docker-compose.yml

#================================================================================================
# Order Service - Docker Compose Configuration
# RESTful API with DDD + CQRS Pattern
#================================================================================================

#================================================================================================
# NETWORK SETUP
#================================================================================================
networks:
  order_service_net:
    name: order_service_net
    driver: bridge
    ipam:
      config:
        - subnet: 172.152.0.0/16

#================================================================================================
# VOLUME SETUP
#================================================================================================
volumes:
  vol_postgres_data:
    driver: local
  vol_prometheus_data:
    driver: local
  vol_grafana_data:
    driver: local

#================================================================================================
# SERVICES
#================================================================================================
services:
  #----------------------------------------------------------------------------------------------
  # POSTGRESQL - Order Data Storage
  #----------------------------------------------------------------------------------------------
  postgres:
    profiles: ["db", "all"]
    platform: linux/amd64
    image: postgres:${POSTGRES_VERSION:-16-alpine}
    container_name: ${CONTAINER_POSTGRES:-TFO-SDK-PostgreSQL}
    restart: unless-stopped
    ports:
      - "${PORT_POSTGRES:-5432}:5432"
    environment:
      - TZ=${TZ:-UTC}
      - POSTGRES_USER=${DB_USER:-postgres}
      - POSTGRES_PASSWORD=${DB_PASSWORD:-password}
      - POSTGRES_DB=${DB_NAME:-orders}
      - PGDATA=/var/lib/postgresql/data/pgdata
    volumes:
      - vol_postgres_data:/var/lib/postgresql/data
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_POSTGRES:-172.152.152.20}
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U ${DB_USER:-postgres} -d ${DB_NAME:-orders}"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  #----------------------------------------------------------------------------------------------
  # API - Order Service RESTful API
  #----------------------------------------------------------------------------------------------
  api:
    profiles: ["app", "all"]
    platform: linux/amd64
    build:
      context: .
      dockerfile: Dockerfile
    container_name: ${CONTAINER_API:-TFO-SDK-Order-Service}
    restart: unless-stopped
    ports:
      - "${PORT:-8080}:8080"
    environment:
      - TZ=${TZ:-UTC}

      # Server
      - SERVER_PORT=8080
      - SERVER_READ_TIMEOUT=${SERVER_READ_TIMEOUT:-15s}
      - SERVER_WRITE_TIMEOUT=${SERVER_WRITE_TIMEOUT:-15s}

      # PostgreSQL
      - DB_DRIVER=${DB_DRIVER:-postgres}
      - DB_HOST=postgres
      - DB_PORT=5432
      - DB_NAME=${DB_NAME:-orders}
      - DB_USER=${DB_USER:-postgres}
      - DB_PASSWORD=${DB_PASSWORD:-password}
      - DB_SSL_MODE=${DB_SSL_MODE:-disable}
      - DB_MAX_OPEN_CONNS=${DB_MAX_OPEN_CONNS:-25}
      - DB_MAX_IDLE_CONNS=${DB_MAX_IDLE_CONNS:-5}
      - DB_CONN_MAX_LIFETIME=${DB_CONN_MAX_LIFETIME:-5m}

      # JWT
      - JWT_SECRET=${JWT_SECRET}
      - JWT_EXPIRATION=${JWT_EXPIRATION:-24h}
      - JWT_REFRESH_EXPIRATION=${JWT_REFRESH_EXPIRATION:-168h}

      # Rate Limiting
      - RATE_LIMIT_REQUESTS=${RATE_LIMIT_REQUESTS:-100}
      - RATE_LIMIT_WINDOW=${RATE_LIMIT_WINDOW:-1m}

      # TelemetryFlow / OpenTelemetry
      - TELEMETRYFLOW_API_KEY_ID=${TELEMETRYFLOW_API_KEY_ID}
      - TELEMETRYFLOW_API_KEY_SECRET=${TELEMETRYFLOW_API_KEY_SECRET}
      - TELEMETRYFLOW_ENDPOINT=otel-collector:4317
      - TELEMETRYFLOW_SERVICE_NAME=${TELEMETRYFLOW_SERVICE_NAME:-Order-Service}
      - TELEMETRYFLOW_SERVICE_VERSION=${TELEMETRYFLOW_SERVICE_VERSION:-1.1.1}
      - TELEMETRYFLOW_INSECURE=${TELEMETRYFLOW_INSECURE:-true}

      # Logging
      - LOG_LEVEL=${LOG_LEVEL:-info}
      - LOG_FORMAT=${LOG_FORMAT:-json}
    depends_on:
      postgres:
        condition: service_healthy
      otel-collector:
        condition: service_started
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_API:-172.152.152.10}
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:8080/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  #----------------------------------------------------------------------------------------------
  # OTEL COLLECTOR - OpenTelemetry Collector
  #----------------------------------------------------------------------------------------------
  # Supports dual ingestion: v1 (OTEL standard) and v2 (TelemetryFlow enhanced)
  #
  # OTLP HTTP Endpoints:
  #   TelemetryFlow Platform (Recommended - TFO Standalone):
  #     POST http://localhost:4318/v2/traces
  #     POST http://localhost:4318/v2/metrics
  #     POST http://localhost:4318/v2/logs
  #
  #   OTEL Community (Backwards Compatible - OCB/Standard):
  #     POST http://localhost:4318/v1/traces
  #     POST http://localhost:4318/v1/metrics
  #     POST http://localhost:4318/v1/logs
  #
  #   gRPC (Both versions via same port): localhost:4317
  #----------------------------------------------------------------------------------------------
  otel-collector:
    profiles: ["monitoring", "all"]
    platform: linux/amd64
    # =============================================================================
    # TelemetryFlow Collector (TFO-Collector) - TFO format with OTLP support (v1.1.2+)
    image: telemetryflow/telemetryflow-collector:${TFO_VERSION:-1.1.2}
    command: ["--config=/etc/tfo-collector/tfo-collector.yaml"]
    # =============================================================================
    # TelemetryFlow Collector OCB (TFO-Collector-OCB) - Standard OTEL format
    # image: telemetryflow/telemetryflow-collector:${TFO_VERSION:-1.1.2}
    # command: ["--config=/etc/tfo-collector/otel-collector.yaml"]
    # =============================================================================
    # OTEL Collector Community Contributor (Standard OTEL format)
    # image: otel/opentelemetry-collector-contrib:${OTEL_VERSION:-0.142.0}
    # command: ["--config=/etc/otelcol-contrib/config.yaml"]
    # =============================================================================
    container_name: ${CONTAINER_OTEL:-TFO-SDK-OTEL}
    restart: unless-stopped
    volumes:
      # TelemetryFlow Collector config (Custom TFO format)
      - ./configs/otel/tfo-collector.yaml:/etc/tfo-collector/tfo-collector.yaml:ro
      # Logs output directory
      - ./logs:/tmp/logs
      # =============================================================================
      # TelemetryFlow Collector OCB config (Standard OTEL format)
      # - ./configs/otel/otel-collector.yaml:/etc/tfo-collector/otel-collector.yaml:ro
      # =============================================================================
      # OTEL Collector Community Contributor config (Standard OTEL format)
      # - ./configs/otel/otel-collector.yaml:/etc/otelcol-contrib/config.yaml:ro
    ports:
      - "${PORT_OTEL_GRPC:-4317}:4317"     # OTLP gRPC (v1 & v2)
      - "${PORT_OTEL_HTTP:-4318}:4318"     # OTLP HTTP (v1 & v2)
      - "${PORT_OTEL_METRICS:-8889}:8889"  # Prometheus metrics
      - "${PORT_OTEL_HEALTH:-13133}:13133" # Health check
      - "${PORT_OTEL_ZPAGES:-55679}:55679" # zPages
      - "${PORT_OTEL_PPROF:-1777}:1777"    # pprof
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_OTEL:-172.152.152.30}
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:13133"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s
    depends_on:
      - jaeger

  #----------------------------------------------------------------------------------------------
  # JAEGER - Distributed Tracing UI
  #----------------------------------------------------------------------------------------------
  jaeger:
    profiles: ["monitoring", "all"]
    platform: linux/amd64
    image: jaegertracing/jaeger:${JAEGER_VERSION:-2.13.0}
    container_name: ${CONTAINER_JAEGER:-TFO-SDK-Jaeger}
    restart: unless-stopped
    ports:
      - "${PORT_JAEGER_UI:-16686}:16686"  # Jaeger UI
    environment:
      - COLLECTOR_OTLP_ENABLED=true
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_JAEGER:-172.152.152.40}
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:16686"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  #----------------------------------------------------------------------------------------------
  # PROMETHEUS - Metrics Collection with Exemplars Support
  #----------------------------------------------------------------------------------------------
  prometheus:
    profiles: ["monitoring", "all"]
    platform: linux/amd64
    image: prom/prometheus:${PROMETHEUS_VERSION:-v3.4.0}
    container_name: ${CONTAINER_PROMETHEUS:-TFO-SDK-Prometheus}
    restart: unless-stopped
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.enable-lifecycle'
      - '--web.enable-remote-write-receiver'
      - '--enable-feature=exemplar-storage'
      - '--enable-feature=native-histograms'
    ports:
      - "${PORT_PROMETHEUS:-9090}:9090"
    volumes:
      - ./configs/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - vol_prometheus_data:/prometheus
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_PROMETHEUS:-172.152.152.50}
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 10s

  #----------------------------------------------------------------------------------------------
  # GRAFANA - Observability Dashboard with Exemplars Visualization
  #----------------------------------------------------------------------------------------------
  grafana:
    profiles: ["monitoring", "all"]
    platform: linux/amd64
    image: grafana/grafana:${GRAFANA_VERSION:-12.3.1}
    container_name: ${CONTAINER_GRAFANA:-TFO-SDK-Grafana}
    restart: unless-stopped
    ports:
      - "${PORT_GRAFANA:-3000}:3000"
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor tempoSearch tempoBackendSearch tempoApmTable
    volumes:
      - ./configs/grafana/provisioning:/etc/grafana/provisioning:ro
      - vol_grafana_data:/var/lib/grafana
    networks:
      order_service_net:
        ipv4_address: ${CONTAINER_IP_GRAFANA:-172.152.152.60}
    depends_on:
      - prometheus
      - jaeger
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 10s
      timeout: 5s
      retries: 5
      start_period: 30s