Xcoms


  Key Value Timestamp Execution Date Task Id Dag Id
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=2024-07-19T07:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 08:05:26.513319+00:00 2024-07-19 07:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2F06G7SQ9RK4K 2024-07-19 08:05:44.031910+00:00 2024-07-19 07:05:00+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=2024-07-19T07:00:00+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=2024-07-19T07:00:00+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=2024-07-19T07:00:00+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=2024-07-19T07:00:00+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=2024-07-19T07:00:00+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=2024-07-19T07:00:00+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", "2024-07-19", "8", "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", "2024-07-19", "7", "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", "2024-07-19", "8", "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", "2024-07-19", "7", "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", "2024-07-19", "8", "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", "2024-07-19", "7", "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", "2024-07-19T07:00:00+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", "2024-07-19T07:00:00+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"}}]} 2024-07-19 08:36:13.384811+00:00 2024-07-19 07:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-AAPFGMWSJSH0 2024-07-19 08:36:32.408924+00:00 2024-07-19 07:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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", "2024-07-19", "9", "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", "2024-07-19", "8", "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", "2024-07-19", "9", "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", "2024-07-19", "8", "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", "2024-07-19", "9", "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", "2024-07-19", "8", "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", "2024-07-19T08:00:00+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", "2024-07-19T08:00:00+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"}}]} 2024-07-19 09:00:09.615896+00:00 2024-07-19 08:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T08:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T08:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T08:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 09:00:13.361956+00:00 2024-07-19 08:00:00+00:00 create_emr_steps booking-processing-job_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-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": "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=2024-07-18T09:00:00+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": []} 2024-07-19 09:00:20.498049+00:00 2024-07-18 09:00:00+00:00 create_emr_steps exchange-daily-revenue-report_v002
return_value j-60I5WMKM4FD9 2024-07-19 09:00:34.335272+00:00 2024-07-19 08:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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-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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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=2024-07-19T08:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 09:00:41.422055+00:00 2024-07-19 08:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-7RV0762ZNOT2 2024-07-19 09:00:42.188356+00:00 2024-07-18 09:00:00+00:00 create_cluster_and_add_emr_steps exchange-daily-revenue-report_v002
return_value j-V7IDWNC4EJ6Y 2024-07-19 09:01:00.366137+00:00 2024-07-19 08:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-J1V1AC6PPMFM 2024-07-19 09:02:18.427081+00:00 2024-07-19 08:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_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-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=2024-07-19T08:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 09:05:05.171119+00:00 2024-07-19 08:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-26AIYS6T2HF2 2024-07-19 09:05:31.040194+00:00 2024-07-19 08:05:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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", "2024-07-19", "10", "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", "2024-07-19", "9", "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", "2024-07-19", "10", "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", "2024-07-19", "9", "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", "2024-07-19", "10", "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", "2024-07-19", "9", "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", "2024-07-19T09:00:00+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", "2024-07-19T09:00:00+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"}}]} 2024-07-19 10:00:13.475361+00:00 2024-07-19 09:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T09:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T09:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T09:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 10:00:20.731347+00:00 2024-07-19 09:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-2VEZZDXLLQ1OR 2024-07-19 10:00:34.154706+00:00 2024-07-19 09:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-126EAVD5DM213 2024-07-19 10:00:40.541003+00:00 2024-07-19 09:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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-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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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=2024-07-19T09:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 10:00:42.338249+00:00 2024-07-19 09:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3A98HX9V44SH8 2024-07-19 10:01:02.457029+00:00 2024-07-19 09:00:00+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=2024-07-19T09:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 10:05:29.622417+00:00 2024-07-19 09:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-D2V97D8OE2AB 2024-07-19 10:05:47.762161+00:00 2024-07-19 09:05:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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", "2024-07-19", "11", "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", "2024-07-19", "10", "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", "2024-07-19", "11", "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", "2024-07-19", "10", "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", "2024-07-19", "11", "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", "2024-07-19", "10", "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", "2024-07-19T10:00:00+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", "2024-07-19T10:00:00+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"}}]} 2024-07-19 11:00:17.237584+00:00 2024-07-19 10:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T10:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T10:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T10:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 11:00:29.122742+00:00 2024-07-19 10:00:00+00:00 create_emr_steps booking-processing-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-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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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=2024-07-19T10:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 11:00:36.920587+00:00 2024-07-19 10:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2R3W5D5EO0TZE 2024-07-19 11:00:38.631861+00:00 2024-07-19 10:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-1ZKPYDDK996QB 2024-07-19 11:00:50.451505+00:00 2024-07-19 10:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-MUCYOTLH2EUE 2024-07-19 11:00:58.429028+00:00 2024-07-19 10:00:00+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=2024-07-19T10:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 11:05:11.988982+00:00 2024-07-19 10:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-P3YJVEL3QTOO 2024-07-19 11:05:33.726180+00:00 2024-07-19 10:05:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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", "2024-07-19", "12", "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", "2024-07-19", "11", "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", "2024-07-19", "12", "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", "2024-07-19", "11", "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", "2024-07-19", "12", "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", "2024-07-19", "11", "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", "2024-07-19T11:00:00+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", "2024-07-19T11:00:00+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"}}]} 2024-07-19 12:00:15.691236+00:00 2024-07-19 11:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T11:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T11:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T11:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 12:00:22.758010+00:00 2024-07-19 11:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-17QV20YRH3B30 2024-07-19 12:00:38.469679+00:00 2024-07-19 11:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-2ACA6ZQZJ4QG0 2024-07-19 12:00:44.226831+00:00 2024-07-19 11:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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-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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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=2024-07-19T11:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 12:00:50.544439+00:00 2024-07-19 11:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-13T2TJZWR0YR4 2024-07-19 12:01:10.434976+00:00 2024-07-19 11:00:00+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=2024-07-19T11:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 12:05:18.063299+00:00 2024-07-19 11:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-XQKRRJSC9IRC 2024-07-19 12:05:42.040130+00:00 2024-07-19 11:05:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T12:00:00+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", "2024-07-19T12:00:00+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"}}]} 2024-07-19 13:00:28.851370+00:00 2024-07-19 12:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T12:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T12:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T12:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 13:00:35.796206+00:00 2024-07-19 12:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-1VA5B5ILIVJF5 2024-07-19 13:00:47.754140+00:00 2024-07-19 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-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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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=2024-07-19T12:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 13:00:52.162009+00:00 2024-07-19 12:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2FL6XHECRPWD1 2024-07-19 13:00:53.790292+00:00 2024-07-19 12:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-2YB36EIPSIA0U 2024-07-19 13:01:12.030624+00:00 2024-07-19 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=2024-07-19T12:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 13:05:20.250349+00:00 2024-07-19 12:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2QGG51EQ7NAWV 2024-07-19 13:05:44.512132+00:00 2024-07-19 12:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T13:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T13:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T13:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 14:00:06.242735+00:00 2024-07-19 13:00:00+00:00 create_emr_steps booking-processing-job_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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T13:00:00+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", "2024-07-19T13:00:00+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"}}]} 2024-07-19 14:00:17.626908+00:00 2024-07-19 13:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-3CCLHR7OFD047 2024-07-19 14:00:26.231559+00:00 2024-07-19 13:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-2GMSBSMRYM5W3 2024-07-19 14:00:35.713683+00:00 2024-07-19 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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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=2024-07-19T13:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 14:00:41.973314+00:00 2024-07-19 13:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3DXHWCWRW5P46 2024-07-19 14:01:03.729601+00:00 2024-07-19 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-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=2024-07-19T13:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 14:05:10.329550+00:00 2024-07-19 13:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-150Y2KRJS7JTE 2024-07-19 14:05:26.131813+00:00 2024-07-19 13:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T14:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T14:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T14:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 15:00:21.905437+00:00 2024-07-19 14:00:00+00:00 create_emr_steps booking-processing-job_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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T14:00:00+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", "2024-07-19T14:00:00+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"}}]} 2024-07-19 15:00:24.048645+00:00 2024-07-19 14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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=2024-07-19T14:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 15:00:32.507438+00:00 2024-07-19 14:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-28Z8NR0IYHPI6 2024-07-19 15:00:58.191131+00:00 2024-07-19 14:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-26AANS10HMXBM 2024-07-19 15:00:59.955028+00:00 2024-07-19 14:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-OC8FJ7FHM5O4 2024-07-19 15:01:04.018104+00:00 2024-07-19 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-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=2024-07-19T14:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 15:05:22.592437+00:00 2024-07-19 14:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-6BHGOGN29IIP 2024-07-19 15:05:46.215457+00:00 2024-07-19 14:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T15:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T15:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T15:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 16:00:18.257338+00:00 2024-07-19 15:00:00+00:00 create_emr_steps booking-processing-job_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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T15:00:00+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", "2024-07-19T15:00:00+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"}}]} 2024-07-19 16:00:25.286345+00:00 2024-07-19 15:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-1VGRCB4R4SVGT 2024-07-19 16:00:38.379881+00:00 2024-07-19 15:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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-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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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=2024-07-19T15:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 16:00:40.953813+00:00 2024-07-19 15:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-55ZEPFV0Y0ZO 2024-07-19 16:00:46.269880+00:00 2024-07-19 15:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-OTAPWK4H1G0Y 2024-07-19 16:01:02.648863+00:00 2024-07-19 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=2024-07-19T15:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 16:05:27.215575+00:00 2024-07-19 15:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3RMFF1W2HEMQF 2024-07-19 16:05:48.289769+00:00 2024-07-19 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-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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T16:00:00+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", "2024-07-19T16:00:00+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"}}]} 2024-07-19 17:00:18.679315+00:00 2024-07-19 16:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T16:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T16:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T16:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 17:00:20.227965+00:00 2024-07-19 16:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-3LT7E1J5GA59P 2024-07-19 17:00:52.270028+00:00 2024-07-19 16:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-2G4DJXX5YL8FO 2024-07-19 17:00:56.366934+00:00 2024-07-19 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-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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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=2024-07-19T16:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 17:01:00.665512+00:00 2024-07-19 16:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2AXTSTB0FJXWL 2024-07-19 17:01:20.096753+00:00 2024-07-19 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=2024-07-19T16:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 17:05:18.879760+00:00 2024-07-19 16:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3772U3N4ICX1F 2024-07-19 17:05:43.889601+00:00 2024-07-19 16:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T17:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T17:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T17:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 18:00:14.673553+00:00 2024-07-19 17:00:00+00:00 create_emr_steps booking-processing-job_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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T17:00:00+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", "2024-07-19T17:00:00+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"}}]} 2024-07-19 18:00:28.611450+00:00 2024-07-19 17:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-3EG6XUI4AR43K 2024-07-19 18:00:37.829041+00:00 2024-07-19 17:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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=2024-07-19T17:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 18:00:42.137267+00:00 2024-07-19 17:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-31A438R4FIZH5 2024-07-19 18:00:47.955347+00:00 2024-07-19 17:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-2DEIU5F1UTAB3 2024-07-19 18:01:04.047675+00:00 2024-07-19 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-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=2024-07-19T17:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 18:05:15.690739+00:00 2024-07-19 17:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1V1UDKL6K7A6A 2024-07-19 18:05:40.138505+00:00 2024-07-19 17:05:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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", "2024-07-19", "19", "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", "2024-07-19", "18", "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", "2024-07-19", "19", "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", "2024-07-19", "18", "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", "2024-07-19", "19", "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", "2024-07-19", "18", "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", "2024-07-19T18:00:00+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", "2024-07-19T18:00:00+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"}}]} 2024-07-19 19:00:06.720648+00:00 2024-07-19 18:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T18:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T18:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T18:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 19:00:24.872134+00:00 2024-07-19 18:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-CIV9M2QOCR7C 2024-07-19 19:00:26.911872+00:00 2024-07-19 18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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=2024-07-19T18:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 19:00:34.048678+00:00 2024-07-19 18:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-31LZ0VQGA6QYB 2024-07-19 19:00:45.485238+00:00 2024-07-19 18:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-X4K9Q0LW8JWS 2024-07-19 19:00:59.670548+00:00 2024-07-19 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-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=2024-07-19T18:05:00+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/1.13.0/daily-import-1.13.0-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": []} 2024-07-19 19:05:30.297740+00:00 2024-07-19 18:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-B73STRIHHDY9 2024-07-19 19:05:52.366261+00:00 2024-07-19 18:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "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"}]}, {"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": "CampaignExtractor", "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=2024-07-19T19:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/connector/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.6.0/campaign-extractor-1.6.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignProcessingJob", "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=2024-07-19T19:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.11.0/campaign-processing-job-1.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CampaignDeltaJob", "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=2024-07-19T19:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/0.0.0/job.yaml", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.20.0/pandora-campaign-delta-1.20.0-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-booking-processing-job"}], "Configurations": []} 2024-07-19 20:00:12.537641+00:00 2024-07-19 19:00:00+00:00 create_emr_steps booking-processing-job_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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19", "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", "2024-07-19T19:00:00+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", "2024-07-19T19:00:00+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"}}]} 2024-07-19 20:00:25.244507+00:00 2024-07-19 19:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-1QBL12P2KSVRB 2024-07-19 20:00:32.100003+00:00 2024-07-19 19:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-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-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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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=2024-07-19T19:00:00+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/1.6.0/pandora-model-transform-1.6.0.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": []} 2024-07-19 20:00:42.522853+00:00 2024-07-19 19:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-BDZITO84CIDO 2024-07-19 20:00:44.103850+00:00 2024-07-19 19:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-ISO69W7TMU4D 2024-07-19 20:01:04.647580+00:00 2024-07-19 19:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004