compose.yml

---
version: "3"

networks:
  observability:

services:

  grafana:
    image: grafana/grafana:latest
    environment:
      - GF_PATHS_PROVISIONING=/etc/grafana/provisioning
      - GF_AUTH_ANONYMOUS_ENABLED=true
      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
    depends_on:
      - loki-gateway
    entrypoint:
      - sh
      - -euc
      - /run.sh
    ports:
      - "3000:3000"
    volumes:
      - ./infra/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/ds.yaml:ro
      - ./infra/grafana-dashboards.yaml:/etc/grafana/provisioning/dashboards/default.yaml
      - ./infra/dashboards/:/etc/grafana/provisioning/dashboards/json/
    healthcheck:
      test: [ "CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1" ]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - observability

  otel-collector:
    image: otel/opentelemetry-collector:latest
    command: --config=/etc/otel-collector.yaml
    volumes:
      - ./infra/otel-collector.yaml:/etc/otel-collector.yaml
    ports:
      - "4317:4317"  # OTLP gRPC receiver
      - "4318:4318"  # OTLP HTTP receiver
    depends_on:
      - tempo
    networks:
      - observability

  tempo:
    image: grafana/tempo:2.3.1
    command: [ "-config.file=/etc/tempo.yaml" ]
    volumes:
      - ./infra/tempo-config.yaml:/etc/tempo.yaml
      - ./infra/.data/tempo:/tmp/tempo
    ports:
      - "9411:9411"  # zipkin
      - "3200:3200"  # tempo
    restart: on-failure
    depends_on:
      - minio
      - prometheus
    networks:
      - observability

  prometheus:
    image: prom/prometheus:latest
    command:
      - --config.file=/etc/prometheus.yaml
      - --web.enable-remote-write-receiver
      - --enable-feature=exemplar-storage
    volumes:
      - ./infra/prometheus.yaml:/etc/prometheus.yaml
    ports:
      - "9090:9090"
    networks:
      - observability

  loki-gateway:
    image: nginx:latest
    depends_on:
      - read
      - write
    entrypoint:
      - sh
      - -euc
      - /docker-entrypoint.sh nginx -g "daemon off;"
    ports:
      - "3100:3100"
    volumes:
      - ./infra/nginx.conf:/etc/nginx/nginx.conf
    healthcheck:
      test: [ "CMD", "service", "nginx", "status" ]
      interval: 10s
      timeout: 5s
      retries: 5
    networks:
      - observability

  read:
    image: grafana/loki:2.9.2
    command: "-config.file=/etc/loki/config.yaml -target=read"
    ports:
      - "3101:3100"
      - "7946"
      - "9095"
    volumes:
      - ./infra/loki-config.yaml:/etc/loki/config.yaml
    depends_on:
      - minio
    healthcheck:
      test: [ "CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1" ]
      interval: 10s
      timeout: 5s
      retries: 5
    networks: &loki-dns
      observability:
        aliases:
          - loki

  write:
    image: grafana/loki:2.9.2
    command: "-config.file=/etc/loki/config.yaml -target=write"
    ports:
      - "3102:3100"
      - "7946"
      - "9095"
    volumes:
      - ./infra/loki-config.yaml:/etc/loki/config.yaml
    healthcheck:
      test: [ "CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1" ]
      interval: 10s
      timeout: 5s
      retries: 5
    depends_on:
      - minio
    networks:
      <<: *loki-dns

  minio:
    image: minio/minio
    entrypoint:
      - sh
      - -euc
      - |
        mkdir -p /data/loki-data && \
        mkdir -p /data/loki-ruler && \
        mkdir -p /data/tempo-data && \
        minio server /data
    environment:
      - MINIO_ROOT_USER=observability
      - MINIO_ROOT_PASSWORD=supersecret
      - MINIO_PROMETHEUS_AUTH_TYPE=public
      - MINIO_UPDATE=off
    ports:
      - "9000"
    volumes:
      - ./infra/.data/minio:/data
    healthcheck:
      test: [ "CMD", "curl", "-f", "http://localhost:9000/minio/health/live" ]
      interval: 15s
      timeout: 20s
      retries: 5
    networks:
      - observability