The below is a complete working example of an EMR cluster
1 X master node, on demand
2X core nodes on demand.
no task group, not auto scaling.
and mydomain.
notice the MasterInstanceGroup, CoreInstanceGroup section in the json.
adding 320 GB to both core and master, and increasing the root partition to 100GB (maximum supported). The reason i am sharing this, as the example provided by AWS are not good enough, and it is very confusing to connect the dots.
If this helps you , please “like” and subscribe 🙂
{
"AWSTemplateFormatVersion": "2010-09-09",
"Conditions": {
"Hbase": {
"Fn::Equals": [
{
"Ref": "Applications"
},
"Hbase"
]
},
"Spark": {
"Fn::Equals": [
{
"Ref": "Applications"
},
"Spark"
]
}
},
"Description": "myProdCluster",
"Mappings": {
},
"Outputs": {
},
"Parameters": {
"Applications": {
"AllowedValues": [
"Spark",
"TBD"
],
"Description": "Cluster setup:",
"Type": "String"
},
"CoreInstanceType": {
"Default": "r4.4xlarge",
"Description": "Instance type to be used for core instances.",
"Type": "String"
},
"EMRClusterName": {
"Default": "myProdCluster",
"Description": "Name of the cluster",
"Type": "String"
},
"KeyName": {
"Default": "walla_omid",
"Description": "Must be an existing Keyname",
"Type": "String"
},
"LogUri": {
"Default": "s3://aws-logs-1123-eu-west-1/elasticmapreduce/",
"Description": "Must be a valid S3 URL",
"Type": "String"
},
"MasterInstacneType": {
"Default": "r4.4xlarge",
"Description": "Instance type to be used for the master instance.",
"Type": "String"
},
"NumberOfCoreInstances": {
"Default": 2,
"Description": "Must be a valid number",
"Type": "Number"
},
"ReleaseLabel": {
"Default": "emr-5.13.0",
"Description": "Must be a valid EMR release version",
"Type": "String"
},
"S3DataUri": {
"Default": "s3://aws-logs-1234-eu-west-1/elasticmapreduce/",
"Description": "Must be a valid S3 bucket URL ",
"Type": "String"
},
"SubnetID": {
"Default": "subnet-0647325e",
"Description": "Must be Valid public subnet ID",
"Type": "String"
}
},
"Resources": {
"EMRCluster": {
"DependsOn": [
"EMRClusterServiceRole",
"EMRClusterinstanceProfileRole",
"EMRClusterinstanceProfile"
],
"Properties": {
"Applications": [
{
"Name": "Ganglia"
},
{
"Name": "Spark"
},
{
"Name": "Hive"
},
{
"Name": "Tez"
},
{
"Name": "Zeppelin"
},
{
"Name": "Oozie"
},
{
"Name": "Hue"
},
{
"Name": "Presto"
},
{
"Name": "Livy"
}
],
"AutoScalingRole": "EMR_AutoScaling_DefaultRole",
"Configurations": [
{
"Classification": "hive-site",
"ConfigurationProperties": {
"hive.metastore.client.factory.class": "com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory"
}
},
{
"Classification": "spark",
"ConfigurationProperties": {
"maximizeResourceAllocation": "true"
}
},
{
"Classification": "presto-connector-hive",
"ConfigurationProperties": {
"hive.metastore.glue.datacatalog.enabled": "true"
}
},
{
"Classification": "spark-hive-site",
"ConfigurationProperties": {
"hive.metastore.client.factory.class": "com.amazonaws.glue.catalog.metastore.AWSGlueDataCatalogHiveClientFactory"
}
}
],
"EbsRootVolumeSize": 100,
"Instances": {
"AdditionalMasterSecurityGroups": [
"sg-111"
],
"AdditionalSlaveSecurityGroups": [
"sg-112"
],
"CoreInstanceGroup": {
"EbsConfiguration": {
"EbsBlockDeviceConfigs": [
{
"VolumeSpecification": {
"SizeInGB": "320",
"VolumeType": "gp2"
},
"VolumesPerInstance": "1"
}
],
"EbsOptimized": "true"
},
"InstanceCount": 2,
"InstanceType": "r4.4xlarge",
"Market": "ON_DEMAND",
"Name": "coreNinja"
},
"MasterInstanceGroup": {
"EbsConfiguration": {
"EbsBlockDeviceConfigs": [
{
"VolumeSpecification": {
"SizeInGB": "320",
"VolumeType": "gp2"
},
"VolumesPerInstance": "1"
}
],
"EbsOptimized": "true"
},
"InstanceCount": 1,
"InstanceType": "r4.4xlarge",
"Market": "ON_DEMAND",
"Name": "masterNinja"
},
"Ec2KeyName": {
"Ref": "KeyName"
},
"Ec2SubnetId": {
"Ref": "SubnetID"
},
"TerminationProtected": false
},
"JobFlowRole": {
"Ref": "EMRClusterinstanceProfile"
},
"LogUri": {
"Ref": "LogUri"
},
"Name": {
"Ref": "EMRClusterName"
},
"ReleaseLabel": {
"Ref": "ReleaseLabel"
},
"ServiceRole": {
"Ref": "EMRClusterServiceRole"
},
"VisibleToAllUsers": true
},
"Type": "AWS::EMR::Cluster"
},
"EMRClusterServiceRole": {
"Properties": {
"AssumeRolePolicyDocument": {
"Statement": [
{
"Action": [
"sts:AssumeRole"
],
"Effect": "Allow",
"Principal": {
"Service": [
"elasticmapreduce.amazonaws.com"
]
}
}
],
"Version": "2012-10-17"
},
"ManagedPolicyArns": [
"arn:aws:iam::aws:policy/service-role/AmazonElasticMapReduceRole"
],
"Path": "/",
"Policies": [
{
"PolicyName": "s3fullaccess",
"PolicyDocument": {
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": "s3:*",
"Resource": "*"
}
]
}
}
]
},
"Type": "AWS::IAM::Role"
},
"EMRClusterinstanceProfile": {
"Properties": {
"Path": "/",
"Roles": [
{
"Ref": "EMRClusterinstanceProfileRole"
}
]
},
"Type": "AWS::IAM::InstanceProfile"
},
"EMRClusterinstanceProfileRole": {
"Properties": {
"AssumeRolePolicyDocument": {
"Statement": [
{
"Action": [
"sts:AssumeRole"
],
"Effect": "Allow",
"Principal": {
"Service": [
"ec2.amazonaws.com"
]
}
}
],
"Version": "2012-10-17"
},
"ManagedPolicyArns": [
"arn:aws:iam::aws:policy/service-role/AmazonElasticMapReduceforEC2Role"
],
"Path": "/"
},
"Type": "AWS::IAM::Role"
},
"TestStep": {
"Type": "AWS::EMR::Step",
"Properties": {
"ActionOnFailure": "CONTINUE",
"HadoopJarStep": {
"Args": [
"s3://byoo-emr-bootstrap/bootstrap-emr.sh"
],
"Jar": "s3://eu-west-1.elasticmapreduce/libs/script-runner/script-runner.jar"
},
"Name": "CustomBootstrap",
"JobFlowId": {
"Ref": "EMRCluster"
}
}
},
"myDNSRecord": {
"Type": "AWS::Route53::RecordSet",
"DependsOn": [
"EMRCluster"
],
"Properties": {
"HostedZoneName": "myDomain.",
"Comment": "DNS name for my instance. for emr. cloud formation",
"Name": "mydomain.com",
"Type": "CNAME",
"TTL": "600",
"ResourceRecords": [
{
"Fn::GetAtt": [
"EMRCluster",
"MasterPublicDNS"
]
}
]
}
}
}
}
——————————————————————————————————————————
I put a lot of thoughts into these blogs, so I could share the information in a clear and useful way. If you have any comments, thoughts, questions, or you need someone to consult with, feel free to contact me: