homeprod/kubernetes/infrastructure/observability/vmalert-rules.yaml

apiVersion: v1
kind: ConfigMap
metadata:
  name: vmalert-rules
  namespace: observability
  labels:
    app.kubernetes.io/name: vmalert
    app.kubernetes.io/component: alerting-rules
data:
  node.rules: |
    groups:
      - name: node
        rules:
          - alert: HighNodeCPU
            expr: 100 - (avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 90
            for: 5m
            labels:
              severity: warning
            annotations:
              summary: "High CPU on {{ $labels.instance }}"
              description: "CPU usage above 90% for 5m on {{ $labels.instance }}."
          - alert: HighNodeRAM
            expr: 1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) > 0.9
            for: 10m
            labels:
              severity: warning
            annotations:
              summary: "RAM >90% on {{ $labels.instance }}"
              description: "Available RAM below 10% for 10m on {{ $labels.instance }}."
          - alert: LowDiskSpace
            expr: 1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes{fstype!~"tmpfs|overlay"}) > 0.85
            for: 10m
            labels:
              severity: warning
            annotations:
              summary: "Disk >85% full on {{ $labels.instance }} {{ $labels.mountpoint }}"
              description: "Filesystem {{ $labels.mountpoint }} on {{ $labels.instance }} is more than 85% full for 10m."