Xcoms


  Key Value Timestamp Execution Date Task Id Dag Id
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "12", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "12", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "12", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T12:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T12:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 13:00:10.877599+00:00 2024-07-07 12:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-25C1UVAV1MSMX 2024-07-07 13:00:29.366598+00:00 2024-07-07 12:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 13:00:48.441196+00:00 2024-07-07 12:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2HYWIC6OWNW3M 2024-07-07 13:01:16.891658+00:00 2024-07-07 12:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T12:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 13:05:25.400870+00:00 2024-07-07 12:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-SNAKWN7YLF5E 2024-07-07 13:05:47.234320+00:00 2024-07-07 12:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "13", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T13:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T13:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 14:00:08.142603+00:00 2024-07-07 13:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-D4ELKIITDUXI 2024-07-07 14:00:27.432913+00:00 2024-07-07 13:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 14:00:38.386688+00:00 2024-07-07 13:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-17YU4LX9NGUMS 2024-07-07 14:00:59.376945+00:00 2024-07-07 13:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T13:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 14:05:05.851704+00:00 2024-07-07 13:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3JNJI4FSG9ZZQ 2024-07-07 14:05:27.415441+00:00 2024-07-07 13:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "14", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T14:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T14:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 15:00:07.856248+00:00 2024-07-07 14:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-1U3Q6OML8VBLH 2024-07-07 15:00:30.704392+00:00 2024-07-07 14:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 15:00:35.701392+00:00 2024-07-07 14:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3IZ4T0O3V8SXA 2024-07-07 15:00:56.808908+00:00 2024-07-07 14:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T14:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 15:05:13.295014+00:00 2024-07-07 14:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-377XAUCM5N9ID 2024-07-07 15:05:32.542644+00:00 2024-07-07 14:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "15", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T15:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T15:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 16:00:25.063463+00:00 2024-07-07 15:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-39KTGRH5X1C7A 2024-07-07 16:00:43.812920+00:00 2024-07-07 15:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 16:00:44.018360+00:00 2024-07-07 15:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1V38V8W4INHN3 2024-07-07 16:01:07.248224+00:00 2024-07-07 15:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T15:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 16:05:11.317709+00:00 2024-07-07 15:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-22459SU3PZQ6W 2024-07-07 16:05:35.243190+00:00 2024-07-07 15:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "16", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T16:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T16:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 17:00:08.248655+00:00 2024-07-07 16:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-WX8ZK4VNBXIL 2024-07-07 17:00:29.132505+00:00 2024-07-07 16:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 17:00:29.827530+00:00 2024-07-07 16:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1PIRTUU7IYCTV 2024-07-07 17:00:59.202438+00:00 2024-07-07 16:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T16:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 17:05:29.412240+00:00 2024-07-07 16:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3CQ7NMCBUKLG0 2024-07-07 17:05:48.782668+00:00 2024-07-07 16:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "18", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "18", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "18", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "17", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T17:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T17:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 18:00:14.796372+00:00 2024-07-07 17:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-2LHHBHJSBNGGZ 2024-07-07 18:00:37.144898+00:00 2024-07-07 17:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 18:00:47.526150+00:00 2024-07-07 17:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2S1A46BW8G43U 2024-07-07 18:01:07.013509+00:00 2024-07-07 17:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T17:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 18:05:21.123634+00:00 2024-07-07 17:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-A3TLDLUVGJIK 2024-07-07 18:05:40.955929+00:00 2024-07-07 17:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T18:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T18:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T18:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 19:00:46.303486+00:00 2024-07-07 18:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1HEI7RVNC60SU 2024-07-07 19:01:09.581256+00:00 2024-07-07 18:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T18:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 19:05:09.739438+00:00 2024-07-07 18:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-19N01SWMEAS3I 2024-07-07 19:05:33.213087+00:00 2024-07-07 18:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "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": "SupplyDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.supply.denormalization.SupplyDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/supply-denormalization/2.15.0/supply-denormalization-2.15.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DemandDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.demand.denormalization.DemandDataDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/demand-denormalization/2.14.0/demand-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealSyncDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.dealsync.denormalization.DealSyncDenormalization", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dealsync-denormalization/2.14.0/dealsync-denormalization-2.14.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ModerationDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.moderation.denormalization.ModerationDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/moderation-denormalization/2.4.0/moderation-denormalization-2.4.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "DealDenormalizationJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.deal.denormalization.DealDenormalization", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/deal-denormalization/1.5.0/deal-denormalization-1.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "ExchangeTradeSummaryJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=6g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.task.maxFailures=20", "--conf", "spark.yarn.maxAppAttempts=10", "--conf", "spark.stage.maxConsecutiveAttempts=20", "--conf", "spark.app.config.key=exchange-trade-summary", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.smex.trade.summary.ExchangeTradeSummary", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/exchange-trade-summary/3.5.0/exchange-trade-summary-3.5.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopySmartExchangeMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "20", "mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "19", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "20", "frame-level-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteFrameLevelMediaOwnerReport", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "19", "frame-level-exchange-lite-mediaowner-trade-report", "frame-level-media-owner-reports", "v1", "csv", "cn-northwest-1"]}}, {"Name": "CopySmartExchangeMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "20", "mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "CopyExchangeLiteMediaOwnerReportV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/1.3.0/job.sh", "uat", "2024-07-07", "19", "exchange-lite-mediaowner-trade-report", "trade-summary-reports", "v2", "json", "cn-northwest-1"]}}, {"Name": "ExportVioohHourLevelReportToDbV2", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-ui-report-v2", "1", "2024-07-07T19:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "deal", "cn-northwest-1"]}}, {"Name": "ExportVioohHourlyCreativeLevelReportToDb", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-trade-summary/sspui_reporting/viooh_sspui_hourly_aggr_report_v2_installer.sh", "uat", "0.0.2", "db-import-viooh-hourly-creative-report", "1", "2024-07-07T19:00:00+00:00", "viooh-spark-artifacts-lab-cn", "scripts/exchange-trade-summary/sspui_reporting", "creative", "cn-northwest-1"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-trade-summary_v1"}], "Configurations": [{"Classification": "yarn-site", "Properties": {"yarn.resourcemanager.am.max-attempts": "2"}}]} 2024-07-07 20:00:18.806652+00:00 2024-07-07 19:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 20:00:29.450270+00:00 2024-07-07 19:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-27JCRJ4MH0S0A 2024-07-07 20:00:52.762260+00:00 2024-07-07 19:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T19:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 20:05:05.636158+00:00 2024-07-07 19:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-SLK5ASWS1DDA 2024-07-07 20:05:27.255583+00:00 2024-07-07 19:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T20:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T20:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T20:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 21:00:50.009325+00:00 2024-07-07 20:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2OYW6N78263GO 2024-07-07 21:01:10.875995+00:00 2024-07-07 20:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T20:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 21:05:09.426550+00:00 2024-07-07 20:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-38O72GXBQE0KQ 2024-07-07 21:05:31.712934+00:00 2024-07-07 20:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T21:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T21:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T21:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 22:00:48.188100+00:00 2024-07-07 21:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-TCY2546CPFV0 2024-07-07 22:01:09.620043+00:00 2024-07-07 21:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T21:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 22:05:35.754302+00:00 2024-07-07 21:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-39PHVPZ39453G 2024-07-07 22:05:54.585970+00:00 2024-07-07 21:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-campaign-delta-past-delete-job", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "CampaignDeltaPastDeleteJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-06T23:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaPastDeleteMain", "--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/pandora-campaign-delta/1.16.0/pandora-campaign-delta-1.16.0-jar-with-dependencies.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-campaign-delta-past-delete-job"}], "Configurations": []} 2024-07-07 23:00:12.110666+00:00 2024-07-06 23:00:00+00:00 create_emr_steps campaign-delta-past-delete-job_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T22:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T22:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T22:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-07 23:00:32.393396+00:00 2024-07-07 22:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1JYMIOTNLWJID 2024-07-07 23:00:59.034156+00:00 2024-07-06 23:00:00+00:00 create_cluster_and_add_emr_steps campaign-delta-past-delete-job_v002
return_value j-3VE8DDZLHOJFJ 2024-07-07 23:00:59.337044+00:00 2024-07-07 22:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T22:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-07 23:05:17.566115+00:00 2024-07-07 22:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-31HY17Q6H42PL 2024-07-07 23:05:39.459110+00:00 2024-07-07 22:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T23:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T23:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T23:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 00:00:33.356419+00:00 2024-07-07 23:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-290TLJ9RKLWDH 2024-07-08 00:00:53.163616+00:00 2024-07-07 23:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T23:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 00:05:11.500672+00:00 2024-07-07 23:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3EJM71INOB9DH 2024-07-08 00:05:31.474675+00:00 2024-07-07 23:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T00:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T00:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T00:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 01:00:30.642152+00:00 2024-07-08 00:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-FDT03NQA0HJ4 2024-07-08 01:00:55.729889+00:00 2024-07-08 00:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T00:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 01:05:29.568262+00:00 2024-07-08 00:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-UQ7GN3AEFYM2 2024-07-08 01:05:50.801026+00:00 2024-07-08 00:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-by-hour-model-transform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "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-06c5b5a18c64a0316", "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": "BookingByHour-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=2024-07-07T01:30:00+00:00", "--class", "com.viooh.transform.BookingModelTransform", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-booking-by-hour-model-transform"}], "Configurations": []} 2024-07-08 01:30:27.369825+00:00 2024-07-07 01:30:00+00:00 create_emr_steps booking-by-hour-model-transform_v002
return_value j-31Y1QV9LPIXO6 2024-07-08 01:30:49.148287+00:00 2024-07-07 01:30:00+00:00 create_cluster_and_add_emr_steps booking-by-hour-model-transform_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T01:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T01:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T01:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 02:00:33.415493+00:00 2024-07-08 01:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-181Q3J0XSTNLP 2024-07-08 02:00:57.054516+00:00 2024-07-08 01:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T01:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 02:05:20.231101+00:00 2024-07-08 01:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1DL4YPAVA2D9J 2024-07-08 02:05:39.441467+00:00 2024-07-08 01:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T02:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T02:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T02:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 03:00:45.768791+00:00 2024-07-08 02:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-31EMOL8QOB8ZK 2024-07-08 03:01:08.895671+00:00 2024-07-08 02:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T02:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 03:05:27.214322+00:00 2024-07-08 02:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2Y2QQORTNFQBT 2024-07-08 03:05:48.660821+00:00 2024-07-08 02:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-dsp-reporting", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "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": "DSPExchangeTradeJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T04:00:00+00:00", "--class", "com.viooh.smex.dsp.DSPExchangeTrade", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dsp-exchange-trade/2.11.0/dsp-exchange-trade-2.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopyDSPReports", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-dsp-reporting/1.0.0/job.sh", "--environment", "uat", "--reportdate", "2024-07-07", "--region", "cn", "--skipFailure"]}}], "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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-dsp-reporting"}], "Configurations": []} 2024-07-08 04:00:12.557434+00:00 2024-07-07 04:00:00+00:00 create_emr_steps exchange-dsp-reporting_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T03:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T03:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T03:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 04:00:32.367242+00:00 2024-07-08 03:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-261QDUTRJ2YI3 2024-07-08 04:00:35.855538+00:00 2024-07-07 04:00:00+00:00 create_cluster_and_add_emr_steps exchange-dsp-reporting_v002
return_value j-3CW6JF5IM7FJM 2024-07-08 04:00:53.697646+00:00 2024-07-08 03:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T03:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 04:05:28.266076+00:00 2024-07-08 03:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-F62N7DY4CCRG 2024-07-08 04:05:54.835826+00:00 2024-07-08 03:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T04:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 05:05:07.964156+00:00 2024-07-08 04:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-BBSUGAY5WBHI 2024-07-08 05:05:28.910517+00:00 2024-07-08 04:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T04:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T04:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T04:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 05:06:03.972382+00:00 2024-07-08 04:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1LMNSPCPI4ZSQ 2024-07-08 05:06:22.987330+00:00 2024-07-08 04:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T05:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T05:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T05:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 06:00:49.633021+00:00 2024-07-08 05:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3S4F6AEL9D7NN 2024-07-08 06:01:08.734646+00:00 2024-07-08 05:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T05:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 06:05:09.114807+00:00 2024-07-08 05:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-MJ6TZTE201B3 2024-07-08 06:05:36.839411+00:00 2024-07-08 05:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T06:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T06:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T06:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 07:00:32.191229+00:00 2024-07-08 06:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3I142DRQL5YAI 2024-07-08 07:00:53.338317+00:00 2024-07-08 06:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T06:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 07:05:11.978305+00:00 2024-07-08 06:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1YV9RS17BMK0T 2024-07-08 07:05:31.071323+00:00 2024-07-08 06:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "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": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T07:00:00+00:00", "--class", "com.viooh.pop.data.live.shuffle.RawLivePOPShuffleMain", "--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", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pop/pop-shuffle-live/1.12.0/pop-shuffle-live-1.12.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "PopAggregator", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T07:00:00+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/1.13.0/pop-data-aggregator-1.13.0.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=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T07:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--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/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.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-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 08:00:39.836955+00:00 2024-07-08 07:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1FC3DSYKHF2R7 2024-07-08 08:01:00.831019+00:00 2024-07-08 07:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T07:05:00+00:00", "--class", "VioohCentralAssetsMain", "--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/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.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-vc-asset-import"}], "Configurations": []} 2024-07-08 08:05:07.724456+00:00 2024-07-08 07:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2IT5YEEVGIJDM 2024-07-08 08:05:29.627169+00:00 2024-07-08 07:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-daily-revenue-report", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-6.14.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 2, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "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": "DailyRevenueReportJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T09:00:00+00:00", "--class", "com.viooh.smex.dailyrevenue.DailyRevenueReport", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/daily-revenue-report/1.3.0/daily-revenue-report-1.3.0-jar-with-dependencies.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": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-daily-revenue-report"}], "Configurations": []} 2024-07-08 09:00:24.584759+00:00 2024-07-07 09:00:00+00:00 create_emr_steps exchange-daily-revenue-report_v002