infra/charts/victoria-metrics-k8s-stack/files/rules/generated/kubernetes-system.yaml
Konstantin Averkiev c45fd1a6ac added vm stack
2025-07-08 17:29:32 +03:00

34 lines
1.9 KiB
YAML

{{- $Values := (.helm).Values | default .Values }}
{{- $runbookUrl := ($Values.defaultRules).runbookUrl | default "https://runbooks.prometheus-operator.dev/runbooks" }}
{{- $clusterLabel := ($Values.global).clusterLabel | default "cluster" }}
{{- $additionalGroupByLabels := append $Values.defaultRules.additionalGroupByLabels $clusterLabel }}
{{- $groupLabels := join "," $additionalGroupByLabels }}
{{- $grafanaHost := ternary (index (($Values.grafana).ingress).hosts 0) (($Values.external).grafana).host ($Values.grafana).enabled }}
condition: '{{ true }}'
name: kubernetes-system
rules:
- alert: KubeVersionMismatch
annotations:
description: 'There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running on cluster {{`{{`}} $labels.{{ $clusterLabel }} {{`}}`}}.'
runbook_url: '{{ $runbookUrl }}/kubernetes/kubeversionmismatch'
summary: 'Different semantic versions of Kubernetes components running.'
condition: '{{ true }}'
expr: count by ({{ $groupLabels }}) (count by (git_version,{{ $groupLabels }}) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1
for: 15m
labels:
severity: warning
- alert: KubeClientErrors
annotations:
description: 'Kubernetes API server client ''{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}'' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors on cluster {{`{{`}} $labels.{{ $clusterLabel }} {{`}}`}}.'
runbook_url: '{{ $runbookUrl }}/kubernetes/kubeclienterrors'
summary: 'Kubernetes API server client is experiencing errors.'
condition: '{{ true }}'
expr: |-
(sum(rate(rest_client_requests_total{job="apiserver",code=~"5.."}[5m])) by (instance,job,namespace,{{ $groupLabels }})
/
sum(rate(rest_client_requests_total{job="apiserver"}[5m])) by (instance,job,namespace,{{ $groupLabels }}))
> 0.01
for: 15m
labels:
severity: warning