第4章 可観測性設定のカスタマイズ

data:
  custom_rules.yaml: |
    groups:
      - name: cluster-health
        rules:
        - alert: ClusterCPUHealth-jb
          annotations:
            summary: Notify when CPU utilization on a cluster is greater than the defined utilization limit
            description: "The cluster has a high CPU usage: {{ $value }} core for {{ $labels.cluster }} {{ $labels.clusterID }}."
          expr: |
            max(cluster:cpu_usage_cores:sum) by (clusterID, cluster, prometheus) > 0
          for: 5s
          labels:
            cluster: "{{ $labels.cluster }}"
            prometheus: "{{ $labels.prometheus }}"
            severity: critical

data:
  custom_rules.yaml: |
    groups:
      - name: container-memory
        rules:
        - record: pod:container_memory_cache:sum
          expr: sum(container_memory_cache{pod!=""}) BY (pod, container)