Docker Compose Airflow

docker-compose-airflow.yaml

version: "3"
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: trading-airflow #${AIRFLOW_IMAGE_NAME:-apache/airflow}
  # build: .
  environment: &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: LocalExecutor
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    # For backward compatibility, with Airflow <2.3
    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CORE__FERNET_KEY: ""
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: "true"
    AIRFLOW__CORE__LOAD_EXAMPLES: "false" # Uncomment to see some tutorials and examples
    AIRFLOW__API__AUTH_BACKENDS: "airflow.api.auth.backend.session"
    AIRFLOW__SECRETS__BACKEND: airflow.secrets.local_filesystem.LocalFilesystemBackend
    AIRFLOW__SECRETS__BACKEND_KWARGS: '{"variables_file_path": "/opt/secrets/variables.yaml", "connections_file_path": "/opt/secrets/connections.yaml"}'
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:- apache-airflow-providers-apache-spark}
  volumes:
    - ${AIRFLOW_DAGS}:/opt/airflow/dags
    - ${AIRFLOW_LOGS}:/opt/airflow/logs
    - ./trading_data_pipeline/:/opt/airflow/trading_data_pipeline
  networks:
    - airflow-spark-network
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on: &airflow-common-depends-on
    postgres:
      condition: service_healthy

services:
  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - 8080:8080
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8080/health"]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-scheduler:
    <<: *airflow-common
    command: scheduler
    healthcheck:
      test:
        [
          "CMD-SHELL",
          'airflow jobs check --job-type SchedulerJob --hostname "$${HOSTNAME}"',
        ]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  postgres:
    image: postgres:13
    networks:
      - airflow-spark-network
    environment:
      POSTGRES_USER: airflow
      POSTGRES_PASSWORD: airflow
      POSTGRES_DB: airflow
    volumes:
      - postgres-db-volume:/var/lib/postgresql/data
    healthcheck:
      test: ["CMD", "pg_isready", "-U", "airflow"]
      interval: 5s
      retries: 5
    restart: always

  airflow-init:
    <<: *airflow-common
    entrypoint: /bin/bash
    # yamllint disable rule:line-length
    command:
      - -c
      - |
        function ver() {
          printf "%04d%04d%04d%04d" $${1//./ }
        }
        airflow_version=$$(AIRFLOW__LOGGING__LOGGING_LEVEL=INFO && gosu airflow airflow version)
        airflow_version_comparable=$$(ver $${airflow_version})
        min_airflow_version=2.2.0
        min_airflow_version_comparable=$$(ver $${min_airflow_version})
        if (( airflow_version_comparable < min_airflow_version_comparable )); then
          echo
          echo -e "\033[1;31mERROR!!!: Too old Airflow version $${airflow_version}!\e[0m"
          echo "The minimum Airflow version supported: $${min_airflow_version}. Only use this or higher!"
          echo
          exit 1
        fi
        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/start/docker.html#setting-the-right-airflow-user"
          echo
        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/start/docker.html#before-you-begin"
          echo
        fi
        mkdir -p /sources/logs /sources/dags /sources/plugins
        chown -R "${AIRFLOW_UID}:0" /sources/{logs,dags,plugins}
        exec /entrypoint airflow version
    # yamllint enable rule:line-length
    environment:
      <<: *airflow-common-env
      _AIRFLOW_DB_UPGRADE: "true"
      _AIRFLOW_WWW_USER_CREATE: "true"
      _AIRFLOW_WWW_USER_USERNAME: ${_AIRFLOW_WWW_USER_USERNAME:-airflow}
      _AIRFLOW_WWW_USER_PASSWORD: ${_AIRFLOW_WWW_USER_PASSWORD:-airflow}
      _PIP_ADDITIONAL_REQUIREMENTS: ""
    user: "0:0"
    volumes:
      - .:/sources

networks:
  airflow-spark-network:
    external: true

volumes:
  postgres-db-volume: