ws-daemon.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:
    prometheus: k8s
    role: alert-rules
  name: ws-daemon-monitoring-satellite-rules
spec:
  groups:
  - name: ws-daemon
    rules:
    - alert: BackupFailureBecauseOfGitpodWsDaemonCrash
      labels:
        severity: critical
      annotations:
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/GitpodWsDaemonCrashLooping.md
        summary: Increase the number of backup failure because of ws-daemon is crashlooping.
        description: Ws-daemon is restarting {{ printf "%.2f" $value }} times / 10 minutes.
        dashboard_url: https://grafana.gitpod.io/d/ws-daemon/gitpod-component-ws-daemon
      expr: |
        sum(increase(kube_pod_container_status_restarts_total{container="ws-daemon"}[10m])) by(cluster) > 0 AND sum(increase(gitpod_ws_manager_mk2_workspace_backups_failure_total{type="Regular"}[10m])) by(cluster) > 0