anya-core 1.2.0

version: '3.8'

services:
  # Prometheus - Metrics Collection
  prometheus:
    image: prom/prometheus:latest
    container_name: prometheus
    user: root
    volumes:
      - ./prometheus:/etc/prometheus
      - prometheus_data:/prometheus
      - /etc/localtime:/etc/localtime:ro
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
    ports:
      - "9090:9090"
    networks:
      - monitoring
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Alertmanager - Alert Management
  alertmanager:
    image: prom/alertmanager:latest
    container_name: alertmanager
    volumes:
      - ./alertmanager:/etc/alertmanager
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
    ports:
      - "9093:9093"
    networks:
      - monitoring
    restart: unless-stopped

  # Grafana - Visualization
  grafana:
    image: grafana/grafana:latest
    container_name: grafana
    user: "472"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning
      - ./grafana/dashboards:/var/lib/grafana/dashboards
      - /etc/localtime:/etc/localtime:ro
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_USERS_DEFAULT_THEME=dark
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-simple-json-datasource,grafana-piechart-panel
    ports:
      - "3000:3000"
    networks:
      - monitoring
    depends_on:
      - prometheus
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "localhost:3000/api/health"]
      interval: 30s
      timeout: 10s
      retries: 3

  # Node Exporter - System Metrics
  node-exporter:
    image: prom/node-exporter:latest
    container_name: node-exporter
    user: root
    command: --path.procfs=/host/proc --path.sysfs=/host/sys
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
    networks:
      - monitoring
    restart: unless-stopped

  # cAdvisor - Container Metrics
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:latest
    container_name: cadvisor
    privileged: true
    devices:
      - /dev/kmsg:/dev/kmsg
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      - /cgroup:/cgroup:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    networks:
      - monitoring
    restart: unless-stopped

  # Blackbox Exporter - Network Probes
  blackbox-exporter:
    image: prom/blackbox-exporter:latest
    container_name: blackbox-exporter
    volumes:
      - ./blackbox:/etc/blackbox_exporter
    ports:
      - "9115:9115"
    networks:
      - monitoring
    restart: unless-stopped

  # Process Exporter - Process Monitoring
  process-exporter:
    image: ncabatoff/process-exporter:latest
    container_name: process-exporter
    command: ["-config.path=/etc/process-exporter/config.yml"]
    volumes:
      - /proc:/host/proc:ro
      - ./process-exporter:/etc/process-exporter
    networks:
      - monitoring
    restart: unless-stopped

  # Redis Exporter - Redis Metrics
  redis-exporter:
    image: oliver006/redis_exporter:latest
    container_name: redis-exporter
    environment:
      - REDIS_ADDR=redis:6379
    ports:
      - "9121:9121"
    networks:
      - monitoring
    restart: unless-stopped
    depends_on:
      - redis

  # Redis - Caching
  redis:
    image: redis:alpine
    container_name: redis
    command: ["redis-server", "--appendonly", "yes"]
    volumes:
      - redis_data:/data
    networks:
      - monitoring
    restart: unless-stopped

  # Loki - Log Aggregation
  loki:
    image: grafana/loki:latest
    container_name: loki
    ports:
      - "3100:3100"
    volumes:
      - loki_data:/loki
      - ./loki:/etc/loki
    command: -config.file=/etc/loki/loki-config.yml
    networks:
      - monitoring
    restart: unless-stopped

  # Promtail - Log Collection
  promtail:
    image: grafana/promtail:latest
    container_name: promtail
    volumes:
      - /var/log:/var/log
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - ./promtail:/etc/promtail
    command: -config.file=/etc/promtail/promtail-config.yml
    networks:
      - monitoring
    restart: unless-stopped

networks:
  monitoring:
    driver: bridge
    ipam:
      driver: default
      config:
        - subnet: 172.20.0.0/16
          gateway: 172.20.0.1

volumes:
  prometheus_data:
  grafana_data:
  alertmanager_data:
  redis_data:
  loki_data: