XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-26 19:37:27 +08:00
Code Issues Projects Releases Packages Wiki Activity

fix(rule): fixing KubernetesPodNotHealthy (#215 #253)

Browse source
This commit is contained in:
m.fin 2021-11-29 15:28:30 +01:00
parent 3ff969670d
commit 39f4180b5a
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
_data/rules.yml
View file

@ -1584,8 +1584,9 @@ groups:
for: 2m for: 2m
- name: Kubernetes Pod not healthy - name: Kubernetes Pod not healthy
description: Pod has been in a non-ready state for longer than 15 minutes. description: Pod has been in a non-ready state for longer than 15 minutes.
query: 'min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0' query: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0'
severity: critical severity: critical
for: 15m
- name: Kubernetes pod crash looping - name: Kubernetes pod crash looping
description: Pod {{ $labels.pod }} is crash looping description: Pod {{ $labels.pod }} is crash looping
query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3' query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'