airflow-docker-compose.yaml

version: '3'
x-airflow-common:
  &airflow-common
  build:
    context: .
    dockerfile: airflow-dockerfile
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
    AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__API__AUTH_BACKEND: 'airflow.api.auth.backend.basic_auth'
    # Scan for DAGs every 60 seconds
    AIRFLOW__SCHEDULER__DAG_DIR_LIST_INTERVAL: '60'
    AIRFLOW__WEBSERVER__SECRET_KEY: '3d6f45a5fc12445dbac2f59c3b6c7cb1'
    # Prevent airflow from reloading the dags all the time and set:
    AIRFLOW__SCHEDULER__MIN_FILE_PROCESS_INTERVAL: '60'
    # 2 * NUM_CPU_CORES + 1
    AIRFLOW__WEBSERVER__WORKERS: '2'
    # Kill workers if they don't start within 5min instead of 2min
    AIRFLOW__WEBSERVER__WEB_SERVER_WORKER_TIMEOUT: '300'
    AIRFLOW_CONN_POSTGRES_TWEETS: postgresql+psycopg2://postgres:postgres@database/tweets

  volumes:
    - ./dags:/opt/airflow/dags
    - ./logs:/opt/airflow/logs
    - ./plugins:/opt/airflow/plugins

  env_file:
    - ./.env
  user: "${AIRFLOW_UID:-50000}:${AIRFLOW_GID:-50000}"
  mem_limit: 4000m
  depends_on:
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy
  networks:
    - etl_network

services:
  postgres:
    image: postgres:13
    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
    networks:
      - etl_network

  redis:
    image: redis:latest
    ports:
      - 6379:6379
    healthcheck:
      test: [ "CMD", "redis-cli", "ping" ]
      interval: 5s
      timeout: 30s
      retries: 50
    restart: always
    mem_limit: 4000m
    networks:
      - etl_network

  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

  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

  airflow-worker:
    <<: *airflow-common
    command: celery worker
    healthcheck:
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.executors.celery_executor.app inspect ping -d
          "celery@$${HOSTNAME}"'
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always

  airflow-init:
    <<: *airflow-common
    command: version
    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}

  flower:
    <<: *airflow-common
    command: celery flower
    ports:
      - 5555:5555
    healthcheck:
      test: [ "CMD", "curl", "--fail", "http://localhost:5555/" ]
      interval: 10s
      timeout: 10s
      retries: 5
    restart: always
    mem_limit: 4000m

volumes:
  postgres-db-volume: null

# Create a custom network for bridging the containers
networks:
  etl_network: null