"Managed Service for Apache Spark" is the new name for the product formerly known as "Dataproc on Compute Engine" (cluster deployment) and "Google Cloud Serverless for Apache Spark" (serverless deployment).

Google uses AI technology to translate content into your preferred language. AI translations can contain errors.

인라인 워크플로 템플릿 인스턴스화

Cloud 클라이언트 라이브러리를 사용하여 인라인 워크플로 템플릿을 인스턴스화합니다.

더 살펴보기

이 코드 샘플이 포함된 자세한 문서는 다음을 참조하세요.

인라인 워크플로 사용

코드 샘플

Go

이 샘플을 사용해 보기 전에 Go 설정 안내를 따르세요. Managed Service for Apache Spark 빠른 시작: 클라이언트 라이브러리 사용 자세한 내용은 Managed Service for Apache Spark Go API 참조 문서를 확인하세요.

Managed Service for Apache Spark에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

import (
	"context"
	"fmt"
	"io"

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

func instantiateInlineWorkflowTemplate(w io.Writer, projectID, region string) error {
	// projectID := "your-project-id"
	// region := "us-central1"

	ctx := context.Background()

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

	// Create jobs for the workflow.
	teragenJob := &dataprocpb.OrderedJob{
		JobType: &dataprocpb.OrderedJob_HadoopJob{
			HadoopJob: &dataprocpb.HadoopJob{
				Driver: &dataprocpb.HadoopJob_MainJarFileUri{
					MainJarFileUri: "file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar",
				},
				Args: []string{
					"teragen",
					"1000",
					"hdfs:///gen/",
				},
			},
		},
		StepId: "teragen",
	}

	terasortJob := &dataprocpb.OrderedJob{
		JobType: &dataprocpb.OrderedJob_HadoopJob{
			HadoopJob: &dataprocpb.HadoopJob{
				Driver: &dataprocpb.HadoopJob_MainJarFileUri{
					MainJarFileUri: "file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar",
				},
				Args: []string{
					"terasort",
					"hdfs:///gen/",
					"hdfs:///sort/",
				},
			},
		},
		StepId: "terasort",
		PrerequisiteStepIds: []string{
			"teragen",
		},
	}

	// Create the cluster placement.
	clusterPlacement := &dataprocpb.WorkflowTemplatePlacement{
		Placement: &dataprocpb.WorkflowTemplatePlacement_ManagedCluster{
			ManagedCluster: &dataprocpb.ManagedCluster{
				ClusterName: "my-managed-cluster",
				Config: &dataprocpb.ClusterConfig{
					GceClusterConfig: &dataprocpb.GceClusterConfig{
						// Leave "ZoneUri" empty for "Auto Zone Placement"
						// ZoneUri: ""
						ZoneUri: "us-central1-a",
					},
				},
			},
		},
	}

	// Create the Instantiate Inline Workflow Template Request.
	req := &dataprocpb.InstantiateInlineWorkflowTemplateRequest{
		Parent: fmt.Sprintf("projects/%s/regions/%s", projectID, region),
		Template: &dataprocpb.WorkflowTemplate{
			Jobs: []*dataprocpb.OrderedJob{
				teragenJob,
				terasortJob,
			},
			Placement: clusterPlacement,
		},
	}

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

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

	// Output a success message.
	fmt.Fprintf(w, "Workflow created successfully.")
	return nil
}

Java

이 샘플을 사용해 보기 전에 Java Managed Service for Apache Spark 빠른 시작: 클라이언트 라이브러리 사용의 Java 설정 안내를 따르세요. 자세한 내용은 Managed Service for Apache Spark Java API 참조 문서를 확인하세요.

Managed Service for Apache Spark에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.dataproc.v1.ClusterConfig;
import com.google.cloud.dataproc.v1.GceClusterConfig;
import com.google.cloud.dataproc.v1.HadoopJob;
import com.google.cloud.dataproc.v1.ManagedCluster;
import com.google.cloud.dataproc.v1.OrderedJob;
import com.google.cloud.dataproc.v1.RegionName;
import com.google.cloud.dataproc.v1.WorkflowMetadata;
import com.google.cloud.dataproc.v1.WorkflowTemplate;
import com.google.cloud.dataproc.v1.WorkflowTemplatePlacement;
import com.google.cloud.dataproc.v1.WorkflowTemplateServiceClient;
import com.google.cloud.dataproc.v1.WorkflowTemplateServiceSettings;
import com.google.protobuf.Empty;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

public class InstantiateInlineWorkflowTemplate {

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

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

    // Configure the settings for the workflow template service client.
    WorkflowTemplateServiceSettings workflowTemplateServiceSettings =
        WorkflowTemplateServiceSettings.newBuilder().setEndpoint(myEndpoint).build();

    // Create a workflow template service 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 (WorkflowTemplateServiceClient workflowTemplateServiceClient =
        WorkflowTemplateServiceClient.create(workflowTemplateServiceSettings)) {

      // Configure the jobs within the workflow.
      HadoopJob teragenHadoopJob =
          HadoopJob.newBuilder()
              .setMainJarFileUri("file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar")
              .addArgs("teragen")
              .addArgs("1000")
              .addArgs("hdfs:///gen/")
              .build();
      OrderedJob teragen =
          OrderedJob.newBuilder().setHadoopJob(teragenHadoopJob).setStepId("teragen").build();

      HadoopJob terasortHadoopJob =
          HadoopJob.newBuilder()
              .setMainJarFileUri("file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar")
              .addArgs("terasort")
              .addArgs("hdfs:///gen/")
              .addArgs("hdfs:///sort/")
              .build();
      OrderedJob terasort =
          OrderedJob.newBuilder()
              .setHadoopJob(terasortHadoopJob)
              .addPrerequisiteStepIds("teragen")
              .setStepId("terasort")
              .build();

      // Configure the cluster placement for the workflow.
      // Leave "ZoneUri" empty for "Auto Zone Placement".
      // GceClusterConfig gceClusterConfig =
      //     GceClusterConfig.newBuilder().setZoneUri("").build();
      GceClusterConfig gceClusterConfig =
          GceClusterConfig.newBuilder().setZoneUri("us-central1-a").build();
      ClusterConfig clusterConfig =
          ClusterConfig.newBuilder().setGceClusterConfig(gceClusterConfig).build();
      ManagedCluster managedCluster =
          ManagedCluster.newBuilder()
              .setClusterName("my-managed-cluster")
              .setConfig(clusterConfig)
              .build();
      WorkflowTemplatePlacement workflowTemplatePlacement =
          WorkflowTemplatePlacement.newBuilder().setManagedCluster(managedCluster).build();

      // Create the inline workflow template.
      WorkflowTemplate workflowTemplate =
          WorkflowTemplate.newBuilder()
              .addJobs(teragen)
              .addJobs(terasort)
              .setPlacement(workflowTemplatePlacement)
              .build();

      // Submit the instantiated inline workflow template request.
      String parent = RegionName.format(projectId, region);
      OperationFuture<Empty, WorkflowMetadata> instantiateInlineWorkflowTemplateAsync =
          workflowTemplateServiceClient.instantiateInlineWorkflowTemplateAsync(
              parent, workflowTemplate);
      instantiateInlineWorkflowTemplateAsync.get();

      // Print out a success message.
      System.out.printf("Workflow ran successfully.");

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

Node.js

이 샘플을 사용해 보기 전에 Node.js Managed Service for Apache Spark 빠른 시작: 클라이언트 라이브러리 사용의 설정 안내를 따르세요. 자세한 내용은 Managed Service for Apache Spark Node.js API 참조 문서를 확인하세요.

Managed Service for Apache Spark에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

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

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

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

async function instantiateInlineWorkflowTemplate() {
  // Create the formatted parent.
  const parent = client.regionPath(projectId, region);

  // Create the template
  const template = {
    jobs: [
      {
        hadoopJob: {
          mainJarFileUri:
            'file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar',
          args: ['teragen', '1000', 'hdfs:///gen/'],
        },
        stepId: 'teragen',
      },
      {
        hadoopJob: {
          mainJarFileUri:
            'file:///usr/lib/hadoop-mapreduce/hadoop-mapreduce-examples.jar',
          args: ['terasort', 'hdfs:///gen/', 'hdfs:///sort/'],
        },
        stepId: 'terasort',
        prerequisiteStepIds: ['teragen'],
      },
    ],
    placement: {
      managedCluster: {
        clusterName: 'my-managed-cluster',
        config: {
          gceClusterConfig: {
            // Leave 'zoneUri' empty for 'Auto Zone Placement'
            // zoneUri: ''
            zoneUri: 'us-central1-a',
          },
        },
      },
    },
  };

  const request = {
    parent: parent,
    template: template,
  };

  // Submit the request to instantiate the workflow from an inline template.
  const [operation] = await client.instantiateInlineWorkflowTemplate(request);
  await operation.promise();

  // Output a success message
  console.log('Workflow ran successfully.');

Python

이 샘플을 사용해 보기 전에 Python 설정 안내를 따르세요. Managed Service for Apache Spark 빠른 시작: 클라이언트 라이브러리 사용 자세한 내용은 Managed Service for Apache Spark Python API 참조 문서를 확인하세요.

Managed Service for Apache Spark에 인증하려면 애플리케이션 기본 사용자 인증 정보를 설정합니다. 자세한 내용은 로컬 개발 환경의 인증 설정을 참조하세요.

from google.cloud import dataproc_v1 as dataproc


def instantiate_inline_workflow_template(project_id, region):
    """This sample walks a user through submitting a workflow
    for a Cloud Dataproc using the Python client library.

    Args:
        project_id (string): Project to use for running the workflow.
        region (string): Region where the workflow resources should live.
    """

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

    parent = f"projects/{project_id}/regions/{region}"

    template = {
        "jobs": [
            {
                "hadoop_job": {
                    "main_jar_file_uri": "file:///usr/lib/hadoop-mapreduce/"
                    "hadoop-mapreduce-examples.jar",
                    "args": ["teragen", "1000", "hdfs:///gen/"],
                },
                "step_id": "teragen",
            },
            {
                "hadoop_job": {
                    "main_jar_file_uri": "file:///usr/lib/hadoop-mapreduce/"
                    "hadoop-mapreduce-examples.jar",
                    "args": ["terasort", "hdfs:///gen/", "hdfs:///sort/"],
                },
                "step_id": "terasort",
                "prerequisite_step_ids": ["teragen"],
            },
        ],
        "placement": {
            "managed_cluster": {
                "cluster_name": "my-managed-cluster",
                "config": {
                    "gce_cluster_config": {
                        # Leave 'zone_uri' empty for 'Auto Zone Placement'
                        # 'zone_uri': ''
                        "zone_uri": "us-central1-a"
                    }
                },
            }
        },
    }

    # Submit the request to instantiate the workflow from an inline template.
    operation = workflow_template_client.instantiate_inline_workflow_template(
        request={"parent": parent, "template": template}
    )
    operation.result()

    # Output a success message.
    print("Workflow ran successfully.")

다음 단계

다른 Google Cloud 제품의 코드 샘플을 검색하고 필터링하려면 Google Cloud 샘플 브라우저 참조하기

인라인 워크플로 템플릿 인스턴스화 컬렉션을 사용해 정리하기 내 환경설정을 기준으로 콘텐츠를 저장하고 분류하세요.

더 살펴보기

코드 샘플

Go

Java

Node.js

Python

다음 단계

인라인 워크플로 템플릿 인스턴스화