Last active
April 29, 2021 14:08
-
-
Save garystafford/a970ceb0a5d654728aa3b5e5a62eb265 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
from datetime import timedelta | |
from airflow import DAG | |
from airflow.contrib.operators.emr_add_steps_operator import EmrAddStepsOperator | |
from airflow.contrib.operators.emr_create_job_flow_operator import EmrCreateJobFlowOperator | |
from airflow.contrib.sensors.emr_step_sensor import EmrStepSensor | |
from airflow.utils.dates import days_ago | |
DAG_ID = os.path.basename(__file__).replace('.py', '') | |
DEFAULT_ARGS = { | |
'owner': 'airflow', | |
'depends_on_past': False, | |
'email': ['airflow@example.com'], | |
'email_on_failure': False, | |
'email_on_retry': False, | |
} | |
SPARK_STEPS = [ | |
{ | |
'Name': 'calculate_pi', | |
'ActionOnFailure': 'CONTINUE', | |
'HadoopJarStep': { | |
'Jar': 'command-runner.jar', | |
'Args': ['/usr/lib/spark/bin/run-example', 'SparkPi', '10'], | |
}, | |
} | |
] | |
JOB_FLOW_OVERRIDES = { | |
'Name': 'demo-cluster-airflow', | |
'ReleaseLabel': 'emr-6.2.0', | |
'Applications': [ | |
{ | |
'Name': 'Spark' | |
}, | |
], | |
'Instances': { | |
'InstanceGroups': [ | |
{ | |
'Name': 'Master nodes', | |
'Market': 'ON_DEMAND', | |
'InstanceRole': 'MASTER', | |
'InstanceType': 'm5.xlarge', | |
'InstanceCount': 1, | |
} | |
], | |
'KeepJobFlowAliveWhenNoSteps': False, | |
'TerminationProtected': False, | |
}, | |
'VisibleToAllUsers': True, | |
'JobFlowRole': 'EMR_EC2_DefaultRole', | |
'ServiceRole': 'EMR_DefaultRole', | |
'Tags': [ | |
{ | |
'Key': 'Environment', | |
'Value': 'Development' | |
}, | |
{ | |
'Key': 'Name', | |
'Value': 'Airflow EMR Demo Project' | |
}, | |
{ | |
'Key': 'Owner', | |
'Value': 'Data Analytics Team' | |
} | |
] | |
} | |
with DAG( | |
dag_id=DAG_ID, | |
description='Run built-in Spark app on Amazon EMR', | |
default_args=DEFAULT_ARGS, | |
dagrun_timeout=timedelta(hours=2), | |
start_date=days_ago(1), | |
schedule_interval='@once', | |
tags=['emr'], | |
) as dag: | |
cluster_creator = EmrCreateJobFlowOperator( | |
task_id='create_job_flow', | |
job_flow_overrides=JOB_FLOW_OVERRIDES | |
) | |
step_adder = EmrAddStepsOperator( | |
task_id='add_steps', | |
job_flow_id="{{ task_instance.xcom_pull(task_ids='create_job_flow', key='return_value') }}", | |
aws_conn_id='aws_default', | |
steps=SPARK_STEPS, | |
) | |
step_checker = EmrStepSensor( | |
task_id='watch_step', | |
job_flow_id="{{ task_instance.xcom_pull('create_job_flow', key='return_value') }}", | |
step_id="{{ task_instance.xcom_pull(task_ids='add_steps', key='return_value')[0] }}", | |
aws_conn_id='aws_default', | |
) | |
cluster_creator >> step_adder >> step_checker |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment