docker-compose.yaml

services:
  backend:
    build:
      context: ./backend
      dockerfile: Dockerfile
    container_name: backend
    ports:
      - "8000:8000"
    labels:
      metrics.scrape: "true"
    environment:
      APP_NAME: backend
      LOG_LEVEL: INFO
      PYROSCOPE_HOST: alloy
      PYROSCOPE_PORT: 4040
      OTLP_HOST: alloy
      OTLP_PORT: 4317
      PROMETHEUS_MULTIPROC_DIR: /tmp/prometheus-metrics
      GUNICORN_WORKERS: 2
    volumes:
      - backend_prometheus_metrics:/tmp/prometheus-metrics
    healthcheck:
      test: [ "CMD-SHELL", "curl -sf http://localhost:8000/health || exit 1" ]
      start_period: 30s
      interval: 10s
      timeout: 3s
      retries: 3
    depends_on:
      alloy:
        condition: service_started
    networks:
      - observability_network

  victoriametrics:
    image: victoriametrics/victoria-metrics:v1.131.0
    container_name: victoriametrics
    volumes:
      - victoriametrics_data:/storage
    command:
      - -storageDataPath=/storage
      - -httpListenAddr=:8428
      - -graphiteListenAddr=:2003
      - -opentsdbListenAddr=:4242
      - -influxListenAddr=:8089
      - -envflag.enable=true
      - -envflag.prefix=VM_
      - -loggerFormat=json
      - -enableTCP6
    environment:
      VM_retentionPeriod: 12
      VM_search_maxUniqueTimeseries: 1000000
    healthcheck:
      test: [ "CMD-SHELL", "wget --quiet --tries=1 --spider http://127.0.0.1:8428/health || exit 1" ]
      start_period: 5s
      interval: 30s
      timeout: 3s
      retries: 3
    networks:
      - observability_network

  vmalert:
    image: victoriametrics/vmalert:v1.131.0
    container_name: vmalert
    healthcheck:
      test: [ "CMD-SHELL", "wget --quiet --tries=1 --spider http://127.0.0.1:8880/health || exit 1" ]
      start_period: 3s
      interval: 30s
      timeout: 3s
      retries: 3
    depends_on:
      victoriametrics:
        condition: service_healthy
      alertmanager:
        condition: service_healthy
    volumes:
      - ./observability/vmalert/rules:/etc/rules
    command:
      - '--datasource.url=http://victoriametrics:8428'
      - '--remoteRead.url=http://victoriametrics:8428'
      - '--remoteWrite.url=http://victoriametrics:8428'
      - '--notifier.url=http://alertmanager:9093'
      - '--rule=/etc/rules/*.yaml'
    networks:
      - observability_network

  alertmanager:
    image: prom/alertmanager:v0.29.0
    container_name: alertmanager
    volumes:
      - ./observability/alertmanager/:/etc/alertmanager/
    command:
      - '--config.file=/etc/alertmanager/config.yaml'
      - '--storage.path=/alertmanager'
    healthcheck:
      test: [ "CMD-SHELL", "wget --quiet --tries=1 --spider http://127.0.0.1:9093/-/healthy || exit 1" ]
      start_period: 3s
      interval: 30s
      timeout: 3s
      retries: 3
    networks:
      - observability_network
    dns:
      - 8.8.8.8
      - 8.8.4.4

  alloy:
    image: grafana/alloy:v1.12.0
    container_name: alloy
    privileged: true
    ports:
      - "12345:12345"
    environment:
      ALLOY_DEPLOY_MODE: docker
    volumes:
      - ./observability/alloy:/etc/alloy
      - /proc:/rootproc:ro
      - /var/run/docker.sock:/var/run/docker.sock
      - /sys:/sys:ro
      - /:/rootfs:ro
      - /dev/disk/:/dev/disk:ro
      - /var/lib/docker/:/var/lib/docker:ro
    command: run --server.http.listen-addr=0.0.0.0:12345 --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy
    extra_hosts:
      - "host.docker.internal:host-gateway"
    devices:
      - /dev/kmsg
    depends_on:
      victoriametrics:
        condition: service_healthy
      loki:
        condition: service_healthy
      tempo:
        condition: service_healthy
    networks:
      - observability_network

  loki:
    # healthcheck broken in 3.6.0: https://github.com/grafana/loki/issues/19923
    image: grafana/loki:3.5.9
    container_name: loki
    user: root
    command:
      - "-config.file=/etc/loki/config.yaml"
      - "-config.expand-env=true"
    volumes:
      - loki_data:/loki
      - ./observability/loki/config.yaml:/etc/loki/config.yaml
    healthcheck:
      test: [ "CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3100/ready || exit 1" ]
      start_period: 30s
      interval: 30s
      timeout: 3s
      retries: 3
    networks:
      - observability_network

  grafana:
    image: grafana/grafana:12.4.0-20082909961-ubuntu
    container_name: grafana
    user: root
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - ./observability/grafana/provisioning/:/etc/grafana/provisioning/
    environment:
      - GF_SECURITY_ADMIN_USER=${GF_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GF_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
    healthcheck:
      test: [ "CMD-SHELL", "curl -s -f http://localhost:3000/api/health || exit 1" ]
      start_period: 3s
      interval: 30s
      timeout: 3s
      retries: 3
    depends_on:
      victoriametrics:
        condition: service_healthy
      loki:
        condition: service_healthy
      alertmanager:
        condition: service_healthy
      tempo:
        condition: service_healthy
    networks:
      - observability_network
    dns:
      - 8.8.8.8
      - 8.8.4.4

  pyroscope:
    container_name: pyroscope
    image: grafana/pyroscope:1.17.0
    command:
      - "server"
    volumes:
      - pyroscope_data:/var/lib/pyroscope
    networks:
      - observability_network

  tempo:
    image: grafana/tempo:2.8.0
    container_name: tempo
    command:
      - "-config.file=/etc/tempo/config.yaml"
    volumes:
      - ./observability/tempo/config.yaml:/etc/tempo/config.yaml
      - tempo_data:/var/tempo
    healthcheck:
      test: [ "CMD", "/busybox/wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3200/ready" ]
      start_period: 10s
      interval: 30s
      timeout: 3s
      retries: 3
    networks:
      - observability_network


networks:
  observability_network:
    driver: bridge

volumes:
  loki_data:
  grafana_data:
  victoriametrics_data:
  pyroscope_data:
  tempo_data:
  backend_prometheus_metrics: