docker-compose.yml

# Copyright (C) 2018-2022 Intel Corporation
# Copyright (C) CVAT.ai Corporation
#
# SPDX-License-Identifier: MIT

name: cvat

x-backend-env: &backend-env
  CVAT_POSTGRES_HOST: cvat_db
  CVAT_REDIS_INMEM_HOST: cvat_redis_inmem
  CVAT_REDIS_INMEM_PORT: 6379
  CVAT_REDIS_ONDISK_HOST: cvat_redis_ondisk
  CVAT_REDIS_ONDISK_PORT: 6666
  CVAT_LOG_IMPORT_ERRORS: 'true'
  CVAT_ALLOW_STATIC_CACHE: '${CVAT_ALLOW_STATIC_CACHE:-no}'
  DJANGO_LOG_SERVER_HOST: vector
  DJANGO_LOG_SERVER_PORT: 80
  no_proxy: clickhouse,grafana,vector,nuclio,opa,${no_proxy:-}
  SMOKESCREEN_OPTS: ${SMOKESCREEN_OPTS:-}

x-backend-deps: &backend-deps
  cvat_redis_inmem:
    condition: service_started
  cvat_redis_ondisk:
    condition: service_started
  cvat_db:
    condition: service_started

x-clickhouse-env: &clickhouse-env
  CLICKHOUSE_HOST: clickhouse
  CLICKHOUSE_PORT: 8123
  CLICKHOUSE_DB: cvat
  CLICKHOUSE_USER: user
  CLICKHOUSE_PASSWORD: user

services:
  cvat_db:
    container_name: cvat_db
    image: postgres:15-alpine
    restart: always
    environment:
      POSTGRES_USER: root
      POSTGRES_DB: cvat
      POSTGRES_HOST_AUTH_METHOD: trust
    volumes:
      - cvat_db:/var/lib/postgresql/data
    networks:
      - cvat

  cvat_redis_inmem:
    container_name: cvat_redis_inmem
    image: redis:7.2.3-alpine
    restart: always
    command: [
      "redis-server",
      "--save", "60", "100",
      "--appendonly", "yes",
    ]
    volumes:
      - cvat_inmem_db:/data
    networks:
      - cvat

  cvat_redis_ondisk:
    container_name: cvat_redis_ondisk
    image: apache/kvrocks:2.7.0
    restart: always
    command: [
      "--dir", "/var/lib/kvrocks/data"
    ]
    # The kvrocks image a) has a healthcheck command, and b) has a root process
    # that doesn't reap children, so it's susceptible to the problem described here:
    # <https://stackoverflow.com/a/77109064>. Kvrocks also uses a tiny timeout for
    # its healthcheck command (1s), which makes the problem more likely to manifest.
    # Use a separate init process as a workaround.
    init: true
    volumes:
      - cvat_cache_db:/var/lib/kvrocks/data
    networks:
      - cvat

  cvat_server:
    container_name: cvat_server
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on:
      <<: *backend-deps
      cvat_opa:
        condition:
          service_started
    environment:
      <<: [*backend-env, *clickhouse-env]
      DJANGO_MODWSGI_EXTRA_ARGS: ''
      ALLOWED_HOSTS: '*'
      ADAPTIVE_AUTO_ANNOTATION: 'false'
      NUMPROCS: 2
      CVAT_ANALYTICS: 1
      CVAT_BASE_URL:
      ONE_RUNNING_JOB_IN_QUEUE_PER_USER:
    command: init run server
    labels:
      - traefik.enable=true
      - traefik.http.services.cvat.loadbalancer.server.port=8080
      - traefik.http.routers.cvat.rule=Host(`${CVAT_HOST:-localhost}`) &&
        PathPrefix(`/api/`, `/static/`, `/admin`, `/documentation/`, `/django-rq`)
      - traefik.http.routers.cvat.entrypoints=web
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      cvat:
        aliases:
          - cvat-server

  cvat_utils:
    container_name: cvat_utils
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      CVAT_REDIS_INMEM_PASSWORD: ''
      NUMPROCS: 1
    command: run utils
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_import:
    container_name: cvat_worker_import
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 2
    command: run worker.import
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_export:
    container_name: cvat_worker_export
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: [*backend-env, *clickhouse-env]
      NUMPROCS: 2
    command: run worker.export
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_annotation:
    container_name: cvat_worker_annotation
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 1
    command: run worker.annotation
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_webhooks:
    container_name: cvat_worker_webhooks
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 1
    command: run worker.webhooks
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_quality_reports:
    container_name: cvat_worker_quality_reports
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 1
    command: run worker.quality_reports
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_analytics_reports:
    container_name: cvat_worker_analytics_reports
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: [*backend-env, *clickhouse-env]
      NUMPROCS: 2
    command: run worker.analytics_reports
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_chunks:
    container_name: cvat_worker_chunks
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 2
    command: run worker.chunks
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_worker_consensus:
    container_name: cvat_worker_consensus
    image: cvat/server:${CVAT_VERSION:-dev}
    restart: always
    depends_on: *backend-deps
    environment:
      <<: *backend-env
      NUMPROCS: 1
    command: run worker.consensus
    volumes:
      - cvat_data:/home/django/data
      - cvat_keys:/home/django/keys
      - cvat_logs:/home/django/logs
    networks:
      - cvat

  cvat_ui:
    container_name: cvat_ui
    image: cvat/ui:${CVAT_VERSION:-dev}
    restart: always
    depends_on:
      - cvat_server
    labels:
      - traefik.enable=true
      - traefik.http.services.cvat-ui.loadbalancer.server.port=80
      - traefik.http.routers.cvat-ui.rule=Host(`${CVAT_HOST:-localhost}`)
      - traefik.http.routers.cvat-ui.entrypoints=web
    networks:
      - cvat

  traefik:
    image: traefik:v2.10
    container_name: traefik
    restart: always
    ports:
      - 8080:8080
      - 8090:8090
    environment:
      CVAT_HOST: ${CVAT_HOST:-localhost}
      DJANGO_LOG_VIEWER_HOST: grafana
      DJANGO_LOG_VIEWER_PORT: 3000

      TRAEFIK_ACCESSLOG_FORMAT: json
      # We ought to restrict which fields get logged, so as to avoid redundant information,
      # but it doesn't work when configuring with environment variables:
      # <https://github.com/traefik/traefik/issues/9755>.
      # And we want to use environment variables to allow individual settings to be
      # overridden by other Compose files.
      TRAEFIK_LOG_FORMAT: json
      TRAEFIK_ENTRYPOINTS_web_ADDRESS: :8080
      TRAEFIK_PROVIDERS_DOCKER_EXPOSEDBYDEFAULT: "false"
      TRAEFIK_PROVIDERS_DOCKER_NETWORK: cvat
      TRAEFIK_PROVIDERS_FILE_DIRECTORY: /etc/traefik/rules
    # Uncomment to get Traefik dashboard
    #   TRAEFIK_API_DASHBOARD: "true"
    #   TRAEFIK_ENTRYPOINTS_dashboard_ADDRESS: :8090
    # labels:
    #   - traefik.enable=true
    #   - traefik.http.routers.dashboard.entrypoints=dashboard
    #   - traefik.http.routers.dashboard.service=api@internal
    #   - traefik.http.routers.dashboard.rule=Host(`${CVAT_HOST:-localhost}`)
    volumes:
      - /var/run/docker.sock:/var/run/docker.sock:ro
      - ./components/analytics/grafana_conf.yml:/etc/traefik/rules/grafana_conf.yml:ro
    networks:
      - cvat
    logging:
      driver: "json-file"
      options:
        max-size: 100m
        max-file: "10"

  cvat_opa:
    container_name: cvat_opa
    image: openpolicyagent/opa:0.63.0
    restart: always
    networks:
      cvat:
        aliases:
          - opa
    command:
      - run
      - --server
      - --log-level=error
      - --set=services.cvat.url=http://cvat-server:8080
      - --set=bundles.cvat.service=cvat
      - --set=bundles.cvat.resource=/api/auth/rules
      - --set=bundles.cvat.polling.min_delay_seconds=5
      - --set=bundles.cvat.polling.max_delay_seconds=15

  cvat_clickhouse:
    container_name: cvat_clickhouse
    image: clickhouse/clickhouse-server:23.11-alpine
    restart: always
    environment:
      <<: *clickhouse-env
    networks:
      cvat:
        aliases:
          - clickhouse
    volumes:
      - ./components/analytics/clickhouse/init.sh:/docker-entrypoint-initdb.d/init.sh:ro
      - cvat_events_db:/var/lib/clickhouse/

  cvat_vector:
    container_name: cvat_vector
    image: timberio/vector:0.26.0-alpine
    restart: always
    depends_on:
      - cvat_clickhouse
    environment:
      <<: *clickhouse-env
    networks:
      cvat:
        aliases:
          - vector
    volumes:
      - ./components/analytics/vector/vector.toml:/etc/vector/vector.toml:ro

  cvat_grafana:
    image: grafana/grafana-oss:10.1.2
    restart: always
    container_name: cvat_grafana
    environment:
      <<: *clickhouse-env
      GF_PATHS_PROVISIONING: /etc/grafana/provisioning
      GF_AUTH_BASIC_ENABLED: false
      GF_AUTH_ANONYMOUS_ENABLED: true
      GF_AUTH_ANONYMOUS_ORG_ROLE: Admin
      GF_AUTH_DISABLE_LOGIN_FORM: true
      GF_PLUGINS_ALLOW_LOADING_UNSIGNED_PLUGINS: grafana-clickhouse-datasource
      GF_SERVER_ROOT_URL: http://${CVAT_HOST:-localhost}/analytics
      GF_INSTALL_PLUGINS: https://github.com/grafana/clickhouse-datasource/releases/download/v4.0.8/grafana-clickhouse-datasource-4.0.8.linux_amd64.zip;grafana-clickhouse-datasource
      GF_DASHBOARDS_DEFAULT_HOME_DASHBOARD_PATH: /var/lib/grafana/dashboards/all_events.json
    volumes:
      - ./components/analytics/grafana/dashboards/:/var/lib/grafana/dashboards/:ro
    entrypoint:
      - sh
      - -euc
      - |
        mkdir -p /etc/grafana/provisioning/datasources
        cat << 'EOF' > /etc/grafana/provisioning/datasources/ds.yaml
        apiVersion: 1
        datasources:
          - name: 'ClickHouse'
            type: 'grafana-clickhouse-datasource'
            isDefault: true
            jsonData:
              defaultDatabase: $${CLICKHOUSE_DB}
              port: $${CLICKHOUSE_PORT}
              server: $${CLICKHOUSE_HOST}
              username: $${CLICKHOUSE_USER}
              tlsSkipVerify: false
              protocol: http
            secureJsonData:
              password: $${CLICKHOUSE_PASSWORD}
            editable: true
        EOF
        mkdir -p /etc/grafana/provisioning/dashboards
        cat << EOF > /etc/grafana/provisioning/dashboards/dashboard.yaml
        apiVersion: 1
        providers:
          - name: cvat-logs
            type: file
            updateIntervalSeconds: 30
            options:
              path:  /var/lib/grafana/dashboards
              foldersFromFilesStructure: true
        EOF
        exec /run.sh
    networks:
      cvat:
        aliases:
          - grafana

volumes:
  cvat_db:
  cvat_data:
  cvat_keys:
  cvat_logs:
  cvat_inmem_db:
  cvat_events_db:
  cvat_cache_db:

networks:
  cvat: