Merge pull request #1860 from JoaoBraveCoding/prometheusRuleRunbook

OCPBUGS-4219: Adds runbook link to PrometheusRuleFailures

Author: openshift-merge-robot

CHANGELOG.md

@@ -3,7 +3,8 @@
 ## 4.13
 
 - [#1830](https://github.com/openshift/cluster-monitoring-operator/pull/1830) Add alert KubePodNotScheduled
-- [#1843](https://github.com/openshift/cluster-monitoring-operator/pull/1830) Node Exporter ignores network interface under name "enP.*".
+- [#1843](https://github.com/openshift/cluster-monitoring-operator/pull/1843) Node Exporter ignores network interface under name "enP.*".
+- [#1860](https://github.com/openshift/cluster-monitoring-operator/pull/1860) Adds runbook for PrometheusRuleFailures
 
 
 ## 4.12

assets/prometheus-k8s/prometheus-rule.yaml

@@ -195,6 +195,7 @@ spec:
       annotations:
         description: Prometheus {{$labels.namespace}}/{{$labels.pod}} has failed to
           evaluate {{ printf "%.0f" $value }} rules in the last 5m.
+        runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-monitoring-operator/PrometheusRuleFailures.md
         summary: Prometheus is failing rule evaluations.
       expr: |
         increase(prometheus_rule_evaluation_failures_total{job=~"prometheus-k8s|prometheus-user-workload"}[5m]) > 0

jsonnet/utils/sanitize-rules.libsonnet

@@ -393,6 +393,7 @@ local includeRunbooks = {
   NodeFilesystemSpaceFillingUp: openShiftRunbookCMO('NodeFilesystemSpaceFillingUp.md'),
   NodeRAIDDegraded: openShiftRunbookCMO('NodeRAIDDegraded.md'),
   NodeClockNotSynchronising: openShiftRunbookCMO('NodeClockNotSynchronising.md'),
+  PrometheusRuleFailures: openShiftRunbookCMO('PrometheusRuleFailures.md'),
   PrometheusTargetSyncFailure: openShiftRunbookCMO('PrometheusTargetSyncFailure.md'),
   ThanosRuleQueueIsDroppingAlerts: openShiftRunbookCMO('ThanosRuleQueueIsDroppingAlerts.md'),
   ThanosRuleRuleEvaluationLatencyHigh: openShiftRunbookCMO('ThanosRuleRuleEvaluationLatencyHigh.md'),