Monitoring et Supervision

# prometheus.yml
global:
  scrape_interval: 15s
  evaluation_interval: 15s

alerting:
  alertmanagers:
    - static_configs:
        - targets: ['alertmanager:9093']

scrape_configs:
  - job_name: 'prometheus'
    static_configs:
      - targets: ['localhost:9090']

  - job_name: 'node'
    static_configs:
      - targets: ['node-exporter:9100']

  - job_name: 'my-app'
    static_configs:
      - targets: ['app:8080']

# CPU usage moyen
100 - (avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)

# Mémoire disponible
node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100

# Requêtes HTTP par seconde
rate(http_requests_total[5m])

# Temps de réponse p95
histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))

# datasource.yml
apiVersion: 1

datasources:
  - name: Prometheus
    type: prometheus
    access: proxy
    url: http://prometheus:9090
    isDefault: true
    
  - name: Loki
    type: loki
    access: proxy
    url: http://loki:3100

# alerts.yml
groups:
  - name: system_alerts
    interval: 30s
    rules:
      - alert: HighCPU
        expr: 100 - (avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "CPU élevé sur {{ $labels.instance }}"
          
      - alert: LowMemory
        expr: node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes * 100 < 10
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Mémoire faible"
          
      - alert: ServiceDown
        expr: up == 0
        for: 2m
        labels:
          severity: critical
        annotations:
          summary: "Service down"

# alertmanager.yml
global:
  smtp_smarthost: 'smtp.example.com:587'
  smtp_from: 'alertmanager@example.com'

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 12h
  receiver: 'team-emails'

receivers:
  - name: 'team-emails'
    email_configs:
      - to: 'team@example.com'

# docker-compose.yml
version: '3.8'

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"

  alertmanager:
    image: prom/alertmanager:latest
    volumes:
      - ./alertmanager.yml:/etc/alertmanager/alertmanager.yml
    ports:
      - "9093:9093"

volumes:
  prometheus-data:
  grafana-data: