Configuration d'un EMR cluster Amazon dans un sous-réseau privé - AWS Data Pipeline

AWS Data Pipeline n'est plus disponible pour les nouveaux clients. Les clients existants de AWS Data Pipeline peut continuer à utiliser le service normalement. En savoir plus

Les traductions sont fournies par des outils de traduction automatique. En cas de conflit entre le contenu d'une traduction et celui de la version originale en anglais, la version anglaise prévaudra.

Configuration d'un EMR cluster Amazon dans un sous-réseau privé

Cet exemple inclut une configuration qui lance le cluster dans un sous-réseau privé dans unVPC. Pour plus d'informations, consultez la section Launch Amazon EMR Clusters into a VPC dans le guide EMR de gestion Amazon. Cette configuration est facultative. Vous pouvez l'utiliser dans n'importe quel pipeline utilisant un objet EmrCluster.

Pour lancer un EMR cluster Amazon dans un sous-réseau privé, spécifiezSubnetId, emrManagedMasterSecurityGroupIdemrManagedSlaveSecurityGroupId, et serviceAccessSecurityGroupId dans votre EmrCluster configuration.

{
  "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}",
      "serviceAccessSecurityGroupId": "#{myServiceAccessSecurityGroup}",
      "region": "#{myDDBRegion}",
      "type": "EmrCluster",
      "keyPair": "user-key-pair"
    },
    {
      "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",
      "myServiceAccessSecurityGroup":  "service access security group",
      "mySlaveSecurityGroup": "slave security group",
      "myMasterSecurityGroup": "master security group",
      "myPipelineLogUri": "s3://s3_path"
  }
}