alertmanager.yaml

# Copyright (c) 2022 Gitpod GmbH. All rights reserved.
# Licensed under the GNU Affero General Public License (AGPL).
# See License.AGPL.txt in the project root for license information.

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  labels:
    app.kubernetes.io/name: kubernetes
    app.kubernetes.io/part-of: kube-prometheus
    prometheus: k8s
    role: alert-rules
  name: alertmanager-monitoring-rules
  namespace: monitoring-satellite
spec:
  groups:
  - name: alertmanager
    rules:
    - alert: AlertmanagerFailedReload
      annotations:
        description: Configuration has failed to load for {{ $labels.namespace }}/{{ $labels.pod}}.
        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="alertmanager-main",namespace="monitoring-satellite"}[5m]) == 0
      for: 10m
      labels:
        severity: critical
        team: delivery-operations-experience
    - alert: AlertmanagerFailedToSendAlerts
      annotations:
        description: Alertmanager {{ $labels.namespace }}/{{ $labels.pod}} failed to send {{ $value | humanizePercentage }} of notifications to {{ $labels.integration }}.
        summary: An Alertmanager instance failed to send notifications.
      expr: |
        (
          rate(alertmanager_notifications_failed_total{job="alertmanager-main",namespace="monitoring-satellite"}[5m])
        /
          rate(alertmanager_notifications_total{job="alertmanager-main",namespace="monitoring-satellite"}[5m])
        )
        > 0.01
      for: 5m
      labels:
        severity: warning
        team: delivery-operations-experience