# 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:latest-python3.11
# AIRFLOW_UID - User ID in Airflow containers
# Default: 50000
# AIRFLOW_PROJ_DIR - Base path to which all the files will be volumed.
# Default: .
# Those configurations are useful mostly in case of standalone testing/running Airflow in test/try-out mode
#
# _AIRFLOW_WWW_USER_USERNAME - Username for the administrator account (if requested).
# Default: airflow
# _AIRFLOW_WWW_USER_PASSWORD - Password for the administrator account (if requested).
# Default: airflow
# _PIP_ADDITIONAL_REQUIREMENTS - Additional PIP requirements to add when starting all containers.
# Use this option ONLY for quick checks. Installing requirements at container
# startup is done EVERY TIME the service is started.
# A better way is to build a custom image or extend the official image
# as described in https://airflow.apache.org/docs/docker-stack/build.html.
# Default: ''
#
# Feel free to modify this file to suit your needs.
---
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.
# AIRFLOW__DATABASE__SQL_ALCHEMY_CONN: postgresql+psycopg2://airflow:airflow@postgres/airflow
# mysql+pymysql://airflow:airflow123456@127.0.0.1:3306/airflow?use_unicode=true&charset=utf8
# AIRFLOW__CELERY__BROKER_URL: redis://:@redis:6379/0
# AIRFLOW__CORE__EXECUTOR: SequentialExecutor
# AIRFLOW__CELERY__RESULT_BACKEND: db+postgresql://airflow:airflow@postgres/airflow
image: ${AIRFLOW_IMAGE_NAME:-apache/airflow:latest-python3.11}
# 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://:@127.0.0.1:6379/0
AIRFLOW__CORE__FERNET_KEY: ''
AIRFLOW__CORE__DAGS_ARE_PAUSED_AT_CREATION: 'true'
AIRFLOW__CORE__LOAD_EXAMPLES: 'true'
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.
# /usr/local/lib/python3.11/site-packages
_PIP_ADDITIONAL_REQUIREMENTS: ${_PIP_ADDITIONAL_REQUIREMENTS:-}
volumes:
- /data/docker-data/airflow/dags:/opt/airflow/dags
- /data/docker-data/airflow/logs:/opt/airflow/logs
- /data/docker-data/airflow/conf:/opt/airflow/config
- /data/docker-data/airflow/plugins:/opt/airflow/plugins
# - /data/soft/python3.11/lib/python3.11/site-packages:/home/airflow/.local/lib/python3.11/site-packages
user: "${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
ports:
- "5432:5432"
volumes:
- /data/docker-data/airflow/data:/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
# privileged: true
# ports:
# - 6379:6379
# environment:
# TZ: Asia/Shanghai
# volumes:
# - /data/docker-data/redis/data:/data
# - /data/docker-data/redis/conf/redis.conf:/usr/local/redis/conf/redis.conf
# - /data/docker-data/redis/logs:/logs
# # command: ["redis-server","/usr/local/redis/conf/redis.conf"]
# command: /bin/sh -c "echo 'vm.overcommit_memory = 1' >> /etc/sysctl.conf && redis-server /usr/local/redis/conf/redis.conf "
airflow-webserver:
<<: *airflow-common
command: webserver
ports:
- "9999:8080"
healthcheck:
test: ["CMD", "curl", "--fail", "http://127.0.0.1:9999/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
ports:
- "9974:8974"
healthcheck:
test: ["CMD", "curl", "--fail", "http://127.0.0.1:9974/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:
- /data/docker-data/airflow:/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:
- "9955:5555"
healthcheck:
test: ["CMD", "curl", "--fail", "http://127.0.0.1:9955/"]
interval: 30s
timeout: 10s
retries: 5
start_period: 30s
restart: always
depends_on:
<<: *airflow-common-depends-on
airflow-init:
condition: service_completed_successfully
## 方式1----本地安装:
### airflow
# yum install postgresql-devel
# yum install -y gcc make libffi-devel zlib*
#pip3.11 install connexion[swagger-ui]
#pip3.11 install psycopg2 virtualenv kubernetes pandas
#pip3.11 install mysqlclient -i https://pypi.tuna.tsinghua.edu.cn/simple
#pip3.11 install apache-airflow initdb
#
### kill掉之前的线程
#ps -aux | grep airflow | awk -F' ' '{ print $2 }' | xargs kill -9
#ps -aux | grep gunicorn | awk -F' ' '{ print $2 }' | xargs kill -9
#
### airflow的前端页面入口
#http://127.0.0.1:9090
#Login with username: admin password: 4tGWQnctusgf9vHW
####################针对已经有历史数据重置的场景##########################
# airflow db reset
# airflow db init
# airflow webserver -D
# airflow scheduler -D # nohup airflow scheduler >>airflow-scheduler.log 2>& 1 &
# airflow users create --role Admin --username airflow --email admin --firstname admin --lastname admin --password airflow
# 通过命令查看并修改dags的目录:cat airflow.cfg | grep dags_folder
# python脚本编写的DAG只有放在该目录下才能够在web界面正常显示
# 方式2----docker-compose安装: 如果启动不成功,可能需要清除目录/data/docker-data/airflow/data下的数据
# docker-compose -f docker_compose_airflow.yml down
# http://127.0.0.1:9999
#
## 守护进程运行webserver
#$ airflow webserver -D
#
## 守护进程运行调度器
#$ airflow scheduler -D
#
## 守护进程运行调度器
#$ airflow worker -D
#
## 守护进程运行celery worker并指定任务并发数为1
#$ airflow worker -c 1 -D
#
## 暂停任务
#$ airflow pause $dag_id
#
## 取消暂停,等同于在管理界面打开off按钮
#$ airflow unpause $dag_id
#
## 查看task列表
#$ airflow list_tasks $dag_id
#
## 清空任务实例
#$ airflow clear $dag_id
#
## 运行整个dag文件
#$ airflow trigger_dag $dag_id -r $RUN_ID -e $EXEC_DATE
#
## 运行task
#$ airflow run $dag_id $task_id $execution_date
docker-compose之airflow搭建
最新推荐文章于 2025-03-14 11:00:00 发布