Xcoms


  Key Value Timestamp Execution Date Task Id Dag Id
return_value j-2YX1WXW59KO16 2024-07-22 08:01:11.143048+00:00 2024-07-22 07:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-22T07:05:00+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": []} 2024-07-22 08:05:18.418089+00:00 2024-07-22 07:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1Z8H160JP1O4I 2024-07-22 08:05:41.813159+00:00 2024-07-22 07:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-daily-revenue-report", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-6.14.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 2, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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": "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=2024-07-21T09:00:00+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": []} 2024-07-22 09:00:10.385311+00:00 2024-07-21 09:00:00+00:00 create_emr_steps exchange-daily-revenue-report_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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T08:00:00+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", "2024-07-22T08:00:00+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"}}]} 2024-07-22 09:00:10.846693+00:00 2024-07-22 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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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": []} 2024-07-22 09:00:18.561997+00:00 2024-07-22 08:00:00+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-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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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=2024-07-22T08:00:00+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": []} 2024-07-22 09:00:26.523933+00:00 2024-07-22 08:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1G5HNF7HEG6UP 2024-07-22 09:00:29.910955+00:00 2024-07-21 09:00:00+00:00 create_cluster_and_add_emr_steps exchange-daily-revenue-report_v002
return_value j-19FRL0VSPA9BD 2024-07-22 09:00:32.565051+00:00 2024-07-22 08:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-9FG2ZSEFANN1 2024-07-22 09:00:37.915128+00:00 2024-07-22 08:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-YOBAZO44671B 2024-07-22 09:00:46.054454+00:00 2024-07-22 08:00:00+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=2024-07-22T08:05:00+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": []} 2024-07-22 09:05:24.339334+00:00 2024-07-22 08:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-38IK73CSBKA2R 2024-07-22 09:05:48.203862+00:00 2024-07-22 08:05:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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": []} 2024-07-22 10:00:09.761462+00:00 2024-07-22 09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T09:00:00+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", "2024-07-22T09:00:00+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"}}]} 2024-07-22 10:00:20.751054+00:00 2024-07-22 09:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-30XJS21L1HIZC 2024-07-22 10:00:27.696221+00:00 2024-07-22 09:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-3C6Q9OP67CD3U 2024-07-22 10:00:40.069750+00:00 2024-07-22 09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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=2024-07-22T09:00:00+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": []} 2024-07-22 10:00:46.251980+00:00 2024-07-22 09:00:00+00:00 create_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=2024-07-22T09:05:00+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": []} 2024-07-22 10:05:08.867272+00:00 2024-07-22 09:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1CCVTQFS4281R 2024-07-22 10:05:28.357932+00:00 2024-07-22 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-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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T10:00:00+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", "2024-07-22T10:00:00+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"}}]} 2024-07-22 11:00:10.343490+00:00 2024-07-22 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-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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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": []} 2024-07-22 11:00:18.793007+00:00 2024-07-22 10:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-SD1NP6V57I3Q 2024-07-22 11:00:27.685731+00:00 2024-07-22 10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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=2024-07-22T10:00:00+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": []} 2024-07-22 11:00:29.942377+00:00 2024-07-22 10:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3IIS535JB679F 2024-07-22 11:00:39.535200+00:00 2024-07-22 10:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-34D927U1LGG2Z 2024-07-22 11:00:49.737638+00:00 2024-07-22 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=2024-07-22T10:05:00+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": []} 2024-07-22 11:05:12.120717+00:00 2024-07-22 10:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-37BNT2DDHCCAI 2024-07-22 11:05:34.135679+00:00 2024-07-22 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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T11:00:00+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", "2024-07-22T11:00:00+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"}}]} 2024-07-22 12:00:12.117382+00:00 2024-07-22 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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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": []} 2024-07-22 12:00:13.968622+00:00 2024-07-22 11:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-3VCF9GGLPNCXY 2024-07-22 12:00:31.423862+00:00 2024-07-22 11:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-GBE892V6NCWM 2024-07-22 12:00:33.187574+00:00 2024-07-22 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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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=2024-07-22T11:00:00+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": []} 2024-07-22 12:00:38.324816+00:00 2024-07-22 11:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-NRFD3ZRHSLWQ 2024-07-22 12:00:59.074007+00:00 2024-07-22 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-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=2024-07-22T11:05:00+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": []} 2024-07-22 12:05:20.921314+00:00 2024-07-22 11:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-FOQ8LVWM4MP5 2024-07-22 12:05:37.482583+00:00 2024-07-22 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-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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T12:00:00+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", "2024-07-22T12:00:00+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"}}]} 2024-07-22 13:00:32.645514+00:00 2024-07-22 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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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": []} 2024-07-22 13:00:36.266342+00:00 2024-07-22 12:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-RHGZGIGQ00LQ 2024-07-22 13:00:51.834306+00:00 2024-07-22 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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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=2024-07-22T12:00:00+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": []} 2024-07-22 13:00:52.269024+00:00 2024-07-22 12:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2CN5D9HFYUGRU 2024-07-22 13:00:55.816046+00:00 2024-07-22 12:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-T6E5QW9OEJED 2024-07-22 13:01:11.621074+00:00 2024-07-22 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-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=2024-07-22T12:05:00+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": []} 2024-07-22 13:05:20.347823+00:00 2024-07-22 12:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2JLQYA1H7AEY7 2024-07-22 13:05:41.926311+00:00 2024-07-22 12:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T13:00:00+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", "2024-07-22T13:00:00+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"}}]} 2024-07-22 14:00:12.363888+00:00 2024-07-22 13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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": []} 2024-07-22 14:00:22.039336+00:00 2024-07-22 13:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-YJ3TYQI6LV6K 2024-07-22 14:00:33.559804+00:00 2024-07-22 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-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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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=2024-07-22T13:00:00+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": []} 2024-07-22 14:00:35.767226+00:00 2024-07-22 13:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2DE290L85I7G3 2024-07-22 14:00:43.442263+00:00 2024-07-22 13:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-305SR8XWJFTHY 2024-07-22 14:00:59.509501+00:00 2024-07-22 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=2024-07-22T13:05:00+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": []} 2024-07-22 14:05:14.861865+00:00 2024-07-22 13:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3T1CDVOLMJRYD 2024-07-22 14:05:36.363767+00:00 2024-07-22 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-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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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": []} 2024-07-22 15:00:13.182047+00:00 2024-07-22 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-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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T14:00:00+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", "2024-07-22T14:00:00+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"}}]} 2024-07-22 15:00:25.244043+00:00 2024-07-22 14:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-2ZXP8EBZTUL8F 2024-07-22 15:00:32.272315+00:00 2024-07-22 14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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=2024-07-22T14:00:00+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": []} 2024-07-22 15:00:45.300484+00:00 2024-07-22 14:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-28ZW6H55II61P 2024-07-22 15:00:47.077488+00:00 2024-07-22 14:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-2Y9CME743TPLW 2024-07-22 15:01:06.268800+00:00 2024-07-22 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-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=2024-07-22T14:05:00+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": []} 2024-07-22 15:05:21.039053+00:00 2024-07-22 14:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-19LV1GTYFD00U 2024-07-22 15:05:40.047128+00:00 2024-07-22 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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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": []} 2024-07-22 16:00:18.959496+00:00 2024-07-22 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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T15:00:00+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", "2024-07-22T15:00:00+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"}}]} 2024-07-22 16:00:23.533560+00:00 2024-07-22 15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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=2024-07-22T15:00:00+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": []} 2024-07-22 16:00:29.301676+00:00 2024-07-22 15:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-Z95V91L8W95H 2024-07-22 16:00:38.376634+00:00 2024-07-22 15:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-1MMN3W56813P3 2024-07-22 16:00:44.477048+00:00 2024-07-22 15:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-1IVYSDV4YL3BC 2024-07-22 16:00:50.234899+00:00 2024-07-22 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-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=2024-07-22T15:05:00+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": []} 2024-07-22 16:05:19.513065+00:00 2024-07-22 15:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-34NT1RDL88SU4 2024-07-22 16:05:41.181146+00:00 2024-07-22 15:05:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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": []} 2024-07-22 17:00:08.398250+00:00 2024-07-22 16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T16:00:00+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", "2024-07-22T16:00:00+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"}}]} 2024-07-22 17:00:10.556569+00:00 2024-07-22 16:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-2HTTH40S7C5I9 2024-07-22 17:00:29.772242+00:00 2024-07-22 16:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-1D9N9KUG8E5ZM 2024-07-22 17:00:31.941539+00:00 2024-07-22 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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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=2024-07-22T16:00:00+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": []} 2024-07-22 17:00:38.059602+00:00 2024-07-22 16:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2WFCILB2MRIDM 2024-07-22 17:00:59.689177+00:00 2024-07-22 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=2024-07-22T16:05:00+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": []} 2024-07-22 17:05:04.285375+00:00 2024-07-22 16:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-19IV7MPHJDU5U 2024-07-22 17:05:28.145335+00:00 2024-07-22 16:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T17:00:00+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", "2024-07-22T17:00:00+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"}}]} 2024-07-22 18:00:10.803227+00:00 2024-07-22 17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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": []} 2024-07-22 18:00:22.602867+00:00 2024-07-22 17:00:00+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-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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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=2024-07-22T17:00:00+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": []} 2024-07-22 18:00:26.583246+00:00 2024-07-22 17:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-11BYY1UQVZVBN 2024-07-22 18:00:32.605850+00:00 2024-07-22 17:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-3TAWK80F2OXWL 2024-07-22 18:00:44.005732+00:00 2024-07-22 17:00:00+00:00 create_cluster_and_add_emr_steps booking-processing-job_v002
return_value j-3L69TFBXDMCH4 2024-07-22 18:00:47.819773+00:00 2024-07-22 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=2024-07-22T17:05:00+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": []} 2024-07-22 18:05:28.220343+00:00 2024-07-22 17:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3H0PXIKOCVKA2 2024-07-22 18:05:48.561884+00:00 2024-07-22 17:05:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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": []} 2024-07-22 19:00:07.021018+00:00 2024-07-22 18:00:00+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-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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T18:00:00+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", "2024-07-22T18:00:00+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"}}]} 2024-07-22 19:00:20.700071+00:00 2024-07-22 18:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002
return_value j-LGC8G2LEVMT4 2024-07-22 19:00:27.708237+00:00 2024-07-22 18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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=2024-07-22T18:00:00+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": []} 2024-07-22 19:00:32.397285+00:00 2024-07-22 18:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2E2F1W3LLMQGR 2024-07-22 19:00:41.874367+00:00 2024-07-22 18:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value j-1U4O6J5K6RWLM 2024-07-22 19:00:55.547570+00:00 2024-07-22 18:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-22T18:05:00+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": []} 2024-07-22 19:05:24.071104+00:00 2024-07-22 18:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3AGPJ5F6QUHO6 2024-07-22 19:05:48.492407+00:00 2024-07-22 18:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-trade-summary_v1", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22", "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", "2024-07-22T19:00:00+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", "2024-07-22T19:00:00+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"}}]} 2024-07-22 20:00:17.470793+00:00 2024-07-22 19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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": []} 2024-07-22 20:00:21.362846+00:00 2024-07-22 19:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value j-DLU2PETD218K 2024-07-22 20:00:38.706176+00:00 2024-07-22 19:00:00+00:00 create_cluster_and_add_emr_steps exchange-trade-summary_v1_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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=2024-07-22T19:00:00+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": []} 2024-07-22 20:00:41.204419+00:00 2024-07-22 19:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-20HOUVKYW493Y 2024-07-22 20:01:00.546961+00:00 2024-07-22 19:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-22T19:05:00+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": []} 2024-07-22 20:05:25.674556+00:00 2024-07-22 19:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3VDY6TQAPMFW 2024-07-22 20:05:47.977417+00:00 2024-07-22 19:05:00+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=2024-07-22T20:00:00+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=2024-07-22T20:00:00+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=2024-07-22T20:00:00+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=2024-07-22T20:00:00+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=2024-07-22T20:00:00+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=2024-07-22T20:00:00+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", "2024-07-22", "21", "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", "2024-07-22", "20", "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", "2024-07-22", "21", "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", "2024-07-22", "20", "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", "2024-07-22", "21", "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", "2024-07-22", "20", "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", "2024-07-22T20:00:00+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", "2024-07-22T20:00:00+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"}}]} 2024-07-22 21:00:18.728586+00:00 2024-07-22 20:00:00+00:00 create_emr_steps exchange-trade-summary_v1_v002