kube-state-metrics/examples/prometheus-alerting-rules/alerts.yaml

32 lines
1.2 KiB
YAML

groups:
- name: kube-state-metrics
rules:
- alert: KubeStateMetricsListErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in
list operations. This is likely causing it to not be able to expose metrics
about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in list operations.
expr: |
(sum(rate(kube_state_metrics_list_total{job="kube-state-metrics",result="error"}[5m]))
/
sum(rate(kube_state_metrics_list_total{job="kube-state-metrics"}[5m])))
> 0.01
for: 15m
labels:
severity: critical
- alert: KubeStateMetricsWatchErrors
annotations:
description: kube-state-metrics is experiencing errors at an elevated rate in
watch operations. This is likely causing it to not be able to expose metrics
about Kubernetes objects correctly or at all.
summary: kube-state-metrics is experiencing errors in watch operations.
expr: |
(sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics",result="error"}[5m]))
/
sum(rate(kube_state_metrics_watch_total{job="kube-state-metrics"}[5m])))
> 0.01
for: 15m
labels:
severity: critical