# 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: kubernetes-monitoring-rules
  namespace: monitoring-satellite
spec:
  groups:
  - name: kubernetes
    rules:
    - alert: KubeDaemonSetNotScheduled
      annotations:
        description: '{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.'
        summary: DaemonSet pods are not scheduled.
      expr: |
        kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
          -
        kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
      for: 10m
      labels:
        severity: warning
        team: platform
    - alert: KubeJobNotCompleted
      annotations:
        description: Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than {{ "43200" | humanizeDuration }} to complete.
        summary: Job did not complete in time
      expr: |
        time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job="kube-state-metrics"}
          and
        kube_job_status_active{job="kube-state-metrics"} > 0) > 43200
      labels:
        severity: warning
        team: platform
    - alert: KubeJobFailed
      annotations:
        description: Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.
        summary: Job failed to complete.
      expr: |
        kube_job_failed{job="kube-state-metrics"}  > 0
      for: 15m
      labels:
        severity: warning
        team: platform
    - alert: KubePersistentVolumeFillingUp
      annotations:
        description: The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.
        summary: PersistentVolume is filling up.
      expr: |
        (
          kubelet_volume_stats_available_bytes{job="kubelet", metrics_path="/metrics"}
            /
          kubelet_volume_stats_capacity_bytes{job="kubelet", metrics_path="/metrics"}
        ) < 0.03
        and
        kubelet_volume_stats_used_bytes{job="kubelet", metrics_path="/metrics"} > 0
        unless on(namespace, persistentvolumeclaim)
        kube_persistentvolumeclaim_access_mode{ access_mode="ReadOnlyMany"} == 1
        unless on(namespace, persistentvolumeclaim)
        kube_persistentvolumeclaim_labels{label_excluded_from_alerts="true"} == 1
      for: 1m
      labels:
        severity: critical
        team: platform
    - alert: KubePersistentVolumeErrors
      annotations:
        description: The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.
        summary: PersistentVolume is having issues with provisioning.
      expr: |
        kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
      for: 5m
      labels:
        severity: critical
        team: platform
    - alert: KubeVersionMismatch
      annotations:
        description: There are {{ $value }} different semantic versions of Kubernetes components running.
        summary: Different semantic versions of Kubernetes components running.
      expr: |
        count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1
      for: 15m
      labels:
        severity: warning
        team: platform
    - alert: KubeNodeNotReady
      annotations:
        description: '{{ $labels.node }} has been unready for more than 15 minutes.'
        runbook_url: https://github.com/gitpod-io/runbooks/blob/main/runbooks/KubeNodeNotReady.md
        summary: Node is not ready.
      expr: |
        kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
      for: 15m
      labels:
        severity: critical
        team: platform
    - alert: KubeletDown
      annotations:
        description: Kubelet has disappeared from Prometheus target discovery.
        summary: Target disappeared from Prometheus target discovery.
      expr: |
        absent(up{job="kubelet", metrics_path="/metrics"} == 1)
      for: 15m
      labels:
        severity: critical
        team: platform