docker-compose.traces-metrics.yaml

x-default-logging: &logging
  driver: "json-file"
  options:
    max-size: "${MAX_LOG_FILE_SIZE}"
    max-file: "${MAX_LOG_FILE_COUNT}"
    tag: "{{.Name}}|{{.ImageName}}|{{.ID}}"

services:
  prometheus:
    image: prom/prometheus:${PROMETHEUS_VERSION}
    restart: on-failure
    # https://prometheus.io/docs/prometheus/latest/feature_flags/
    command:
      - "--web.console.templates=/etc/prometheus/consoles"
      - "--web.console.libraries=/etc/prometheus/console_libraries"
      - "--storage.tsdb.retention.time=1y"
      - "--storage.tsdb.path=/prometheus"
      - "--config.file=/etc/prometheus/prometheus-config.yaml"
      - "--web.enable-lifecycle"
      - "--web.route-prefix=/"
      - "--enable-feature=exemplar-storage"
      - "--enable-feature=otlp-write-receiver"
      - "--web.enable-remote-write-receiver"
      # - "--enable-feature=auto-gomaxprocs"
      # - "--enable-feature=auto-gomemlimit"
      - "--enable-feature=concurrent-rule-eval"
    volumes:
      - ./src/prometheus:/etc/prometheus
      - prometheus-data:/prometheus
    environment:
      - GOMAXPROCS=${GOMAXPROCS}
      - GOMEMLIMIT=${GOMEMLIMIT}
    ports:
      - ${PROMETHEUS_PORT}:9090
    deploy:
      resources:
        limits:
          cpus: ${CPU_LIMIT}
          memory: ${MEM_LIMIT}
    healthcheck:
      test: "wget -q -t 1 -O - http://localhost:9090/-/ready | grep -q 'Prometheus Server is Ready.'"
      interval: 1s
      timeout: 1s
      retries: 120
    logging: *logging

  # https://www.jaegertracing.io/docs/1.56/deployment/
  jaeger:
    image: jaegertracing/all-in-one:${JAEGER_VERSION}
    restart: on-failure
    ports:
      - "4317"
      - "4318"
      - ${JAEGERQUERY_PORT}:16686
    # https://www.jaegertracing.io/docs/1.56/cli/#jaeger-all-in-one-prometheus
    environment:
      - GOMAXPROCS=${GOMAXPROCS}
      - GOMEMLIMIT=${GOMEMLIMIT}
      - METRICS_STORAGE_TYPE=prometheus
      - PROMETHEUS_SERVER_URL=http://prometheus:9090
      - PROMETHEUS_QUERY_SUPPORT_SPANMETRICS_CONNECTOR=true
      - PROMETHEUS_QUERY_NORMALIZE_CALLS=true
      - PROMETHEUS_QUERY_NORMALIZE_DURATION=true
    command:
      - "--log-level=info"
    deploy:
      resources:
        limits:
          cpus: ${CPU_LIMIT}
          memory: ${MEM_LIMIT}
    healthcheck:
      test: "wget -q -t 1 -O - http://localhost:14269 | grep -q 'Server available'"
      interval: 1s
      timeout: 1s
      retries: 120
    depends_on:
      prometheus:
        condition: service_healthy
    logging: *logging

  grafana:
    image: grafana/grafana:${GRAFANA_VERSION}
    restart: on-failure
    volumes:
      - ./src/grafana/grafana.ini:/etc/grafana/grafana.ini
      - ./src/grafana/provisioning/:/etc/grafana/provisioning/
      - grafana-data:/var/lib/grafana
    ports:
      - ${GRAFANA_PORT}:3000
    environment:
      - GOMAXPROCS=${GOMAXPROCS}
      - GOMEMLIMIT=${GOMEMLIMIT}
      - GF_SERVER_ROOT_URL=http://${CLUSTER_IP}:${GRAFANA_PORT}
    deploy:
      resources:
        limits:
          cpus: ${CPU_LIMIT}
          memory: ${MEM_LIMIT}
    healthcheck:
      test: 'curl -s --retry 0 http://localhost:3000/api/health | grep -q ''"database": "ok"'''
      interval: 1s
      timeout: 1s
      retries: 120
    depends_on:
      prometheus:
        condition: service_healthy
    logging: *logging

volumes:
  prometheus-data:
  grafana-data: