example alertmanager configuration

alertmanager.yaml

global:
  resolve_timeout: 5m
  pagerduty_url: https://events.pagerduty.com/v2/enqueue
route:
  receiver: "null"
  group_by:
  - job
  routes:
  - receiver: "null"
    group_by:
    - alertname
    - severity
    continue: true
    routes:
    - receiver: "null"
      match:
        alertname: KubeQuotaExceeded
    - receiver: "null"
      match:
        alertname: UsingDeprecatedAPIAppsV1Beta1
    - receiver: "null"
      match:
        alertname: UsingDeprecatedAPIAppsV1Beta2
    - receiver: "null"
      match:
        alertname: UsingDeprecatedAPIExtensionsV1Beta1
    - receiver: "null"
      match:
        alertname: CPUThrottlingHigh
        container: registry-server
    - receiver: "null"
      match:
        alertname: CPUThrottlingHigh
        container: configmap-registry-server
    - receiver: "null"
      match:
        alertname: NodeFilesystemSpaceFillingUp
        severity: warning
    - receiver: "null"
      match:
        namespace: openshift-customer-monitoring
    - receiver: "null"
      match:
        namespace: openshift-operators
    - receiver: "null"
      match:
        alertname: SLAUptimeSRE
    - receiver: "null"
      match:
        alertname: CustomResourceDetected
    - receiver: "null"
      match:
        alertname: ImagePruningDisabled
    - receiver: "null"
      match:
        severity: info
    - receiver: make-it-warning
      match:
        alertname: KubeAPILatencyHigh
        severity: critical
    - receiver: pagerduty
      match_re:
        exported_namespace: ^default$|^kube.*|^openshift.*|^redhat-.*
    - receiver: pagerduty
      match:
        exported_namespace: ""
      match_re:
        namespace: ^default$|^kube.*|^openshift.*|^redhat-.*
    - receiver: pagerduty
      match:
        job: fluentd
    - receiver: pagerduty
      match:
        alertname: FluentdNodeDown
    - receiver: pagerduty
      match:
        cluster: elasticsearch
  - receiver: watchdog
    match:
      alertname: Watchdog
    repeat_interval: 5m
  group_wait: 30s
  group_interval: 5m
  repeat_interval: 12h
receivers:
- name: pagerduty
  pagerduty_configs:
  - send_resolved: true
    routing_key: REDACTED
    description: '{{ .CommonLabels.alertname }} {{ .CommonLabels.severity | toUpper
      }} ({{ len .Alerts }})'
    details:
      component: '{{ .CommonLabels.alertname }}'
      group: '{{ .CommonLabels.alertname }}'
      link: '{{ if .CommonAnnotations.link }}{{ .CommonAnnotations.link }}{{ else
        }}https://github.com/openshift/ops-sop/tree/master/v4/alerts/{{ .CommonLabels.alertname
        }}.md{{ end }}'
      link2: '{{ if .CommonAnnotations.runbook }}{{ .CommonAnnotations.runbook }}{{
        else }}{{ end }}'
      num_firing: '{{ .Alerts.Firing | len }}'
      num_resolved: '{{ .Alerts.Resolved | len }}'
      resolved: '{{ template "pagerduty.default.instances" .Alerts.Resolved }}'
    severity: '{{ if .CommonLabels.severity }}{{ .CommonLabels.severity | toLower
      }}{{ else }}critical{{ end }}'
- name: make-it-warning
  pagerduty_configs:
  - send_resolved: true
    routing_key: REDACTED
    description: '{{ .CommonLabels.alertname }} {{ .CommonLabels.severity | toUpper
      }} ({{ len .Alerts }})'
    details:
      component: '{{ .CommonLabels.alertname }}'
      group: '{{ .CommonLabels.alertname }}'
      link: '{{ if .CommonAnnotations.link }}{{ .CommonAnnotations.link }}{{ else
        }}https://github.com/openshift/ops-sop/tree/master/v4/alerts/{{ .CommonLabels.alertname
        }}.md{{ end }}'
      link2: '{{ if .CommonAnnotations.runbook }}{{ .CommonAnnotations.runbook }}{{
        else }}{{ end }}'
      num_firing: '{{ .Alerts.Firing | len }}'
      num_resolved: '{{ .Alerts.Resolved | len }}'
      resolved: '{{ template "pagerduty.default.instances" .Alerts.Resolved }}'
    severity: warning
- name: watchdog
  webhook_configs:
  - send_resolved: true
    url: REDACTED
- name: "null"
templates: []