Source code for tests.system.providers.google.cloud.dataproc.example_dataproc_spark_async

#
# 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.
"""
Example Airflow DAG for DataprocSubmitJobOperator with async spark job.
"""

from __future__ import annotations

import os
from datetime import datetime

from google.api_core.retry import Retry

from airflow.models.dag import DAG
from airflow.providers.google.cloud.operators.dataproc import (
    DataprocCreateClusterOperator,
    DataprocDeleteClusterOperator,
    DataprocSubmitJobOperator,
)
from airflow.providers.google.cloud.sensors.dataproc import DataprocJobSensor
from airflow.utils.trigger_rule import TriggerRule
from tests.system.providers.google import DEFAULT_GCP_SYSTEM_TEST_PROJECT_ID

[docs]ENV_ID = os.environ.get("SYSTEM_TESTS_ENV_ID", "default")
[docs]DAG_ID = "dataproc_spark_async"
[docs]PROJECT_ID = os.environ.get("SYSTEM_TESTS_GCP_PROJECT") or DEFAULT_GCP_SYSTEM_TEST_PROJECT_ID
[docs]CLUSTER_NAME_BASE = f"cluster-{DAG_ID}".replace("_", "-")
[docs]CLUSTER_NAME_FULL = CLUSTER_NAME_BASE + f"-{ENV_ID}".replace("_", "-")
[docs]CLUSTER_NAME = CLUSTER_NAME_BASE if len(CLUSTER_NAME_FULL) >= 33 else CLUSTER_NAME_FULL
[docs]REGION = "europe-west1"
# Cluster definition
[docs]CLUSTER_CONFIG = { "master_config": { "num_instances": 1, "machine_type_uri": "n1-standard-4", "disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 32}, }, "worker_config": { "num_instances": 2, "machine_type_uri": "n1-standard-4", "disk_config": {"boot_disk_type": "pd-standard", "boot_disk_size_gb": 32}, }, }
# Jobs definitions
[docs]SPARK_JOB = { "reference": {"project_id": PROJECT_ID}, "placement": {"cluster_name": CLUSTER_NAME}, "spark_job": { "jar_file_uris": ["file:///usr/lib/spark/examples/jars/spark-examples.jar"], "main_class": "org.apache.spark.examples.SparkPi", }, }
with DAG( DAG_ID, schedule="@once", start_date=datetime(2021, 1, 1), catchup=False, tags=["example", "dataproc", "spark", "async"], ) as dag:
[docs] create_cluster = DataprocCreateClusterOperator( task_id="create_cluster", project_id=PROJECT_ID, cluster_config=CLUSTER_CONFIG, region=REGION, cluster_name=CLUSTER_NAME, retry=Retry(maximum=100.0, initial=10.0, multiplier=1.0), )
# [START cloud_dataproc_async_submit_sensor] spark_task_async = DataprocSubmitJobOperator( task_id="spark_task_async", job=SPARK_JOB, region=REGION, project_id=PROJECT_ID, asynchronous=True ) spark_task_async_sensor = DataprocJobSensor( task_id="spark_task_async_sensor_task", region=REGION, project_id=PROJECT_ID, dataproc_job_id=spark_task_async.output, poke_interval=10, ) # [END cloud_dataproc_async_submit_sensor] delete_cluster = DataprocDeleteClusterOperator( task_id="delete_cluster", project_id=PROJECT_ID, cluster_name=CLUSTER_NAME, region=REGION, trigger_rule=TriggerRule.ALL_DONE, ) ( # TEST SETUP create_cluster # TEST BODY >> spark_task_async >> spark_task_async_sensor # TEST TEARDOWN >> delete_cluster ) from tests.system.utils.watcher import watcher # This test needs watcher in order to properly mark success/failure # when "teardown" task with trigger rule is part of the DAG list(dag.tasks) >> watcher() from tests.system.utils import get_test_run # noqa: E402 # Needed to run the example DAG with pytest (see: tests/system/README.md#run_via_pytest)
[docs]test_run = get_test_run(dag)

Was this entry helpful?