Airflow Installation

#1. venv 생성 및 가상환경 활성화

python3 -m venv ~/airflow_workspace/airflow_env

source ~/airflow_worspace/airflow_env/bin/activate

#2. airflow 홈디렉토리 설정

$AIRFLOW_HOME=~/airflow_workspace/airflow

#3. airflow 설치

pip install "apache-airflow[celery]==2.3.0" --constraint "https://raw.githubusercontent.com/apache/airflow/constraints-2.3.0/constraints-3.7.txt"

#4. DB 초기화 및 계정 생성

airflow users create --username admin --firstname ds --lastname kim --role Admin --email test@test.com --password admin

#5. Airflow Web/Scheduler 기동

airflow webserver -p 8083
airflow scheduler

#6. Airflow Dag 폴더 생성 및 테스트 파일 생성

mkdir ~/airflow_workspace/airflow/dags
cd ~/airflow_workspace/airflow/dags
vi test_dag.py

from airflow import DAG
from airflow.operators.bash_operator import BashOperator
from datetime import datetime, timedelta

default_args = {
    'owner': 'airflow',
    'depends_on_past': False,
    'start_date': datetime(2023, 2, 7),
    'email_on_failure': False,
    'email_on_retry': False,
    'retries': 1,
    'retry_delay': timedelta(minutes=5),
}

dag = DAG(
    'test_dag',
    default_args=default_args,
    description='My first Apache Airflow DAG',
    schedule_interval=timedelta(hours=1),
)

task_1 = BashOperator(
    task_id='print_hello',
    bash_command='echo "Hello, World!"',
    dag=dag,
)

task_2 = BashOperator(
    task_id='sleep',
    bash_command='sleep 5',
    dag=dag,
)

task_1 >> task_2