emr_eks_job

This is an example dag for an Amazon EMR on EKS Spark job.


Providers:

Run this DAG

1. Install the Astronomer CLI:Skip if you already have the CLI

2. Initate the project in a local directory:

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 from the local directory where the project was initiated:

# 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 an Amazon EMR on EKS Spark job.
"""
import os
from datetime import timedelta
from airflow import DAG
from airflow.providers.amazon.aws.operators.emr_containers import EMRContainerOperator
from airflow.utils.dates import days_ago
# [START howto_operator_emr_eks_env_variables]
VIRTUAL_CLUSTER_ID = os.getenv("VIRTUAL_CLUSTER_ID", "test-cluster")
JOB_ROLE_ARN = os.getenv("JOB_ROLE_ARN", "arn:aws:iam::012345678912:role/emr_eks_default_role")
# [END howto_operator_emr_eks_env_variables]
# [START howto_operator_emr_eks_config]
JOB_DRIVER_ARG = {
"sparkSubmitJobDriver": {
"entryPoint": "local:///usr/lib/spark/examples/src/main/python/pi.py",
"sparkSubmitParameters": "--conf spark.executors.instances=2 --conf spark.executors.memory=2G --conf spark.executor.cores=2 --conf spark.driver.cores=1", # noqa: E501
}
}
CONFIGURATION_OVERRIDES_ARG = {
"applicationConfiguration": [
{
"classification": "spark-defaults",
"properties": {
"spark.hadoop.hive.metastore.client.factory.class": "com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory", # noqa: E501
},
}
],
"monitoringConfiguration": {
"cloudWatchMonitoringConfiguration": {
"logGroupName": "/aws/emr-eks-spark",
"logStreamNamePrefix": "airflow",
}
},
}
# [END howto_operator_emr_eks_config]
with DAG(
dag_id='emr_eks_pi_job',
dagrun_timeout=timedelta(hours=2),
start_date=days_ago(1),
schedule_interval="@once",
tags=["emr_containers", "example"],
) as dag:
# An example of how to get the cluster id and arn from an Airflow connection
# VIRTUAL_CLUSTER_ID = '{{ conn.emr_eks.extra_dejson["virtual_cluster_id"] }}'
# JOB_ROLE_ARN = '{{ conn.emr_eks.extra_dejson["job_role_arn"] }}'
# [START howto_operator_emr_eks_jobrun]
job_starter = EMRContainerOperator(
task_id="start_job",
virtual_cluster_id=VIRTUAL_CLUSTER_ID,
execution_role_arn=JOB_ROLE_ARN,
release_label="emr-6.3.0-latest",
job_driver=JOB_DRIVER_ARG,
configuration_overrides=CONFIGURATION_OVERRIDES_ARG,
name="pi.py",
)
# [END howto_operator_emr_eks_jobrun]