从 docker env 上的气流在 Trino 上运行查询

Question

我正在尝试构建非常简单的 DAG，就像 POC 一样，它从 Trino 表中读取一些愚蠢的内容。 这是我的 docker-compose 文件，取自 Airflow 文档 + 我为 Trino 添加的内容：

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:2.8.1}
  # build: .
  environment:
    &airflow-common-env
    AIRFLOW__CORE__EXECUTOR: CeleryExecutor
    AIRFLOW__DATABASE__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_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
    - ${AIRFLOW_PROJ_DIR:-.}/plugins:/opt/airflow/plugins
  user: "${AIRFLOW_UID:-50000}:0"
  depends_on:
    &airflow-common-depends-on
    redis:
      condition: service_healthy
    postgres:
      condition: service_healthy

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: 10s
      retries: 5
      start_period: 5s
    restart: always

  redis:
    image: redis:latest
    expose:
      - 6379
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 10s
      timeout: 30s
      retries: 50
      start_period: 30s
    restart: always

  airflow-webserver:
    <<: *airflow-common
    command: webserver
    ports:
      - "8080:8080"
    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
    healthcheck:
      # yamllint disable rule:line-length
      test:
        - "CMD-SHELL"
        - 'celery --app airflow.providers.celery.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}" || celery --app airflow.executors.celery_executor.app inspect ping -d "celery@$${HOSTNAME}"'
      interval: 30s
      timeout: 10s
      retries: 5
      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
    healthcheck:
      test: ["CMD-SHELL", 'airflow jobs check --job-type TriggererJob --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-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
        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_MIGRATE: '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

  trino:
    image: trinodb/trino
    environment:
      - QUERY_MAX_MEMORY=1GB
    ports:
      - "8081:8080"
    healthcheck:
      test: ["CMD", "curl", "--fail", "http://localhost:8081/v1/status"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: always
    depends_on:
      - postgres

volumes:
  postgres-db-volume:

服务似乎一切正常，我在 UI 中看到了其他 DAG。 不直接相关，但这是我想要运行的查询，并且它在 trino 容器内部工作：

SELECT COUNT(*) FROM tpch.sf1.nation

问题在于 DAG 的导入。 这是 DAG 的脚本：

from datetime import datetime, timedelta
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from airflow.providers.trino.transfers.sql_check import TrinoSQLValueCheckOperator
from airflow.operators.dummy_operator import DummyOperator
from airflow.providers.trino.operators.check import TrinoCheckOperator

default_args = {
    'owner': 'airflow',
    'start_date': datetime(2024, 2, 13),
    'retries': 1,
    'retry_delay': timedelta(minutes=5),
}

dag = DAG(
    'trino_example',
    default_args=default_args,
    description='A simple DAG to execute Trino queries',
    schedule_interval=timedelta(days=1),
)

start_task = DummyOperator(task_id='start', dag=dag)

# Assume you have a Trino connection named 'trino_default' in your Airflow configuration
trino_conn_id = 'trino_default'

# Execute the SQL query and store the result in XCom
query_task = TrinoSQLValueCheckOperator(
    task_id='execute_query',
    sql="SELECT COUNT(*) FROM tpch.sf1.nation",
    conn_id=trino_conn_id,
    dag=dag,
)

# Print the result
def print_result(**kwargs):
    ti = kwargs['ti']
    result = ti.xcom_pull(task_ids='execute_query')
    print(f"Query Result: {result}")

print_task = PythonOperator(
    task_id='print_result',
    python_callable=print_result,
    provide_context=True,
    dag=dag,
)

end_task = DummyOperator(task_id='end', dag=dag)

start_task >> query_task >> print_task >> end_task

这是我在用户界面中遇到的错误：

Broken DAG: [/opt/airflow/dags/example_trino_dag.py] Traceback (most recent call last):
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "/opt/airflow/dags/example_trino_dag.py", line 4, in <module>
    from airflow.providers.trino.transfers.sql_check import TrinoSQLValueCheckOperator
ModuleNotFoundError: No module named 'airflow.providers.trino.transfers.sql_check'

chatGPT 和副驾驶提出了诸如

之类的建议

docker-compose exec airflow-webserver pip install apache-airflow-providers-trino
docker-compose exec airflow-scheduler pip install apache-airflow-providers-trino
docker-compose exec airflow-worker pip install apache-airflow-providers-trino

和

from airflow.providers.trino.transfers.sql_check import TrinoSQLValueCheckOperator

还有更多类似进口的东西，其中最奇怪的是：

from datetime import datetime, timedelta
from airflow import DAG
from airflow.operators.python_operator import PythonOperator
from airflow.operators.dummy_operator import DummyOperator

try:
    # Try importing the Trino operators with the new-style import
    from airflow.providers.trino.transfers.sql_check import TrinoSQLValueCheckOperator
except ImportError:
    # Fallback to the old-style import if the new-style is not available
    from airflow.operators.trino_check_operator import TrinoCheckOperator as TrinoSQLValueCheckOperator

try:
    # Try importing the Trino operators with the new-style import
    from airflow.providers.trino.operators.check import TrinoCheckOperator
except ImportError:
    # Fallback to the old-style import if the new-style is not available
    from airflow.operators.trino_check_operator import TrinoCheckOperator

但是导入和缺少模块的错误仍然存在。

我最终想要的就是能够在 Trino 上运行最基本的查询，并将其保存到 xcom。仅供学习使用。

任何有助于理解我在这里缺少的内容的帮助。 我在这里找不到相关主题。

Answer 1

我也遇到过同样的问题。你解决了吗？