emr_job_flow_manual_steps

This is an example dag for a AWS EMR Pipeline.

Big Data & Analytics


Providers:

Run this DAG

1. Install Astronomer CLISkip if you already have the CLI

2. Initate the project:

3. Copy and paste the code below into a file in the

dags
directory.

4. Add the following to your requirements.txt file:

5. Run the DAG:

#
# 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.
Starting by creating a cluster, adding steps/operations, checking steps and finally when finished
terminating the cluster.
"""
from datetime import timedelta
from airflow import DAG
from airflow.providers.amazon.aws.operators.emr_add_steps import EmrAddStepsOperator
from airflow.providers.amazon.aws.operators.emr_create_job_flow import EmrCreateJobFlowOperator
from airflow.providers.amazon.aws.operators.emr_terminate_job_flow import EmrTerminateJobFlowOperator
from airflow.providers.amazon.aws.sensors.emr_step import EmrStepSensor
from airflow.utils.dates import days_ago
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': 'PiCalc',
'ReleaseLabel': 'emr-5.29.0',
'Instances': {
'InstanceGroups': [
{
'Name': 'Master node',
'Market': 'SPOT',
'InstanceRole': 'MASTER',
'InstanceType': 'm1.medium',
'InstanceCount': 1,
}
],
'KeepJobFlowAliveWhenNoSteps': True,
'TerminationProtected': False,
},
'JobFlowRole': 'EMR_EC2_DefaultRole',
'ServiceRole': 'EMR_DefaultRole',
}
with DAG(
dag_id='emr_job_flow_manual_steps_dag',
default_args=DEFAULT_ARGS,
dagrun_timeout=timedelta(hours=2),
start_date=days_ago(2),
schedule_interval='0 3 * * *',
tags=['example'],
) as dag:
# [START howto_operator_emr_manual_steps_tasks]
cluster_creator = EmrCreateJobFlowOperator(
task_id='create_job_flow',
job_flow_overrides=JOB_FLOW_OVERRIDES,
aws_conn_id='aws_default',
emr_conn_id='emr_default',
)
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_remover = EmrTerminateJobFlowOperator(
task_id='remove_cluster',
job_flow_id="{{ task_instance.xcom_pull(task_ids='create_job_flow', key='return_value') }}",
aws_conn_id='aws_default',
)
cluster_creator >> step_adder >> step_checker >> cluster_remover
# [END howto_operator_emr_manual_steps_tasks]