the name of secret that contains Azure Storage Account Name and Key + type: string + shareName: + description: shareName is the azure share Name + type: string + required: + - secretName + - shareName + type: object + cephfs: + description: cephFS represents a Ceph FS mount on the host that shares a pod's lifetime + properties: + monitors: + description: 'monitors is Required: Monitors is a collection of Ceph monitors More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + items: + type: string + type: array + path: + description: 'path is Optional: Used as the mounted root, rather than the full Ceph tree, default is /' + type: string + readOnly: + description: 'readOnly is Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: boolean + secretFile: + description: 'secretFile is Optional: SecretFile is the path to key ring for User, default is /etc/ceph/user.secret More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + secretRef: + description: 'secretRef is Optional: SecretRef is reference to the authentication secret for User, default is empty. More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + user: + description: 'user is optional: User is the rados user name, default is admin More info: https://examples.k8s.io/volumes/cephfs/README.md#how-to-use-it' + type: string + required: + - monitors + type: object + cinder: + description: 'cinder represents a cinder volume attached and mounted on kubelets host machine. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + properties: + fsType: + description: 'fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + readOnly: + description: 'readOnly defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: boolean + secretRef: + description: 'secretRef is optional: points to a secret object containing parameters used to connect to OpenStack.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + volumeID: + description: 'volumeID used to identify the volume in cinder. More info: https://examples.k8s.io/mysql-cinder-pd/README.md' + type: string + required: + - volumeID + type: object + configMap: + description: configMap represents a configMap that should populate this volume + properties: + defaultMode: + description: 'defaultMode is optional: mode bits used to set permissions on created files by default. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: items if unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: key is the key to project. + type: string + mode: + description: 'mode is Optional: mode bits used to set permissions on this file. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: path is the relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: optional specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + csi: + description: csi (Container Storage Interface) represents ephemeral storage that is handled by certain external CSI drivers (Beta feature). + properties: + driver: + description: driver is the name of the CSI driver that handles this volume. Consult with your admin for the correct name as registered in the cluster. + type: string + fsType: + description: fsType to mount. Ex. "ext4", "xfs", "ntfs". If not provided, the empty value is passed to the associated CSI driver which will determine the default filesystem to apply. + type: string + nodePublishSecretRef: + description: nodePublishSecretRef is a reference to the secret object containing sensitive information to pass to the CSI driver to complete the CSI NodePublishVolume and NodeUnpublishVolume calls. This field is optional, and may be empty if no secret is required. If the secret object contains more than one secret, all secret references are passed. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + readOnly: + description: readOnly specifies a read-only configuration for the volume. Defaults to false (read/write). + type: boolean + volumeAttributes: + additionalProperties: + type: string + description: volumeAttributes stores driver-specific properties that are passed to the CSI driver. Consult your driver's documentation for supported values. + type: object + required: + - driver + type: object + downwardAPI: + description: downwardAPI represents downward API about the pod that should populate this volume + properties: + defaultMode: + description: 'Optional: mode bits to use on created files by default. Must be a Optional: mode bits used to set permissions on created files by default. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: Items is a list of downward API volume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + description: 'Optional: mode bits used to set permissions on this file, must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + emptyDir: + description: 'emptyDir represents a temporary directory that shares a pod''s lifetime. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + properties: + medium: + description: 'medium represents what type of storage medium should back this directory. The default is "" which means to use the node''s default medium. Must be an empty string (default) or Memory. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + type: string + sizeLimit: + anyOf: + - type: integer + - type: string + description: 'sizeLimit is the total amount of local storage required for this EmptyDir volume. The size limit is also applicable for memory medium. The maximum usage on memory medium EmptyDir would be the minimum value between the SizeLimit specified here and the sum of memory limits of all containers in a pod. The default is nil which means that the limit is undefined. More info: https://kubernetes.io/docs/concepts/storage/volumes#emptydir' + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + type: object + ephemeral: + description: "ephemeral represents a volume that is handled by a cluster storage driver. The volume's lifecycle is tied to the pod that defines it - it will be created before the pod starts, and deleted when the pod is removed. \n Use this if: a) the volume is only needed while the pod runs, b) features of normal volumes like restoring from snapshot or capacity tracking are needed, c) the storage driver is specified through a storage class, and d) the storage driver supports dynamic volume provisioning through a PersistentVolumeClaim (see EphemeralVolumeSource for more information on the connection between this volume type and PersistentVolumeClaim). \n Use PersistentVolumeClaim or one of the vendor-specific APIs for volumes that persist for longer than the lifecycle of an individual pod. \n Use CSI for light-weight local ephemeral volumes if the CSI driver is meant to be used that way - see the documentation of the driver for more information. \n A pod can use both types of ephemeral volumes and persistent volumes at the same time." + properties: + volumeClaimTemplate: + description: "Will be used to create a stand-alone PVC to provision the volume. The pod in which this EphemeralVolumeSource is embedded will be the owner of the PVC, i.e. the PVC will be deleted together with the pod. The name of the PVC will be `-` where `` is the name from the `PodSpec.Volumes` array entry. Pod validation will reject the pod if the concatenated name is not valid for a PVC (for example, too long). \n An existing PVC with that name that is not owned by the pod will *not* be used for the pod to avoid using an unrelated volume by mistake. Starting the pod is then blocked until the unrelated PVC is removed. If such a pre-created PVC is meant to be used by the pod, the PVC has to updated with an owner reference to the pod once the pod exists. Normally this should not be necessary, but it may be useful when manually reconstructing a broken cluster. \n This field is read-only and no changes will be made by Kubernetes to the PVC after it has been created. \n Required, must not be nil." + properties: + metadata: + description: May contain labels and annotations that will be copied into the PVC when creating it. No other fields are allowed and will be rejected during validation. + type: object + spec: + description: The specification for the PersistentVolumeClaim. The entire content is copied unchanged into the PVC that gets created from this template. The same fields as in a PersistentVolumeClaim are also valid here. + properties: + accessModes: + description: 'accessModes contains the desired access modes the volume should have. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#access-modes-1' + items: + type: string + type: array + dataSource: + description: 'dataSource field can be used to specify either: * An existing VolumeSnapshot object (snapshot.storage.k8s.io/VolumeSnapshot) * An existing PVC (PersistentVolumeClaim) If the provisioner or an external controller can support the specified data source, it will create a new volume based on the contents of the specified data source. When the AnyVolumeDataSource feature gate is enabled, dataSource contents will be copied to dataSourceRef, and dataSourceRef contents will be copied to dataSource when dataSourceRef.namespace is not specified. If the namespace is specified, then dataSourceRef will not be copied to dataSource.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + required: + - kind + - name + type: object + x-kubernetes-map-type: atomic + dataSourceRef: + description: 'dataSourceRef specifies the object from which to populate the volume with data, if a non-empty volume is desired. This may be any object from a non-empty API group (non core object) or a PersistentVolumeClaim object. When this field is specified, volume binding will only succeed if the type of the specified object matches some installed volume populator or dynamic provisioner. This field will replace the functionality of the dataSource field and as such if both fields are non-empty, they must have the same value. For backwards compatibility, when namespace isn''t specified in dataSourceRef, both fields (dataSource and dataSourceRef) will be set to the same value automatically if one of them is empty and the other is non-empty. When namespace is specified in dataSourceRef, dataSource isn''t set to the same value and must be empty. There are three important differences between dataSource and dataSourceRef: * While dataSource only allows two specific types of objects, dataSourceRef allows any non-core object, as well as PersistentVolumeClaim objects. * While dataSource ignores disallowed values (dropping them), dataSourceRef preserves all values, and generates an error if a disallowed value is specified. * While dataSource only allows local objects, dataSourceRef allows objects in any namespaces. (Beta) Using this field requires the AnyVolumeDataSource feature gate to be enabled. (Alpha) Using the namespace field of dataSourceRef requires the CrossNamespaceVolumeDataSource feature gate to be enabled.' + properties: + apiGroup: + description: APIGroup is the group for the resource being referenced. If APIGroup is not specified, the specified Kind must be in the core API group. For any other third-party types, APIGroup is required. + type: string + kind: + description: Kind is the type of resource being referenced + type: string + name: + description: Name is the name of resource being referenced + type: string + namespace: + description: Namespace is the namespace of resource being referenced Note that when a namespace is specified, a gateway.networking.k8s.io/ReferenceGrant object is required in the referent namespace to allow that namespace's owner to accept the reference. See the ReferenceGrant documentation for details. (Alpha) This field requires the CrossNamespaceVolumeDataSource feature gate to be enabled. + type: string + required: + - kind + - name + type: object + resources: + description: 'resources represents the minimum resources the volume should have. If RecoverVolumeExpansionFailure feature is enabled users are allowed to specify resource requirements that are lower than previous value but must still be higher than capacity recorded in the status field of the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#resources' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + selector: + description: selector is a label query over volumes to consider for binding. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + storageClassName: + description: 'storageClassName is the name of the StorageClass required by the claim. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#class-1' + type: string + volumeMode: + description: volumeMode defines what type of volume is required by the claim. Value of Filesystem is implied when not included in claim spec. + type: string + volumeName: + description: volumeName is the binding reference to the PersistentVolume backing this claim. + type: string + type: object + required: + - spec + type: object + type: object + fc: + description: fc represents a Fibre Channel resource that is attached to a kubelet's host machine and then exposed to the pod. + properties: + fsType: + description: 'fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + lun: + description: 'lun is Optional: FC target lun number' + format: int32 + type: integer + readOnly: + description: 'readOnly is Optional: Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + targetWWNs: + description: 'targetWWNs is Optional: FC target worldwide names (WWNs)' + items: + type: string + type: array + wwids: + description: 'wwids Optional: FC volume world wide identifiers (wwids) Either wwids or combination of targetWWNs and lun must be set, but not both simultaneously.' + items: + type: string + type: array + type: object + flexVolume: + description: flexVolume represents a generic volume resource that is provisioned/attached using an exec based plugin. + properties: + driver: + description: driver is the name of the driver to use for this volume. + type: string + fsType: + description: fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". The default filesystem depends on FlexVolume script. + type: string + options: + additionalProperties: + type: string + description: 'options is Optional: this field holds extra command options if any.' + type: object + readOnly: + description: 'readOnly is Optional: defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts.' + type: boolean + secretRef: + description: 'secretRef is Optional: secretRef is reference to the secret object containing sensitive information to pass to the plugin scripts. This may be empty if no secret object is specified. If the secret object contains more than one secret, all secrets are passed to the plugin scripts.' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + required: + - driver + type: object + flocker: + description: flocker represents a Flocker volume attached to a kubelet's host machine. This depends on the Flocker control service being running + properties: + datasetName: + description: datasetName is Name of the dataset stored as metadata -> name on the dataset for Flocker should be considered as deprecated + type: string + datasetUUID: + description: datasetUUID is the UUID of the dataset. This is unique identifier of a Flocker dataset + type: string + type: object + gcePersistentDisk: + description: 'gcePersistentDisk represents a GCE Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + properties: + fsType: + description: 'fsType is filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + partition: + description: 'partition is the partition in the volume that you want to mount. If omitted, the default is to mount by volume name. Examples: For volume /dev/sda1, you specify the partition as "1". Similarly, the volume partition for /dev/sda is "0" (or you can leave the property empty). More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + format: int32 + type: integer + pdName: + description: 'pdName is unique name of the PD resource in GCE. Used to identify the disk in GCE. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: string + readOnly: + description: 'readOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#gcepersistentdisk' + type: boolean + required: + - pdName + type: object + gitRepo: + description: 'gitRepo represents a git repository at a particular revision. DEPRECATED: GitRepo is deprecated. To provision a container with a git repo, mount an EmptyDir into an InitContainer that clones the repo using git, then mount the EmptyDir into the Pod''s container.' + properties: + directory: + description: directory is the target directory name. Must not contain or start with '..'. If '.' is supplied, the volume directory will be the git repository. Otherwise, if specified, the volume will contain the git repository in the subdirectory with the given name. + type: string + repository: + description: repository is the URL + type: string + revision: + description: revision is the commit hash for the specified revision. + type: string + required: + - repository + type: object + glusterfs: + description: 'glusterfs represents a Glusterfs mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/glusterfs/README.md' + properties: + endpoints: + description: 'endpoints is the endpoint name that details Glusterfs topology. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + path: + description: 'path is the Glusterfs volume path. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: string + readOnly: + description: 'readOnly here will force the Glusterfs volume to be mounted with read-only permissions. Defaults to false. More info: https://examples.k8s.io/volumes/glusterfs/README.md#create-a-pod' + type: boolean + required: + - endpoints + - path + type: object + hostPath: + description: 'hostPath represents a pre-existing file or directory on the host machine that is directly exposed to the container. This is generally used for system agents or other privileged things that are allowed to see the host machine. Most containers will NOT need this. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath --- TODO(jonesdl) We need to restrict who can use host directory mounts and who can/can not mount host directories as read/write.' + properties: + path: + description: 'path of the directory on the host. If the path is a symlink, it will follow the link to the real path. More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + type: + description: 'type for HostPath Volume Defaults to "" More info: https://kubernetes.io/docs/concepts/storage/volumes#hostpath' + type: string + required: + - path + type: object + iscsi: + description: 'iscsi represents an ISCSI Disk resource that is attached to a kubelet''s host machine and then exposed to the pod. More info: https://examples.k8s.io/volumes/iscsi/README.md' + properties: + chapAuthDiscovery: + description: chapAuthDiscovery defines whether support iSCSI Discovery CHAP authentication + type: boolean + chapAuthSession: + description: chapAuthSession defines whether support iSCSI Session CHAP authentication + type: boolean + fsType: + description: 'fsType is the filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#iscsi TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + initiatorName: + description: initiatorName is the custom iSCSI Initiator Name. If initiatorName is specified with iscsiInterface simultaneously, new iSCSI interface : will be created for the connection. + type: string + iqn: + description: iqn is the target iSCSI Qualified Name. + type: string + iscsiInterface: + description: iscsiInterface is the interface Name that uses an iSCSI transport. Defaults to 'default' (tcp). + type: string + lun: + description: lun represents iSCSI Target Lun number. + format: int32 + type: integer + portals: + description: portals is the iSCSI Target Portal List. The portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + items: + type: string + type: array + readOnly: + description: readOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. + type: boolean + secretRef: + description: secretRef is the CHAP Secret for iSCSI target and initiator authentication + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + targetPortal: + description: targetPortal is iSCSI Target Portal. The Portal is either an IP or ip_addr:port if the port is other than default (typically TCP ports 860 and 3260). + type: string + required: + - iqn + - lun + - targetPortal + type: object + name: + description: 'name of the volume. Must be a DNS_LABEL and unique within the pod. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names' + type: string + nfs: + description: 'nfs represents an NFS mount on the host that shares a pod''s lifetime More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + properties: + path: + description: 'path that is exported by the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + readOnly: + description: 'readOnly here will force the NFS export to be mounted with read-only permissions. Defaults to false. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: boolean + server: + description: 'server is the hostname or IP address of the NFS server. More info: https://kubernetes.io/docs/concepts/storage/volumes#nfs' + type: string + required: + - path + - server + type: object + persistentVolumeClaim: + description: 'persistentVolumeClaimVolumeSource represents a reference to a PersistentVolumeClaim in the same namespace. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + properties: + claimName: + description: 'claimName is the name of a PersistentVolumeClaim in the same namespace as the pod using this volume. More info: https://kubernetes.io/docs/concepts/storage/persistent-volumes#persistentvolumeclaims' + type: string + readOnly: + description: readOnly Will force the ReadOnly setting in VolumeMounts. Default false. + type: boolean + required: + - claimName + type: object + photonPersistentDisk: + description: photonPersistentDisk represents a PhotonController persistent disk attached and mounted on kubelets host machine + properties: + fsType: + description: fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + pdID: + description: pdID is the ID that identifies Photon Controller persistent disk + type: string + required: + - pdID + type: object + portworxVolume: + description: portworxVolume represents a portworx volume attached and mounted on kubelets host machine + properties: + fsType: + description: fSType represents the filesystem type to mount Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: readOnly defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + volumeID: + description: volumeID uniquely identifies a Portworx volume + type: string + required: + - volumeID + type: object + projected: + description: projected items for all in one resources secrets, configmaps, and downward API + properties: + defaultMode: + description: defaultMode are the mode bits used to set permissions on created files by default. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set. + format: int32 + type: integer + sources: + description: sources is the list of volume projections + items: + description: Projection that may be projected along with other supported volume types + properties: + configMap: + description: configMap information about the configMap data to project + properties: + items: + description: items if unspecified, each key-value pair in the Data field of the referenced ConfigMap will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the ConfigMap, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: key is the key to project. + type: string + mode: + description: 'mode is Optional: mode bits used to set permissions on this file. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: path is the relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: optional specify whether the ConfigMap or its keys must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + downwardAPI: + description: downwardAPI information about the downwardAPI data to project + properties: + items: + description: Items is a list of DownwardAPIVolume file + items: + description: DownwardAPIVolumeFile represents information to create the file containing the pod field + properties: + fieldRef: + description: 'Required: Selects a field of the pod: only annotations, labels, name and namespace are supported.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + mode: + description: 'Optional: mode bits used to set permissions on this file, must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: 'Required: Path is the relative path name of the file to be created. Must not be absolute or contain the ''..'' path. Must be utf-8 encoded. The first item of the relative path must not start with ''..''' + type: string + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, requests.cpu and requests.memory) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + required: + - path + type: object + type: array + type: object + secret: + description: secret information about the secret data to project + properties: + items: + description: items if unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: key is the key to project. + type: string + mode: + description: 'mode is Optional: mode bits used to set permissions on this file. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: path is the relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: optional field specify whether the Secret or its key must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + serviceAccountToken: + description: serviceAccountToken is information about the serviceAccountToken data to project + properties: + audience: + description: audience is the intended audience of the token. A recipient of a token must identify itself with an identifier specified in the audience of the token, and otherwise should reject the token. The audience defaults to the identifier of the apiserver. + type: string + expirationSeconds: + description: expirationSeconds is the requested duration of validity of the service account token. As the token approaches expiration, the kubelet volume plugin will proactively rotate the service account token. The kubelet will start trying to rotate the token if the token is older than 80 percent of its time to live or if the token is older than 24 hours.Defaults to 1 hour and must be at least 10 minutes. + format: int64 + type: integer + path: + description: path is the path relative to the mount point of the file to project the token into. + type: string + required: + - path + type: object + type: object + type: array + type: object + quobyte: + description: quobyte represents a Quobyte mount on the host that shares a pod's lifetime + properties: + group: + description: group to map volume access to Default is no group + type: string + readOnly: + description: readOnly here will force the Quobyte volume to be mounted with read-only permissions. Defaults to false. + type: boolean + registry: + description: registry represents a single or multiple Quobyte Registry services specified as a string as host:port pair (multiple entries are separated with commas) which acts as the central registry for volumes + type: string + tenant: + description: tenant owning the given Quobyte volume in the Backend Used with dynamically provisioned Quobyte volumes, value is set by the plugin + type: string + user: + description: user to map volume access to Defaults to serivceaccount user + type: string + volume: + description: volume is a string that references an already created Quobyte volume by name. + type: string + required: + - registry + - volume + type: object + rbd: + description: 'rbd represents a Rados Block Device mount on the host that shares a pod''s lifetime. More info: https://examples.k8s.io/volumes/rbd/README.md' + properties: + fsType: + description: 'fsType is the filesystem type of the volume that you want to mount. Tip: Ensure that the filesystem type is supported by the host operating system. Examples: "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. More info: https://kubernetes.io/docs/concepts/storage/volumes#rbd TODO: how do we prevent errors in the filesystem from compromising the machine' + type: string + image: + description: 'image is the rados image name. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + keyring: + description: 'keyring is the path to key ring for RBDUser. Default is /etc/ceph/keyring. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + monitors: + description: 'monitors is a collection of Ceph monitors. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + items: + type: string + type: array + pool: + description: 'pool is the rados pool name. Default is rbd. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + readOnly: + description: 'readOnly here will force the ReadOnly setting in VolumeMounts. Defaults to false. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: boolean + secretRef: + description: 'secretRef is name of the authentication secret for RBDUser. If provided overrides keyring. Default is nil. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + user: + description: 'user is the rados user name. Default is admin. More info: https://examples.k8s.io/volumes/rbd/README.md#how-to-use-it' + type: string + required: + - image + - monitors + type: object + scaleIO: + description: scaleIO represents a ScaleIO persistent volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Default is "xfs". + type: string + gateway: + description: gateway is the host address of the ScaleIO API Gateway. + type: string + protectionDomain: + description: protectionDomain is the name of the ScaleIO Protection Domain for the configured storage. + type: string + readOnly: + description: readOnly Defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: secretRef references to the secret for ScaleIO user and other sensitive information. If this is not provided, Login operation will fail. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + sslEnabled: + description: sslEnabled Flag enable/disable SSL communication with Gateway, default false + type: boolean + storageMode: + description: storageMode indicates whether the storage for a volume should be ThickProvisioned or ThinProvisioned. Default is ThinProvisioned. + type: string + storagePool: + description: storagePool is the ScaleIO Storage Pool associated with the protection domain. + type: string + system: + description: system is the name of the storage system as configured in ScaleIO. + type: string + volumeName: + description: volumeName is the name of a volume already created in the ScaleIO system that is associated with this volume source. + type: string + required: + - gateway + - secretRef + - system + type: object + secret: + description: 'secret represents a secret that should populate this volume. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + properties: + defaultMode: + description: 'defaultMode is Optional: mode bits used to set permissions on created files by default. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. Defaults to 0644. Directories within the path are not affected by this setting. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + items: + description: items If unspecified, each key-value pair in the Data field of the referenced Secret will be projected into the volume as a file whose name is the key and content is the value. If specified, the listed keys will be projected into the specified paths, and unlisted keys will not be present. If a key is specified which is not present in the Secret, the volume setup will error unless it is marked optional. Paths must be relative and may not contain the '..' path or start with '..'. + items: + description: Maps a string key to a path within a volume. + properties: + key: + description: key is the key to project. + type: string + mode: + description: 'mode is Optional: mode bits used to set permissions on this file. Must be an octal value between 0000 and 0777 or a decimal value between 0 and 511. YAML accepts both octal and decimal values, JSON requires decimal values for mode bits. If not specified, the volume defaultMode will be used. This might be in conflict with other options that affect the file mode, like fsGroup, and the result can be other mode bits set.' + format: int32 + type: integer + path: + description: path is the relative path of the file to map the key to. May not be an absolute path. May not contain the path element '..'. May not start with the string '..'. + type: string + required: + - key + - path + type: object + type: array + optional: + description: optional field specify whether the Secret or its keys must be defined + type: boolean + secretName: + description: 'secretName is the name of the secret in the pod''s namespace to use. More info: https://kubernetes.io/docs/concepts/storage/volumes#secret' + type: string + type: object + storageos: + description: storageOS represents a StorageOS volume attached and mounted on Kubernetes nodes. + properties: + fsType: + description: fsType is the filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + readOnly: + description: readOnly defaults to false (read/write). ReadOnly here will force the ReadOnly setting in VolumeMounts. + type: boolean + secretRef: + description: secretRef specifies the secret to use for obtaining the StorageOS API credentials. If not specified, default values will be attempted. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + volumeName: + description: volumeName is the human-readable name of the StorageOS volume. Volume names are only unique within a namespace. + type: string + volumeNamespace: + description: volumeNamespace specifies the scope of the volume within StorageOS. If no namespace is specified then the Pod's namespace will be used. This allows the Kubernetes name scoping to be mirrored within StorageOS for tighter integration. Set VolumeName to any name to override the default behaviour. Set to "default" if you are not using namespaces within StorageOS. Namespaces that do not pre-exist within StorageOS will be created. + type: string + type: object + vsphereVolume: + description: vsphereVolume represents a vSphere volume attached and mounted on kubelets host machine + properties: + fsType: + description: fsType is filesystem type to mount. Must be a filesystem type supported by the host operating system. Ex. "ext4", "xfs", "ntfs". Implicitly inferred to be "ext4" if unspecified. + type: string + storagePolicyID: + description: storagePolicyID is the storage Policy Based Management (SPBM) profile ID associated with the StoragePolicyName. + type: string + storagePolicyName: + description: storagePolicyName is the storage Policy Based Management (SPBM) profile name. + type: string + volumePath: + description: volumePath is the path that identifies vSphere volume vmdk + type: string + required: + - volumePath + type: object + required: + - name + type: object + type: array + web: + description: Defines the web command line flags when starting Alertmanager. + properties: + getConcurrency: + description: Maximum number of GET requests processed concurrently. This corresponds to the Alertmanager's `--web.get-concurrency` flag. + format: int32 + type: integer + httpConfig: + description: Defines HTTP parameters for web server. + properties: + headers: + description: List of headers that can be added to HTTP responses. + properties: + contentSecurityPolicy: + description: Set the Content-Security-Policy header to HTTP responses. Unset if blank. + type: string + strictTransportSecurity: + description: Set the Strict-Transport-Security header to HTTP responses. Unset if blank. Please make sure that you use this with care as this header might force browsers to load Prometheus and the other applications hosted on the same domain and subdomains over HTTPS. https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/Strict-Transport-Security + type: string + xContentTypeOptions: + description: Set the X-Content-Type-Options header to HTTP responses. Unset if blank. Accepted value is nosniff. https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Content-Type-Options + enum: + - "" + - NoSniff + type: string + xFrameOptions: + description: Set the X-Frame-Options header to HTTP responses. Unset if blank. Accepted values are deny and sameorigin. https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-Frame-Options + enum: + - "" + - Deny + - SameOrigin + type: string + xXSSProtection: + description: Set the X-XSS-Protection header to all responses. Unset if blank. https://developer.mozilla.org/en-US/docs/Web/HTTP/Headers/X-XSS-Protection + type: string + type: object + http2: + description: Enable HTTP/2 support. Note that HTTP/2 is only supported with TLS. When TLSConfig is not configured, HTTP/2 will be disabled. Whenever the value of the field changes, a rolling update will be triggered. + type: boolean + type: object + timeout: + description: Timeout for HTTP requests. This corresponds to the Alertmanager's `--web.timeout` flag. + format: int32 + type: integer + tlsConfig: + description: Defines the TLS parameters for HTTPS. + properties: + cert: + description: Contains the TLS certificate for the server. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cipherSuites: + description: 'List of supported cipher suites for TLS versions up to TLS 1.2. If empty, Go default cipher suites are used. Available cipher suites are documented in the go documentation: https://golang.org/pkg/crypto/tls/#pkg-constants' + items: + type: string + type: array + client_ca: + description: Contains the CA certificate for client certificate authentication to the server. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientAuthType: + description: 'Server policy for client authentication. Maps to ClientAuth Policies. For more detail on clientAuth options: https://golang.org/pkg/crypto/tls/#ClientAuthType' + type: string + curvePreferences: + description: 'Elliptic curves that will be used in an ECDHE handshake, in preference order. Available curves are documented in the go documentation: https://golang.org/pkg/crypto/tls/#CurveID' + items: + type: string + type: array + keySecret: + description: Secret containing the TLS key for the server. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + maxVersion: + description: Maximum TLS version that is acceptable. Defaults to TLS13. + type: string + minVersion: + description: Minimum TLS version that is acceptable. Defaults to TLS12. + type: string + preferServerCipherSuites: + description: Controls whether the server selects the client's most preferred cipher suite, or the server's most preferred cipher suite. If true then the server's preference, as expressed in the order of elements in cipherSuites, is used. + type: boolean + required: + - cert + - keySecret + type: object + type: object + type: object + status: + description: 'Most recent observed status of the Alertmanager cluster. Read-only. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + availableReplicas: + description: Total number of available pods (ready for at least minReadySeconds) targeted by this Alertmanager cluster. + format: int32 + type: integer + conditions: + description: The current state of the Alertmanager object. + items: + description: Condition represents the state of the resources associated with the Prometheus, Alertmanager or ThanosRuler resource. + properties: + lastTransitionTime: + description: lastTransitionTime is the time of the last update to the current status property. + format: date-time + type: string + message: + description: Human-readable message indicating details for the condition's last transition. + type: string + observedGeneration: + description: ObservedGeneration represents the .metadata.generation that the condition was set based upon. For instance, if `.metadata.generation` is currently 12, but the `.status.conditions[].observedGeneration` is 9, the condition is out of date with respect to the current state of the instance. + format: int64 + type: integer + reason: + description: Reason for the condition's last transition. + type: string + status: + description: Status of the condition. + type: string + type: + description: Type of the condition being reported. + type: string + required: + - lastTransitionTime + - status + - type + type: object + type: array + x-kubernetes-list-map-keys: + - type + x-kubernetes-list-type: map + paused: + description: Represents whether any actions on the underlying managed objects are being performed. Only delete actions will be performed. + type: boolean + replicas: + description: Total number of non-terminated pods targeted by this Alertmanager object (their labels match the selector). + format: int32 + type: integer + unavailableReplicas: + description: Total number of unavailable pods targeted by this Alertmanager object. + format: int32 + type: integer + updatedReplicas: + description: Total number of non-terminated pods targeted by this Alertmanager object that have the desired version spec. + format: int32 + type: integer + required: + - availableReplicas + - paused + - replicas + - unavailableReplicas + - updatedReplicas + type: object + required: + - spec + type: object + served: true + storage: true + subresources: + status: {} diff --git a/deployment/helm/prometheus-crd/0podmonitorCustomResourceDefinition.yaml b/deployment/helm/prometheus-crd/0podmonitorCustomResourceDefinition.yaml new file mode 100644 index 00000000..47c4b988 --- /dev/null +++ b/deployment/helm/prometheus-crd/0podmonitorCustomResourceDefinition.yaml @@ -0,0 +1,542 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.11.1 + creationTimestamp: null + name: podmonitors.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: PodMonitor + listKind: PodMonitorList + plural: podmonitors + shortNames: + - pmon + singular: podmonitor + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: PodMonitor defines monitoring for a set of pods. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Pod selection for target discovery by Prometheus. + properties: + attachMetadata: + description: Attaches node metadata to discovered targets. Requires Prometheus v2.35.0 and above. + properties: + node: + description: When set to true, Prometheus must have permissions to get Nodes. + type: boolean + type: object + jobLabel: + description: The label to use to retrieve the job name from. + type: string + labelLimit: + description: Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelNameLengthLimit: + description: Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelValueLengthLimit: + description: Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + namespaceSelector: + description: Selector to select which namespaces the Endpoints objects are discovered from. + properties: + any: + description: Boolean describing whether all namespaces are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + podMetricsEndpoints: + description: A list of endpoints allowed as part of this PodMonitor. + items: + description: PodMetricsEndpoint defines a scrapeable endpoint of a Kubernetes Pod serving Prometheus metrics. + properties: + authorization: + description: Authorization section for this endpoint + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint' + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the pod monitor and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + enableHttp2: + description: Whether to enable HTTP2. + type: boolean + filterRunning: + description: 'Drop pods that are not running. (Failed, Succeeded). Enabled by default. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle/#pod-phase' + type: boolean + followRedirects: + description: FollowRedirects configures whether scrape requests follow HTTP 3xx redirects. + type: boolean + honorLabels: + description: HonorLabels chooses the metric's labels on collisions with target labels. + type: boolean + honorTimestamps: + description: HonorTimestamps controls whether Prometheus respects the timestamps present in scraped data. + type: boolean + interval: + description: Interval at which metrics should be scraped If not specified Prometheus' global scrape interval is used. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36. + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + oauth2: + description: OAuth2 for the URL. Only valid in Prometheus versions 2.27.0 and newer. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + params: + additionalProperties: + items: + type: string + type: array + description: Optional HTTP URL parameters + type: object + path: + description: HTTP path to scrape for metrics. If empty, Prometheus uses the default value (e.g. `/metrics`). + type: string + port: + description: Name of the pod port this endpoint refers to. Mutually exclusive with targetPort. + type: string + proxyUrl: + description: ProxyURL eg http://proxyserver:2195 Directs scrapes to proxy through this endpoint. + type: string + relabelings: + description: 'RelabelConfigs to apply to samples before scraping. Prometheus Operator automatically adds relabelings for a few standard Kubernetes fields. The original scrape job''s name is available via the `__tmp_prometheus_job_name` label. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36. + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + scheme: + description: HTTP scheme to use for scraping. `http` and `https` are the expected values unless you rewrite the `__scheme__` label via relabeling. If empty, Prometheus uses the default value `http`. + enum: + - http + - https + type: string + scrapeTimeout: + description: Timeout after which the scrape is ended If not specified, the Prometheus global scrape interval is used. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + targetPort: + anyOf: + - type: integer + - type: string + description: 'Deprecated: Use ''port'' instead.' + x-kubernetes-int-or-string: true + tlsConfig: + description: TLS configuration to use when scraping the endpoint. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + type: array + podTargetLabels: + description: PodTargetLabels transfers labels on the Kubernetes Pod onto the target. + items: + type: string + type: array + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + format: int64 + type: integer + selector: + description: Selector to select Pod objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + targetLimit: + description: TargetLimit defines a limit on the number of scraped targets that will be accepted. + format: int64 + type: integer + required: + - podMetricsEndpoints + - selector + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/deployment/helm/prometheus-crd/0probeCustomResourceDefinition.yaml b/deployment/helm/prometheus-crd/0probeCustomResourceDefinition.yaml new file mode 100644 index 00000000..d8e4a89c --- /dev/null +++ b/deployment/helm/prometheus-crd/0probeCustomResourceDefinition.yaml @@ -0,0 +1,581 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.11.1 + creationTimestamp: null + name: probes.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: Probe + listKind: ProbeList + plural: probes + shortNames: + - prb + singular: probe + scope: Namespaced + versions: + - name: v1 + schema: + openAPIV3Schema: + description: Probe defines monitoring for a set of static targets or ingresses. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: Specification of desired Ingress selection for target discovery by Prometheus. + properties: + authorization: + description: Authorization section for this endpoint + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: 'BasicAuth allow an endpoint to authenticate over basic authentication. More info: https://prometheus.io/docs/operating/configuration/#endpoint' + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenSecret: + description: Secret to mount to read bearer token for scraping targets. The secret needs to be in the same namespace as the probe and accessible by the Prometheus Operator. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + interval: + description: Interval at which targets are probed using the configured prober. If not specified Prometheus' global scrape interval is used. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + jobName: + description: The job name assigned to scraped metrics by default. + type: string + labelLimit: + description: Per-scrape limit on number of labels that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelNameLengthLimit: + description: Per-scrape limit on length of labels name that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + labelValueLengthLimit: + description: Per-scrape limit on length of labels value that will be accepted for a sample. Only valid in Prometheus versions 2.27.0 and newer. + format: int64 + type: integer + metricRelabelings: + description: MetricRelabelConfigs to apply to samples before ingestion. + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36. + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + module: + description: 'The module to use for probing specifying how to probe the target. Example module configuring in the blackbox exporter: https://github.com/prometheus/blackbox_exporter/blob/master/example.yml' + type: string + oauth2: + description: OAuth2 for the URL. Only valid in Prometheus versions 2.27.0 and newer. + properties: + clientId: + description: The secret or configmap containing the OAuth2 client id + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + clientSecret: + description: The secret containing the OAuth2 client secret + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + endpointParams: + additionalProperties: + type: string + description: Parameters to append to the token URL + type: object + scopes: + description: OAuth2 scopes used for the token request + items: + type: string + type: array + tokenUrl: + description: The URL to fetch the token from + minLength: 1 + type: string + required: + - clientId + - clientSecret + - tokenUrl + type: object + prober: + description: Specification for the prober to use for probing targets. The prober.URL parameter is required. Targets cannot be probed if left empty. + properties: + path: + default: /probe + description: Path to collect metrics from. Defaults to `/probe`. + type: string + proxyUrl: + description: Optional ProxyURL. + type: string + scheme: + description: HTTP scheme to use for scraping. `http` and `https` are the expected values unless you rewrite the `__scheme__` label via relabeling. If empty, Prometheus uses the default value `http`. + enum: + - http + - https + type: string + url: + description: Mandatory URL of the prober. + type: string + required: + - url + type: object + sampleLimit: + description: SampleLimit defines per-scrape limit on number of scraped samples that will be accepted. + format: int64 + type: integer + scrapeTimeout: + description: Timeout for scraping metrics from the Prometheus exporter. If not specified, the Prometheus global scrape timeout is used. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + targetLimit: + description: TargetLimit defines a limit on the number of scraped targets that will be accepted. + format: int64 + type: integer + targets: + description: Targets defines a set of static or dynamically discovered targets to probe. + properties: + ingress: + description: ingress defines the Ingress objects to probe and the relabeling configuration. If `staticConfig` is also defined, `staticConfig` takes precedence. + properties: + namespaceSelector: + description: From which namespaces to select Ingress objects. + properties: + any: + description: Boolean describing whether all namespaces are selected in contrast to a list restricting them. + type: boolean + matchNames: + description: List of namespace names to select from. + items: + type: string + type: array + type: object + relabelingConfigs: + description: 'RelabelConfigs to apply to the label set of the target before it gets scraped. The original ingress address is available via the `__tmp_prometheus_ingress_address` label. It can be used to customize the probed URL. The original scrape job''s name is available via the `__tmp_prometheus_job_name` label. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36. + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + selector: + description: Selector to select the Ingress objects. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + type: object + staticConfig: + description: 'staticConfig defines the static list of targets to probe and the relabeling configuration. If `ingress` is also defined, `staticConfig` takes precedence. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#static_config.' + properties: + labels: + additionalProperties: + type: string + description: Labels assigned to all metrics scraped from the targets. + type: object + relabelingConfigs: + description: 'RelabelConfigs to apply to the label set of the targets before it gets scraped. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#relabel_config' + items: + description: 'RelabelConfig allows dynamic rewriting of the label set, being applied to samples before ingestion. It defines ``-section of Prometheus configuration. More info: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#metric_relabel_configs' + properties: + action: + default: replace + description: Action to perform based on regex matching. Default is 'replace'. uppercase and lowercase actions require Prometheus >= 2.36. + enum: + - replace + - Replace + - keep + - Keep + - drop + - Drop + - hashmod + - HashMod + - labelmap + - LabelMap + - labeldrop + - LabelDrop + - labelkeep + - LabelKeep + - lowercase + - Lowercase + - uppercase + - Uppercase + - keepequal + - KeepEqual + - dropequal + - DropEqual + type: string + modulus: + description: Modulus to take of the hash of the source label values. + format: int64 + type: integer + regex: + description: Regular expression against which the extracted value is matched. Default is '(.*)' + type: string + replacement: + description: Replacement value against which a regex replace is performed if the regular expression matches. Regex capture groups are available. Default is '$1' + type: string + separator: + description: Separator placed between concatenated source label values. default is ';'. + type: string + sourceLabels: + description: The source labels select values from existing labels. Their content is concatenated using the configured separator and matched against the configured regular expression for the replace, keep, and drop actions. + items: + description: LabelName is a valid Prometheus label name which may only contain ASCII letters, numbers, as well as underscores. + pattern: ^[a-zA-Z_][a-zA-Z0-9_]*$ + type: string + type: array + targetLabel: + description: Label to which the resulting value is written in a replace action. It is mandatory for replace actions. Regex capture groups are available. + type: string + type: object + type: array + static: + description: The list of hosts to probe. + items: + type: string + type: array + type: object + type: object + tlsConfig: + description: TLS configuration to use when scraping the endpoint. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + type: object + required: + - spec + type: object + served: true + storage: true diff --git a/deployment/helm/prometheus-crd/0prometheusCustomResourceDefinition.yaml b/deployment/helm/prometheus-crd/0prometheusCustomResourceDefinition.yaml new file mode 100644 index 00000000..d48961ea --- /dev/null +++ b/deployment/helm/prometheus-crd/0prometheusCustomResourceDefinition.yaml @@ -0,0 +1,6268 @@ +apiVersion: apiextensions.k8s.io/v1 +kind: CustomResourceDefinition +metadata: + annotations: + controller-gen.kubebuilder.io/version: v0.11.1 + creationTimestamp: null + name: prometheuses.monitoring.coreos.com +spec: + group: monitoring.coreos.com + names: + categories: + - prometheus-operator + kind: Prometheus + listKind: PrometheusList + plural: prometheuses + shortNames: + - prom + singular: prometheus + scope: Namespaced + versions: + - additionalPrinterColumns: + - description: The version of Prometheus + jsonPath: .spec.version + name: Version + type: string + - description: The number of desired replicas + jsonPath: .spec.replicas + name: Desired + type: integer + - description: The number of ready replicas + jsonPath: .status.availableReplicas + name: Ready + type: integer + - jsonPath: .status.conditions[?(@.type == 'Reconciled')].status + name: Reconciled + type: string + - jsonPath: .status.conditions[?(@.type == 'Available')].status + name: Available + type: string + - jsonPath: .metadata.creationTimestamp + name: Age + type: date + - description: Whether the resource reconciliation is paused or not + jsonPath: .status.paused + name: Paused + priority: 1 + type: boolean + name: v1 + schema: + openAPIV3Schema: + description: Prometheus defines a Prometheus deployment. + properties: + apiVersion: + description: 'APIVersion defines the versioned schema of this representation of an object. Servers should convert recognized schemas to the latest internal value, and may reject unrecognized values. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#resources' + type: string + kind: + description: 'Kind is a string value representing the REST resource this object represents. Servers may infer this from the endpoint the client submits requests to. Cannot be updated. In CamelCase. More info: https://git.k8s.io/community/contributors/devel/sig-architecture/api-conventions.md#types-kinds' + type: string + metadata: + type: object + spec: + description: 'Specification of the desired behavior of the Prometheus cluster. More info: https://github.com/kubernetes/community/blob/master/contributors/devel/sig-architecture/api-conventions.md#spec-and-status' + properties: + additionalAlertManagerConfigs: + description: "AdditionalAlertManagerConfigs specifies a key of a Secret containing additional Prometheus Alertmanager configurations. The Alertmanager configurations are appended to the configuration generated by the Prometheus Operator. They must be formatted according to the official Prometheus documentation: \n https://prometheus.io/docs/prometheus/latest/configuration/configuration/#alertmanager_config \n The user is responsible for making sure that the configurations are valid \n Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible AlertManager configs are going to break Prometheus after the upgrade." + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + additionalAlertRelabelConfigs: + description: "AdditionalAlertRelabelConfigs specifies a key of a Secret containing additional Prometheus alert relabel configurations. The alert relabel configurations are appended to the configuration generated by the Prometheus Operator. They must be formatted according to the official Prometheus documentation: \n https://prometheus.io/docs/prometheus/latest/configuration/configuration/#alert_relabel_configs \n The user is responsible for making sure that the configurations are valid \n Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible alert relabel configs are going to break Prometheus after the upgrade." + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + additionalArgs: + description: "AdditionalArgs allows setting additional arguments for the 'prometheus' container. \n It is intended for e.g. activating hidden flags which are not supported by the dedicated configuration options yet. The arguments are passed as-is to the Prometheus container which may cause issues if they are invalid or not supported by the given Prometheus version. \n In case of an argument conflict (e.g. an argument which is already set by the operator itself) or when providing an invalid argument, the reconciliation will fail and an error will be logged." + items: + description: Argument as part of the AdditionalArgs list. + properties: + name: + description: Name of the argument, e.g. "scrape.discovery-reload-interval". + minLength: 1 + type: string + value: + description: Argument value, e.g. 30s. Can be empty for name-only arguments (e.g. --storage.tsdb.no-lockfile) + type: string + required: + - name + type: object + type: array + additionalScrapeConfigs: + description: 'AdditionalScrapeConfigs allows specifying a key of a Secret containing additional Prometheus scrape configurations. Scrape configurations specified are appended to the configurations generated by the Prometheus Operator. Job configurations specified must have the form as specified in the official Prometheus documentation: https://prometheus.io/docs/prometheus/latest/configuration/configuration/#scrape_config. As scrape configs are appended, the user is responsible to make sure it is valid. Note that using this feature may expose the possibility to break upgrades of Prometheus. It is advised to review Prometheus release notes to ensure that no incompatible scrape configs are going to break Prometheus after the upgrade.' + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + affinity: + description: Defines the Pods' affinity scheduling rules if specified. + properties: + nodeAffinity: + description: Describes node affinity scheduling rules for the pod. + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node matches the corresponding matchExpressions; the node(s) with the highest sum are the most preferred. + items: + description: An empty preferred scheduling term matches all objects with implicit weight 0 (i.e. it's a no-op). A null preferred scheduling term matches no objects (i.e. is also a no-op). + properties: + preference: + description: A node selector term, associated with the corresponding weight. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + weight: + description: Weight associated with matching the corresponding nodeSelectorTerm, in the range 1-100. + format: int32 + type: integer + required: + - preference + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to an update), the system may or may not try to eventually evict the pod from its node. + properties: + nodeSelectorTerms: + description: Required. A list of node selector terms. The terms are ORed. + items: + description: A null or empty node selector term matches no objects. The requirements of them are ANDed. The TopologySelectorTerm type implements a subset of the NodeSelectorTerm. + properties: + matchExpressions: + description: A list of node selector requirements by node's labels. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchFields: + description: A list of node selector requirements by node's fields. + items: + description: A node selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: The label key that the selector applies to. + type: string + operator: + description: Represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists, DoesNotExist. Gt, and Lt. + type: string + values: + description: An array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. If the operator is Gt or Lt, the values array must have a single element, which will be interpreted as an integer. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + type: object + x-kubernetes-map-type: atomic + type: array + required: + - nodeSelectorTerms + type: object + x-kubernetes-map-type: atomic + type: object + podAffinity: + description: Describes pod affinity scheduling rules (e.g. co-locate this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + podAntiAffinity: + description: Describes pod anti-affinity scheduling rules (e.g. avoid putting this pod in the same node, zone, etc. as some other pod(s)). + properties: + preferredDuringSchedulingIgnoredDuringExecution: + description: The scheduler will prefer to schedule pods to nodes that satisfy the anti-affinity expressions specified by this field, but it may choose a node that violates one or more of the expressions. The node that is most preferred is the one with the greatest sum of weights, i.e. for each node that meets all of the scheduling requirements (resource request, requiredDuringScheduling anti-affinity expressions, etc.), compute a sum by iterating through the elements of this field and adding "weight" to the sum if the node has pods which matches the corresponding podAffinityTerm; the node(s) with the highest sum are the most preferred. + items: + description: The weights of all of the matched WeightedPodAffinityTerm fields are added per-node to find the most preferred node(s) + properties: + podAffinityTerm: + description: Required. A pod affinity term, associated with the corresponding weight. + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + weight: + description: weight associated with matching the corresponding podAffinityTerm, in the range 1-100. + format: int32 + type: integer + required: + - podAffinityTerm + - weight + type: object + type: array + requiredDuringSchedulingIgnoredDuringExecution: + description: If the anti-affinity requirements specified by this field are not met at scheduling time, the pod will not be scheduled onto the node. If the anti-affinity requirements specified by this field cease to be met at some point during pod execution (e.g. due to a pod label update), the system may or may not try to eventually evict the pod from its node. When there are multiple elements, the lists of nodes corresponding to each podAffinityTerm are intersected, i.e. all terms must be satisfied. + items: + description: Defines a set of pods (namely those matching the labelSelector relative to the given namespace(s)) that this pod should be co-located (affinity) or not co-located (anti-affinity) with, where co-located is defined as running on a node whose value of the label with key matches that of any node on which a pod of the set of pods is running + properties: + labelSelector: + description: A label query over a set of resources, in this case pods. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaceSelector: + description: A label query over the set of namespaces that the term applies to. The term is applied to the union of the namespaces selected by this field and the ones listed in the namespaces field. null selector and null or empty namespaces list means "this pod's namespace". An empty selector ({}) matches all namespaces. + properties: + matchExpressions: + description: matchExpressions is a list of label selector requirements. The requirements are ANDed. + items: + description: A label selector requirement is a selector that contains values, a key, and an operator that relates the key and values. + properties: + key: + description: key is the label key that the selector applies to. + type: string + operator: + description: operator represents a key's relationship to a set of values. Valid operators are In, NotIn, Exists and DoesNotExist. + type: string + values: + description: values is an array of string values. If the operator is In or NotIn, the values array must be non-empty. If the operator is Exists or DoesNotExist, the values array must be empty. This array is replaced during a strategic merge patch. + items: + type: string + type: array + required: + - key + - operator + type: object + type: array + matchLabels: + additionalProperties: + type: string + description: matchLabels is a map of {key,value} pairs. A single {key,value} in the matchLabels map is equivalent to an element of matchExpressions, whose key field is "key", the operator is "In", and the values array contains only "value". The requirements are ANDed. + type: object + type: object + x-kubernetes-map-type: atomic + namespaces: + description: namespaces specifies a static list of namespace names that the term applies to. The term is applied to the union of the namespaces listed in this field and the ones selected by namespaceSelector. null or empty namespaces list and null namespaceSelector means "this pod's namespace". + items: + type: string + type: array + topologyKey: + description: This pod should be co-located (affinity) or not co-located (anti-affinity) with the pods matching the labelSelector in the specified namespaces, where co-located is defined as running on a node whose value of the label with key topologyKey matches that of any node on which any of the selected pods is running. Empty topologyKey is not allowed. + type: string + required: + - topologyKey + type: object + type: array + type: object + type: object + alerting: + description: Defines the settings related to Alertmanager. + properties: + alertmanagers: + description: AlertmanagerEndpoints Prometheus should fire alerts against. + items: + description: AlertmanagerEndpoints defines a selection of a single Endpoints object containing alertmanager IPs to fire alerts against. + properties: + apiVersion: + description: Version of the Alertmanager API that Prometheus uses to send alerts. It can be "v1" or "v2". + type: string + authorization: + description: Authorization section for this alertmanager endpoint + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth allow an endpoint to authenticate over basic authentication + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerTokenFile: + description: BearerTokenFile to read from filesystem to use when authenticating to Alertmanager. + type: string + enableHttp2: + description: Whether to enable HTTP2. + type: boolean + name: + description: Name of Endpoints object in Namespace. + type: string + namespace: + description: Namespace of Endpoints object. + type: string + pathPrefix: + description: Prefix for the HTTP path alerts are pushed to. + type: string + port: + anyOf: + - type: integer + - type: string + description: Port the Alertmanager API is exposed on. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use when firing alerts. + type: string + timeout: + description: Timeout is a per-target Alertmanager timeout when pushing alerts. + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + tlsConfig: + description: TLS Config to use for alertmanager connection. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + required: + - name + - namespace + - port + type: object + type: array + required: + - alertmanagers + type: object + allowOverlappingBlocks: + description: "AllowOverlappingBlocks enables vertical compaction and vertical query merge in Prometheus. \n *Deprecated: this flag has no effect for Prometheus >= 2.39.0 where overlapping blocks are enabled by default.*" + type: boolean + apiserverConfig: + description: 'APIServerConfig allows specifying a host and auth methods to access the Kuberntees API server. If null, Prometheus is assumed to run inside of the cluster: it will discover the API servers automatically and use the Pod''s CA certificate and bearer token file at /var/run/secrets/kubernetes.io/serviceaccount/.' + properties: + authorization: + description: Authorization section for accessing apiserver + properties: + credentials: + description: The secret's key that contains the credentials of the request + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + credentialsFile: + description: File to read a secret from, mutually exclusive with Credentials (from SafeAuthorization) + type: string + type: + description: Set the authentication type. Defaults to Bearer, Basic will cause an error + type: string + type: object + basicAuth: + description: BasicAuth allow an endpoint to authenticate over basic authentication + properties: + password: + description: The secret in the service monitor namespace that contains the password for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + username: + description: The secret in the service monitor namespace that contains the username for authentication. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + bearerToken: + description: Bearer token for accessing apiserver. + type: string + bearerTokenFile: + description: File to read bearer token for accessing apiserver. + type: string + host: + description: Host of apiserver. A valid string consisting of a hostname or IP followed by an optional port number + type: string + tlsConfig: + description: TLS Config to use for accessing apiserver. + properties: + ca: + description: Certificate authority used when verifying server certificates. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + caFile: + description: Path to the CA cert in the Prometheus container to use for the targets. + type: string + cert: + description: Client certificate to present when doing client-authentication. + properties: + configMap: + description: ConfigMap containing data to use for the targets. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + secret: + description: Secret containing data to use for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + certFile: + description: Path to the client cert file in the Prometheus container for the targets. + type: string + insecureSkipVerify: + description: Disable target certificate validation. + type: boolean + keyFile: + description: Path to the client key file in the Prometheus container for the targets. + type: string + keySecret: + description: Secret containing the client key file for the targets. + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + serverName: + description: Used to verify the hostname for the targets. + type: string + type: object + required: + - host + type: object + arbitraryFSAccessThroughSMs: + description: When true, ServiceMonitor, PodMonitor and Probe object are forbidden to reference arbitrary files on the file system of the 'prometheus' container. When a ServiceMonitor's endpoint specifies a `bearerTokenFile` value (e.g. '/var/run/secrets/kubernetes.io/serviceaccount/token'), a malicious target can get access to the Prometheus service account's token in the Prometheus' scrape request. Setting `spec.arbitraryFSAccessThroughSM` to 'true' would prevent the attack. Users should instead provide the credentials using the `spec.bearerTokenSecret` field. + properties: + deny: + type: boolean + type: object + baseImage: + description: '*Deprecated: use ''spec.image'' instead.*' + type: string + configMaps: + description: ConfigMaps is a list of ConfigMaps in the same namespace as the Prometheus object, which shall be mounted into the Prometheus Pods. Each ConfigMap is added to the StatefulSet definition as a volume named `configmap-`. The ConfigMaps are mounted into /etc/prometheus/configmaps/ in the 'prometheus' container. + items: + type: string + type: array + containers: + description: "Containers allows injecting additional containers or modifying operator generated containers. This can be used to allow adding an authentication proxy to the Pods or to change the behavior of an operator generated container. Containers described here modify an operator generated container if they share the same name and modifications are done via a strategic merge patch. \n The names of containers managed by the operator are: * `prometheus` * `config-reloader` * `thanos-sidecar` \n Overriding containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice." + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The container image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The container image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['''']`, `metadata.annotations['''']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + description: 'Container image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The Pod''s termination grace period countdown begins before the PreStop hook is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period (unless delayed by finalizers). Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Modifying this array with strategic merge patch may corrupt the data. For more information See https://github.com/kubernetes/kubernetes/issues/108255. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resizePolicy: + description: Resources resize policy for the container. + items: + description: ContainerResizePolicy represents resource resize policy for the container. + properties: + resourceName: + description: 'Name of the resource to which this resource resize policy applies. Supported values: cpu, memory.' + type: string + restartPolicy: + description: Restart policy to apply when specified resource is resized. If not specified, it defaults to NotRequired. + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the container should be run with. If set, the fields of SecurityContext override the equivalent fields of PodSecurityContext. More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN Note that this field cannot be set when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. Note that this field cannot be set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. Note that this field cannot be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. If seccomp options are provided at both the pod & container level, the container options override the pod options. Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile will be applied. Valid options are: \n Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should be run as a 'Host Process' container. This field is alpha-level and will only be honored by components that enable the WindowsHostProcessContainers feature flag. Setting this field without the feature flag will result in errors when validating the Pod. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + disableCompaction: + description: When true, the Prometheus compaction is disabled. + type: boolean + enableAdminAPI: + description: "Enables access to the Prometheus web admin API. \n WARNING: Enabling the admin APIs enables mutating endpoints, to delete data, shutdown Prometheus, and more. Enabling this should be done with care and the user is advised to add additional authentication authorization via a proxy to ensure only clients authorized to perform these actions can do so. \n For more information: https://prometheus.io/docs/prometheus/latest/querying/api/#tsdb-admin-apis" + type: boolean + enableFeatures: + description: "Enable access to Prometheus feature flags. By default, no features are enabled. \n Enabling features which are disabled by default is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice. \n For more information see https://prometheus.io/docs/prometheus/latest/feature_flags/" + items: + type: string + type: array + enableRemoteWriteReceiver: + description: "Enable Prometheus to be used as a receiver for the Prometheus remote write protocol. \n WARNING: This is not considered an efficient way of ingesting samples. Use it with caution for specific low-volume use cases. It is not suitable for replacing the ingestion via scraping and turning Prometheus into a push-based metrics collection system. For more information see https://prometheus.io/docs/prometheus/latest/querying/api/#remote-write-receiver \n It requires Prometheus >= v2.33.0." + type: boolean + enforcedBodySizeLimit: + description: "When defined, enforcedBodySizeLimit specifies a global limit on the size of uncompressed response body that will be accepted by Prometheus. Targets responding with a body larger than this many bytes will cause the scrape to fail. \n It requires Prometheus >= v2.28.0." + pattern: (^0|([0-9]*[.])?[0-9]+((K|M|G|T|E|P)i?)?B)$ + type: string + enforcedLabelLimit: + description: "When defined, enforcedLabelLimit specifies a global limit on the number of labels per sample. The value overrides any `spec.labelLimit` set by ServiceMonitor, PodMonitor, Probe objects unless `spec.labelLimit` is greater than zero and less than `spec.enforcedLabelLimit`. \n It requires Prometheus >= v2.27.0." + format: int64 + type: integer + enforcedLabelNameLengthLimit: + description: "When defined, enforcedLabelNameLengthLimit specifies a global limit on the length of labels name per sample. The value overrides any `spec.labelNameLengthLimit` set by ServiceMonitor, PodMonitor, Probe objects unless `spec.labelNameLengthLimit` is greater than zero and less than `spec.enforcedLabelNameLengthLimit`. \n It requires Prometheus >= v2.27.0." + format: int64 + type: integer + enforcedLabelValueLengthLimit: + description: "When not null, enforcedLabelValueLengthLimit defines a global limit on the length of labels value per sample. The value overrides any `spec.labelValueLengthLimit` set by ServiceMonitor, PodMonitor, Probe objects unless `spec.labelValueLengthLimit` is greater than zero and less than `spec.enforcedLabelValueLengthLimit`. \n It requires Prometheus >= v2.27.0." + format: int64 + type: integer + enforcedNamespaceLabel: + description: "When not empty, a label will be added to \n 1. All metrics scraped from `ServiceMonitor`, `PodMonitor`, `Probe` and `ScrapeConfig` objects. 2. All metrics generated from recording rules defined in `PrometheusRule` objects. 3. All alerts generated from alerting rules defined in `PrometheusRule` objects. 4. All vector selectors of PromQL expressions defined in `PrometheusRule` objects. \n The label will not added for objects referenced in `spec.excludedFromEnforcement`. \n The label's name is this field's value. The label's value is the namespace of the `ServiceMonitor`, `PodMonitor`, `Probe` or `PrometheusRule` object." + type: string + enforcedSampleLimit: + description: "When defined, enforcedSampleLimit specifies a global limit on the number of scraped samples that will be accepted. This overrides any `spec.sampleLimit` set by ServiceMonitor, PodMonitor, Probe objects unless `spec.sampleLimit` is greater than zero and less than than `spec.enforcedSampleLimit`. \n It is meant to be used by admins to keep the overall number of samples/series under a desired limit." + format: int64 + type: integer + enforcedTargetLimit: + description: "When defined, enforcedTargetLimit specifies a global limit on the number of scraped targets. The value overrides any `spec.targetLimit` set by ServiceMonitor, PodMonitor, Probe objects unless `spec.targetLimit` is greater than zero and less than `spec.enforcedTargetLimit`. \n It is meant to be used by admins to to keep the overall number of targets under a desired limit." + format: int64 + type: integer + evaluationInterval: + default: 30s + description: 'Interval between rule evaluations. Default: "30s"' + pattern: ^(0|(([0-9]+)y)?(([0-9]+)w)?(([0-9]+)d)?(([0-9]+)h)?(([0-9]+)m)?(([0-9]+)s)?(([0-9]+)ms)?)$ + type: string + excludedFromEnforcement: + description: "List of references to PodMonitor, ServiceMonitor, Probe and PrometheusRule objects to be excluded from enforcing a namespace label of origin. \n It is only applicable if `spec.enforcedNamespaceLabel` set to true." + items: + description: ObjectReference references a PodMonitor, ServiceMonitor, Probe or PrometheusRule object. + properties: + group: + default: monitoring.coreos.com + description: Group of the referent. When not specified, it defaults to `monitoring.coreos.com` + enum: + - monitoring.coreos.com + type: string + name: + description: Name of the referent. When not set, all resources in the namespace are matched. + type: string + namespace: + description: 'Namespace of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/namespaces/' + minLength: 1 + type: string + resource: + description: Resource of the referent. + enum: + - prometheusrules + - servicemonitors + - podmonitors + - probes + type: string + required: + - namespace + - resource + type: object + type: array + exemplars: + description: Exemplars related settings that are runtime reloadable. It requires to enable the `exemplar-storage` feature flag to be effective. + properties: + maxSize: + description: Maximum number of exemplars stored in memory for all series. If not set, Prometheus uses its default value. A value of zero or less than zero disables the storage. + format: int64 + type: integer + type: object + externalLabels: + additionalProperties: + type: string + description: The labels to add to any time series or alerts when communicating with external systems (federation, remote storage, Alertmanager). Labels defined by `spec.replicaExternalLabelName` and `spec.prometheusExternalLabelName` take precedence over this list. + type: object + externalUrl: + description: The external URL under which the Prometheus service is externally available. This is necessary to generate correct URLs (for instance if Prometheus is accessible behind an Ingress resource). + type: string + hostAliases: + description: Optional list of hosts and IPs that will be injected into the Pod's hosts file if specified. + items: + description: HostAlias holds the mapping between IP and hostnames that will be injected as an entry in the pod's hosts file. + properties: + hostnames: + description: Hostnames for the above IP address. + items: + type: string + type: array + ip: + description: IP address of the host file entry. + type: string + required: + - hostnames + - ip + type: object + type: array + x-kubernetes-list-map-keys: + - ip + x-kubernetes-list-type: map + hostNetwork: + description: "Use the host's network namespace if true. \n Make sure to understand the security implications if you want to enable it (https://kubernetes.io/docs/concepts/configuration/overview/). \n When hostNetwork is enabled, this will set the DNS policy to `ClusterFirstWithHostNet` automatically." + type: boolean + ignoreNamespaceSelectors: + description: When true, `spec.namespaceSelector` from all PodMonitor, ServiceMonitor and Probe objects will be ignored. They will only discover targets within the namespace of the PodMonitor, ServiceMonitor and Probe objec. + type: boolean + image: + description: "Container image name for Prometheus. If specified, it takes precedence over the `spec.baseImage`, `spec.tag` and `spec.sha` fields. \n Specifying `spec.version` is still necessary to ensure the Prometheus Operator knows which version of Prometheus is being configured. \n If neither `spec.image` nor `spec.baseImage` are defined, the operator will use the latest upstream version of Prometheus available at the time when the operator was released." + type: string + imagePullPolicy: + description: Image pull policy for the 'prometheus', 'init-config-reloader' and 'config-reloader' containers. See https://kubernetes.io/docs/concepts/containers/images/#image-pull-policy for more details. + enum: + - "" + - Always + - Never + - IfNotPresent + type: string + imagePullSecrets: + description: An optional list of references to Secrets in the same namespace to use for pulling images from registries. See http://kubernetes.io/docs/user-guide/images#specifying-imagepullsecrets-on-a-pod + items: + description: LocalObjectReference contains enough information to let you locate the referenced object inside the same namespace. + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + type: object + x-kubernetes-map-type: atomic + type: array + initContainers: + description: "InitContainers allows injecting initContainers to the Pod definition. Those can be used to e.g. fetch secrets for injection into the Prometheus configuration from external sources. Any errors during the execution of an initContainer will lead to a restart of the Pod. More info: https://kubernetes.io/docs/concepts/workloads/pods/init-containers/ InitContainers described here modify an operator generated init containers if they share the same name and modifications are done via a strategic merge patch. \n The names of init container name managed by the operator are: * `init-config-reloader`. \n Overriding init containers is entirely outside the scope of what the maintainers will support and by doing so, you accept that this behaviour may break at any time without notice." + items: + description: A single application container that you want to run within a pod. + properties: + args: + description: 'Arguments to the entrypoint. The container image''s CMD is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + command: + description: 'Entrypoint array. Not executed within a shell. The container image''s ENTRYPOINT is used if this is not provided. Variable references $(VAR_NAME) are expanded using the container''s environment. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Cannot be updated. More info: https://kubernetes.io/docs/tasks/inject-data-application/define-command-argument-container/#running-a-command-in-a-shell' + items: + type: string + type: array + env: + description: List of environment variables to set in the container. Cannot be updated. + items: + description: EnvVar represents an environment variable present in a Container. + properties: + name: + description: Name of the environment variable. Must be a C_IDENTIFIER. + type: string + value: + description: 'Variable references $(VAR_NAME) are expanded using the previously defined environment variables in the container and any service environment variables. If a variable cannot be resolved, the reference in the input string will be unchanged. Double $$ are reduced to a single $, which allows for escaping the $(VAR_NAME) syntax: i.e. "$$(VAR_NAME)" will produce the string literal "$(VAR_NAME)". Escaped references will never be expanded, regardless of whether the variable exists or not. Defaults to "".' + type: string + valueFrom: + description: Source for the environment variable's value. Cannot be used if value is not empty. + properties: + configMapKeyRef: + description: Selects a key of a ConfigMap. + properties: + key: + description: The key to select. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + fieldRef: + description: 'Selects a field of the pod: supports metadata.name, metadata.namespace, `metadata.labels['''']`, `metadata.annotations['''']`, spec.nodeName, spec.serviceAccountName, status.hostIP, status.podIP, status.podIPs.' + properties: + apiVersion: + description: Version of the schema the FieldPath is written in terms of, defaults to "v1". + type: string + fieldPath: + description: Path of the field to select in the specified API version. + type: string + required: + - fieldPath + type: object + x-kubernetes-map-type: atomic + resourceFieldRef: + description: 'Selects a resource of the container: only resources limits and requests (limits.cpu, limits.memory, limits.ephemeral-storage, requests.cpu, requests.memory and requests.ephemeral-storage) are currently supported.' + properties: + containerName: + description: 'Container name: required for volumes, optional for env vars' + type: string + divisor: + anyOf: + - type: integer + - type: string + description: Specifies the output format of the exposed resources, defaults to "1" + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + resource: + description: 'Required: resource to select' + type: string + required: + - resource + type: object + x-kubernetes-map-type: atomic + secretKeyRef: + description: Selects a key of a secret in the pod's namespace + properties: + key: + description: The key of the secret to select from. Must be a valid secret key. + type: string + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret or its key must be defined + type: boolean + required: + - key + type: object + x-kubernetes-map-type: atomic + type: object + required: + - name + type: object + type: array + envFrom: + description: List of sources to populate environment variables in the container. The keys defined within a source must be a C_IDENTIFIER. All invalid keys will be reported as an event when the container is starting. When a key exists in multiple sources, the value associated with the last source will take precedence. Values defined by an Env with a duplicate key will take precedence. Cannot be updated. + items: + description: EnvFromSource represents the source of a set of ConfigMaps + properties: + configMapRef: + description: The ConfigMap to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the ConfigMap must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + prefix: + description: An optional identifier to prepend to each key in the ConfigMap. Must be a C_IDENTIFIER. + type: string + secretRef: + description: The Secret to select from + properties: + name: + description: 'Name of the referent. More info: https://kubernetes.io/docs/concepts/overview/working-with-objects/names/#names TODO: Add other useful fields. apiVersion, kind, uid?' + type: string + optional: + description: Specify whether the Secret must be defined + type: boolean + type: object + x-kubernetes-map-type: atomic + type: object + type: array + image: + description: 'Container image name. More info: https://kubernetes.io/docs/concepts/containers/images This field is optional to allow higher level config management to default or override container images in workload controllers like Deployments and StatefulSets.' + type: string + imagePullPolicy: + description: 'Image pull policy. One of Always, Never, IfNotPresent. Defaults to Always if :latest tag is specified, or IfNotPresent otherwise. Cannot be updated. More info: https://kubernetes.io/docs/concepts/containers/images#updating-images' + type: string + lifecycle: + description: Actions that the management system should take in response to container lifecycle events. Cannot be updated. + properties: + postStart: + description: 'PostStart is called immediately after a container is created. If the handler fails, the container is terminated and restarted according to its restart policy. Other management of the container blocks until the hook completes. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + preStop: + description: 'PreStop is called immediately before a container is terminated due to an API request or management event such as liveness/startup probe failure, preemption, resource contention, etc. The handler is not called if the container crashes or exits. The Pod''s termination grace period countdown begins before the PreStop hook is executed. Regardless of the outcome of the handler, the container will eventually terminate within the Pod''s termination grace period (unless delayed by finalizers). Other management of the container blocks until the hook completes or until the termination grace period is reached. More info: https://kubernetes.io/docs/concepts/containers/container-lifecycle-hooks/#container-hooks' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + tcpSocket: + description: Deprecated. TCPSocket is NOT supported as a LifecycleHandler and kept for the backward compatibility. There are no validation of this field and lifecycle hooks will fail in runtime when tcp handler is specified. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + type: object + type: object + livenessProbe: + description: 'Periodic probe of container liveness. Container will be restarted if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + name: + description: Name of the container specified as a DNS_LABEL. Each container in a pod must have a unique name (DNS_LABEL). Cannot be updated. + type: string + ports: + description: List of ports to expose from the container. Not specifying a port here DOES NOT prevent that port from being exposed. Any port which is listening on the default "0.0.0.0" address inside a container will be accessible from the network. Modifying this array with strategic merge patch may corrupt the data. For more information See https://github.com/kubernetes/kubernetes/issues/108255. Cannot be updated. + items: + description: ContainerPort represents a network port in a single container. + properties: + containerPort: + description: Number of port to expose on the pod's IP address. This must be a valid port number, 0 < x < 65536. + format: int32 + type: integer + hostIP: + description: What host IP to bind the external port to. + type: string + hostPort: + description: Number of port to expose on the host. If specified, this must be a valid port number, 0 < x < 65536. If HostNetwork is specified, this must match ContainerPort. Most containers do not need this. + format: int32 + type: integer + name: + description: If specified, this must be an IANA_SVC_NAME and unique within the pod. Each named port in a pod must have a unique name. Name for the port that can be referred to by services. + type: string + protocol: + default: TCP + description: Protocol for port. Must be UDP, TCP, or SCTP. Defaults to "TCP". + type: string + required: + - containerPort + type: object + type: array + x-kubernetes-list-map-keys: + - containerPort + - protocol + x-kubernetes-list-type: map + readinessProbe: + description: 'Periodic probe of container service readiness. Container will be removed from service endpoints if the probe fails. Cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + resizePolicy: + description: Resources resize policy for the container. + items: + description: ContainerResizePolicy represents resource resize policy for the container. + properties: + resourceName: + description: 'Name of the resource to which this resource resize policy applies. Supported values: cpu, memory.' + type: string + restartPolicy: + description: Restart policy to apply when specified resource is resized. If not specified, it defaults to NotRequired. + type: string + required: + - resourceName + - restartPolicy + type: object + type: array + x-kubernetes-list-type: atomic + resources: + description: 'Compute Resources required by this container. Cannot be updated. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + properties: + claims: + description: "Claims lists the names of resources, defined in spec.resourceClaims, that are used by this container. \n This is an alpha field and requires enabling the DynamicResourceAllocation feature gate. \n This field is immutable. It can only be set for containers." + items: + description: ResourceClaim references one entry in PodSpec.ResourceClaims. + properties: + name: + description: Name must match the name of one entry in pod.spec.resourceClaims of the Pod where this field is used. It makes that resource available inside a container. + type: string + required: + - name + type: object + type: array + x-kubernetes-list-map-keys: + - name + x-kubernetes-list-type: map + limits: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Limits describes the maximum amount of compute resources allowed. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + requests: + additionalProperties: + anyOf: + - type: integer + - type: string + pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$ + x-kubernetes-int-or-string: true + description: 'Requests describes the minimum amount of compute resources required. If Requests is omitted for a container, it defaults to Limits if that is explicitly specified, otherwise to an implementation-defined value. Requests cannot exceed Limits. More info: https://kubernetes.io/docs/concepts/configuration/manage-resources-containers/' + type: object + type: object + securityContext: + description: 'SecurityContext defines the security options the container should be run with. If set, the fields of SecurityContext override the equivalent fields of PodSecurityContext. More info: https://kubernetes.io/docs/tasks/configure-pod-container/security-context/' + properties: + allowPrivilegeEscalation: + description: 'AllowPrivilegeEscalation controls whether a process can gain more privileges than its parent process. This bool directly controls if the no_new_privs flag will be set on the container process. AllowPrivilegeEscalation is true always when the container is: 1) run as Privileged 2) has CAP_SYS_ADMIN Note that this field cannot be set when spec.os.name is windows.' + type: boolean + capabilities: + description: The capabilities to add/drop when running containers. Defaults to the default set of capabilities granted by the container runtime. Note that this field cannot be set when spec.os.name is windows. + properties: + add: + description: Added capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + drop: + description: Removed capabilities + items: + description: Capability represent POSIX capabilities type + type: string + type: array + type: object + privileged: + description: Run container in privileged mode. Processes in privileged containers are essentially equivalent to root on the host. Defaults to false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + procMount: + description: procMount denotes the type of proc mount to use for the containers. The default is DefaultProcMount which uses the container runtime defaults for readonly paths and masked paths. This requires the ProcMountType feature flag to be enabled. Note that this field cannot be set when spec.os.name is windows. + type: string + readOnlyRootFilesystem: + description: Whether this container has a read-only root filesystem. Default is false. Note that this field cannot be set when spec.os.name is windows. + type: boolean + runAsGroup: + description: The GID to run the entrypoint of the container process. Uses runtime default if unset. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + runAsNonRoot: + description: Indicates that the container must run as a non-root user. If true, the Kubelet will validate the image at runtime to ensure that it does not run as UID 0 (root) and fail to start the container if it does. If unset or false, no such validation will be performed. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: boolean + runAsUser: + description: The UID to run the entrypoint of the container process. Defaults to user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + format: int64 + type: integer + seLinuxOptions: + description: The SELinux context to be applied to the container. If unspecified, the container runtime will allocate a random SELinux context for each container. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is windows. + properties: + level: + description: Level is SELinux level label that applies to the container. + type: string + role: + description: Role is a SELinux role label that applies to the container. + type: string + type: + description: Type is a SELinux type label that applies to the container. + type: string + user: + description: User is a SELinux user label that applies to the container. + type: string + type: object + seccompProfile: + description: The seccomp options to use by this container. If seccomp options are provided at both the pod & container level, the container options override the pod options. Note that this field cannot be set when spec.os.name is windows. + properties: + localhostProfile: + description: localhostProfile indicates a profile defined in a file on the node should be used. The profile must be preconfigured on the node to work. Must be a descending path, relative to the kubelet's configured seccomp profile location. Must only be set if type is "Localhost". + type: string + type: + description: "type indicates which kind of seccomp profile will be applied. Valid options are: \n Localhost - a profile defined in a file on the node should be used. RuntimeDefault - the container runtime default profile should be used. Unconfined - no profile should be applied." + type: string + required: + - type + type: object + windowsOptions: + description: The Windows specific settings applied to all containers. If unspecified, the options from the PodSecurityContext will be used. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. Note that this field cannot be set when spec.os.name is linux. + properties: + gmsaCredentialSpec: + description: GMSACredentialSpec is where the GMSA admission webhook (https://github.com/kubernetes-sigs/windows-gmsa) inlines the contents of the GMSA credential spec named by the GMSACredentialSpecName field. + type: string + gmsaCredentialSpecName: + description: GMSACredentialSpecName is the name of the GMSA credential spec to use. + type: string + hostProcess: + description: HostProcess determines if a container should be run as a 'Host Process' container. This field is alpha-level and will only be honored by components that enable the WindowsHostProcessContainers feature flag. Setting this field without the feature flag will result in errors when validating the Pod. All of a Pod's containers must have the same effective HostProcess value (it is not allowed to have a mix of HostProcess containers and non-HostProcess containers). In addition, if HostProcess is true then HostNetwork must also be set to true. + type: boolean + runAsUserName: + description: The UserName in Windows to run the entrypoint of the container process. Defaults to the user specified in image metadata if unspecified. May also be set in PodSecurityContext. If set in both SecurityContext and PodSecurityContext, the value specified in SecurityContext takes precedence. + type: string + type: object + type: object + startupProbe: + description: 'StartupProbe indicates that the Pod has successfully initialized. If specified, no other probes are executed until this completes successfully. If this probe fails, the Pod will be restarted, just as if the livenessProbe failed. This can be used to provide different probe parameters at the beginning of a Pod''s lifecycle, when it might take a long time to load data or warm a cache, than during steady-state operation. This cannot be updated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + properties: + exec: + description: Exec specifies the action to take. + properties: + command: + description: Command is the command line to execute inside the container, the working directory for the command is root ('/') in the container's filesystem. The command is simply exec'd, it is not run inside a shell, so traditional shell instructions ('|', etc) won't work. To use a shell, you need to explicitly call out to that shell. Exit status of 0 is treated as live/healthy and non-zero is unhealthy. + items: + type: string + type: array + type: object + failureThreshold: + description: Minimum consecutive failures for the probe to be considered failed after having succeeded. Defaults to 3. Minimum value is 1. + format: int32 + type: integer + grpc: + description: GRPC specifies an action involving a GRPC port. + properties: + port: + description: Port number of the gRPC service. Number must be in the range 1 to 65535. + format: int32 + type: integer + service: + description: "Service is the name of the service to place in the gRPC HealthCheckRequest (see https://github.com/grpc/grpc/blob/master/doc/health-checking.md). \n If this is not specified, the default behavior is defined by gRPC." + type: string + required: + - port + type: object + httpGet: + description: HTTPGet specifies the http request to perform. + properties: + host: + description: Host name to connect to, defaults to the pod IP. You probably want to set "Host" in httpHeaders instead. + type: string + httpHeaders: + description: Custom headers to set in the request. HTTP allows repeated headers. + items: + description: HTTPHeader describes a custom header to be used in HTTP probes + properties: + name: + description: The header field name. This will be canonicalized upon output, so case-variant names will be understood as the same header. + type: string + value: + description: The header field value + type: string + required: + - name + - value + type: object + type: array + path: + description: Path to access on the HTTP server. + type: string + port: + anyOf: + - type: integer + - type: string + description: Name or number of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + scheme: + description: Scheme to use for connecting to the host. Defaults to HTTP. + type: string + required: + - port + type: object + initialDelaySeconds: + description: 'Number of seconds after the container has started before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + periodSeconds: + description: How often (in seconds) to perform the probe. Default to 10 seconds. Minimum value is 1. + format: int32 + type: integer + successThreshold: + description: Minimum consecutive successes for the probe to be considered successful after having failed. Defaults to 1. Must be 1 for liveness and startup. Minimum value is 1. + format: int32 + type: integer + tcpSocket: + description: TCPSocket specifies an action involving a TCP port. + properties: + host: + description: 'Optional: Host name to connect to, defaults to the pod IP.' + type: string + port: + anyOf: + - type: integer + - type: string + description: Number or name of the port to access on the container. Number must be in the range 1 to 65535. Name must be an IANA_SVC_NAME. + x-kubernetes-int-or-string: true + required: + - port + type: object + terminationGracePeriodSeconds: + description: Optional duration in seconds the pod needs to terminate gracefully upon probe failure. The grace period is the duration in seconds after the processes running in the pod are sent a termination signal and the time when the processes are forcibly halted with a kill signal. Set this value longer than the expected cleanup time for your process. If this value is nil, the pod's terminationGracePeriodSeconds will be used. Otherwise, this value overrides the value provided by the pod spec. Value must be non-negative integer. The value zero indicates stop immediately via the kill signal (no opportunity to shut down). This is a beta field and requires enabling ProbeTerminationGracePeriod feature gate. Minimum value is 1. spec.terminationGracePeriodSeconds is used if unset. + format: int64 + type: integer + timeoutSeconds: + description: 'Number of seconds after which the probe times out. Defaults to 1 second. Minimum value is 1. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes' + format: int32 + type: integer + type: object + stdin: + description: Whether this container should allocate a buffer for stdin in the container runtime. If this is not set, reads from stdin in the container will always result in EOF. Default is false. + type: boolean + stdinOnce: + description: Whether the container runtime should close the stdin channel after it has been opened by a single attach. When stdin is true the stdin stream will remain open across multiple attach sessions. If stdinOnce is set to true, stdin is opened on container start, is empty until the first client attaches to stdin, and then remains open and accepts data until the client disconnects, at which time stdin is closed and remains closed until the container is restarted. If this flag is false, a container processes that reads from stdin will never receive an EOF. Default is false + type: boolean + terminationMessagePath: + description: 'Optional: Path at which the file to which the container''s termination message will be written is mounted into the container''s filesystem. Message written is intended to be brief final status, such as an assertion failure message. Will be truncated by the node if greater than 4096 bytes. The total message length across all containers will be limited to 12kb. Defaults to /dev/termination-log. Cannot be updated.' + type: string + terminationMessagePolicy: + description: Indicate how the termination message should be populated. File will use the contents of terminationMessagePath to populate the container status message on both success and failure. FallbackToLogsOnError will use the last chunk of container log output if the termination message file is empty and the container exited with an error. The log output is limited to 2048 bytes or 80 lines, whichever is smaller. Defaults to File. Cannot be updated. + type: string + tty: + description: Whether this container should allocate a TTY for itself, also requires 'stdin' to be true. Default is false. + type: boolean + volumeDevices: + description: volumeDevices is the list of block devices to be used by the container. + items: + description: volumeDevice describes a mapping of a raw block device within a container. + properties: + devicePath: + description: devicePath is the path inside of the container that the device will be mapped to. + type: string + name: + description: name must match the name of a persistentVolumeClaim in the pod + type: string + required: + - devicePath + - name + type: object + type: array + volumeMounts: + description: Pod volumes to mount into the container's filesystem. Cannot be updated. + items: + description: VolumeMount describes a mounting of a Volume within a container. + properties: + mountPath: + description: Path within the container at which the volume should be mounted. Must not contain ':'. + type: string + mountPropagation: + description: mountPropagation determines how mounts are propagated from the host to container and the other way around. When not set, MountPropagationNone is used. This field is beta in 1.10. + type: string + name: + description: This must match the Name of a Volume. + type: string + readOnly: + description: Mounted read-only if true, read-write otherwise (false or unspecified). Defaults to false. + type: boolean + subPath: + description: Path within the volume from which the container's volume should be mounted. Defaults to "" (volume's root). + type: string + subPathExpr: + description: Expanded path within the volume from which the container's volume should be mounted. Behaves similarly to SubPath but environment variable references $(VAR_NAME) are expanded using the container's environment. Defaults to "" (volume's root). SubPathExpr and SubPath are mutually exclusive. + type: string + required: + - mountPath + - name + type: object + type: array + workingDir: + description: Container's working directory. If not specified, the container runtime's default will be used, which might be configured in the container image. Cannot be updated. + type: string + required: + - name + type: object + type: array + listenLocal: + description: When true, the Prometheus server listens on the loopback address instead of the Pod IP's address. + type: boolean + logFormat: + description: Log format for Log level for Prometheus and the config-reloader sidecar. + enum: + - "" + - logfmt + - json + type: string + logLevel: + description: Log level for Prometheus and the config-reloader sidecar. + enum: + - "" + - debug + - info + - warn + - error + type: string + minReadySeconds: + description: "Minimum number of seconds for which a newly created Pod should be ready without any of its container crashing for it to be considered available. Defaults to 0 (pod will be considered available as soon as it is ready) \n This is an alpha field from kubernetes 1.22 until 1.24 which requires enabling the StatefulSetMinReadySeconds feature gate." + format: int32 + type: integer + nodeSelector: + additionalProperties: + type: string + description: Defines on which Nodes the Pods are scheduled. + type: object + overrideHonorLabels: + description: When true, Prometheus resolves label conflicts by renaming the labels in the scraped data to "exported_