code-infrastructure-lab/workflow/dnet/run_spark.py

#
# 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 which uses SparkKubernetesOperator and SparkKubernetesSensor.
In this example, we create two tasks which execute sequentially.
The first task is to submit sparkApplication on Kubernetes cluster(the example uses spark-pi application).
and the second task is to check the final state of the sparkApplication that submitted in the first state.

Spark-on-k8s operator is required to be already installed on Kubernetes
https://github.com/GoogleCloudPlatform/spark-on-k8s-operator
"""

from os import path
from datetime import timedelta, datetime
# from workflow.dnet.spark_configurator import SparkConfigurator

# [START import_module]
# The DAG object; we'll need this to instantiate a DAG
from airflow import DAG
# Operators; we need this to operate!
from airflow.providers.cncf.kubernetes.operators.spark_kubernetes import SparkKubernetesOperator
from airflow.providers.cncf.kubernetes.sensors.spark_kubernetes import SparkKubernetesSensor
from airflow.utils.dates import days_ago


# [END import_module]


class SparkConfigurator:
    def __init__(self,
                 name, 
                 mainClass,
                 jarLocation:str,
                 arguments,
                 apiVersion=None,
                 namespace="dnet-spark-jobs",
                 image= "dnet-spark:1.0.0",
                 driver_cores=1,
                 driver_memory='1G',
                 executor_cores=1,
                 executor_memory="1G",
                 executor_memoryOverhead= "1G",
                 executor_instances=1
                 ) -> None:
        if apiVersion:
            self.apiVersion = apiVersion
        else:
            self.apiVersion = "sparkoperator.k8s.io/v1beta2"
        self.namespace= namespace
        self.name = name
        self.image= image
        self.mainClass = mainClass
        self.jarLocation = jarLocation
        self.arguments= arguments
        self.s3Configuration =  {
                    "spark.driver.extraJavaOptions": "-Divy.cache.dir=/tmp -Dcom.amazonaws.sdk.disableCertChecking=true -Dcom.cloudera.com.amazonaws.sdk.disableCertChecking=true",
                    "spark.executor.extraJavaOptions": "-Divy.cache.dir=/tmp -Dcom.amazonaws.sdk.disableCertChecking=true -Dcom.cloudera.com.amazonaws.sdk.disableCertChecking=true",
                    "spark.hadoop.fs.defaultFS": "s3a://spark",
                    "spark.hadoop.fs.s3a.access.key": "minio",
                    "spark.hadoop.fs.s3a.secret.key": "minio123",
                    "spark.hadoop.fs.s3a.endpoint": "https://minio.dnet-minio-tenant.svc.cluster.local",
                    "spark.hadoop.fs.s3a.impl": "org.apache.hadoop.fs.s3a.S3AFileSystem",
                    "spark.hadoop.fs.s3a.path.style.access": "true",
                    "spark.hadoop.fs.s3a.attempts.maximum": "1",
                    "spark.hadoop.fs.s3a.connection.establish.timeout": "5000",
                    "spark.hadoop.fs.s3a.connection.timeout": "10001",
                    "spark.hadoop.fs.s3a.connection.ssl.enabled": "false",
                    "com.amazonaws.sdk.disableCertChecking": "true",
                    "com.cloudera.com.amazonaws.sdk.disableCertChecking": "true",
                    "fs.s3a.connection.ssl.strictverify": "false",
                    "fs.s3a.connection.ssl.enabled": "false",
                    "fs.s3a.ssl.enabled": "false",
                    "spark.hadoop.fs.s3a.ssl.enabled": "false"
                }
        self.sparkResoruceConf= {
            'driver_cores':driver_cores,
            'driver_memory':driver_memory,
            'executor_cores':executor_cores,
            'executor_memory':executor_memory,
            'executor_instances':executor_instances,
            'memoryOverhead':executor_memoryOverhead 
            
        }

    def get_configuration(self) -> dict:
        return {
            "apiVersion": self.apiVersion,
            "kind": "SparkApplication",
            "metadata": {
                "name": self.name,
                "namespace": self.namespace
            },
            "spec": {
                "type": "Scala",
                "mode": "cluster",
                "image":self.image,
                "imagePullPolicy": "IfNotPresent",
                "mainClass": self.mainClass,
                "mainApplicationFile": self.jarLocation,
                "arguments": self.arguments,
                "sparkVersion": "3.5.1",
                "sparkConf": self.s3Configuration,
                "restartPolicy": {
                    "type": "Never"
                },
                "volumes": [
                    {
                        "name": "test-volume",
                        "persistentVolumeClaim": {
                            "claimName": "my-spark-pvc-tmp"
                        }
                    }
                ],
                "driver": {
                    "javaOptions": "-Dcom.amazonaws.sdk.disableCertChecking=true -Dcom.cloudera.com.amazonaws.sdk.disableCertChecking=true",
                    "cores": self.sparkResoruceConf['driver_cores'],
                    "coreLimit": "1200m",
                    "memory": self.sparkResoruceConf['driver_memory'],
                    "labels": {
                        "version": "3.5.1"
                    },
                    "serviceAccount": "spark",
                    "volumeMounts": [
                        {
                            "name": "test-volume",
                            "mountPath": "/tmp"
                        }
                    ]
                },
                "executor": {
                    "javaOptions": "-Dcom.amazonaws.sdk.disableCertChecking=true  -Dcom.cloudera.com.amazonaws.sdk.disableCertChecking=true",
                    "cores": self.sparkResoruceConf['executor_cores'],
                    "memoryOverhead": self.sparkResoruceConf['memoryOverhead'],
                    "memory": self.sparkResoruceConf['executor_memory'],
                    "instances": self.sparkResoruceConf['executor_instances'],
                    "labels": {
                        "version": "3.5.1"
                    },
                    "volumeMounts": [
                        {
                            "name": "test-volume",
                            "mountPath": "/tmp"
                        }
                    ]
                }
            }
        }


# [START default_args]
# These args will get passed on to each operator
# You can override them on a per-task basis during operator initialization
default_args = {
    'owner': 'airflow',
    'depends_on_past': False,
    'start_date': days_ago(1),
    'email': ['airflow@example.com'],
    'email_on_failure': False,
    'email_on_retry': False,
    'max_active_runs': 1,
    'retries': 3
}

spec =SparkConfigurator(
    name="spark-scholix-{{ ds }}-{{ task_instance.try_number }}", 
        mainClass="eu.dnetlib.dhp.sx.graph.SparkCreateScholexplorerDump", 
        jarLocation = 's3a://deps/dhp-shade-package-1.2.5-SNAPSHOT.jar',
        arguments =[ "--sourcePath", "s3a://raw-graph/01", "--targetPath", "s3a://scholix"],\
        executor_cores=10,
        executor_memory="4G", 
        executor_instances=1, 
        executor_memoryOverhead="3G").get_configuration()

dag = DAG(
    'spark_run_test',
    default_args=default_args,
    schedule_interval=None,
    tags=['example', 'spark']
)

submit = SparkKubernetesOperator(
    task_id='spark-scholix',
    namespace='dnet-spark-jobs',
    template_spec=spec,
    kubernetes_conn_id="kubernetes_default",
    #    do_xcom_push=True,
    #    delete_on_termination=True,
    # base_container_name="spark-kubernetes-driver",
    dag=dag
)



submit