215 lines
11 KiB
YAML
215 lines
11 KiB
YAML
{{- /*
|
|
Generated from 'alertmanager.rules' group from https://raw.githubusercontent.com/prometheus-operator/kube-prometheus/main/manifests/alertmanager-prometheusRule.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:
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerFailedReload | default false) }}
|
|
- alert: AlertmanagerFailedReload
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: Configuration has failed to load for {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerfailedreload
|
|
summary: Reloading an Alertmanager configuration has failed.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(alertmanager_config_last_reload_successful{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) == 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerMembersInconsistent | default false) }}
|
|
- alert: AlertmanagerMembersInconsistent
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} has only found {{`{{`}} $value {{`}}`}} members of the {{`{{`}}$labels.job{{`}}`}} cluster.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagermembersinconsistent
|
|
summary: A member of an Alertmanager cluster has not found all other cluster members.
|
|
expr: |-
|
|
# Without max_over_time, failed scrapes could create false negatives, see
|
|
# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.
|
|
max_over_time(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
|
|
< on (namespace,service) group_left
|
|
count by (namespace,service) (max_over_time(alertmanager_cluster_members{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]))
|
|
for: 15m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerFailedToSendAlerts | default false) }}
|
|
- alert: AlertmanagerFailedToSendAlerts
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: Alertmanager {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod{{`}}`}} failed to send {{`{{`}} $value | humanizePercentage {{`}}`}} of notifications to {{`{{`}} $labels.integration {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerfailedtosendalerts
|
|
summary: An Alertmanager instance failed to send notifications.
|
|
expr: |-
|
|
(
|
|
rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
|
|
/
|
|
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterFailedToSendAlerts | default false) }}
|
|
- alert: AlertmanagerClusterFailedToSendAlerts
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: The minimum notification failure rate to {{`{{`}} $labels.integration {{`}}`}} sent from any instance in the {{`{{`}}$labels.job{{`}}`}} cluster is {{`{{`}} $value | humanizePercentage {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterfailedtosendalerts
|
|
summary: All Alertmanager instances in a cluster failed to send notifications to a critical integration.
|
|
expr: |-
|
|
min by (namespace,service, integration) (
|
|
rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m])
|
|
/
|
|
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration=~`.*`}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterFailedToSendAlerts | default false) }}
|
|
- alert: AlertmanagerClusterFailedToSendAlerts
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: The minimum notification failure rate to {{`{{`}} $labels.integration {{`}}`}} sent from any instance in the {{`{{`}}$labels.job{{`}}`}} cluster is {{`{{`}} $value | humanizePercentage {{`}}`}}.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterfailedtosendalerts
|
|
summary: All Alertmanager instances in a cluster failed to send notifications to a non-critical integration.
|
|
expr: |-
|
|
min by (namespace,service, integration) (
|
|
rate(alertmanager_notifications_failed_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m])
|
|
/
|
|
rate(alertmanager_notifications_total{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}", integration!~`.*`}[5m])
|
|
)
|
|
> 0.01
|
|
for: 5m
|
|
labels:
|
|
severity: warning
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerConfigInconsistent | default false) }}
|
|
- alert: AlertmanagerConfigInconsistent
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have different configurations.
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerconfiginconsistent
|
|
summary: Alertmanager instances within the same cluster have different configurations.
|
|
expr: |-
|
|
count by (namespace,service) (
|
|
count_values by (namespace,service) ("config_hash", alertmanager_config_hash{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"})
|
|
)
|
|
!= 1
|
|
for: 20m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterDown | default false) }}
|
|
- alert: AlertmanagerClusterDown
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have been up for less than half of the last 5m.'
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclusterdown
|
|
summary: Half or more of the Alertmanager instances within the same cluster are down.
|
|
expr: |-
|
|
(
|
|
count by (namespace,service) (
|
|
avg_over_time(up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[5m]) < 0.5
|
|
)
|
|
/
|
|
count by (namespace,service) (
|
|
up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
|
|
)
|
|
)
|
|
>= 0.5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- if not (.Values.defaultRules.disabled.AlertmanagerClusterCrashlooping | default false) }}
|
|
- alert: AlertmanagerClusterCrashlooping
|
|
annotations:
|
|
{{- if .Values.defaultRules.additionalRuleAnnotations }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
|
|
{{- end }}
|
|
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} of Alertmanager instances within the {{`{{`}}$labels.job{{`}}`}} cluster have restarted at least 5 times in the last 10m.'
|
|
runbook_url: {{ .Values.defaultRules.runbookUrl }}/alertmanager/alertmanagerclustercrashlooping
|
|
summary: Half or more of the Alertmanager instances within the same cluster are crashlooping.
|
|
expr: |-
|
|
(
|
|
count by (namespace,service) (
|
|
changes(process_start_time_seconds{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}[10m]) > 4
|
|
)
|
|
/
|
|
count by (namespace,service) (
|
|
up{job="{{ $alertmanagerJob }}",namespace="{{ $namespace }}"}
|
|
)
|
|
)
|
|
>= 0.5
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
{{- if .Values.defaultRules.additionalRuleLabels }}
|
|
{{ toYaml .Values.defaultRules.additionalRuleLabels | indent 8 }}
|
|
{{- end }}
|
|
{{- end }}
|
|
{{- end }} |