docker-compose.prod.yml

version: '3.8'

# Production Docker Compose Override File
# Use with: docker-compose -f docker-compose.yml -f docker-compose.prod.yml up

services:
  # PostgreSQL Database - Production
  postgres:
    image: postgres:15-alpine
    container_name: astroml-postgres-prod
    restart: always
    environment:
      POSTGRES_DB: ${POSTGRES_DB:-astroml}
      POSTGRES_USER: ${POSTGRES_USER:-astroml}
      POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?POSTGRES_PASSWORD is required}
      POSTGRES_INITDB_ARGS: "--encoding=UTF-8 --lc-collate=C --lc-ctype=C --shared-buffers=256MB --max-connections=200"
    ports:
      - "${POSTGRES_PORT:-5432}:5432"
    volumes:
      - postgres_data:/var/lib/postgresql/data
      - ./monitoring/postgres/backup:/backup
      - ./migrations:/docker-entrypoint-initdb.d
    networks:
      - astroml-network
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${POSTGRES_USER:-astroml} -d ${POSTGRES_DB:-astroml}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 2G
        reservations:
          cpus: '0.5'
          memory: 512M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # Redis - Production
  redis:
    image: redis:7-alpine
    container_name: astroml-redis-prod
    restart: always
    command: redis-server --appendonly yes --maxmemory 512mb --maxmemory-policy allkeys-lru
    ports:
      - "${REDIS_PORT:-6379}:6379"
    networks:
      - astroml-network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 512M
        reservations:
          cpus: '0.25'
          memory: 128M
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

networks:
  astroml-network:
    driver: bridge

volumes:
  postgres_data:
    volumes:
      - redis_data:/data
    networks:
      - astroml-network
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 5s
      retries: 5
    command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD}
    deploy:
      resources:
        limits:
          cpus: '1.0'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M
    start_period: 10s
    restart: unless-stopped
    logging:
      driver: "json-file"
      options:
        max-size: "10m"
        max-file: "3"

  # Production application service
  production:
    environment:
      - LOG_LEVEL=WARNING
      - DEBUG=False
      - APP_ENV=production
    restart: always
    deploy:
      resources:
        limits:
          cpus: '4'
          memory: 4G
        reservations:
          cpus: '2'
          memory: 2G
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]

  # AstroML Ingestion Service
  ingestion:
    build:
      context: .
      dockerfile: Dockerfile
      target: production
    container_name: astroml-ingestion-prod
    environment:
      ASTROML_ENV: production
      DATABASE_URL: postgresql://${POSTGRES_USER:-astroml}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-astroml}
      REDIS_URL: redis://redis:6379/0
      FEATURE_STORE_PATH: /app/feature_store
    volumes:
      - feature_store:/app/feature_store
      - ./config:/app/config:ro
    networks:
      - astroml-network
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "import astroml.ingestion; import astroml.features; print('OK')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 60s
  ingestion:
    # Production ingestion service
    restart: unless-stopped
    environment:
      - LOG_LEVEL=INFO
      - APP_ENV=production
    deploy:
      resources:
        limits:
          cpus: '4.0'
          memory: 8G
        reservations:
          cpus: '1.0'
          memory: 2G
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  streaming:
    # Production streaming service
    restart: always
    environment:
      - LOG_LEVEL=INFO
      - APP_ENV=production
    deploy:
      resources:
        limits:
          cpus: '2'
          memory: 2G
        reservations:
          cpus: '1'
          memory: 1G

  # AstroML Training Service
  training:
    build:
      context: .
      dockerfile: Dockerfile
      target: training
    container_name: astroml-training-prod
    environment:
      ASTROML_ENV: production
      DATABASE_URL: postgresql://${POSTGRES_USER:-astroml}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-astroml}
      REDIS_URL: redis://redis:6379/0
      FEATURE_STORE_PATH: /app/feature_store
      CUDA_VISIBLE_DEVICES: ${CUDA_VISIBLE_DEVICES:-0}
    volumes:
      - feature_store:/app/feature_store
      - ./config:/app/config:ro
      - model_store:/app/models
    networks:
      - astroml-network
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "import torch; import astroml.features; print('OK')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '8.0'
          memory: 32G
        reservations:
          cpus: '2.0'
          memory: 4G
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  # Feature Store Service
  feature-store:
    build:
      context: .
      dockerfile: Dockerfile
      target: feature-store
    container_name: astroml-feature-store-prod
    environment:
      ASTROML_ENV: production
      DATABASE_URL: postgresql://${POSTGRES_USER:-astroml}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-astroml}
      REDIS_URL: redis://redis:6379/0
      FEATURE_STORE_PATH: /app/feature_store
    ports:
      - "${FEATURE_STORE_PORT:-8000}:8000"
    volumes:
      - feature_store:/app/feature_store
    networks:
      - astroml-network
    depends_on:
      postgres:
        condition: service_healthy
      redis:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "python", "-c", "from astroml.features import create_feature_store; store = create_feature_store('/app/feature_store'); print('OK')"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 30s
    restart: unless-stopped
    deploy:
      resources:
        limits:
          cpus: '2.0'
          memory: 4G
        reservations:
          cpus: '0.5'
          memory: 1G
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  prometheus:
    # Production Prometheus with persistent storage
    image: prom/prometheus:latest
    restart: always
    environment:
      - PROMETHEUS_ARGS=--storage.tsdb.retention.time=30d --storage.tsdb.retention.size=50GB
    volumes:
      - ./monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./monitoring/prometheus/alert_rules.yml:/etc/prometheus/alert_rules.yml:ro
      - prometheus_data:/prometheus
    networks:
      - astroml-network
    profiles:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '2'
          memory: 2G
        reservations:
          cpus: '1'
          memory: 1G

  grafana:
    # Production Grafana with persistent storage
    image: grafana/grafana:latest
    restart: always
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_LOG_LEVEL=warn
      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
    volumes:
      - grafana_data:/var/lib/grafana
      - ./monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
    networks:
      - astroml-network
    depends_on:
      - prometheus
    profiles:
      - monitoring
    deploy:
      resources:
        limits:
          cpus: '1'
          memory: 1G
        reservations:
          cpus: '0.5'
          memory: 512M

networks:
  astroml-network:
    driver: bridge
    ipam:
      config:
        - subnet: 172.20.0.0/16

volumes:
  postgres_data:
    driver: local
  redis_data:
    driver: local
volumes:
  prometheus_data:
    driver: local
  grafana_data:
    driver: local
  feature_store:
    driver: local
  model_store:
    driver: local

networks:
  astroml-network:
    driver: bridge