-
Notifications
You must be signed in to change notification settings - Fork 55
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge pull request #1301 from cloudflare/offset
Add offset test
- Loading branch information
Showing
1 changed file
with
255 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,255 @@ | ||
| exec pint --no-color lint rules | ||
| ! stdout . | ||
| cmp stderr stderr.txt | ||
|
|
||
| -- stderr.txt -- | ||
| level=INFO msg="Loading configuration file" path=.pint.hcl | ||
| level=INFO msg="Finding all rules to check" paths=["rules"] | ||
| level=INFO msg="Checking Prometheus rules" entries=9 workers=10 online=true | ||
| rules/1.yaml:149-150 Warning: `summary` annotation is required. (alerts/annotation) | ||
| 149 | annotations: | ||
| 150 | description: Thanos Ruler has not been able to reload its configuration. | ||
|
|
||
| level=INFO msg="Problems found" Warning=1 | ||
| -- .pint.hcl -- | ||
| parser { | ||
| relaxed = [".*"] | ||
| } | ||
| rule { | ||
| match { | ||
| kind = "alerting" | ||
| } | ||
| annotation "summary" { | ||
| severity = "warning" | ||
| required = true | ||
| } | ||
| } | ||
|
|
||
| -- rules/1.yaml -- | ||
| --- | ||
| apiVersion: apps/v1 | ||
| kind: StatefulSet | ||
| metadata: | ||
| namespace: thanos | ||
| spec: | ||
| replicas: 2 | ||
| selector: | ||
| matchLabels: | ||
| app: ruler-core | ||
| component: ruler | ||
| serviceName: thanos-ruler | ||
| template: | ||
| metadata: | ||
| labels: | ||
| app: ruler-core | ||
| component: ruler | ||
| spec: | ||
| containers: | ||
| - args: | ||
| - --log.format=json | ||
| - --http-address=0.0.0.0:10902 | ||
| - --grpc-address=0.0.0.0:10901 | ||
| - --eval-interval=1m | ||
| - | | ||
| --tracing.config= | ||
| type: JAEGER | ||
| config: | ||
| sampler_param: 0.01 | ||
| sampler_type: probabilistic | ||
| command: | ||
| - /bin/thanos | ||
| - rule | ||
| imagePullPolicy: IfNotPresent | ||
| livenessProbe: | ||
| httpGet: | ||
| path: /-/healthy | ||
| port: 10902 | ||
| initialDelaySeconds: 30 | ||
| terminationGracePeriodSeconds: 300 | ||
| timeoutSeconds: 5 | ||
| name: ruler | ||
| ports: | ||
| - containerPort: 10902 | ||
| name: http-metrics | ||
| readinessProbe: | ||
| httpGet: | ||
| path: /-/ready | ||
| port: 10902 | ||
| initialDelaySeconds: 30 | ||
| timeoutSeconds: 1 | ||
| resources: | ||
| limits: | ||
| cpu: "4" | ||
| memory: 4G | ||
| requests: | ||
| cpu: "4" | ||
| memory: 4G | ||
| - args: | ||
| - --config=/rules/current/.pint.hcl | ||
| - watch | ||
| - --listen=:10904 | ||
| - --max-problems=50 | ||
| - glob | ||
| - /rules/current/rules/* | ||
| command: | ||
| - /usr/local/bin/pint | ||
| imagePullPolicy: IfNotPresent | ||
| livenessProbe: | ||
| httpGet: | ||
| path: /health | ||
| port: 10904 | ||
| initialDelaySeconds: 30 | ||
| timeoutSeconds: 5 | ||
| name: pint | ||
| ports: | ||
| - containerPort: 10904 | ||
| name: pint | ||
| resources: | ||
| limits: | ||
| cpu: "1" | ||
| memory: 256Mi | ||
| requests: | ||
| cpu: "1" | ||
| memory: 256Mi | ||
| volumeMounts: | ||
| - mountPath: /rules | ||
| name: rules | ||
| --- | ||
| apiVersion: v1 | ||
| kind: ConfigMap | ||
| metadata: | ||
| labels: | ||
| prometheus.cfplat.com/rules: "true" | ||
| name: ruler-core-ruler | ||
| namespace: thanos | ||
| data: | ||
| rules: | | ||
| groups: | ||
| - name: ruler-health-alerts | ||
| rules: | ||
| - alert: Thanos_Rule_Queue_Is_Dropping_Alerts | ||
| expr: rate(thanos_alert_queue_alerts_dropped_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m]) > 0 | ||
| for: 5m | ||
| labels: | ||
| priority: "3" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| summary: Thanos Ruler is failing to queue alerts. | ||
| - alert: Thanos_Rule_Sender_Is_Dropping_Alerts | ||
| expr: rate(thanos_alert_sender_alerts_dropped_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m]) > 0 | ||
| for: 5m | ||
| labels: | ||
| priority: "3" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| summary: Thanos Ruler is failing to send alerts. | ||
| - alert: Thanos_Rule_High_Rule_Evaluation_Failures | ||
| expr: |2- | ||
|
|
||
| ( | ||
| sum(rate(prometheus_rule_evaluation_failures_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m])) | ||
| by (job,kubernetes_name,pod, pod_app, pod_component) | ||
| / | ||
| sum(rate(prometheus_rule_evaluations_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m])) | ||
| by (job,kubernetes_name,pod, pod_app, pod_component) | ||
| * 100 > 5 | ||
| ) | ||
| for: 5m | ||
| labels: | ||
| priority: "3" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| summary: Thanos Ruler is failing to evaluate {{ $value | humanize }}% of rules. | ||
| - alert: Thanos_Rule_High_Rule_Evaluation_Warnings | ||
| expr: rate(thanos_rule_evaluation_with_warnings_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m]) > 0 | ||
| for: 30m | ||
| labels: | ||
| priority: "4" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| summary: Thanos Ruler has high number of evaluation warnings. | ||
| - alert: Thanos_Rule_Config_Reload_Failed | ||
| expr: max_over_time(thanos_rule_config_last_reload_successful{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[10m]) < 1 | ||
| for: 5m | ||
| labels: | ||
| priority: "3" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| description: Thanos Ruler has not been able to reload its configuration. | ||
| - alert: Thanos_Rule_No_Evaluations | ||
| expr: |2- | ||
|
|
||
| label_replace( | ||
| ( | ||
| (time() - prometheus_rule_group_last_evaluation_timestamp_seconds{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}) | ||
| > | ||
| (prometheus_rule_group_interval_seconds{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"} * 10) | ||
| ), "rule_group_name", "$1", "rule_group", ".*;(.+)") | ||
| for: 5m | ||
| labels: | ||
| priority: "3" | ||
| notify: chat-obs-metrics | ||
| annotations: | ||
| summary: Thanos Ruler did not evalute {{ $labels.rule_group_name }} for multiple intervals. | ||
| - alert: Thanos_Rule_Evaluations_Are_Failing | ||
| expr: |2- | ||
|
|
||
| label_replace( | ||
| label_replace( | ||
| rate(prometheus_rule_evaluation_failures_total{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"}[2m]) > 0, | ||
| "rule_group_name", "$1", | ||
| "rule_group", ".*;(.+)" | ||
| ), | ||
| "filename", "$1", | ||
| "rule_group", ".*/current/rules/(.+);.+" | ||
| ) | ||
| * on(filename, node) group_left(owner) | ||
| label_replace(pint_rule_file_owner, "filename", "$1", "filename", "/rules/.*/rules/(.+)") | ||
| for: 15m | ||
| labels: | ||
| priority: "3" | ||
| notify: "{{ $labels.owner }}" | ||
| annotations: | ||
| summary: Thanos Ruler failed to execute rules in rule group {{ $labels.rule_group_name }} in {{ $labels.filename }} for the last 15 minutes or more. All affected alerts won't work until this is resolved. | ||
| - alert: Thanos_Rule_Evaluation_Latency_Is_High | ||
| expr: |2- | ||
|
|
||
| label_replace( | ||
| label_replace( | ||
| ( | ||
| prometheus_rule_group_last_duration_seconds{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"} | ||
| >= | ||
| prometheus_rule_group_interval_seconds{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"} | ||
| ), | ||
| "rule_group_name", "$1", | ||
| "rule_group", ".*;(.+)" | ||
| ), | ||
| "filename", "$1", | ||
| "rule_group", ".*/current/rules/(.+);.+" | ||
| ) | ||
| * on(filename, node) group_left(owner) | ||
| label_replace(pint_rule_file_owner, "filename", "$1", "filename", "/rules/.*/rules/(.+)") | ||
| for: 15m | ||
| labels: | ||
| priority: "4" | ||
| notify: "{{ $labels.owner }}" | ||
| annotations: | ||
| summary: Thanos Ruler has higher evaluation latency than interval for rule group {{ $labels.rule_group_name }} in {{ $labels.filename }}. Alert query is too expensive to keep up with how frequently it runs. | ||
| - alert: Prometheus_Rule_Failed_Checks | ||
| expr: |2- | ||
|
|
||
| sum( | ||
| pint_problem{kubernetes_namespace="thanos", pod_app="ruler-core", pod_component="ruler"} | ||
| ) without(instance, problem) > 0 | ||
| for: 4h | ||
| labels: | ||
| priority: "4" | ||
| notify: "{{ $labels.owner }}" | ||
| annotations: | ||
| summary: |2- | ||
|
|
||
| {{ with printf "pint_problem{kubernetes_namespace='thanos', pod_app='ruler-core', pod_component='ruler', filename='%s', name='%s', owner='%s', reporter='%s'}" .Labels.filename .Labels.name .Labels.owner .Labels.reporter | query }} | ||
| {{ . | first | label "problem" }} | ||
| {{ end }} | ||
| help: pint detected a problem with {{ $labels.name }} rule on {{ $externalLabels.prometheus }}, this means that a rule might be trying to query non-existent metrics or deployed to the wrong server | ||
| docs: https://cloudflare.github.io/pint/checks/{{ $labels.reporter }}.html |