Document Details

# hdfs-site.xml configuration
$HdfsConfigValues = @{ "dfs.blocksize"="64m" } #default is 128MB in HDI 3.0 and 256MB in HDI 2.1

# core-site.xml configuration
$CoreConfigValues = @{ "ipc.client.connect.max.retries"="60" } #default 50

# mapred-site.xml configuration
$MapRedConfigValues = @{ "mapreduce.task.timeout"="1200000" } #default 600000

# oozie-site.xml configuration
$OozieConfigValues = @{ "oozie.service.coord.normal.default.timeout"="150" }  # default 120

# hive-site.xml configuration
$hiveConfigValues = @{ "hive.metastore.client.socket.timeout"="90s" }

$config = New-AzHDInsightClusterConfig `
         -ClusterType "Spark"  `
    | Set-AzHDInsightDefaultStorage `
        -StorageAccountResourceId "$storageAccountResourceId" `
        -StorageAccountKey $defaultStorageAccountKey `
    | Add-AzHDInsightConfigValue `
        -HiveSite $hiveConfigValues `
        -Spark2Defaults @{}

New-AzHDInsightCluster `
    -ResourceGroupName $resourceGroupName `
    -ClusterName $hdinsightClusterName `
    -Location $location `
    -ClusterSizeInNodes 2 `
    -Version "4.0" `
    -HttpCredential $httpCredential `
    -SshCredential $sshCredential `
    -Config $config

####################################
# Service names and variables
####################################

$nameToken = "<ENTER AN ALIAS>"
$namePrefix = $nameToken.ToLower() + (Get-Date -Format "MMdd")
$resourceGroupName = $namePrefix + "rg"
$hdinsightClusterName = $namePrefix + "hdi"
$defaultStorageAccountName = $namePrefix + "store"
$defaultBlobContainerName = $hdinsightClusterName
$location = "East US"

####################################
# Connect to Azure
####################################

Write-Host "Connecting to your Azure subscription ..." -ForegroundColor Green
$sub = Get-AzSubscription -ErrorAction SilentlyContinue
if(-not($sub))
{
    Connect-AzAccount
}

# If you have multiple subscriptions, set the one to use
#$context = Get-AzSubscription -SubscriptionId "<subscriptionID>"
#Set-AzContext $context

####################################
# Create a resource group
####################################

Write-Host "Creating a resource group ..." -ForegroundColor Green
New-AzResourceGroup `
    -Name  $resourceGroupName `
    -Location $location

####################################
# Create a storage account and container
####################################
	
Write-Host "Creating the default storage account and default blob container ..."  -ForegroundColor Green
New-AzStorageAccount `
    -ResourceGroupName $resourceGroupName `
    -Name $defaultStorageAccountName `
    -Location $location `
    -SkuName Standard_LRS `
    -Kind StorageV2 `
    -EnableHttpsTrafficOnly 1
	
$defaultStorageAccountKey = (Get-AzStorageAccountKey `
                                -ResourceGroupName $resourceGroupName `
                                -Name $defaultStorageAccountName)[0].Value

$defaultStorageContext = New-AzStorageContext `
                                -StorageAccountName $defaultStorageAccountName `
                                -StorageAccountKey $defaultStorageAccountKey
								
New-AzStorageContainer `
    -Name $defaultBlobContainerName `
    -Context $defaultStorageContext #use the cluster name as the container name

####################################
# Create a configuration object
####################################

$hiveConfigValues = @{"hive.metastore.client.socket.timeout"="90s"}
$storageAccountResourceId = (Get-AzStorageAccount -ResourceGroupName $resourceGroupName ` -Name $defaultStorageAccountName).Id

$config = New-AzHDInsightClusterConfig `
          -ClusterType "Spark"  `
    | Set-AzHDInsightDefaultStorage `
        -StorageAccountResourceId "$storageAccountResourceId" `
        -StorageAccountKey $defaultStorageAccountKey `
    | Add-AzHDInsightConfigValue `
        -HiveSite $hiveConfigValues `
		-Spark2Defaults @{}
		
####################################
# Set Ambari admin username/password
####################################

$httpUserName = "admin"  #HDInsight cluster username
$httpPassword = '<ENTER A PASSWORD>'

$httpPW = ConvertTo-SecureString -String $httpPassword -AsPlainText -Force
$httpCredential = New-Object System.Management.Automation.PSCredential($httpUserName,$httpPW)

####################################
# Set ssh username/password
####################################

$sshUserName = "sshuser" #HDInsight ssh user name
$sshPassword = '<ENTER A PASSWORD>'

$sshPW = ConvertTo-SecureString -String $sshPassword -AsPlainText -Force
$sshCredential = New-Object System.Management.Automation.PSCredential($sshUserName,$sshPW)

####################################
# Create an HDInsight cluster
####################################

New-AzHDInsightCluster `
    -ResourceGroupName $resourceGroupName `
    -ClusterName $hdinsightClusterName `
    -Location $location `
    -ClusterSizeInNodes 2 `
    -Version "4.0" `
    -HttpCredential $httpCredential `
    -SshCredential $sshCredential `
    -Config $config
	
####################################
# Verify the cluster
####################################

Get-AzHDInsightCluster `
    -ClusterName $hdinsightClusterName