From 39f4180b5ab849f676ac52165d581f3350e51caa Mon Sep 17 00:00:00 2001 From: "m.fin" Date: Mon, 29 Nov 2021 15:28:30 +0100 Subject: [PATCH] fix(rule): fixing KubernetesPodNotHealthy (#215 #253) --- _data/rules.yml | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/_data/rules.yml b/_data/rules.yml index 1fbd5ff..cb7ddfb 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -1584,8 +1584,9 @@ groups: for: 2m - name: Kubernetes Pod not healthy 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 + for: 15m - name: Kubernetes pod crash looping description: Pod {{ $labels.pod }} is crash looping query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3'