Airflow 2.2.6 + MySQL 8.0.27 + Redis 7.0.12 部署Airflow任务调度平台

本 docker-compose 文件在 centos7.9 系统, docker 版本为 24.0.2 上测试的

如果你的 docker 版本低于 24.xxx 就需要手动安装 docker-compose, 高于 24 就不需要安装了, docker 已经自带了
官方文档, 关于 docker 部署

1. 先执行 mkdir -p ./dags ./logs ./plugins ./config ./data/mysql/data ./data/mysql/conf
echo -e "AIRFLOW_UID=$(id -u)" > .env
2. 初始化数据库 docker compose up airflow-init
3. 启动服务docker compose up

附上修改过后的 docker-compose.yaml

version: '3.8'
x-airflow-common:
  &airflow-common
  image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.6.3}
  # build: .
  environment:
    &airflow-common-env
    # [core]
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__CORE__FERNET_KEY: ''
    AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
    AIRFLOW__CORE__LOAD_EXAMPLES: 'false'
    AIRFLOW__CORE__DEFAULT_TIMEZONE: "Asia/Shanghai "

    # [database]
    # AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
    AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: mysql+mysqldb://airflow:airflow@mysql/airflow

    # [celery]
    AIRFLOW__CELERY__RESULT_BACKEND: db+mysql://airflow:airflow@mysql/airflow # 此处替换为mysql连接方式
    AIRFLOW__CELERY__BROKER_URL: redis://:admin1234@redis:6379/0

    # [webserver]
    AIRFLOW__WEBSERVER__BROKER_URL: ""
    AIRFLOW__WEBSERVER__DEFAULT_UI_TIMEZONE: "Asia/Shanghai"
    AIRFLOW__WEBSERVER__WARN_DEPLOYMENT_EXPOSURE: False

    # [smtp]
#    smtp_host = email-smtp.amazonaws.com
#    smtp_user = AKI
#    smtp_password = BCIXc
#    smtp_port = 587
#    smtp_mail_from = cs@amazon.com

    # [api]
    AIRFLOW__API__AUTH_BACKENDS: 'airflow.api.auth.backend.basic_auth,airflow.api.auth.backend.session'
    # 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'
    # WARNING: Use _PIP_ADDITIONAL_REQUIREMENTS option ONLY for a quick checks
    # for other purpose (development, test and especially production usage) build/extend Airflow image.
    _PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
  volumes:
    - ${AIRFLOW_PROJ_DIR:-.}/dags:/opt/airflow/dags
    - ${AIRFLOW_PROJ_DIR:-.}/logs:/opt/airflow/logs
    - ${AIRFLOW_PROJ_DIR:-.}/config:/opt/airflow/config
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
#    - ./airflow.cfg:/opt/airflow/airflow.cfg
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    mysql:
      condition: service_healthy

services:
  mysql:
    image: mysql:8.0.27 # 修改为mysql最新版镜像
    environment:
      MYSQL_ROOT_PASSWORD: root  # MySQL root账号密码
      MYSQL_USER: airflow
      MYSQL_PASSWORD: airflow  # airflow用户的密码
      MYSQL_DATABASE: airflow
    # docker安全验证
    security_opt:
      - seccomp:unconfined
    command:
      - --default-authentication-plugin=mysql_native_password  # 指定默认的认证插件
#      - --collation-server=utf8_general_ci  # 依据官方指定字符集
#      - --character-set-server=utf8  # 依据官方指定字符编码
    volumes:
      - ./data/mysql/data:/var/lib/mysql # 持久化MySQL数据
      - ./data/mysql/conf/mysql.cnf:/etc/mysql.cnf # 持久化MySQL配置文件
    healthcheck:
      test: mysql --user=$$MYSQL_USER --password=$$MYSQL_PASSWORD -e 'SHOW DATABASES;'  # healthcheck command
      interval: 5s
      retries: 5
    restart: always

  redis:
    image: redis:latest
    expose:
      - 6379
    command: redis-server --requirepass admin1234 # redis-server开启密码认证
    healthcheck:
      test: [ "CMD", "redis-cli", "-a","admin1234","ping" ]
      interval: 10s
      timeout: 30s
      retries: 50
      start_period: 30s
    restart: always

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8083:8080"
    healthcheck:
      test: [ "CMD", "curl", "--fail", "http://localhost:8080/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-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-worker:
    <<: *airflow-common
    command: celery worker
    user: 'airflow'
    healthcheck:
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 1
      start_period: 30s
    environment:
      <<: *airflow-common-env
      # Required to handle warm shutdown of the celery workers properly
      # See https://airflow.apache.org/docs/docker-stack/entrypoint.html#signal-propagation
      DUMB_INIT_SETSID: "0"
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  airflow-triggerer:
    <<: *airflow-common
    command: triggerer
    user: 'airflow'
    healthcheck:
      test: [ "CMD-SHELL", 'airflow jobs check --job-type TriggererJob --hostname "$${HOSTNAME}"' ]
      interval: 30s
      timeout: 10s
      retries: 1
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

  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/howto/docker-compose/index.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/howto/docker-compose/index.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:
      - ${AIRFLOW_PROJ_DIR:-.}:/sources

  airflow-cli:
    <<: *airflow-common
    profiles:
      - debug
    environment:
      <<: *airflow-common-env
      CONNECTION_CHECK_MAX_COUNT: "0"
    # Workaround for entrypoint issue. See: https://github.com/apache/airflow/issues/16252
    command:
      - bash
      - -c
      - airflow

  # You can enable flower by adding "--profile flower" option e.g. docker-compose --profile flower up
  # or by explicitly targeted on the command line e.g. docker-compose up flower.
  # See: https://docs.docker.com/compose/profiles/
  flower:
    <<: *airflow-common
    command: celery flower
    profiles:
      - flower
    ports:
      - "5555:5555"
    healthcheck:
      test: [ "CMD", "curl", "--fail", "http://localhost:5555/" ]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      <<: *airflow-common-depends-on
      airflow-init:
        condition: service_completed_successfully

volumes:
  postgres-db-volume: