docker-compose.yaml

---
x-airflow-common:
  &airflow-common
  # In order to add custom dependencies or upgrade provider packages you can use your extended image.
  # Comment the image line, place your Dockerfile in the directory where you placed the docker-compose.yaml
  # and uncomment the "build" line below, Then run `docker-compose build` to build the images.
  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.10.5}
  # build: .
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: LocalExecutor
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://${_AIRFLOW_POSTGRES_USER}:${_AIRFLOW_POSTGRES_PASSWORD}@postgres/${_AIRFLOW_POSTGRES_DB}
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__CORE__AUTH_MANAGER: airflow.providers.fab.auth_manager.fab_auth_manager.FabAuthManager
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__EXECUTION_API_SERVER_URL: 'http://airflow-apiserver:8080/execution/'
    AIRFLOW_CONFIG: '/opt/airflow/config/airflow.cfg'
    _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_USER:-airflow}
    _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_PASSWORD:-airflow}
    # yamllint disable rule:line-length
    # Use simple http server on scheduler for health checks
    # See https://airflow.apache.org/docs/apache-airflow/stable/administration-and-deployment/logging-monitoring/check-health.html#scheduler-health-check-server
    # yamllint enable rule:line-length
    AIRFLOW__SCHEDULER__ENABLE_HEALTH_CHECK: 'true'
    WORKSPACE_DIR: ${WORKSPACE_DIR}
    DATA_DIR: ${DATA_DIR}
    INPUT_DATA_DIR: ${INPUT_DATA_DIR}
    AIRFLOW_INPUT_DATA_DIR: /input_data
    AIRFLOW_DATA_DIR: /data
    AIRFLOW_WORKSPACE_DIR: /workspace
    PYTHONPATH: /opt/airflow/dags/:/opt/airflow/dags/user:/yaml_dags
    CONTAINER_TYPE: ${CONTAINER_TYPE:-'docker'}

  volumes:
    - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs
    - ${AIRFLOW_PROJ_DIR:-.}/config:/opt/airflow/config
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
    - ${YAML_DAGS_DIR:-./dags_from_yaml}:/yaml_dags
    - ${WORKSPACE_DIR:-/.workspace}:/workspace
    - ${INPUT_DATA_DIR:-./input_data}:/input_data
    - ${DATA_DIR:-./workspace/data}:/data
    - /var/run/docker.sock:/var/run/docker.sock:rw
    
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    postgres:
      condition: service_healthy

services:
  postgres:
    image: postgres:13
    environment:
      POSTGRES_USER: ${_AIRFLOW_POSTGRES_USER}
      POSTGRES_PASSWORD: ${_AIRFLOW_POSTGRES_PASSWORD}
      POSTGRES_DB: ${_AIRFLOW_POSTGRES_DB}
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "${_AIRFLOW_POSTGRES_USER}", "-d", "${_AIRFLOW_POSTGRES_DB}"]
      interval: 10s
      retries: 5
      start_period: 5s
    restart: always

  airflow-apiserver:
    <<: *airflow-common
    command: api-server
    ports:
      - "8080:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/api/v2/version"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 60s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8974/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-dag-processor:
    <<: *airflow-common
    environment:
      <<: *airflow-common-env
      IS_DAG_PROCESSOR: true
    command: dag-processor
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type DagProcessorJob --hostname "$${HOSTNAME}"']
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully
      airflow-apiserver:
        condition: service_healthy

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    # yamllint disable rule:line-length
    command:
      - -c
      - |
        if [[ -z "${AIRFLOW_UID}" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: AIRFLOW_UID not set!\e[0m"
          echo "If you are on Linux, you SHOULD follow the instructions below to set "
          echo "AIRFLOW_UID environment variable, otherwise files will be owned by root."
          echo "For other operating systems you can get rid of the warning with manually created .env file:"
          echo "    See: https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#setting-the-right-airflow-user"
          echo
          export AIRFLOW_UID=$(id -u)
        fi
        one_meg=1048576
        mem_available=$$(($$(getconf _PHYS_PAGES) * $$(getconf PAGE_SIZE) / one_meg))
        cpus_available=$$(grep -cE 'cpu[0-9]+' /proc/stat)
        disk_available=$$(df / | tail -1 | awk '{print $$4}')
        warning_resources="false"
        if (( mem_available < 4000 )) ; then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough memory available for Docker.\e[0m"
          echo "At least 4GB of memory required. You have $$(numfmt --to iec $$((mem_available * one_meg)))"
          echo
          warning_resources="true"
        fi
        if (( cpus_available < 2 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough CPUS available for Docker.\e[0m"
          echo "At least 2 CPUs recommended. You have $${cpus_available}"
          echo
          warning_resources="true"
        fi
        if (( disk_available < one_meg * 10 )); then
          echo
          echo -e "\033[1;33mWARNING!!!: Not enough Disk space available for Docker.\e[0m"
          echo "At least 10 GBs recommended. You have $$(numfmt --to iec $$((disk_available * 1024 )))"
          echo
          warning_resources="true"
        fi
        if [[ $${warning_resources} == "true" ]]; then
          echo
          echo -e "\033[1;33mWARNING!!!: You have not enough resources to run Airflow (see above)!\e[0m"
          echo "Please follow the instructions to increase amount of resources available:"
          echo "   https://airflow.apache.org/docs/apache-airflow/stable/howto/docker-compose/index.html#before-you-begin"
          echo
        fi
        echo
        echo "Creating missing opt dirs if missing:"
        echo
        mkdir -v -p /opt/airflow/{logs,dags,plugins,config}
        echo
        echo "Airflow version:"
        /entrypoint airflow version
        echo
        echo "Files in shared volumes:"
        echo
        ls -la /opt/airflow/{logs,dags,plugins,config}
        echo
        echo "Running airflow config list to create default config file if missing."
        echo
        /entrypoint airflow config list >/dev/null
        echo
        echo "Files in shared volumes:"
        echo
        ls -la /opt/airflow/{logs,dags,plugins,config}
        echo
        echo "Change ownership of files in /opt/airflow to ${AIRFLOW_UID}:0"
        echo
        chown -R "${AIRFLOW_UID}:0" /opt/airflow/
        echo
        echo "Change ownership of files in shared volumes to ${AIRFLOW_UID}:0"
        echo
        chown -v -R "${AIRFLOW_UID}:0" /opt/airflow/{logs,dags,plugins,config}
        echo
        echo "Files in shared volumes:"
        echo
        ls -la /opt/airflow/{logs,dags,plugins,config}

    # yamllint enable rule:line-length
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_MIGRATE: 'true'
      _AIRFLOW_WWW_USER_CREATE: 'true'
      _PIP_ADDITIONAL_REQUIREMENTS: ''
    user: "0:0"
    volumes:
      - ${AIRFLOW_PROJ_DIR:-.}:/sources

volumes:
  postgres-db-volume: