diff --git a/jsonnetfile.lock.json b/jsonnetfile.lock.json index 1bb3428d70541a7390b9b66c13f75e1ecf53a2b3..2000ec9a2768cf23b886b7f55472991b3f1c7f33 100644 --- a/jsonnetfile.lock.json +++ b/jsonnetfile.lock.json @@ -28,7 +28,7 @@ "subdir": "grafonnet" } }, - "version": "3626fc4dc2326931c530861ac5bebe39444f6cbf", + "version": "6db00c292d3a1c71661fc875f90e0ec7caa538c2", "sum": "gF8foHByYcB25jcUOBqP6jxk0OPifQMjPvKY0HaCk6w=" }, { @@ -38,8 +38,8 @@ "subdir": "grafana-builder" } }, - "version": "2ed138b205717af721af57b572bc7cd63bda62fd", - "sum": "U34Nd1ViO2LZ3D8IzygPPRfUcy6zOgCnTMVHZ+9O/QE=" + "version": "98c3060877aa178f6bdfc6ac618fbe0043fc3de7", + "sum": "0KkygBQd/AFzUvVzezE4qF/uDYgrwUXVpZfINBti0oc=" }, { "source": { @@ -59,8 +59,8 @@ "subdir": "" } }, - "version": "d0d7d5324f4d5333ee47e1895e726fe44bcb7094", - "sum": "wQw1hzPBgZPKcdoBBFmlnimOUrPSrfwejVpzyV47Hwg=" + "version": "7d3bb79a4983052d421264a7e0f3c9b0d4a22268", + "sum": "DFo3YX4xc6GJTSZDaG5XRE/ixY/5GZJwdyqBkvons4M=" }, { "source": { @@ -69,7 +69,7 @@ "subdir": "lib/promgrafonnet" } }, - "version": "06d00e40b43e4e618afbebe8e453b5650c659015", + "version": "0f0f3dc472ff2a8cdc6a6c6f938a2c450cb493ec", "sum": "zv7hXGui6BfHzE9wPatHI/AGZa4A2WKo6pq7ZdqBsps=" }, { diff --git a/manifests/kubernetes-prometheusRule.yaml b/manifests/kubernetes-prometheusRule.yaml index 88af1579cafd76555ab11b39a12cd576cfc272e7..f07ccfca50bec31087c09a75c0ee768c012018db 100644 --- a/manifests/kubernetes-prometheusRule.yaml +++ b/manifests/kubernetes-prometheusRule.yaml @@ -14,11 +14,11 @@ spec: rules: - alert: KubePodCrashLooping annotations: - description: Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf "%.2f" $value }} times / 10 minutes. + description: 'Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: "CrashLoopBackOff").' runbook_url: https://github.com/prometheus-operator/kube-prometheus/wiki/kubepodcrashlooping summary: Pod is crash looping. expr: | - rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[10m]) * 60 * 5 > 0 + max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics"}[5m]) >= 1 for: 15m labels: severity: warning