diff --git a/_data/rules.yml b/_data/rules.yml index ae80cfe..4ec03cb 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -961,7 +961,7 @@ groups: severity: warning - name: Kubernetes Pod not healthy description: Pod has been in a non-ready state for longer than an hour. - query: 'min_over_time(sum by (namespace, pod, env, stage) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[1h]) > 0' + query: 'min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[1h:])' severity: error - name: Kubernetes pod crash looping description: Pod {{ $labels.pod }} is crash looping