데이터 엔지니어 이것저것

Docker-compose Airflow ( version 2.0) 본문

오픈소스/airflow

Docker-compose Airflow ( version 2.0)

pastime 2021. 5. 10. 21:45
728x90

Airflow 2.0 버전이 나왔다.

시간날때마다 조금씩 커스터 마이징 하자. ( 특히 image 가져올때 원하는 docker image로 바꾸기)
-> docker baseimage를 airflow 2.0.2? 그런걸로 세팅하면 됨

# Licensed to the Apache Software Foundation (ASF) under one
# or more contributor license agreements.  See the NOTICE file
# distributed with this work for additional information
# regarding copyright ownership.  The ASF licenses this file
# to you under the Apache License, Version 2.0 (the
# "License"); you may not use this file except in compliance
# with the License.  You may obtain a copy of the License at
#
#   http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing,
# software distributed under the License is distributed on an
# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
# KIND, either express or implied.  See the License for the
# specific language governing permissions and limitations
# under the License.
#

# Basic Airflow cluster configuration for CeleryExecutor with Redis and PostgreSQL.
#
# WARNING: This configuration is for local development. Do not use it in a production deployment.
#
# This configuration supports basic configuration using environment variables or an .env file
# The following variables are supported:
#
# AIRFLOW_IMAGE_NAME         - Docker image name used to run Airflow.
#                              Default: apache/airflow:master-python3.8
# AIRFLOW_UID                - User ID in Airflow containers
#                              Default: 50000
# AIRFLOW_GID                - Group ID in Airflow containers
#                              Default: 50000
# _AIRFLOW_WWW_USER_USERNAME - Username for the administrator account.
#                              Default: airflow
# _AIRFLOW_WWW_USER_PASSWORD - Password for the administrator account.
#                              Default: airflow
#
# Feel free to modify this file to suit your needs.
---
    version: '3'
    x-airflow-common:
      &airflow-common
      image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:2.0.2}
      environment:
        &airflow-common-env
        AIRFLOW__CORE__EXECUTOR: CeleryExecutor
        AIRFLOW__CORE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
        AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
        AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
        AIRFLOW__CORE__FERNET_KEY: ''
        AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
        AIRFLOW__CORE__LOAD_EXAMPLES: 'true'
        AIRFLOW__API__AUTH_BACKEND: 'airflow.api.auth.backend.basic_auth'
      volumes:
        - ./dags:/opt/airflow/dags
        - ./logs:/opt/airflow/logs
        - ./plugins:/opt/airflow/plugins
      user: "${AIRFLOW_UID:-50000}:${AIRFLOW_GID:-50000}"
      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: 5s
          retries: 5
        restart: always
    
      redis:
        image: redis:latest
        ports:
          - 6379:6379
        healthcheck:
          test: ["CMD", "redis-cli", "ping"]
          interval: 5s
          timeout: 30s
          retries: 50
        restart: always
    
      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
        restart: always
    
      airflow-worker:
        <<: *airflow-common
        command: celery worker
        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
    
    volumes:
      postgres-db-volume:
728x90

'오픈소스 > airflow' 카테고리의 다른 글

airflow vs argo  (0) 2021.12.27
왜 airflow를 사용할까  (0) 2021.07.27
airflow helm install  (0) 2021.05.17
Airflow  (0) 2021.05.09
airflow chart  (0) 2020.12.23