Générateur de Règles d'Alerte Prometheus

# Prometheus Alert Rules
# Generated by MiniToolDesk (https://minitooldesk.com/tools/prometheus-alert-generator/)
groups:
  - name: node-exporter-alerts
    interval: 30s
    rules:
      - alert: HostInstanceDown
        expr: up == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Instance {{ $labels.instance }} is down"
          description: "Target exporter {{ $labels.instance }} has been unreachable for more than 2 minutes."
          runbook_url: "https://runbooks.prometheus-operator.dev/runbooks/general/targetdown"
      - alert: HostHighCpuLoad
        expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 85
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High CPU utilization on {{ $labels.instance }}"
          description: "CPU load is over 85% for > 5m (current value: {{ $value }}%)."
      - alert: HostHighMemoryUsage
        expr: (node_memory_MemTotal_bytes - node_memory_MemAvailable_bytes) / node_memory_MemTotal_bytes * 100 > 90
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage on {{ $labels.instance }}"
          description: "Host memory usage exceeds 90% (current: {{ $value }}%)."
      - alert: HostDiskSpaceFillingFast
        expr: node_filesystem_free_bytes{mountpoint="/"}/node_filesystem_size_bytes{mountpoint="/"} * 100 < 10
        for: 10m
        labels:
          severity: critical
        annotations:
          summary: "Disk root volume low on {{ $labels.instance }}"
          description: "Root filesystem has less than 10% free space remaining."