0000_90_cluster-version-operator_02_servicemonitor.yaml

apiVersion: monitoring.coreos.com/v1
kind: ServiceMonitor
metadata:
  labels:
    k8s-app: cluster-version-operator
  name: cluster-version-operator
  namespace: openshift-cluster-version
  annotations:
    exclude.release.openshift.io/internal-openshift-hosted: "true"
spec:
  endpoints:
  - interval: 30s
    port: metrics
    scheme: http
  namespaceSelector:
    matchNames:
    - openshift-cluster-version
  selector:
    matchLabels:
      k8s-app: cluster-version-operator
---
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    k8s-app: cluster-version-operator
  name: cluster-version-operator
  namespace: openshift-cluster-version
  annotations:
    exclude.release.openshift.io/internal-openshift-hosted: "true"
spec:
  groups:
  - name: cluster-version
    rules:
    - alert: ClusterVersionOperatorDown
      annotations:
        message: Cluster version operator has disappeared from Prometheus target discovery. Operator may be down or disabled, cluster will not be kept up to date and upgrades will not be possible.
      expr: |
        absent(up{job="cluster-version-operator"} == 1)
      for: 10m
      labels:
        severity: critical
  - name: cluster-operators
    rules:
    - alert: ClusterOperatorDown
      annotations:
        message: Cluster operator {{ "{{ $labels.name }}" }} has not been available for 10 mins. Operator may be down or disabled, cluster will not be kept up to date and upgrades will not be possible.
      expr: |
        cluster_operator_up{job="cluster-version-operator"} == 0
      for: 10m
      labels:
        severity: critical
    - alert: ClusterOperatorDegraded
      annotations:
        message: Cluster operator {{ "{{ $labels.name }}" }} has been degraded for 10 mins. Operator is degraded because {{ "{{ $labels.reason }}" }} and cluster upgrades will be unstable.
      expr: |
        cluster_operator_conditions{job="cluster-version-operator", condition="Degraded"} == 1
      for: 10m
      labels:
        severity: critical
    - alert: ClusterOperatorFlapping
      annotations:
        message: Cluster operator {{ "{{ $labels.name }}" }} up status is changing often. This might cause upgrades to be unstable.
      expr: |
        changes(cluster_operator_up{job="cluster-version-operator"}[2m]) > 2
      for: 10m
      labels:
        severity: warning