docker-compose.yml

# =============================================================================
# infra-observability — Local Development Stack
# Usage: docker compose up -d
# =============================================================================

name: infra-observability

x-logging: &default-logging
  driver: json-file
  options:
    max-size: "10m"
    max-file: "3"

services:
  # ---------------------------------------------------------------------------
  # OTEL Collector — gateway for all telemetry
  # ---------------------------------------------------------------------------
  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.97.0
    container_name: otel-collector
    restart: unless-stopped
    command: ["--config=/etc/otelcol-contrib/otel-collector-config.yaml"]
    volumes:
      - ./otel-collector/config/otel-collector-config.yaml:/etc/otelcol-contrib/otel-collector-config.yaml:ro
    ports:
      - "4317:4317"    # OTLP gRPC — services send telemetry here
      - "4318:4318"    # OTLP HTTP — services send telemetry here
      - "8888:8888"    # Collector internal metrics
      - "8889:8889"    # Prometheus exporter (scraped by Prometheus)
      - "13133:13133"  # Health check
      - "55679:55679"  # zPages debug UI
    environment:
      - ENVIRONMENT=${ENVIRONMENT:-local}
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:13133/"]
      interval: 10s
      timeout: 5s
      retries: 3
    logging: *default-logging
    networks:
      - observability

  # ---------------------------------------------------------------------------
  # Prometheus — metrics storage & alerting
  # ---------------------------------------------------------------------------
  prometheus:
    image: prom/prometheus:v2.51.0
    container_name: prometheus
    restart: unless-stopped
    command:
      - "--config.file=/etc/prometheus/prometheus.yml"
      - "--storage.tsdb.path=/prometheus"
      - "--storage.tsdb.retention.time=30d"
      - "--web.enable-lifecycle"           # allow hot-reload via POST /-/reload
      - "--web.enable-remote-write-receiver"
      - "--web.console.libraries=/usr/share/prometheus/console_libraries"
      - "--web.console.templates=/usr/share/prometheus/consoles"
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus_data:/prometheus
    ports:
      - "9090:9090"
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 10s
      timeout: 5s
      retries: 3
    depends_on:
      otel-collector:
        condition: service_healthy
    logging: *default-logging
    networks:
      - observability

  # ---------------------------------------------------------------------------
  # Grafana Tempo — distributed tracing backend
  # ---------------------------------------------------------------------------
  tempo:
    image: grafana/tempo:2.4.1
    container_name: tempo
    restart: unless-stopped
    command: ["-config.file=/etc/tempo.yaml"]
    volumes:
      - ./tempo/tempo.yaml:/etc/tempo.yaml:ro
      - tempo_data:/var/tempo
    ports:
      - "3200:3200"   # Tempo HTTP API
      - "4317"        # OTLP gRPC (internal only)
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3200/ready"]
      interval: 10s
      timeout: 5s
      retries: 3
    logging: *default-logging
    networks:
      - observability

  # ---------------------------------------------------------------------------
  # Grafana — dashboards & visualization
  # ---------------------------------------------------------------------------
  grafana:
    image: grafana/grafana:10.4.2
    container_name: grafana
    restart: unless-stopped
    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 traceQLStreaming metricsSummary
      - GF_AUTH_ANONYMOUS_ENABLED=false
      - GF_ANALYTICS_REPORTING_ENABLED=false
      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-piechart-panel
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana_data:/var/lib/grafana
    ports:
      - "3000:3000"
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 10s
      timeout: 5s
      retries: 3
    depends_on:
      prometheus:
        condition: service_healthy
      tempo:
        condition: service_healthy
    logging: *default-logging
    networks:
      - observability

  # ---------------------------------------------------------------------------
  # Node Exporter — host metrics (CPU, memory, disk, network)
  # ---------------------------------------------------------------------------
  node-exporter:
    image: prom/node-exporter:v1.7.0
    container_name: node-exporter
    restart: unless-stopped
    command:
      - "--path.rootfs=/host"
      - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    ports:
      - "9100:9100"
    logging: *default-logging
    networks:
      - observability

# -----------------------------------------------------------------------------
# Volumes
# -----------------------------------------------------------------------------
volumes:
  prometheus_data:
    driver: local
  grafana_data:
    driver: local
  tempo_data:
    driver: local

# -----------------------------------------------------------------------------
# Networks
# -----------------------------------------------------------------------------
networks:
  observability:
    name: observability
    driver: bridge