本頁面由 Cloud Translation API 翻譯而成。

使用內嵌 Dataproc 工作流程

標準工作流程會執行個體化先前建立的工作流程範本資源，但內嵌工作流程會使用 YAML 檔案或內嵌的 WorkflowTemplate 定義來執行工作流程。

建立及執行內嵌工作流程

gcloud

請參閱「使用 YAML 檔案例項化工作流程」。

REST

使用任何要求資料之前，請先替換以下項目：

project-id： Google Cloud 專案 ID
region：叢集區域，例如「us-central1」
zoneUri：在叢集的zone 地區中指定，例如「us-central1-b」，或留空 (「」) 以使用 Dataproc 自動選擇區域位置
clusterName：叢集名稱

HTTP 方法和網址：

POST https://dataproc.googleapis.com/v1/projects/project-id/regions/region/workflowTemplates:instantiateInline

JSON 要求主體：

{
  "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": "cluster-name",
      "config": {
        "gceClusterConfig": {
          "zoneUri": "zone"
        }
      }
    }
  }
}

如要傳送要求，請展開以下其中一個選項：

curl (Linux、macOS 或 Cloud Shell)

注意： 下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI，或使用 Cloud Shell，自動登入 gcloud CLI。您可以執行 gcloud auth list 查看目前有效的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://dataproc.googleapis.com/v1/projects/project-id/regions/region/workflowTemplates:instantiateInline"

PowerShell (Windows)

注意： 下列指令假設您已執行 gcloud init 或 gcloud auth login，透過使用者帳戶登入 gcloud CLI。您可以執行 gcloud auth list 查看目前有效的帳戶。

將要求主體儲存在名為 request.json 的檔案中，然後執行下列指令：

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
    -Method POST `
    -Headers $headers `
    -ContentType: "application/json; charset=utf-8" `
    -InFile request.json `
    -Uri "https://dataproc.googleapis.com/v1/projects/project-id/regions/region/workflowTemplates:instantiateInline" | Select-Object -Expand Content

您應該會收到如下的 JSON 回應：

{
  "name": "projects/project-id/regions/region/operations/2fbd0dad-...",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.dataproc.v1.WorkflowMetadata",
    "graph": {
      "nodes": [
        {
          "stepId": "teragen",
          "state": "RUNNABLE"
        },
        {
          "stepId": "terasort",
          "prerequisiteStepIds": [
            "teragen"
          ],
          "state": "BLOCKED"
        }
      ]
    },
    "state": "PENDING",
    "startTime": "2020-04-02T22:50:44.826Z"
  }
}

控制台

目前 Google Cloud 控制台不支援建立內嵌工作流程。您可以透過 Dataproc 工作流程頁面，查看工作流程範本和已執行的工作流程。

Go

安裝用戶端程式庫

設定應用程式預設憑證

執行程式碼

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

安裝用戶端程式庫

設定應用程式預設憑證

執行程式碼

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

安裝用戶端程式庫

設定應用程式預設憑證

執行程式碼

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

安裝用戶端程式庫

設定應用程式預設憑證

執行程式碼

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.")

使用內嵌 Dataproc 工作流程 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

建立及執行內嵌工作流程

gcloud

REST

curl (Linux、macOS 或 Cloud Shell)

PowerShell (Windows)

控制台

Go

Java

Node.js

Python

使用內嵌 Dataproc 工作流程