Create cluster

Creates a Dataproc cluster.

Explore further

For detailed documentation that includes this code sample, see the following:

Code sample

Go

Before trying this sample, follow the Go setup instructions in the Managed Service for Apache Spark quickstart using client libraries. For more information, see the Managed Service for Apache Spark Go API reference documentation.

To authenticate to Managed Service for Apache Spark, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

import (
	"context"
	"fmt"
	"io"

	dataproc "cloud.google.com/go/dataproc/apiv1"
	"cloud.google.com/go/dataproc/apiv1/dataprocpb"
	"google.golang.org/api/option"
)

func createCluster(w io.Writer, projectID, region, clusterName string) error {
	// projectID := "your-project-id"
	// region := "us-central1"
	// clusterName := "your-cluster"
	ctx := context.Background()

	// Create the cluster client.
	endpoint := region + "-dataproc.googleapis.com:443"
	clusterClient, err := dataproc.NewClusterControllerClient(ctx, option.WithEndpoint(endpoint))
	if err != nil {
		return fmt.Errorf("dataproc.NewClusterControllerClient: %w", err)
	}
	defer clusterClient.Close()

	// Create the cluster config.
	req := &dataprocpb.CreateClusterRequest{
		ProjectId: projectID,
		Region:    region,
		Cluster: &dataprocpb.Cluster{
			ProjectId:   projectID,
			ClusterName: clusterName,
			Config: &dataprocpb.ClusterConfig{
				MasterConfig: &dataprocpb.InstanceGroupConfig{
					NumInstances:   1,
					MachineTypeUri: "n1-standard-2",
				},
				WorkerConfig: &dataprocpb.InstanceGroupConfig{
					NumInstances:   2,
					MachineTypeUri: "n1-standard-2",
				},
			},
		},
	}

	// Create the cluster.
	op, err := clusterClient.CreateCluster(ctx, req)
	if err != nil {
		return fmt.Errorf("CreateCluster: %w", err)
	}

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("CreateCluster.Wait: %w", err)
	}

	// Output a success message.
	fmt.Fprintf(w, "Cluster created successfully: %s", resp.ClusterName)
	return nil
}

Java

Before trying this sample, follow the Java setup instructions in the Managed Service for Apache Spark quickstart using client libraries. For more information, see the Managed Service for Apache Spark Java API reference documentation.

To authenticate to Managed Service for Apache Spark, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.dataproc.v1.Cluster;
import com.google.cloud.dataproc.v1.ClusterConfig;
import com.google.cloud.dataproc.v1.ClusterControllerClient;
import com.google.cloud.dataproc.v1.ClusterControllerSettings;
import com.google.cloud.dataproc.v1.ClusterOperationMetadata;
import com.google.cloud.dataproc.v1.InstanceGroupConfig;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

public class CreateCluster {

  public static void createCluster() throws IOException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-project-id";
    String region = "your-project-region";
    String clusterName = "your-cluster-name";
    createCluster(projectId, region, clusterName);
  }

  public static void createCluster(String projectId, String region, String clusterName)
      throws IOException, InterruptedException {
    String myEndpoint = String.format("%s-dataproc.googleapis.com:443", region);

    // Configure the settings for the cluster controller client.
    ClusterControllerSettings clusterControllerSettings =
        ClusterControllerSettings.newBuilder().setEndpoint(myEndpoint).build();

    // Create a cluster controller client with the configured settings. The client only needs to be
    // created once and can be reused for multiple requests. Using a try-with-resources
    // closes the client, but this can also be done manually with the .close() method.
    try (ClusterControllerClient clusterControllerClient =
        ClusterControllerClient.create(clusterControllerSettings)) {
      // Configure the settings for our cluster.
      InstanceGroupConfig masterConfig =
          InstanceGroupConfig.newBuilder()
              .setMachineTypeUri("n1-standard-2")
              .setNumInstances(1)
              .build();
      InstanceGroupConfig workerConfig =
          InstanceGroupConfig.newBuilder()
              .setMachineTypeUri("n1-standard-2")
              .setNumInstances(2)
              .build();
      ClusterConfig clusterConfig =
          ClusterConfig.newBuilder()
              .setMasterConfig(masterConfig)
              .setWorkerConfig(workerConfig)
              .build();
      // Create the cluster object with the desired cluster config.
      Cluster cluster =
          Cluster.newBuilder().setClusterName(clusterName).setConfig(clusterConfig).build();

      // Create the Cloud Dataproc cluster.
      OperationFuture<Cluster, ClusterOperationMetadata> createClusterAsyncRequest =
          clusterControllerClient.createClusterAsync(projectId, region, cluster);
      Cluster response = createClusterAsyncRequest.get();

      // Print out a success message.
      System.out.printf("Cluster created successfully: %s", response.getClusterName());

    } catch (ExecutionException e) {
      System.err.println(String.format("Error executing createCluster: %s ", e.getMessage()));
    }
  }
}

Node.js

Before trying this sample, follow the Node.js setup instructions in the Managed Service for Apache Spark quickstart using client libraries. For more information, see the Managed Service for Apache Spark Node.js API reference documentation.

To authenticate to Managed Service for Apache Spark, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

const dataproc = require('@google-cloud/dataproc');

// TODO(developer): Uncomment and set the following variables
// projectId = 'YOUR_PROJECT_ID'
// region = 'YOUR_CLUSTER_REGION'
// clusterName = 'YOUR_CLUSTER_NAME'

// Create a client with the endpoint set to the desired cluster region
const client = new dataproc.v1.ClusterControllerClient({
  apiEndpoint: `${region}-dataproc.googleapis.com`,
  projectId: projectId,
});

async function createCluster() {
  // Create the cluster config
  const request = {
    projectId: projectId,
    region: region,
    cluster: {
      clusterName: clusterName,
      config: {
        masterConfig: {
          numInstances: 1,
          machineTypeUri: 'n1-standard-2',
        },
        workerConfig: {
          numInstances: 2,
          machineTypeUri: 'n1-standard-2',
        },
      },
    },
  };

  // Create the cluster
  const [operation] = await client.createCluster(request);
  const [response] = await operation.promise();

  // Output a success message
  console.log(`Cluster created successfully: ${response.clusterName}`);

Python

Before trying this sample, follow the Python setup instructions in the Managed Service for Apache Spark quickstart using client libraries. For more information, see the Managed Service for Apache Spark Python API reference documentation.

To authenticate to Managed Service for Apache Spark, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

from google.cloud import dataproc_v1 as dataproc


def create_cluster(project_id, region, cluster_name):
    """This sample walks a user through creating a Cloud Dataproc cluster
    using the Python client library.

    Args:
        project_id (string): Project to use for creating resources.
        region (string): Region where the resources should live.
        cluster_name (string): Name to use for creating a cluster.
    """

    # Create a client with the endpoint set to the desired cluster region.
    cluster_client = dataproc.ClusterControllerClient(
        client_options={"api_endpoint": f"{region}-dataproc.googleapis.com:443"}
    )

    # Create the cluster config.
    cluster = {
        "project_id": project_id,
        "cluster_name": cluster_name,
        "config": {
            "master_config": {"num_instances": 1, "machine_type_uri": "n1-standard-2"},
            "worker_config": {"num_instances": 2, "machine_type_uri": "n1-standard-2"},
        },
    }

    # Create the cluster.
    operation = cluster_client.create_cluster(
        request={"project_id": project_id, "region": region, "cluster": cluster}
    )
    result = operation.result()

    # Output a success message.
    print(f"Cluster created successfully: {result.cluster_name}")

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.