Source code for airflow.providers.amazon.aws.example_dags.example_emr_job_flow_automatic_steps
#
# 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.
"""
This is an example dag for a AWS EMR Pipeline with auto steps.
"""
from datetime import timedelta
from airflow import DAG
from airflow.providers.amazon.aws.operators.emr_create_job_flow import EmrCreateJobFlowOperator
from airflow.providers.amazon.aws.sensors.emr_job_flow import EmrJobFlowSensor
from airflow.utils.dates import days_ago
# [START howto_operator_emr_automatic_steps_config]
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': 'PiCalc',
'ReleaseLabel': 'emr-5.29.0',
'Applications': [{'Name': 'Spark'}],
'Instances': {
'InstanceGroups': [
{
'Name': 'Primary node',
'Market': 'SPOT',
'InstanceRole': 'MASTER',
'InstanceType': 'm1.medium',
'InstanceCount': 1,
}
],
'KeepJobFlowAliveWhenNoSteps': False,
'TerminationProtected': False,
},
'Steps': SPARK_STEPS,
'JobFlowRole': 'EMR_EC2_DefaultRole',
'ServiceRole': 'EMR_DefaultRole',
}
# [END howto_operator_emr_automatic_steps_config]
with DAG(
dag_id='emr_job_flow_automatic_steps_dag',
default_args={
'owner': 'airflow',
'depends_on_past': False,
'email': ['airflow@example.com'],
'email_on_failure': False,
'email_on_retry': False,
},
dagrun_timeout=timedelta(hours=2),
start_date=days_ago(2),
schedule_interval='0 3 * * *',
tags=['example'],
) as dag:
# [START howto_operator_emr_automatic_steps_tasks]
job_flow_creator = EmrCreateJobFlowOperator(
task_id='create_job_flow',
job_flow_overrides=JOB_FLOW_OVERRIDES,
aws_conn_id='aws_default',
emr_conn_id='emr_default',
)
job_sensor = EmrJobFlowSensor(
task_id='check_job_flow',
job_flow_id=job_flow_creator.output,
aws_conn_id='aws_default',
)
# [END howto_operator_emr_automatic_steps_tasks]
# Task dependency created via `XComArgs`:
# job_flow_creator >> job_sensor