Xcoms


  Key Value Timestamp Execution Date Task Id Dag Id
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=2024-07-08T08:00:00+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=2024-07-08T08:00:00+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=2024-07-08T08:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 09:00:39.417011+00:00 2024-07-08 08:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-275QURC8WI15R 2024-07-08 09:00:45.058246+00:00 2024-07-07 09:00:00+00:00 create_cluster_and_add_emr_steps exchange-daily-revenue-report_v002
return_value j-37ENSEOSBJ3AJ 2024-07-08 09:00:58.703088+00:00 2024-07-08 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-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=2024-07-08T08:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 09:05:17.625452+00:00 2024-07-08 08:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3KUNQBZS4TTTL 2024-07-08 09:05:39.174928+00:00 2024-07-08 08:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T09:00:00+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=2024-07-08T09:00:00+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=2024-07-08T09:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 10:00:38.203914+00:00 2024-07-08 09:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-GCRYCHQS31GI 2024-07-08 10:00:59.412096+00:00 2024-07-08 09:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T09:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 10:05:16.688809+00:00 2024-07-08 09:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2850N0QC7OO4G 2024-07-08 10:05:38.003582+00:00 2024-07-08 09:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T10:00:00+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=2024-07-08T10:00:00+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=2024-07-08T10:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 11:00:35.729576+00:00 2024-07-08 10:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-BPS6NQ3GGSC7 2024-07-08 11:00:57.092713+00:00 2024-07-08 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-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=2024-07-08T10:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 11:05:16.086755+00:00 2024-07-08 10:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-DCQYUMZQPJBN 2024-07-08 11:05:37.405994+00:00 2024-07-08 10:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T11:00:00+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=2024-07-08T11:00:00+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=2024-07-08T11:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 12:00:30.153653+00:00 2024-07-08 11:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1ZXZ6V2O2MIXS 2024-07-08 12:00:55.652912+00:00 2024-07-08 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-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=2024-07-08T11:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 12:05:14.984740+00:00 2024-07-08 11:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3IVDRASVLZVLK 2024-07-08 12:05:37.511371+00:00 2024-07-08 11:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T12:00:00+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=2024-07-08T12:00:00+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=2024-07-08T12:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 13:00:35.684594+00:00 2024-07-08 12:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-OCXCVZLUSP47 2024-07-08 13:00:57.277806+00:00 2024-07-08 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=2024-07-08T12:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 13:05:28.035035+00:00 2024-07-08 12:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2SFXIRF08JPUN 2024-07-08 13:06:04.686928+00:00 2024-07-08 12:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T13:00:00+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=2024-07-08T13:00:00+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=2024-07-08T13:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 14:00:35.216178+00:00 2024-07-08 13:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2JWJT30NJ2JZS 2024-07-08 14:00:57.552895+00:00 2024-07-08 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-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=2024-07-08T13:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 14:05:24.693014+00:00 2024-07-08 13:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3VP8MLGR84LA1 2024-07-08 14:05:45.843198+00:00 2024-07-08 13:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T14:00:00+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=2024-07-08T14:00:00+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=2024-07-08T14:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 15:00:30.075224+00:00 2024-07-08 14:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1E66UXM6IX3OY 2024-07-08 15:00:56.995531+00:00 2024-07-08 14:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T14:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 15:05:27.799038+00:00 2024-07-08 14:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3I73VEVE7J62Q 2024-07-08 15:05:47.138103+00:00 2024-07-08 14:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T15:00:00+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=2024-07-08T15:00:00+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=2024-07-08T15:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 16:00:35.877784+00:00 2024-07-08 15:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2X1I6XWM16X2M 2024-07-08 16:00:53.971493+00:00 2024-07-08 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=2024-07-08T15:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 16:05:08.437264+00:00 2024-07-08 15:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-PE9G447RS2NO 2024-07-08 16:05:31.219976+00:00 2024-07-08 15:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T16:00:00+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=2024-07-08T16:00:00+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=2024-07-08T16:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 17:00:56.114799+00:00 2024-07-08 16:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2BOBSQKKWOR0N 2024-07-08 17:01:14.788535+00:00 2024-07-08 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-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=2024-07-08T16:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 17:05:07.816177+00:00 2024-07-08 16:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2AKR9ZGU3R9X8 2024-07-08 17:05:31.813777+00:00 2024-07-08 16:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T17:00:00+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=2024-07-08T17:00:00+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=2024-07-08T17:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 18:00:59.263918+00:00 2024-07-08 17:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2MV5RP4EKNXPG 2024-07-08 18:01:20.614334+00:00 2024-07-08 17:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-09a80b42d0e6dedd8", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T17:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 18:05:09.465206+00:00 2024-07-08 17:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1GV2WH4P8PPI1 2024-07-08 18:05:31.258479+00:00 2024-07-08 17:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T18:00:00+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=2024-07-08T18:00:00+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=2024-07-08T18:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 19:00:44.216312+00:00 2024-07-08 18:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2YRE8CFN9NH1U 2024-07-08 19:01:05.868677+00:00 2024-07-08 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-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=2024-07-08T18:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 19:05:10.684528+00:00 2024-07-08 18:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1MYA73R5NKMJO 2024-07-08 19:05:33.994781+00:00 2024-07-08 18:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T19:00:00+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=2024-07-08T19:00:00+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=2024-07-08T19:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 20:00:33.984255+00:00 2024-07-08 19:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-389CUJFN0VUJQ 2024-07-08 20:00:53.369254+00:00 2024-07-08 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-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=2024-07-08T19:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 20:05:24.506284+00:00 2024-07-08 19:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1N3M8E60V8Z3W 2024-07-08 20:05:43.911144+00:00 2024-07-08 19:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T20:00:00+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=2024-07-08T20:00:00+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=2024-07-08T20:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 21:00:39.028015+00:00 2024-07-08 20:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2PAE0TFR3G1IU 2024-07-08 21:01:03.101105+00:00 2024-07-08 20:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T20:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 21:05:31.696657+00:00 2024-07-08 20:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-1WHACWFPAQ1ZB 2024-07-08 21:05:53.206186+00:00 2024-07-08 20:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T21:00:00+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=2024-07-08T21:00:00+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=2024-07-08T21:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 22:00:39.182538+00:00 2024-07-08 21:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1SGE2U3AS9ITO 2024-07-08 22:01:02.141796+00:00 2024-07-08 21:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T21:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 22:05:06.032414+00:00 2024-07-08 21:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-XOHPV0KCT8TH 2024-07-08 22:05:31.856390+00:00 2024-07-08 21:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-campaign-delta-past-delete-job", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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": "CampaignDeltaPastDeleteJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-07T23:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaPastDeleteMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.16.0/pandora-campaign-delta-1.16.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-campaign-delta-past-delete-job"}], "Configurations": []} 2024-07-08 23:00:24.945845+00:00 2024-07-07 23:00:00+00:00 create_emr_steps campaign-delta-past-delete-job_v002
return_value j-37ZAGHAPQ51NY 2024-07-08 23:00:43.518707+00:00 2024-07-07 23:00:00+00:00 create_cluster_and_add_emr_steps campaign-delta-past-delete-job_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T22:00:00+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=2024-07-08T22:00:00+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=2024-07-08T22:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-08 23:00:48.137360+00:00 2024-07-08 22:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-242RVST1OZJGA 2024-07-08 23:01:09.124389+00:00 2024-07-08 22:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T22:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-08 23:05:34.554070+00:00 2024-07-08 22:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-3FHPUGY2Z1FTD 2024-07-08 23:05:55.224635+00:00 2024-07-08 22:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T23:00:00+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=2024-07-08T23:00:00+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=2024-07-08T23:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 00:00:40.495865+00:00 2024-07-08 23:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3KLKPUKL72D5Q 2024-07-09 00:01:02.305327+00:00 2024-07-08 23:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-08T23:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 00:05:20.009749+00:00 2024-07-08 23:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-277ZLMGA2RY4M 2024-07-09 00:05:39.513050+00:00 2024-07-08 23:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T00:00:00+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=2024-07-09T00:00:00+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=2024-07-09T00:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 01:00:43.040823+00:00 2024-07-09 00:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-29QWUQQQNSXCA 2024-07-09 01:01:04.196516+00:00 2024-07-09 00:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T00:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 01:05:23.941432+00:00 2024-07-09 00:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-D4F5HGTP53ZO 2024-07-09 01:05:55.628638+00:00 2024-07-09 00:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-06c5b5a18c64a0316", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "LivePOPShuffle", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.serializer=org.apache.spark.serializer.KryoSerializer", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-09T01:00:00+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=2024-07-09T01:00:00+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=2024-07-09T01:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 02:00:57.700629+00:00 2024-07-09 01:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-3LWXY2M0D42FH 2024-07-09 02:01:23.553544+00:00 2024-07-09 01:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T01:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 02:05:14.068036+00:00 2024-07-09 01:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-V8M1GV6U9J59 2024-07-09 02:05:35.941287+00:00 2024-07-09 01:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T02:00:00+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=2024-07-09T02:00:00+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=2024-07-09T02:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 03:00:26.482324+00:00 2024-07-09 02:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1KOP63GCRHSZ4 2024-07-09 03:00:47.758791+00:00 2024-07-09 02:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T02:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 03:05:07.613303+00:00 2024-07-09 02:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-20VJLZS47MM9U 2024-07-09 03:05:29.473367+00:00 2024-07-09 02:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-exchange-dsp-reporting", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 5, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}, {"InstanceType": "m5.4xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "DSPExchangeTradeJob", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-08T04:00:00+00:00", "--class", "com.viooh.smex.dsp.DSPExchangeTrade", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/smex/dsp-exchange-trade/2.11.0/dsp-exchange-trade-2.11.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}, {"Name": "CopyDSPReports", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "s3://cn-northwest-1.elasticmapreduce/libs/script-runner/script-runner.jar", "Args": ["s3://viooh-spark-artifacts-lab-cn/scripts/exchange-dsp-reporting/1.0.0/job.sh", "--environment", "uat", "--reportdate", "2024-07-08", "--region", "cn", "--skipFailure"]}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "exchange-reporting"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-exchange-dsp-reporting"}], "Configurations": []} 2024-07-09 04:00:23.692905+00:00 2024-07-08 04:00:00+00:00 create_emr_steps exchange-dsp-reporting_v002
return_value j-37LAGJKIP0VNT 2024-07-09 04:00:43.584320+00:00 2024-07-08 04:00:00+00:00 create_cluster_and_add_emr_steps exchange-dsp-reporting_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T03:00:00+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=2024-07-09T03:00:00+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=2024-07-09T03:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 04:00:46.744459+00:00 2024-07-09 03:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2AZ7IJE6FWM5V 2024-07-09 04:01:09.810205+00:00 2024-07-09 03:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T03:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 04:05:33.476830+00:00 2024-07-09 03:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-A61T5T6YRKK9 2024-07-09 04:05:53.600209+00:00 2024-07-09 03:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T04:00:00+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=2024-07-09T04:00:00+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=2024-07-09T04:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 05:00:38.570374+00:00 2024-07-09 04:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2INBTLZ35ZQ6C 2024-07-09 05:01:02.297491+00:00 2024-07-09 04:00:00+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=2024-07-09T04:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 05:05:29.750851+00:00 2024-07-09 04:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-124QWQAIZ6MA2 2024-07-09 05:05:51.341435+00:00 2024-07-09 04:05:00+00:00 create_cluster_and_add_emr_steps vc-asset-import_v002
return_value {"Name": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}, {"InstanceType": "m5.2xlarge", "EbsConfiguration": {"EbsBlockDeviceConfigs": [{"VolumeSpecification": {"VolumeType": "gp2", "SizeInGB": 50}, "VolumesPerInstance": 1}], "EbsOptimized": true}}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-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=2024-07-09T05:00:00+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=2024-07-09T05:00:00+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=2024-07-09T05:00:00+00:00", "--class", "uk.co.viooh.job.modeltransform.ModelTransform", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/uk/co/viooh/pandora-model-transform/1.5.0/pandora-model-transform-1.5.0.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-livepop-shuffle-aggregator-modeltransform"}], "Configurations": []} 2024-07-09 06:00:30.264359+00:00 2024-07-09 05:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-2T5OGZ4XCMYSO 2024-07-09 06:00:57.712538+00:00 2024-07-09 05:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-09T05:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 06:05:32.284473+00:00 2024-07-09 05:05:00+00:00 create_emr_steps vc-asset-import_v002
return_value j-2KFZS53SZWRXY 2024-07-09 06:05:51.967095+00:00 2024-07-09 05:05:00+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-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": "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=2024-03-08T09:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.3.0/campaign-extractor-1.3.0-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=2024-03-08T09:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.7.0/campaign-processing-job-1.7.0.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=2024-03-08T09:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.16.0/pandora-campaign-delta-1.16.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-booking-processing-job"}], "Configurations": []} 2024-07-09 06:16:49.316493+00:00 2024-03-08 09:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "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=2024-03-08T12:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.3.0/campaign-extractor-1.3.0-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=2024-03-08T12:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.7.0/campaign-processing-job-1.7.0.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=2024-03-08T12:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.16.0/pandora-campaign-delta-1.16.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-booking-processing-job"}], "Configurations": []} 2024-07-09 06:17:11.143320+00:00 2024-03-08 12:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "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=2024-03-08T20:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.3.0/campaign-extractor-1.3.0-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=2024-03-08T20:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.7.0/campaign-processing-job-1.7.0.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=2024-03-08T20:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.16.0/pandora-campaign-delta-1.16.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-booking-processing-job"}], "Configurations": []} 2024-07-09 06:18:01.288678+00:00 2024-03-08 20:00:00+00:00 create_emr_steps booking-processing-job_v002
return_value {"Name": "vd-uat-viooh-booking-processing-job", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge", "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=2024-07-09T06:00:00+00:00", "--class", "com.viooh.campaignextractor.CampaignExtractorMain", "--jars", "/usr/lib/spark/external/lib/spark-avro.jar", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaignextractor/campaign-extractor/1.5.0/campaign-extractor-1.5.0-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=2024-07-09T06:00:00+00:00", "--class", "com.viooh.CampaignProcessingMain", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/campaign-processing-job/1.10.0/campaign-processing-job-1.10.0.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=2024-07-09T06:00:00+00:00", "--class", "com.viooh.booking.delta.CampaignDeltaMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/pandora-campaign-delta/1.19.0/pandora-campaign-delta-1.19.0-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": []} 2024-07-09 07:00:18.487126+00:00 2024-07-09 06:00:00+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=2024-07-09T06:00:00+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=2024-07-09T06:00:00+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=2024-07-09T06:00:00+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": []} 2024-07-09 07:00:34.082647+00:00 2024-07-09 06:00:00+00:00 create_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value j-1UKDI8HFWE3NP 2024-07-09 07:00:55.815957+00:00 2024-07-09 06:00:00+00:00 create_cluster_and_add_emr_steps livepop-shuffle-aggregator-modeltransform_v004
return_value {"Name": "vd-uat-viooh-vc-asset-import", "LogUri": "s3n://viooh-emr-logs-lab-cn/bigdata/emr/", "ReleaseLabel": "emr-5.35.0", "Instances": {"InstanceFleets": [{"Name": "Masterfleet", "InstanceFleetType": "MASTER", "TargetOnDemandCapacity": 1, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}, {"Name": "Corefleet", "InstanceFleetType": "CORE", "TargetOnDemandCapacity": 3, "InstanceTypeConfigs": [{"InstanceType": "m5.xlarge"}, {"InstanceType": "m5.2xlarge"}]}], "Ec2KeyName": "data.engineer.lab", "KeepJobFlowAliveWhenNoSteps": false, "TerminationProtected": false, "Ec2SubnetId": "subnet-0e214a494e67e2266", "EmrManagedMasterSecurityGroup": "sg-0da002beeed87fb1a", "EmrManagedSlaveSecurityGroup": "sg-0f1a0b7517309fcf0", "ServiceAccessSecurityGroup": "sg-009528c399781cc69"}, "BootstrapActions": [], "Applications": [{"Name": "Spark"}, {"Name": "Hadoop"}, {"Name": "Ganglia"}, {"Name": "Zeppelin"}], "VisibleToAllUsers": true, "Steps": [{"Name": "Setup Hadoop Debugging", "ActionOnFailure": "TERMINATE_JOB_FLOW", "HadoopJarStep": {"Jar": "command-runner.jar", "Args": ["state-pusher-script"]}}, {"Name": "PopulateVCAssetsToCassandra", "ActionOnFailure": "TERMINATE_CLUSTER", "HadoopJarStep": {"Args": ["spark-submit", "--deploy-mode", "cluster", "--master", "yarn", "--conf", "spark.yarn.submit.waitAppCompletion=true", "--conf", "spark.driver.memory=9g", "--conf", "spark.app.viooh.compliance.assets.write.flag=true", "--conf", "spark.app.save.latest.frame.state.flag=true", "--conf", "spark.app.viooh.central.raw.assets.write.flag=true", "--conf", "spark.app.env=uat", "--conf", "spark.dag.execution.time=2024-07-09T06:05:00+00:00", "--class", "VioohCentralAssetsMain", "--files", "s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.conf,s3://viooh-spark-artifacts-lab-cn/metrics/batch-job-metrics/1.0.0/job.yaml", "--conf", "spark.metrics.conf=job.conf", "s3://viooh-spark-artifacts-lab-cn/releases/com/viooh/daily-import/1.10.0/daily-import-1.10.0-jar-with-dependencies.jar"], "Jar": "command-runner.jar"}}], "JobFlowRole": "DeEmrInstanceRole", "ServiceRole": "DeEmrServiceRole", "SecurityConfiguration": "bigdata_emr_cn_sec_conf", "Tags": [{"Key": "environment", "Value": "uat"}, {"Key": "role", "Value": "analysis"}, {"Key": "application", "Value": "emr"}, {"Key": "project", "Value": "campaign-compliance"}, {"Key": "TerminationPolicy", "Value": "OFFICE-HOURS"}, {"Key": "ContactEmail", "Value": "viooh.data@viooh.com"}, {"Key": "team", "Value": "bigdata"}, {"Key": "Name", "Value": "vd-uat-viooh-vc-asset-import"}], "Configurations": []} 2024-07-09 07:05:04.595228+00:00 2024-07-09 06:05:00+00:00 create_emr_steps vc-asset-import_v002