DAG: livepop-aggregator-modeltransform_v002

schedule: None


Task Instance: create_emr_steps


XCom

Key Value
return_value {'Name': 'vd-uat-viooh-livepop-aggregator-modeltransform', 'LogUri': 's3n://viooh-emr-logs-lab-cn/bigdata/emr/', 'ReleaseLabel': 'emr-5.33.0', 'Instances': {'InstanceFleets': [{'Name': 'Masterfleet', 'InstanceFleetType': 'MASTER', 'TargetOnDemandCapacity': 1, 'InstanceTypeConfigs': [{'InstanceType': 'm5.2xlarge'}, {'InstanceType': 'm5.4xlarge'}]}, {'Name': 'Corefleet', 'InstanceFleetType': 'CORE', 'TargetOnDemandCapacity': 20, 'InstanceTypeConfigs': [{'InstanceType': 'm5.2xlarge', 'EbsConfiguration': {'EbsBlockDeviceConfigs': [{'VolumeSpecification': {'VolumeType': 'gp2', 'SizeInGB': 50}, 'VolumesPerInstance': 1}], 'EbsOptimized': True}}, {'InstanceType': 'm5.4xlarge', 'EbsConfiguration': {'EbsBlockDeviceConfigs': [{'VolumeSpecification': {'VolumeType': 'gp2', 'SizeInGB': 50}, 'VolumesPerInstance': 1}], 'EbsOptimized': True}}]}], 'Ec2KeyName': 'data.engineer.lab', 'KeepJobFlowAliveWhenNoSteps': False, 'TerminationProtected': False, 'Ec2SubnetId': 'subnet-0e214a494e67e2266', 'EmrManagedMasterSecurityGroup': 'sg-0da002beeed87fb1a', 'EmrManagedSlaveSecurityGroup': 'sg-0f1a0b7517309fcf0', 'ServiceAccessSecurityGroup': 'sg-009528c399781cc69'}, 'BootstrapActions': [], 'Applications': [{'Name': 'Spark'}, {'Name': 'Hadoop'}, {'Name': 'Ganglia'}, {'Name': 'Zeppelin'}], 'VisibleToAllUsers': True, 'Steps': [{'Name': 'Setup Hadoop Debugging', 'ActionOnFailure': 'TERMINATE_JOB_FLOW', 'HadoopJarStep': {'Jar': 'command-runner.jar', 'Args': ['state-pusher-script']}}, {'Name': 'PopAggregator', 'ActionOnFailure': 'TERMINATE_CLUSTER', 'HadoopJarStep': {'Args': ['spark-submit', '--deploy-mode', 'cluster', '--master', 'yarn', '--conf', 'spark.yarn.submit.waitAppCompletion=true', '--conf', 'spark.driver.memory=20g', '--conf', 'spark.serializer=org.apache.spark.serializer.KryoSerializer', '--conf', 'spark.app.env=uat', '--conf', 'spark.dag.execution.time=2021-07-02T16:32:56.641913+00:00', '--class', 'com.viooh.pop.aggregator.livepop.LivePOPAggregatorMain', '--files', 's3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml', '--conf', 'spark.metrics.conf=job.conf', 's3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-data-aggregator/1.7.1/pop-data-aggregator-1.7.1.jar'], 'Jar': 'command-runner.jar'}}, {'Name': 'ModelTransform', 'ActionOnFailure': 'TERMINATE_CLUSTER', 'HadoopJarStep': {'Args': ['spark-submit', '--deploy-mode', 'cluster', '--master', 'yarn', '--conf', 'spark.yarn.submit.waitAppCompletion=true', '--conf', 'spark.driver.memory=20g', '--conf', 'spark.app.env=uat', '--conf', 'spark.dag.execution.time=2021-07-02T16:32:56.641913+00:00', '--class', 'uk.co.viooh.job.modeltransform.ModelTransform', 's3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.3.2/pandora-model-transform-1.3.2.jar'], 'Jar': 'command-runner.jar'}}], 'JobFlowRole': 'DeEmrInstanceRole', 'ServiceRole': 'DeEmrServiceRole', 'SecurityConfiguration': 'bigdata_emr_cn_sec_conf', 'Tags': [{'Key': 'environment', 'Value': 'uat'}, {'Key': 'role', 'Value': 'analysis'}, {'Key': 'application', 'Value': 'emr'}, {'Key': 'project', 'Value': 'campaign-compliance'}, {'Key': 'TerminationPolicy', 'Value': 'OFFICE-HOURS'}, {'Key': 'ContactEmail', 'Value': 'viooh.data@viooh.com'}, {'Key': 'team', 'Value': 'bigdata'}, {'Key': 'Name', 'Value': 'vd-uat-viooh-livepop-aggregator-modeltransform'}], 'Configurations': []}