groups:
- name: general.rules
  rules:
  - alert: InstanceDown
    expr: up == 0
    for: 2m
    labels: { severity: critical }
    annotations:
      summary: "Instance {{ $labels.instance }} down"
      description: "{{ $labels.instance }} of job {{ $labels.job }} has been down for more than 2 minutes"
  - alert: HighCPUUsage
    expr: 100 - (avg by(instance)(rate(node_cpu_seconds_total{mode="idle"}[5m]))*100) > 80
    for: 5m
    labels: { severity: warning }
    annotations:
      summary: "High CPU usage on {{ $labels.instance }}"
      description: "CPU usage is above 80% for more than 5 minutes on {{ $labels.instance }}"
  - alert: HighMemoryUsage
    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: "Memory usage is above 90% for more than 5 minutes on {{ $labels.instance }}"
  - alert: DiskSpaceLow
    expr: (node_filesystem_avail_bytes{fstype!~"tmpfs|overlay"}/node_filesystem_size_bytes) < 0.1
    for: 10m
    labels: { severity: warning }
    annotations:
      summary: "Low disk space on {{ $labels.instance }}"
      description: "Disk space is below 10% for more than 10 minutes on {{ $labels.instance }}"
  - alert: CertificateExpiration
    expr: probe_ssl_earliest_cert_expiry - time() < 604800
    for: 0m
    labels: { severity: warning }
    annotations:
      summary: "SSL certificate expiring soon on {{ $labels.instance }}"
      description: "SSL certificate for {{ $labels.instance }} expires in less than 7 days"