70 lines
3.4 KiB
YAML
70 lines
3.4 KiB
YAML
{{- /*
|
|
Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/master/manifests/prometheus-rules.yaml
|
|
Do not change in-place! In order to change this file first read following link:
|
|
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
|
|
*/ -}}
|
|
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
|
|
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.alertmanager }}
|
|
{{- $alertmanagerJob := printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager" }}
|
|
{{- $namespace := printf "%s" (include "kube-prometheus-stack.namespace" .) }}
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "alertmanager.rules" | trunc 63 | trimSuffix "-" }}
|
|
namespace: {{ template "kube-prometheus-stack.namespace" . }}
|
|
labels:
|
|
app: {{ template "kube-prometheus-stack.name" . }}
|
|
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
|
|
{{- if .Values.defaultRules.labels }}
|
|
{{ toYaml .Values.defaultRules.labels | indent 4 }}
|
|
{{- end }}
|
|
{{- if .Values.defaultRules.annotations }}
|
|
annotations:
|
|
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
|
|
{{- end }}
|
|
spec:
|
|
groups:
|
|
- name: alertmanager.rules
|
|
rules:
|
|
- alert: AlertmanagerConfigInconsistent
|
|
annotations:
|
|
message: 'The configuration of the instances of the Alertmanager cluster `{{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.service {{`}}`}}` are out of sync.
|
|
|
|
{{`{{`}} range printf "alertmanager_config_hash{namespace=\"%s\",service=\"%s\"}" $labels.namespace $labels.service | query {{`}}`}}
|
|
|
|
Configuration hash for pod {{`{{`}} .Labels.pod {{`}}`}} is "{{`{{`}} printf "%.f" .Value {{`}}`}}"
|
|
|
|
{{`{{`}} end {{`}}`}}
|
|
|
|
'
|
|
expr: count by(namespace,service) (count_values by(namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})) != 1
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: AlertmanagerFailedReload
|
|
annotations:
|
|
message: Reloading Alertmanager's configuration has failed for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}.
|
|
expr: alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"} == 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
- alert: AlertmanagerMembersInconsistent
|
|
annotations:
|
|
message: Alertmanager has not found all other members of the cluster.
|
|
expr: |-
|
|
alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
|
|
!= on (service) GROUP_LEFT()
|
|
count by (service) (alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }} |