|
| 1 | +apiVersion: monitoring.coreos.com/v1 |
| 2 | +kind: PrometheusRule |
| 3 | +metadata: |
| 4 | + name: kubernetes-system-apiserver |
| 5 | + namespace: openshift-kube-apiserver |
| 6 | +spec: |
| 7 | + groups: |
| 8 | + - name: kubernetes-system-apiserver |
| 9 | + rules: |
| 10 | + - alert: KubeAggregatedAPIErrors |
| 11 | + annotations: |
| 12 | + description: Kubernetes aggregated API {{ $labels.instance }}/{{ $labels.name }} has reported {{ $labels.reason }} errors. |
| 13 | + runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-kube-apiserver-operator/KubeAggregatedAPIErrors.md |
| 14 | + summary: Kubernetes aggregated API has reported errors. |
| 15 | + expr: | |
| 16 | + sum by(cluster, instance, name, reason)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[1m])) > 0 |
| 17 | + for: 10m |
| 18 | + labels: |
| 19 | + severity: warning |
| 20 | + - alert: KubeAggregatedAPIDown |
| 21 | + annotations: |
| 22 | + description: Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m. |
| 23 | + summary: Kubernetes aggregated API is down. |
| 24 | + expr: | |
| 25 | + (1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85 |
| 26 | + for: 15m |
| 27 | + labels: |
| 28 | + severity: warning |
| 29 | + - alert: KubeAPIDown |
| 30 | + annotations: |
| 31 | + description: KubeAPI has disappeared from Prometheus target discovery. |
| 32 | + runbook_url: https://github.com/openshift/runbooks/blob/master/alerts/cluster-kube-apiserver-operator/KubeAPIDown.md |
| 33 | + summary: Target disappeared from Prometheus target discovery. |
| 34 | + expr: | |
| 35 | + absent(up{job="apiserver"} == 1) |
| 36 | + for: 15m |
| 37 | + labels: |
| 38 | + severity: critical |
| 39 | + - alert: KubeAPITerminatedRequests |
| 40 | + annotations: |
| 41 | + description: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. |
| 42 | + summary: The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests. |
| 43 | + expr: | |
| 44 | + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20 |
| 45 | + for: 5m |
| 46 | + labels: |
| 47 | + severity: warning |
0 commit comments