mik-laj commented on a change in pull request #6371: [AIRFLOW-5691] Rewrite
Dataproc operators to use python library
URL: https://github.com/apache/airflow/pull/6371#discussion_r336745852
##########
File path: airflow/gcp/example_dags/example_dataproc.py
##########
@@ -41,69 +40,130 @@
PYSPARK_MAIN = os.environ.get("PYSPARK_MAIN", "hello_world.py")
PYSPARK_URI = "gs://{}/{}".format(BUCKET, PYSPARK_MAIN)
+
+# Cluster definition
+CLUSTER = {
+ "project_id": PROJECT_ID,
+ "cluster_name": CLUSTER_NAME,
+ "config": {
+ "master_config": {
+ "num_instances": 1,
+ "machine_type_uri": "n1-standard-4",
+ "disk_config": {"boot_disk_type": "pd-standard",
"boot_disk_size_gb": 1024},
+ },
+ "worker_config": {
+ "num_instances": 2,
+ "machine_type_uri": "n1-standard-4",
+ "disk_config": {"boot_disk_type": "pd-standard",
"boot_disk_size_gb": 1024},
+ },
+ },
+}
+
+
+# Update options
+CLUSTER_UPDATE = {
+ "config": {
+ "worker_config": {"num_instances": 3},
+ "secondary_worker_config": {"num_instances": 3},
+ }
+}
+UPDATE_MASK = {
+ "paths": [
+ "config.worker_config.num_instances",
+ "config.secondary_worker_config.num_instances",
+ ]
+}
+
+TIMEOUT = {"seconds": 1 * 24 * 60 * 60}
+
+
+# Jobs definitions
+PIG_JOB = {
+ "reference": {"project_id": PROJECT_ID},
+ "placement": {"cluster_name": CLUSTER_NAME},
+ "pig_job": {"query_list": {"queries": ["define sin HiveUDF('sin');"]}},
+}
+
+SPARK_SQL_JOB = {
+ "reference": {"project_id": PROJECT_ID},
+ "placement": {"cluster_name": CLUSTER_NAME},
+ "spark_sql_job": {"query_list": {"queries": ["SHOW DATABASES;"]}},
+}
+
+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",
+ },
+}
+
+PYSPARK_JOB = {
+ "reference": {"project_id": PROJECT_ID},
+ "placement": {"cluster_name": CLUSTER_NAME},
+ "pyspark_job": {"main_python_file_uri": PYSPARK_URI},
+}
+
+HIVE_JOB = {
+ "reference": {"project_id": PROJECT_ID},
+ "placement": {"cluster_name": CLUSTER_NAME},
+ "hive_job": {"query_list": {"queries": ["SHOW DATABASES;"]}},
+}
+
+HADOOP_JOB = {
+ "reference": {"project_id": PROJECT_ID},
+ "placement": {"cluster_name": CLUSTER_NAME},
+ "hadoop_job": {
+ "main_jar_file_uri":
"file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar",
+ "args": ["wordcount", "gs://pub/shakespeare/rose.txt", OUTPUT_PATH],
+ },
+}
+
with models.DAG(
"example_gcp_dataproc",
default_args={"start_date": airflow.utils.dates.days_ago(1)},
schedule_interval=None,
) as dag:
create_cluster = DataprocClusterCreateOperator(
- task_id="create_cluster",
- cluster_name=CLUSTER_NAME,
- project_id=PROJECT_ID,
- num_workers=2,
- region=REGION,
+ task_id="create_cluster", project_id=PROJECT_ID, cluster=CLUSTER,
region=REGION
Review comment:
Have you tested this change with the original DAG?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
