fix alerts 🤕

This commit is contained in:
Aaron Riedel 2023-04-21 08:18:39 +02:00
parent 414b7d9318
commit 928ef62122
Signed by: aaron
GPG key ID: 643004654D40D577

View file

@ -47,12 +47,12 @@ data:
- name: KubernetesUnhealthyPod - name: KubernetesUnhealthyPod
rules: rules:
- alert: KubernetesUnhealthyPod - alert: KubernetesUnhealthyPod
expr: kube_pod_container_status_waiting_reason = 1 expr: kube_pod_container_status_waiting_reason == 1
for: 5m for: 5m
labels: labels:
severity: warning severity: warning
annotations: annotations:
summary: "The Pod {{ $labels.pod }} is {{ $labels.reason }}"" summary: "The Pod {{ $labels.pod }} is {{ $labels.reason }}"
description: "The Pod {{ $labels.pod }} is in the state {{ $labels.reason }} for more than 5m. The Pod is in namespace {{ $labels.namespace }} and on node {{ $labels.node }}." description: "The Pod {{ $labels.pod }} is in the state {{ $labels.reason }} for more than 5m. The Pod is in namespace {{ $labels.namespace }} and on node {{ $labels.node }}."
- name: PrometheusTargetMissing - name: PrometheusTargetMissing
rules: rules:
@ -63,7 +63,7 @@ data:
severity: critical severity: critical
annotations: annotations:
summary: Prometheus target missing (instance {{ $labels.instance }}) summary: Prometheus target missing (instance {{ $labels.instance }})
description: "A Prometheus target has disappeared. {{if ne $labels.job ""}}\n Job: {{ $labels.job }}{{end}}{{if ne $labels.app ""}}\n App: {{ $labels.app }}{{end}}{{if ne $labels.pod ""}}\n Pod: {{ $labels.pod }}{{end}}{{if ne $labels.node ""}}\n Node: {{ $labels.node }}{{end}}{{if ne $labels.namespace ""}}\n Namespace: {{ $labels.namespace }}{{end}}" description: 'A Prometheus target has disappeared. {{if ne $labels.job ""}}\n Job: {{ $labels.job }}{{end}}{{if ne $labels.app ""}}\n App: {{ $labels.app }}{{end}}{{if ne $labels.pod ""}}\n Pod: {{ $labels.pod }}{{end}}{{if ne $labels.node ""}}\n Node: {{ $labels.node }}{{end}}{{if ne $labels.namespace ""}}\n Namespace: {{ $labels.namespace }}{{end}}'
- name: PrometheusConfigurationReloadFailure - name: PrometheusConfigurationReloadFailure
rules: rules:
- alert: PrometheusConfigurationReloadFailure - alert: PrometheusConfigurationReloadFailure