The Monitoring Stack Docker Compose File

version: '3.8'

services:
  prometheus:
    image: prom/prometheus:v2.48.0
    container_name: prometheus
    ports:
      - "9090:9090"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml
      - ./prometheus/alerts.yml:/etc/prometheus/alerts.yml
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.retention.time=30d'
    restart: unless-stopped

  grafana:
    image: grafana/grafana:10.2.0
    container_name: grafana
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=your_secure_password
      - GF_USERS_ALLOW_SIGN_UP=false
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/dashboards:/etc/grafana/provisioning/dashboards
      - ./grafana/datasources:/etc/grafana/provisioning/datasources
    restart: unless-stopped

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: alertmanager
    ports:
      - "9093:9093"
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml
    restart: unless-stopped

  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: node-exporter
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
    restart: unless-stopped

volumes:
  prometheus_data:
  grafana_data:

Prometheus Config (prometheus.yml)

global:
  scrape_interval: 15s
  evaluation_interval: 15s

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

rule_files:
  - 'alerts.yml'

scrape_configs:
  - job_name: 'node'
    static_configs:
      - targets: ['node-exporter:9100']
  
  - job_name: 'your-app'
    static_configs:
      - targets: ['your-app-container:8080']
    metrics_path: '/metrics'

Alert Rules (alerts.yml)

groups:
  - name: infrastructure
    rules:
      - alert: HighCPU
        expr: 100 - (avg(rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100) > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "CPU usage above 80%"

      - alert: HighMemory
        expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
        for: 5m
        labels:
          severity: critical
        annotations:
          summary: "Memory usage above 85%"

      - alert: DiskSpaceLow
        expr: (1 - (node_filesystem_avail_bytes{mountpoint="/"} / node_filesystem_size_bytes{mountpoint="/"})) * 100 > 80
        for: 5m
        labels:
          severity: warning
        annotations:
          summary: "Disk usage above 80%"

Alertmanager Config — Slack Notifications

route:
  group_by: ['alertname']
  group_wait: 10s
  group_interval: 10s
  repeat_interval: 1h
  receiver: 'slack-notifications'

receivers:
  - name: 'slack-notifications'
    slack_configs:
      - api_url: 'YOUR_SLACK_WEBHOOK_URL'
        channel: '#alerts'
        title: '{{ .CommonAnnotations.summary }}'
        text: '{{ range .Alerts }}{{ .Annotations.description }}{{ end }}'

Run It

docker compose up -d
# Prometheus: http://localhost:9090
# Grafana: http://localhost:3000 (admin / your_password)
# Import dashboard ID 1860 for Node Exporter Full dashboard