المراقبة والسجلات (Monitoring & Logging)

global: scrape_interval: 15s scrape_configs: - job_name: 'prometheus' static_configs: - targets: ['localhost:9090'] - job_name: 'node-exporter' static_configs: - targets: ['localhost:9100'] - job_name: 'nginx' static_configs: - targets: ['localhost:9113']

# استخدام CPU (متوسط 5 دقائق) rate(node_cpu_seconds_total{mode="idle"}[5m]) # استخدام الذاكرة node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 # طلبات HTTP في الثانية rate(http_requests_total[5m]) # معدل الأخطاء 5xx rate(http_requests_total{status=~"5.."}[5m])

services: prometheus: image: prom/prometheus:latest volumes: - ./prometheus.yml:/etc/prometheus/prometheus.yml - prometheus-data:/prometheus ports: - "9090:9090" grafana: image: grafana/grafana:latest volumes: - grafana-data:/var/lib/grafana ports: - "3000:3000" environment: - GF_SECURITY_ADMIN_PASSWORD=admin node-exporter: image: prom/node-exporter:latest ports: - "9100:9100" volumes: prometheus-data: grafana-data:

# كل سجلات Nginx {job="nginx"} # أخطاء فقط {job="nginx"} |= "error" # عدد الأخطاء في الساعة count_over_time({job="nginx"} |= "error" [1h]) # سجلات تطبيق معين {app="myapp", level="error"}

groups: - name: server-alerts rules: - alert: HighCPUUsage expr: 100 - (avg by(instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80 for: 5m labels: severity: warning annotations: summary: "CPU usage > 80% on {{ $labels.instance }}" - alert: HighMemoryUsage expr: (1 - node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes) * 100 > 90 for: 5m labels: severity: critical annotations: summary: "Memory usage > 90% on {{ $labels.instance }}" - alert: ServiceDown expr: up == 0 for: 1m labels: severity: critical annotations: summary: "{{ $labels.job }} is down"