AWS Data Pipeline is no longer available to new customers. Existing customers of AWS Data Pipeline can continue to use the service as normal. [Learn more](https://aws.amazon.com/blogs/big-data/migrate-workloads-from-aws-data-pipeline/)
# Examples
The following are examples of this object type.
**Topics**
+ [Launch an Amazon EMR cluster with hadoopVersion](emrcluster-example-launch.md)
+ [Launch an Amazon EMR cluster with release label emr-4.x or greater](emrcluster-example-release-label.md)
+ [Install additional software on your Amazon EMR cluster](emrcluster-example-install-software.md)
+ [Disable server-side encryption on 3.x releases](emrcluster-example1-disable-encryption.md)
+ [Disable server-side encryption on 4.x releases](emrcluster-example2-disable-encryption.md)
+ [Configure Hadoop KMS ACLs and create encryption zones in HDFS](emrcluster-example-hadoop-kms.md)
+ [Specify custom IAM roles](emrcluster-example-custom-iam-roles.md)
+ [Use EmrCluster Resource in AWS SDK for Java](emrcluster-example-java.md)
+ [Configure an Amazon EMR cluster in a private subnet](emrcluster-example-private-subnet.md)
+ [Attach EBS volumes to cluster nodes](emrcluster-example-ebs.md)
# Launch an Amazon EMR cluster with hadoopVersion
**Example**
The following example launches an Amazon EMR cluster using AMI version 1.0 and Hadoop 0.20.
```
{
"id" : "MyEmrCluster",
"type" : "EmrCluster",
"hadoopVersion" : "0.20",
"keyPair" : "my-key-pair",
"masterInstanceType" : "m3.xlarge",
"coreInstanceType" : "m3.xlarge",
"coreInstanceCount" : "10",
"taskInstanceType" : "m3.xlarge",
"taskInstanceCount": "10",
"bootstrapAction" : ["s3://Region.elasticmapreduce/bootstrap-actions/configure-hadoop,arg1,arg2,arg3","s3://Region.elasticmapreduce/bootstrap-actions/configure-hadoop/configure-other-stuff,arg1,arg2"]
}
```
# Launch an Amazon EMR cluster with release label emr-4.x or greater
**Example**
The following example launches an Amazon EMR cluster using the newer `releaseLabel` field:
```
{
"id" : "MyEmrCluster",
"type" : "EmrCluster",
"keyPair" : "my-key-pair",
"masterInstanceType" : "m3.xlarge",
"coreInstanceType" : "m3.xlarge",
"coreInstanceCount" : "10",
"taskInstanceType" : "m3.xlarge",
"taskInstanceCount": "10",
"releaseLabel": "emr-4.1.0",
"applications": ["spark", "hive", "pig"],
"configuration": {"ref":"myConfiguration"}
}
```
# Install additional software on your Amazon EMR cluster
**Example**
`EmrCluster` provides the `supportedProducts` field that installs third-party software on an Amazon EMR cluster, for example, it lets you install a custom distribution of Hadoop, such as MapR. It accepts a comma-separated list of arguments for the third-party software to read and act on. The following example shows how to use the `supportedProducts` field of `EmrCluster` to create a custom MapR M3 edition cluster with Karmasphere Analytics installed, and run an `EmrActivity` object on it.
```
{
"id": "MyEmrActivity",
"type": "EmrActivity",
"schedule": {"ref": "ResourcePeriod"},
"runsOn": {"ref": "MyEmrCluster"},
"postStepCommand": "echo Ending job >> /mnt/var/log/stepCommand.txt",
"preStepCommand": "echo Starting job > /mnt/var/log/stepCommand.txt",
"step": "/home/hadoop/contrib/streaming/hadoop-streaming.jar,-input,s3n://elasticmapreduce/samples/wordcount/input,-output, \
hdfs:///output32113/,-mapper,s3n://elasticmapreduce/samples/wordcount/wordSplitter.py,-reducer,aggregate"
},
{
"id": "MyEmrCluster",
"type": "EmrCluster",
"schedule": {"ref": "ResourcePeriod"},
"supportedProducts": ["mapr,--edition,m3,--version,1.2,--key1,value1","karmasphere-enterprise-utility"],
"masterInstanceType": "m3.xlarge",
"taskInstanceType": "m3.xlarge"
}
```
# Disable server-side encryption on 3.x releases
**Example**
An `EmrCluster` activity with a Hadoop version 2.x created by AWS Data Pipeline enables server-side encryption by default. If you would like to disable server-side encryption, you must specify a bootstrap action in the cluster object definition.
The following example creates an `EmrCluster` activity with server-side encryption disabled:
```
{
"id":"NoSSEEmrCluster",
"type":"EmrCluster",
"hadoopVersion":"2.x",
"keyPair":"my-key-pair",
"masterInstanceType":"m3.xlarge",
"coreInstanceType":"m3.large",
"coreInstanceCount":"10",
"taskInstanceType":"m3.large",
"taskInstanceCount":"10",
"bootstrapAction":["s3://Region.elasticmapreduce/bootstrap-actions/configure-hadoop,-e, fs.s3.enableServerSideEncryption=false"]
}
```
# Disable server-side encryption on 4.x releases
**Example**
You must disable server-side encryption using a `EmrConfiguration` object.
The following example creates an `EmrCluster` activity with server-side encryption disabled:
```
{
"name": "ReleaseLabelCluster",
"releaseLabel": "emr-4.1.0",
"applications": ["spark", "hive", "pig"],
"id": "myResourceId",
"type": "EmrCluster",
"configuration": {
"ref": "disableSSE"
}
},
{
"name": "disableSSE",
"id": "disableSSE",
"type": "EmrConfiguration",
"classification": "emrfs-site",
"property": [{
"ref": "enableServerSideEncryption"
}
]
},
{
"name": "enableServerSideEncryption",
"id": "enableServerSideEncryption",
"type": "Property",
"key": "fs.s3.enableServerSideEncryption",
"value": "false"
}
```
# Configure Hadoop KMS ACLs and create encryption zones in HDFS
**Example**
The following objects create ACLs for Hadoop KMS and create encryption zones and corresponding encryption keys in HDFS:
```
{
"name": "kmsAcls",
"id": "kmsAcls",
"type": "EmrConfiguration",
"classification": "hadoop-kms-acls",
"property": [
{"ref":"kmsBlacklist"},
{"ref":"kmsAcl"}
]
},
{
"name": "hdfsEncryptionZone",
"id": "hdfsEncryptionZone",
"type": "EmrConfiguration",
"classification": "hdfs-encryption-zones",
"property": [
{"ref":"hdfsPath1"},
{"ref":"hdfsPath2"}
]
},
{
"name": "kmsBlacklist",
"id": "kmsBlacklist",
"type": "Property",
"key": "hadoop.kms.blacklist.CREATE",
"value": "foo,myBannedUser"
},
{
"name": "kmsAcl",
"id": "kmsAcl",
"type": "Property",
"key": "hadoop.kms.acl.ROLLOVER",
"value": "myAllowedUser"
},
{
"name": "hdfsPath1",
"id": "hdfsPath1",
"type": "Property",
"key": "/myHDFSPath1",
"value": "path1_key"
},
{
"name": "hdfsPath2",
"id": "hdfsPath2",
"type": "Property",
"key": "/myHDFSPath2",
"value": "path2_key"
}
```
# Specify custom IAM roles
**Example**
By default, AWS Data Pipeline passes `DataPipelineDefaultRole` as the Amazon EMR service role and `DataPipelineDefaultResourceRole` as the Amazon EC2 instance profile to create resources on your behalf. However, you can create a custom Amazon EMR service role and a custom instance profile and use them instead. AWS Data Pipeline should have sufficient permissions to create clusters using the custom role, and you must add AWS Data Pipeline as a trusted entity.
The following example object specifies custom roles for the Amazon EMR cluster:
```
{
"id":"MyEmrCluster",
"type":"EmrCluster",
"hadoopVersion":"2.x",
"keyPair":"my-key-pair",
"masterInstanceType":"m3.xlarge",
"coreInstanceType":"m3.large",
"coreInstanceCount":"10",
"taskInstanceType":"m3.large",
"taskInstanceCount":"10",
"role":"emrServiceRole",
"resourceRole":"emrInstanceProfile"
}
```
# Use EmrCluster Resource in AWS SDK for Java
**Example**
The following example shows how to use an `EmrCluster` and `EmrActivity` to create an Amazon EMR 4.x cluster to run a Spark step using the Java SDK:
```
public class dataPipelineEmr4 {
public static void main(String[] args) {
AWSCredentials credentials = null;
credentials = new ProfileCredentialsProvider("/path/to/AwsCredentials.properties","default").getCredentials();
DataPipelineClient dp = new DataPipelineClient(credentials);
CreatePipelineRequest createPipeline = new CreatePipelineRequest().withName("EMR4SDK").withUniqueId("unique");
CreatePipelineResult createPipelineResult = dp.createPipeline(createPipeline);
String pipelineId = createPipelineResult.getPipelineId();
PipelineObject emrCluster = new PipelineObject()
.withName("EmrClusterObj")
.withId("EmrClusterObj")
.withFields(
new Field().withKey("releaseLabel").withStringValue("emr-4.1.0"),
new Field().withKey("coreInstanceCount").withStringValue("3"),
new Field().withKey("applications").withStringValue("spark"),
new Field().withKey("applications").withStringValue("Presto-Sandbox"),
new Field().withKey("type").withStringValue("EmrCluster"),
new Field().withKey("keyPair").withStringValue("myKeyName"),
new Field().withKey("masterInstanceType").withStringValue("m3.xlarge"),
new Field().withKey("coreInstanceType").withStringValue("m3.xlarge")
);
PipelineObject emrActivity = new PipelineObject()
.withName("EmrActivityObj")
.withId("EmrActivityObj")
.withFields(
new Field().withKey("step").withStringValue("command-runner.jar,spark-submit,--executor-memory,1g,--class,org.apache.spark.examples.SparkPi,/usr/lib/spark/lib/spark-examples.jar,10"),
new Field().withKey("runsOn").withRefValue("EmrClusterObj"),
new Field().withKey("type").withStringValue("EmrActivity")
);
PipelineObject schedule = new PipelineObject()
.withName("Every 15 Minutes")
.withId("DefaultSchedule")
.withFields(
new Field().withKey("type").withStringValue("Schedule"),
new Field().withKey("period").withStringValue("15 Minutes"),
new Field().withKey("startAt").withStringValue("FIRST_ACTIVATION_DATE_TIME")
);
PipelineObject defaultObject = new PipelineObject()
.withName("Default")
.withId("Default")
.withFields(
new Field().withKey("failureAndRerunMode").withStringValue("CASCADE"),
new Field().withKey("schedule").withRefValue("DefaultSchedule"),
new Field().withKey("resourceRole").withStringValue("DataPipelineDefaultResourceRole"),
new Field().withKey("role").withStringValue("DataPipelineDefaultRole"),
new Field().withKey("pipelineLogUri").withStringValue("s3://myLogUri"),
new Field().withKey("scheduleType").withStringValue("cron")
);
List pipelineObjects = new ArrayList();
pipelineObjects.add(emrActivity);
pipelineObjects.add(emrCluster);
pipelineObjects.add(defaultObject);
pipelineObjects.add(schedule);
PutPipelineDefinitionRequest putPipelineDefintion = new PutPipelineDefinitionRequest()
.withPipelineId(pipelineId)
.withPipelineObjects(pipelineObjects);
PutPipelineDefinitionResult putPipelineResult = dp.putPipelineDefinition(putPipelineDefintion);
System.out.println(putPipelineResult);
ActivatePipelineRequest activatePipelineReq = new ActivatePipelineRequest()
.withPipelineId(pipelineId);
ActivatePipelineResult activatePipelineRes = dp.activatePipeline(activatePipelineReq);
System.out.println(activatePipelineRes);
System.out.println(pipelineId);
}
}
```
# Configure an Amazon EMR cluster in a private subnet
**Example**
This example includes a configuration that launches the cluster into a private subnet in a VPC. For more information, see [Launch Amazon EMR Clusters into a VPC](https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-vpc-launching-job-flows.html) in the *Amazon EMR Management Guide*. This configuration is optional. You can use it in any pipeline that uses an `EmrCluster` object.
To launch an Amazon EMR cluster in a private subnet, specify `SubnetId`, `emrManagedMasterSecurityGroupId`, `emrManagedSlaveSecurityGroupId`, and `serviceAccessSecurityGroupId` in your `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"
}
}
```
# Attach EBS volumes to cluster nodes
**Example**
You can attach EBS volumes to any type of node in the EMR cluster within your pipeline. To attach EBS volumes to nodes, use `coreEbsConfiguration`, `masterEbsConfiguration`, and `TaskEbsConfiguration` in your `EmrCluster` configuration.
This example of the Amazon EMR cluster uses Amazon EBS volumes for its master, task, and core nodes. For more information, see [Amazon EBS volumes in Amazon EMR](https://docs.aws.amazon.com/emr/latest/ManagementGuide/emr-plan-storage.html) in the *Amazon EMR Management Guide*.
These configurations are optional. You can use them in any pipeline that uses an `EmrCluster` object.
In the pipeline, click the `EmrCluster` object configuration, choose **Master EBS Configuration**, **Core EBS Configuration**, or **Task EBS Configuration**, and enter the configuration details similar to the following example.
```
{
"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"
}
}
```