alert.rules.yml

groups:
  - name: atlas_service_health
    rules:
      - alert: ServiceDown
        expr: up == 0
        for: 30s
        labels:
          severity: critical
        annotations:
          summary: "Service {{ $labels.job }} is down"
          description: "{{ $labels.job }} has been unreachable for more than 30 seconds."

      - alert: HighErrorRate
        expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.05
        for: 1m
        labels:
          severity: warning
        annotations:
          summary: "High error rate on {{ $labels.job }}"
          description: "Error rate on {{ $labels.job }} is {{ $value | humanizePercentage }}"

      - alert: HighMemoryUsage
        expr: process_resident_memory_bytes / process_virtual_memory_bytes > 0.9
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "High memory usage on {{ $labels.job }}"
          description: "{{ $labels.job }} memory usage is above 90%"