Merge branch 'main' into hotfix/solve-grafana-hpa-selector

.github/workflows/release.yaml

@@ -47,14 +47,19 @@ jobs:
           CR_TOKEN: "${{ secrets.GITHUB_TOKEN }}"
           CR_SKIP_EXISTING: "true"
 
+      - name: Login to GHCR
+        uses: docker/[email protected]
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
       - name: Push charts to GHCR
         run: |
           shopt -s nullglob
-          for pkg in .cr-release-packages/*; do
+          for pkg in .cr-release-packages/*.tgz; do
             if [ -z "${pkg:-}" ]; then
               break
             fi
-            if ! helm push "${pkg}" "oci://ghcr.io/${GITHUB_REPOSITORY_OWNER}/charts"; then
-              echo '::warning:: helm push failed!'
-            fi
+            helm push "${pkg}" "oci://ghcr.io/${GITHUB_REPOSITORY_OWNER}/helm-charts"
           done

charts/agent-operator/Chart.yaml

@@ -2,7 +2,7 @@ apiVersion: v2
 name: grafana-agent-operator
 description: A Helm chart for Grafana Agent Operator
 type: application
-version: 0.3.19
+version: 0.3.20
 appVersion: "0.40.3"
 home: https://grafana.com/docs/agent/v0.40/
 icon: https://raw.githubusercontent.com/grafana/agent/v0.40.3/docs/sources/assets/logo_and_name.png

charts/agent-operator/README.md

@@ -1,6 +1,6 @@
 # grafana-agent-operator
 
-![Version: 0.3.19](https://img.shields.io/badge/Version-0.3.19-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.40.3](https://img.shields.io/badge/AppVersion-0.40.3-informational?style=flat-square)
+![Version: 0.3.20](https://img.shields.io/badge/Version-0.3.20-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 0.40.3](https://img.shields.io/badge/AppVersion-0.40.3-informational?style=flat-square)
 
 A Helm chart for Grafana Agent Operator
 
@@ -75,4 +75,7 @@ A major chart version change (like v1.2.3 -> v2.0.0) indicates that there is an
 | resources | object | `{}` | Resource limits and requests config |
 | serviceAccount.create | bool | `true` | Toggle to create ServiceAccount |
 | serviceAccount.name | string | `nil` | Service account name |
+| test.image.registry | string | `"docker.io"` | Test image registry |
+| test.image.repository | string | `"library/busybox"` | Test image repo |
+| test.image.tag | string | `"latest"` | Test image tag |
 | tolerations | list | `[]` | Tolerations applied to Pods |

charts/agent-operator/templates/tests/test-grafanaagent.yaml

@@ -107,12 +107,12 @@ metadata:
 spec:
   containers:
   - name: busybox
-    image: busybox
+    image: "{{ .Values.test.image.registry }}/{{ .Values.test.image.repository }}:{{ .Values.test.image.tag }}"
     command: ['wget']
     args:  ['grafana-agent-test-operated:8080/-/healthy']
   # Wait for GrafanaAgent CR
   initContainers:
   - name: sleep
-    image: busybox
+    image: "{{ .Values.test.image.registry }}/{{ .Values.test.image.repository }}:{{ .Values.test.image.tag }}"
     command: ['sleep', '60']
   restartPolicy: Never

charts/agent-operator/values.yaml

@@ -43,6 +43,15 @@ image:
   # -- Image pull secrets
   pullSecrets: []
 
+test:
+  image:
+    # -- Test image registry
+    registry: docker.io
+    # -- Test image repo
+    repository: library/busybox
+    # -- Test image tag
+    tag: latest
+
 # -- hostAliases to add
 hostAliases: []
 #  - ip: 1.2.3.4

charts/grafana-sampling/.helmignore

@@ -0,0 +1,23 @@
+# Patterns to ignore when building packages.
+# This supports shell glob matching, relative path matching, and
+# negation (prefixed with !). Only one pattern per line.
+.DS_Store
+# Common VCS dirs
+.git/
+.gitignore
+.bzr/
+.bzrignore
+.hg/
+.hgignore
+.svn/
+# Common backup files
+*.swp
+*.bak
+*.tmp
+*.orig
+*~
+# Various IDEs
+.project
+.idea/
+*.tmproj
+.vscode/

charts/grafana-sampling/Chart.lock

@@ -0,0 +1,9 @@
+dependencies:
+- name: grafana-agent
+  repository: https://grafana.github.io/helm-charts
+  version: 0.36.0
+- name: grafana-agent
+  repository: https://grafana.github.io/helm-charts
+  version: 0.36.0
+digest: sha256:6d04a55dce2c09c4c250c6453e0d58f7280750bf04fce51027b4e235062413e5
+generated: "2024-03-11T15:41:30.921516-07:00"

charts/grafana-sampling/Chart.yaml

@@ -0,0 +1,18 @@
+apiVersion: v2
+name: grafana-sampling
+description: A Helm chart for a layered OTLP tail sampling and metrics generation pipeline.
+type: application
+version: 0.1.0
+appVersion: "v0.40.2"
+sources:
+  - https://github.com/grafana/agent
+  - https://grafana.com/docs/grafana-cloud/monitor-applications/application-observability/setup/sampling/tail/
+dependencies:
+  - name: grafana-agent
+    version: 0.36.0
+    repository: https://grafana.github.io/helm-charts
+    alias: grafana-agent-deployment
+  - name: grafana-agent
+    version: 0.36.0
+    repository: https://grafana.github.io/helm-charts
+    alias: grafana-agent-statefulset

charts/grafana-sampling/README.md

@@ -0,0 +1,124 @@
+# grafana-sampling
+
+![Version: 0.1.0](https://img.shields.io/badge/Version-0.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: v0.40.2](https://img.shields.io/badge/AppVersion-v0.40.2-informational?style=flat-square)
+
+A Helm chart for a layered OTLP tail sampling and metrics generation pipeline.
+
+This chart deploys the following architecture to your environment:
+![Photo of sampling architecture](./sampling-architecture.png)
+
+Note: by default, only OTLP traces are accepted at the load balancing layer.
+
+## Chart Repo
+
+Add the following repo to use the chart:
+
+```console
+helm repo add grafana https://grafana.github.io/helm-charts
+```
+## Installing the Chart
+
+Use the following command to install the chart with the release name `my-release`. Make sure to populate the required values.
+
+```console
+helm install my-release grafana/grafana-sampling --values - <<EOF | less
+grafana-agent-statefulset:
+  agent:
+    extraEnv:
+      - name: GRAFANA_CLOUD_API_KEY
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_PROMETHEUS_URL
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_PROMETHEUS_USERNAME
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_TEMPO_ENDPOINT
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_TEMPO_USERNAME
+        value: <REQUIRED>
+      # This is required for adaptive metric deduplication in Grafana Cloud
+      - name: POD_UID
+        valueFrom:
+          fieldRef:
+            apiVersion: v1
+            fieldPath: metadata.uid
+EOF
+```
+
+## Uninstalling the Chart
+
+To uninstall/delete the my-release deployment:
+
+```console
+helm delete my-release
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+## Upgrading
+
+A major chart version change indicates that there is an incompatible breaking change needing manual actions.
+
+## Values
+
+| Key | Type | Default | Description |
+|-----|------|---------|-------------|
+| grafana-agent-deployment.agent.configMap.create | bool | `false` |  |
+| grafana-agent-deployment.agent.extraPorts[0].name | string | `"otlp-grpc"` |  |
+| grafana-agent-deployment.agent.extraPorts[0].port | int | `4317` |  |
+| grafana-agent-deployment.agent.extraPorts[0].protocol | string | `"TCP"` |  |
+| grafana-agent-deployment.agent.extraPorts[0].targetPort | int | `4317` |  |
+| grafana-agent-deployment.agent.extraPorts[1].name | string | `"otlp-http"` |  |
+| grafana-agent-deployment.agent.extraPorts[1].port | int | `4318` |  |
+| grafana-agent-deployment.agent.extraPorts[1].protocol | string | `"TCP"` |  |
+| grafana-agent-deployment.agent.extraPorts[1].targetPort | int | `4318` |  |
+| grafana-agent-deployment.agent.resources.requests.cpu | string | `"1"` |  |
+| grafana-agent-deployment.agent.resources.requests.memory | string | `"2G"` |  |
+| grafana-agent-deployment.controller.autoscaling.enabled | bool | `false` | Creates a HorizontalPodAutoscaler for controller type deployment. |
+| grafana-agent-deployment.controller.autoscaling.maxReplicas | int | `5` | The upper limit for the number of replicas to which the autoscaler can scale up. |
+| grafana-agent-deployment.controller.autoscaling.minReplicas | int | `2` | The lower limit for the number of replicas to which the autoscaler can scale down. |
+| grafana-agent-deployment.controller.autoscaling.targetCPUUtilizationPercentage | int | `0` | Average CPU utilization across all relevant pods, a percentage of the requested value of the resource for the pods. Setting `targetCPUUtilizationPercentage` to 0 will disable CPU scaling. |
+| grafana-agent-deployment.controller.autoscaling.targetMemoryUtilizationPercentage | int | `80` | Average Memory utilization across all relevant pods, a percentage of the requested value of the resource for the pods. Setting `targetMemoryUtilizationPercentage` to 0 will disable Memory scaling. |
+| grafana-agent-deployment.controller.replicas | int | `1` |  |
+| grafana-agent-deployment.controller.type | string | `"deployment"` |  |
+| grafana-agent-deployment.nameOverride | string | `"deployment"` | Do not change this. |
+| grafana-agent-statefulset.agent.configMap.create | bool | `false` |  |
+| grafana-agent-statefulset.agent.extraEnv[0].name | string | `"GRAFANA_CLOUD_API_KEY"` |  |
+| grafana-agent-statefulset.agent.extraEnv[0].value | string | `"<REQUIRED>"` |  |
+| grafana-agent-statefulset.agent.extraEnv[1].name | string | `"GRAFANA_CLOUD_PROMETHEUS_URL"` |  |
+| grafana-agent-statefulset.agent.extraEnv[1].value | string | `"<REQUIRED>"` |  |
+| grafana-agent-statefulset.agent.extraEnv[2].name | string | `"GRAFANA_CLOUD_PROMETHEUS_USERNAME"` |  |
+| grafana-agent-statefulset.agent.extraEnv[2].value | string | `"<REQUIRED>"` |  |
+| grafana-agent-statefulset.agent.extraEnv[3].name | string | `"GRAFANA_CLOUD_TEMPO_ENDPOINT"` |  |
+| grafana-agent-statefulset.agent.extraEnv[3].value | string | `"<REQUIRED>"` |  |
+| grafana-agent-statefulset.agent.extraEnv[4].name | string | `"GRAFANA_CLOUD_TEMPO_USERNAME"` |  |
+| grafana-agent-statefulset.agent.extraEnv[4].value | string | `"<REQUIRED>"` |  |
+| grafana-agent-statefulset.agent.extraEnv[5].name | string | `"POD_UID"` |  |
+| grafana-agent-statefulset.agent.extraEnv[5].valueFrom.fieldRef.apiVersion | string | `"v1"` |  |
+| grafana-agent-statefulset.agent.extraEnv[5].valueFrom.fieldRef.fieldPath | string | `"metadata.uid"` |  |
+| grafana-agent-statefulset.agent.extraPorts[0].name | string | `"otlp-grpc"` |  |
+| grafana-agent-statefulset.agent.extraPorts[0].port | int | `4317` |  |
+| grafana-agent-statefulset.agent.extraPorts[0].protocol | string | `"TCP"` |  |
+| grafana-agent-statefulset.agent.extraPorts[0].targetPort | int | `4317` |  |
+| grafana-agent-statefulset.agent.resources.requests.cpu | string | `"1"` |  |
+| grafana-agent-statefulset.agent.resources.requests.memory | string | `"2G"` |  |
+| grafana-agent-statefulset.controller.autoscaling.enabled | bool | `false` | Creates a HorizontalPodAutoscaler for controller type deployment. |
+| grafana-agent-statefulset.controller.autoscaling.maxReplicas | int | `5` | The upper limit for the number of replicas to which the autoscaler can scale up. |
+| grafana-agent-statefulset.controller.autoscaling.minReplicas | int | `2` | The lower limit for the number of replicas to which the autoscaler can scale down. |
+| grafana-agent-statefulset.controller.autoscaling.targetCPUUtilizationPercentage | int | `0` | Average CPU utilization across all relevant pods, a percentage of the requested value of the resource for the pods. Setting `targetCPUUtilizationPercentage` to 0 will disable CPU scaling. |
+| grafana-agent-statefulset.controller.autoscaling.targetMemoryUtilizationPercentage | int | `80` | Average Memory utilization across all relevant pods, a percentage of the requested value of the resource for the pods. Setting `targetMemoryUtilizationPercentage` to 0 will disable Memory scaling. |
+| grafana-agent-statefulset.controller.replicas | int | `1` |  |
+| grafana-agent-statefulset.controller.type | string | `"statefulset"` |  |
+| grafana-agent-statefulset.nameOverride | string | `"statefulset"` | Do not change this. |
+| grafana-agent-statefulset.rbac.create | bool | `false` |  |
+| grafana-agent-statefulset.service.clusterIP | string | `"None"` |  |
+| grafana-agent-statefulset.serviceAccount.create | bool | `false` |  |
+| metricsGeneration.dimensions | list | `["service.namespace","service.version","deployment.environment","k8s.cluster.name"]` | Additional dimensions to add to generated metrics. |
+| metricsGeneration.enabled | bool | `true` | Toggle generation of spanmetrics and servicegraph metrics. |
+| sampling.decisionWait | string | `"15s"` | Wait time since the first span of a trace before making a sampling decision. |
+| sampling.enabled | bool | `true` | Toggle tail sampling. |
+| sampling.extraPolicies | string | A policy to sample long requests is added by default. | User-defined policies in river format. |
+| sampling.failedRequests.percentage | int | `50` | Percentage of failed requests to sample. |
+| sampling.failedRequests.sample | bool | `false` | Toggle sampling failed requests. |
+| sampling.successfulRequests.percentage | int | `10` | Percentage of successful requests to sample. |
+| sampling.successfulRequests.sample | bool | `true` | Toggle sampling successful requests. |
+

charts/grafana-sampling/README.md.gotmpl

@@ -0,0 +1,63 @@
+{{ template "chart.header" . }}
+
+{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
+
+{{ template "chart.description" . }}
+
+This chart deploys the following architecture to your environment:
+![Photo of sampling architecture](./sampling-architecture.png)
+
+Note: by default, only OTLP traces are accepted at the load balancing layer.
+
+
+## Chart Repo
+
+Add the following repo to use the chart:
+
+```console
+helm repo add grafana https://grafana.github.io/helm-charts
+```
+## Installing the Chart
+
+Use the following command to install the chart with the release name `my-release`. Make sure to populate the required values.
+
+```console
+helm install my-release grafana/grafana-sampling --values - <<EOF | less
+grafana-agent-statefulset:
+  agent:
+    extraEnv:
+      - name: GRAFANA_CLOUD_API_KEY
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_PROMETHEUS_URL
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_PROMETHEUS_USERNAME
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_TEMPO_ENDPOINT
+        value: <REQUIRED>
+      - name: GRAFANA_CLOUD_TEMPO_USERNAME
+        value: <REQUIRED>
+      # This is required for adaptive metric deduplication in Grafana Cloud
+      - name: POD_UID
+        valueFrom:
+          fieldRef:
+            apiVersion: v1
+            fieldPath: metadata.uid
+EOF
+```
+
+## Uninstalling the Chart
+
+To uninstall/delete the my-release deployment:
+
+```console
+helm delete my-release
+```
+
+The command removes all the Kubernetes components associated with the chart and deletes the release.
+
+## Upgrading
+
+A major chart version change indicates that there is an incompatible breaking change needing manual actions.
+
+{{ template "chart.valuesSection" . }}
+

charts/grafana-sampling/templates/_agent_config_deployment.river.txt

@@ -0,0 +1,5 @@
+{{- define "agent.config.deployment" -}}
+  {{- include "deployment.receiver.otlp" . }}
+  {{- include "deployment.processor.batch" . }}
+  {{- include "deployment.exporter.loadbalancing" . }}
+{{- end -}}

charts/grafana-sampling/templates/_agent_config_statefulset.river.txt

@@ -0,0 +1,18 @@
+{{- define "agent.config.statefulset" -}}
+  {{- include "statefulset.receiver.otlp" . }}
+  {{- if .Values.metricsGeneration.enabled -}}
+    {{- include "statefulset.connector.spanmetrics" . }}
+    {{- include "statefulset.processor.transform.drop_unneeded_resource_attributes" . }}
+    {{- include "statefulset.processor.transform.use_grafana_metric_names" . }}
+    {{- include "statefulset.processor.filter" . }}
+    {{- include "statefulset.connector.servicegraph" . }}
+    {{- include "statefulset.exporter.prometheus" . }}
+    {{- include "statefulset.prometheus.remote_write" . }}
+  {{- end -}}
+  {{- if .Values.sampling.enabled -}}
+    {{- include "statefulset.processor.tail_sampling" . }}
+  {{- end -}}
+  {{- include "statefulset.processor.batch" . }}
+  {{- include "exporter.otlp" . }}
+  {{- include "auth.basic" . }}
+{{- end -}}

charts/grafana-sampling/templates/_helpers.tpl

@@ -0,0 +1,9 @@
+{{/* use the release name as the serviceAccount name for deployment and statefulset agents */}}
+{{- define "grafana-agent.serviceAccountName" -}}
+{{- default .Release.Name }}
+{{- end }}
+
+{{/* Calculate name of image ID to use for "grafana-agent". */}}
+{{- define "grafana-agent.imageId" -}}
+{{- printf ":%s" .Chart.AppVersion }}
+{{- end }}

charts/grafana-sampling/templates/_otelcol_auth_basic.river.txt

@@ -0,0 +1,8 @@
+{{- define "auth.basic" -}}
+otelcol.auth.basic "grafana_cloud_tempo" {
+  // https://grafana.com/docs/agent/latest/flow/reference/components/otelcol.auth.basic/
+  username = env("GRAFANA_CLOUD_TEMPO_USERNAME")
+  password = env("GRAFANA_CLOUD_API_KEY")
+}
+
+{{ end }}

charts/grafana-sampling/templates/_otelcol_connector_servicegraph.river.txt

@@ -0,0 +1,20 @@
+{{- define "statefulset.connector.servicegraph" -}}
+otelcol.connector.servicegraph "default" {
+  // https://grafana.com/docs/agent/latest/flow/reference/components/otelcol.connector.servicegraph/
+  dimensions = [
+    {{- range $.Values.metricsGeneration.dimensions }}
+    {{ . | quote }},
+    {{- end }}
+  ]
+  latency_histogram_buckets = ["0s", "0.005s", "0.01s", "0.025s", "0.05s", "0.075s", "0.1s", "0.25s", "0.5s", "0.75s", "1s", "2.5s", "5s", "7.5s", "10s"]
+
+  store {
+    ttl = "2s"
+  }
+
+  output {
+    metrics = [otelcol.processor.batch.default.input]
+  }
+}
+
+{{ end }}