dags/emr_job/1.10/emr_job.py [30:114]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
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,
}

JOB_FLOW_OVERRIDES = {
    'Name': 'my-demo-cluster',
    'ReleaseLabel': 'emr-5.30.1',
    'Applications': [
        {
            'Name': 'Spark'
        },
    ],    
    'Instances': {
        'InstanceGroups': [
            {
                'Name': "Master nodes",
                'Market': 'ON_DEMAND',
                'InstanceRole': 'MASTER',
                'InstanceType': 'm5.xlarge',
                'InstanceCount': 1,
            },
            {
                'Name': "Slave nodes",
                'Market': 'ON_DEMAND',
                'InstanceRole': 'CORE',
                'InstanceType': 'm5.xlarge',
                'InstanceCount': 2,
            }
        ],
        'KeepJobFlowAliveWhenNoSteps': False,
        'TerminationProtected': False,
        'Ec2KeyName': 'DemoKeyPair',
    },
    'VisibleToAllUsers': True,
    'JobFlowRole': 'EMR_EC2_DefaultRole',
    'ServiceRole': 'EMR_DefaultRole'
}

SPARK_STEPS = [
    {
        'Name': 'calculate_pi',
        'ActionOnFailure': 'CONTINUE',
        'HadoopJarStep': {
            'Jar': 'command-runner.jar',
            'Args': ['/usr/lib/spark/bin/run-example', 'SparkPi', '10'],
        },
    }
]

with DAG(
    dag_id=DAG_ID,
    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', 
        emr_conn_id='aws_default', 
        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 
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



dags/emr_job/2.0/emr_job.py [28:112]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
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,
}

JOB_FLOW_OVERRIDES = {
    'Name': 'my-demo-cluster',
    'ReleaseLabel': 'emr-5.30.1',
    'Applications': [
        {
            'Name': 'Spark'
        },
    ],    
    'Instances': {
        'InstanceGroups': [
            {
                'Name': "Master nodes",
                'Market': 'ON_DEMAND',
                'InstanceRole': 'MASTER',
                'InstanceType': 'm5.xlarge',
                'InstanceCount': 1,
            },
            {
                'Name': "Slave nodes",
                'Market': 'ON_DEMAND',
                'InstanceRole': 'CORE',
                'InstanceType': 'm5.xlarge',
                'InstanceCount': 2,
            }
        ],
        'KeepJobFlowAliveWhenNoSteps': False,
        'TerminationProtected': False,
        'Ec2KeyName': 'DemoKeyPair',
    },
    'VisibleToAllUsers': True,
    'JobFlowRole': 'EMR_EC2_DefaultRole',
    'ServiceRole': 'EMR_DefaultRole'
}

SPARK_STEPS = [
    {
        'Name': 'calculate_pi',
        'ActionOnFailure': 'CONTINUE',
        'HadoopJarStep': {
            'Jar': 'command-runner.jar',
            'Args': ['/usr/lib/spark/bin/run-example', 'SparkPi', '10'],
        },
    }
]

with DAG(
    dag_id=DAG_ID,
    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', 
        emr_conn_id='aws_default', 
        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 
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -