didi-lot2-backend/backend/observability/docker-compose.yml

# DiDi Observability Stack
# ========================
# Implements LOT 2 modul 8 (Observabilitate & Logging) conform oferta EVOTECH §A.9:
#   - Prometheus     — metrics scraping
#   - Grafana        — dashboards
#   - Loki           — log aggregation
#   - Promtail       — log shipper (Docker logs → Loki)
#   - Jaeger         — distributed tracing UI
#   - OTel Collector — receives traces from services, forwards to Jaeger
#   - Alertmanager   — alert routing (email, Slack/Teams, PagerDuty)
#
# Network: didi-network (shared cu DIDI + AI platform stacks)
# Storage: volumes locale persistente
#
# Quick start:
#   cd /home/admin365/didi_mono/didi_mono/backend/observability
#   docker compose up -d
#
# UI access:
#   Grafana:       http://didi.local:3030  (admin / GRAFANA_ADMIN_PASSWORD)
#   Prometheus:    http://didi.local:9090
#   Jaeger UI:     http://didi.local:16686
#   Alertmanager:  http://didi.local:9093

services:
  prometheus:
    image: prom/prometheus:v2.55.0
    container_name: didi-prometheus
    restart: unless-stopped
    user: "65534:65534"  # nobody:nobody (avoids root warnings)
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/rules:/etc/prometheus/rules:ro
      - prometheus-data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=20GB'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
    ports:
      - "0.0.0.0:9090:9090"
    networks:
      - didi-network
    healthcheck:
      test: ["CMD", "wget", "--quiet", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3

  grafana:
    image: grafana/grafana:11.3.0
    container_name: didi-grafana
    restart: unless-stopped
    depends_on:
      prometheus:
        condition: service_healthy
    environment:
      GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-admin}
      GF_USERS_ALLOW_SIGN_UP: "false"
      GF_AUTH_ANONYMOUS_ENABLED: "false"
      GF_INSTALL_PLUGINS: "grafana-piechart-panel,grafana-clock-panel"
      GF_FEATURE_TOGGLES_ENABLE: "traceqlEditor"
    volumes:
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
      - grafana-data:/var/lib/grafana
    ports:
      - "0.0.0.0:3030:3000"
    networks:
      - didi-network
    healthcheck:
      test: ["CMD-SHELL", "wget --quiet --tries=1 --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 3

  loki:
    image: grafana/loki:3.2.0
    container_name: didi-loki
    restart: unless-stopped
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/local-config.yaml:ro
      - loki-data:/loki
    command: -config.file=/etc/loki/local-config.yaml
    ports:
      - "0.0.0.0:3100:3100"
    networks:
      - didi-network
    healthcheck:
      test: ["CMD-SHELL", "wget --quiet --tries=1 --spider http://localhost:3100/ready || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 30s

  promtail:
    image: grafana/promtail:3.2.0
    container_name: didi-promtail
    restart: unless-stopped
    depends_on:
      loki:
        condition: service_healthy
    volumes:
      - ./promtail/promtail-config.yaml:/etc/promtail/config.yaml:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - promtail-data:/tmp
    command: -config.file=/etc/promtail/config.yaml
    networks:
      - didi-network

  jaeger:
    image: jaegertracing/all-in-one:1.62.0
    container_name: didi-jaeger
    restart: unless-stopped
    environment:
      COLLECTOR_OTLP_ENABLED: "true"
      SPAN_STORAGE_TYPE: memory
      BADGER_EPHEMERAL: "false"
      BADGER_DIRECTORY_VALUE: /badger/data
      BADGER_DIRECTORY_KEY: /badger/key
    volumes:
      - jaeger-data:/badger
    ports:
      - "0.0.0.0:16686:16686"   # Jaeger UI
      - "0.0.0.0:14250:14250"   # gRPC collector (legacy)
      - "0.0.0.0:14268:14268"   # HTTP collector (legacy)
      - "0.0.0.0:4317:4317"     # OTLP gRPC
      - "0.0.0.0:4318:4318"     # OTLP HTTP
    networks:
      - didi-network

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.110.0
    container_name: didi-otel-collector
    restart: unless-stopped
    depends_on:
      - jaeger
      - prometheus
    volumes:
      - ./otel-collector/otel-collector.yaml:/etc/otelcol-contrib/config.yaml:ro
    command: ["--config=/etc/otelcol-contrib/config.yaml"]
    ports:
      - "0.0.0.0:4319:4317"   # OTLP gRPC (services push traces here)
      - "0.0.0.0:4320:4318"   # OTLP HTTP
      - "0.0.0.0:8888:8888"   # collector self-metrics
      - "0.0.0.0:8889:8889"   # prometheus exporter
    networks:
      - didi-network

  alertmanager:
    image: prom/alertmanager:v0.27.0
    container_name: didi-alertmanager
    restart: unless-stopped
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager-data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    ports:
      - "0.0.0.0:9093:9093"
    networks:
      - didi-network
    healthcheck:
      test: ["CMD-SHELL", "wget --quiet --tries=1 --spider http://localhost:9093/-/healthy || exit 1"]
      interval: 30s
      timeout: 5s
      retries: 3

volumes:
  prometheus-data: {}
  grafana-data: {}
  loki-data: {}
  promtail-data: {}
  jaeger-data: {}
  alertmanager-data: {}

networks:
  didi-network:
    external: true