Asociar volúmenes de EBS a los nodos del clúster

Puede asociar volúmenes de EBS a cualquier tipo de nodo en el clúster de EMR dentro de la canalización. Para asociar volúmenes de EBS a los nodos, utilice coreEbsConfiguration, masterEbsConfiguration y TaskEbsConfiguration en su configuración EmrCluster.

Este ejemplo del clúster Amazon EMR utiliza volúmenes de Amazon EBS para sus nodos de tarea, maestro y principal. Para más información, consulte Volúmenes de Amazon EBS en Amazon EMR en la Guía de administración de Amazon EMR.

Estas configuraciones son opcionales. Puede utilizarlas en cualquier canalización que use un objeto EmrCluster.

En la canalización, haga clic en la configuración del objeto EmrCluster, seleccione Master EBS Configuration, (Configuración de EBS maestra) Core EBS Configuration, (Configuración de EBS principal) Task EBS Configuration (Configuración de EBS de tareas) y especifique los detalles de configuración de modo similar a como se muestra en el siguiente ejemplo.

{
  "objects": [
    {
      "output": {
        "ref": "S3BackupLocation"
      },
      "input": {
        "ref": "DDBSourceTable"
      },
      "maximumRetries": "2",
      "name": "TableBackupActivity",
      "step": "s3://dynamodb-emr-#{myDDBRegion}/emr-ddb-storage-handler/2.1.0/emr-ddb-2.1.0.jar,org.apache.hadoop.dynamodb.tools.DynamoDbExport,#{output.directoryPath},#{input.tableName},#{input.readThroughputPercent}",
      "id": "TableBackupActivity",
      "runsOn": {
        "ref": "EmrClusterForBackup"
      },
      "type": "EmrActivity",
      "resizeClusterBeforeRunning": "false"
    },
    {
      "readThroughputPercent": "#{myDDBReadThroughputRatio}",
      "name": "DDBSourceTable",
      "id": "DDBSourceTable",
      "type": "DynamoDBDataNode",
      "tableName": "#{myDDBTableName}"
    },
    {
      "directoryPath": "#{myOutputS3Loc}/#{format(@scheduledStartTime, 'YYYY-MM-dd-HH-mm-ss')}",
      "name": "S3BackupLocation",
      "id": "S3BackupLocation",
      "type": "S3DataNode"
    },
    {
      "name": "EmrClusterForBackup",
      "coreInstanceCount": "1",
      "taskInstanceCount": "1",
      "taskInstanceType": "m4.xlarge",
      "coreInstanceType": "m4.xlarge",
      "releaseLabel": "emr-4.7.0",
      "masterInstanceType": "m4.xlarge",
      "id": "EmrClusterForBackup",
      "subnetId": "#{mySubnetId}",
      "emrManagedMasterSecurityGroupId": "#{myMasterSecurityGroup}",
      "emrManagedSlaveSecurityGroupId": "#{mySlaveSecurityGroup}",
      "region": "#{myDDBRegion}",
      "type": "EmrCluster",
      "coreEbsConfiguration": {
        "ref": "EBSConfiguration"
      },
      "masterEbsConfiguration": {
        "ref": "EBSConfiguration"
      },
      "taskEbsConfiguration": {
        "ref": "EBSConfiguration"
      },
      "keyPair": "user-key-pair"
    },
    {
       "name": "EBSConfiguration",
        "id": "EBSConfiguration",
        "ebsOptimized": "true",
        "ebsBlockDeviceConfig" : [
            { "ref": "EbsBlockDeviceConfig" }
        ],
        "type": "EbsConfiguration"
    },
    {
        "name": "EbsBlockDeviceConfig",
        "id": "EbsBlockDeviceConfig",
        "type": "EbsBlockDeviceConfig",
        "volumesPerInstance" : "2",
        "volumeSpecification" : {
            "ref": "VolumeSpecification"
        }
    },
    {
      "name": "VolumeSpecification",
      "id": "VolumeSpecification",
      "type": "VolumeSpecification",
      "sizeInGB": "500",
      "volumeType": "io1",
      "iops": "1000"
    },
    {
      "failureAndRerunMode": "CASCADE",
      "resourceRole": "DataPipelineDefaultResourceRole",
      "role": "DataPipelineDefaultRole",
      "pipelineLogUri": "#{myPipelineLogUri}",
      "scheduleType": "ONDEMAND",
      "name": "Default",
      "id": "Default"
    }
  ],
  "parameters": [
    {
      "description": "Output S3 folder",
      "id": "myOutputS3Loc",
      "type": "AWS::S3::ObjectKey"
    },
    {
      "description": "Source DynamoDB table name",
      "id": "myDDBTableName",
      "type": "String"
    },
    {
      "default": "0.25",
      "watermark": "Enter value between 0.1-1.0",
      "description": "DynamoDB read throughput ratio",
      "id": "myDDBReadThroughputRatio",
      "type": "Double"
    },
    {
      "default": "us-east-1",
      "watermark": "us-east-1",
      "description": "Region of the DynamoDB table",
      "id": "myDDBRegion",
      "type": "String"
    }
  ],
  "values": {
     "myDDBRegion": "us-east-1",
      "myDDBTableName": "ddb_table",
      "myDDBReadThroughputRatio": "0.25",
      "myOutputS3Loc": "s3://s3_path",
      "mySubnetId": "subnet_id",
      "mySlaveSecurityGroup": "slave security group",
      "myMasterSecurityGroup": "master security group",
      "myPipelineLogUri": "s3://s3_path"
  }
}