Criar e enviar um job que usa um bucket do Cloud Storage

Crie e envie um job de amostra do Batch que execute um script que acessa um bucket do Cloud Storage. A definição do job especifica a montagem do bucket em todas as VMs para que as tarefas do job possam ler dados de entrada ou gravar resultados neles. Depois que você envia o job, o Batch automaticamente enfileira, programa e executa o job nas VMs do Compute Engine.

Mais informações

Para ver a documentação detalhada que inclui este exemplo de código, consulte:

Exemplo de código

C++

Para mais informações, consulte a documentação de referência da API C++ em lote.

Para autenticar no Batch, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

#include "google/cloud/batch/v1/batch_client.h"

  [](std::string const& project_id, std::string const& location_id,
     std::string const& job_id, std::string const& bucket_name) {
    // Initialize the request; start with the fields that depend on the sample
    // input.
    google::cloud::batch::v1::CreateJobRequest request;
    request.set_parent("projects/" + project_id + "/locations/" + location_id);
    request.set_job_id(job_id);
    // Most of the job description is fixed in this example; use a string to
    // initialize it, and then override the GCS remote path.
    auto constexpr kText = R"pb(
      task_groups {
        task_count: 4
        task_spec {
          compute_resource { cpu_milli: 500 memory_mib: 16 }
          max_retry_count: 2
          max_run_duration { seconds: 3600 }
          runnables {
            script {
              text: "echo Hello world from task ${BATCH_TASK_INDEX}. >> /mnt/share/output_task_${BATCH_TASK_INDEX}.txt"
            }
          }
          volumes { mount_path: "/mnt/share" }
        }
      }
      allocation_policy {
        instances {
          policy { machine_type: "e2-standard-4" provisioning_model: STANDARD }
        }
      }
      labels { key: "env" value: "testing" }
      labels { key: "type" value: "script" }
      logs_policy { destination: CLOUD_LOGGING }
    )pb";
    auto* job = request.mutable_job();
    if (!google::protobuf::TextFormat::ParseFromString(kText, job)) {
      throw std::runtime_error("Error parsing Job description");
    }
    job->mutable_task_groups(0)
        ->mutable_task_spec()
        ->mutable_volumes(0)
        ->mutable_gcs()
        ->set_remote_path(bucket_name);
    // Create a client and issue the request.
    auto client = google::cloud::batch_v1::BatchServiceClient(
        google::cloud::batch_v1::MakeBatchServiceConnection());
    auto response = client.CreateJob(request);
    if (!response) throw std::move(response).status();
    std::cout << "Job : " << response->DebugString() << "\n";
  }

Go

Para mais informações, consulte a documentação de referência da API Go em lote.

Para autenticar no Batch, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

import (
	"context"
	"fmt"
	"io"

	batch "cloud.google.com/go/batch/apiv1"
	batchpb "google.golang.org/genproto/googleapis/cloud/batch/v1"
	durationpb "google.golang.org/protobuf/types/known/durationpb"
)

// Creates and runs a job that executes the specified script
func createScriptJobWithBucket(w io.Writer, projectID, region, jobName, bucketName string) error {
	// projectID := "your_project_id"
	// region := "us-central1"
	// jobName := "some-job"
	// jobName := "some-bucket"

	ctx := context.Background()
	batchClient, err := batch.NewClient(ctx)
	if err != nil {
		return fmt.Errorf("NewClient: %w", err)
	}
	defer batchClient.Close()

	// Define what will be done as part of the job.
	command := &batchpb.Runnable_Script_Text{
		Text: "echo Hello world from task ${BATCH_TASK_INDEX}. >> /mnt/share/output_task_${BATCH_TASK_INDEX}.txt",
	}

	// Specify the Google Cloud Storage bucket to mount
	volume := &batchpb.Volume{
		Source: &batchpb.Volume_Gcs{
			Gcs: &batchpb.GCS{
				RemotePath: bucketName,
			},
		},
		MountPath:    "/mnt/share",
		MountOptions: []string{},
	}

	// We can specify what resources are requested by each task.
	resources := &batchpb.ComputeResource{
		// CpuMilli is milliseconds per cpu-second. This means the task requires 50% of a single CPUs.
		CpuMilli:  500,
		MemoryMib: 16,
	}

	taskSpec := &batchpb.TaskSpec{
		Runnables: []*batchpb.Runnable{{
			Executable: &batchpb.Runnable_Script_{
				Script: &batchpb.Runnable_Script{Command: command},
			},
		}},
		ComputeResource: resources,
		MaxRunDuration: &durationpb.Duration{
			Seconds: 3600,
		},
		MaxRetryCount: 2,
		Volumes:       []*batchpb.Volume{volume},
	}

	// Tasks are grouped inside a job using TaskGroups.
	taskGroups := []*batchpb.TaskGroup{
		{
			TaskCount: 4,
			TaskSpec:  taskSpec,
		},
	}

	// Policies are used to define on what kind of virtual machines the tasks will run on.
	// In this case, we tell the system to use "e2-standard-4" machine type.
	// Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
	allocationPolicy := &batchpb.AllocationPolicy{
		Instances: []*batchpb.AllocationPolicy_InstancePolicyOrTemplate{{
			PolicyTemplate: &batchpb.AllocationPolicy_InstancePolicyOrTemplate_Policy{
				Policy: &batchpb.AllocationPolicy_InstancePolicy{
					MachineType: "e2-standard-4",
				},
			},
		}},
	}

	// We use Cloud Logging as it's an out of the box available option
	logsPolicy := &batchpb.LogsPolicy{
		Destination: batchpb.LogsPolicy_CLOUD_LOGGING,
	}

	jobLabels := map[string]string{"env": "testing", "type": "script"}

	// The job's parent is the region in which the job will run
	parent := fmt.Sprintf("projects/%s/locations/%s", projectID, region)

	job := batchpb.Job{
		TaskGroups:       taskGroups,
		AllocationPolicy: allocationPolicy,
		Labels:           jobLabels,
		LogsPolicy:       logsPolicy,
	}

	req := &batchpb.CreateJobRequest{
		Parent: parent,
		JobId:  jobName,
		Job:    &job,
	}

	created_job, err := batchClient.CreateJob(ctx, req)
	if err != nil {
		return fmt.Errorf("unable to create job: %w", err)
	}

	fmt.Fprintf(w, "Job created: %v\n", created_job)

	return nil
}

Java

Para mais informações, consulte a documentação de referência da API Java em lote.

Para autenticar no Batch, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

import com.google.cloud.batch.v1.AllocationPolicy;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicy;
import com.google.cloud.batch.v1.AllocationPolicy.InstancePolicyOrTemplate;
import com.google.cloud.batch.v1.BatchServiceClient;
import com.google.cloud.batch.v1.ComputeResource;
import com.google.cloud.batch.v1.CreateJobRequest;
import com.google.cloud.batch.v1.GCS;
import com.google.cloud.batch.v1.Job;
import com.google.cloud.batch.v1.LogsPolicy;
import com.google.cloud.batch.v1.LogsPolicy.Destination;
import com.google.cloud.batch.v1.Runnable;
import com.google.cloud.batch.v1.Runnable.Script;
import com.google.cloud.batch.v1.TaskGroup;
import com.google.cloud.batch.v1.TaskSpec;
import com.google.cloud.batch.v1.Volume;
import com.google.protobuf.Duration;
import java.io.IOException;
import java.util.concurrent.ExecutionException;
import java.util.concurrent.TimeUnit;
import java.util.concurrent.TimeoutException;

public class CreateWithMountedBucket {

  public static void main(String[] args)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // TODO(developer): Replace these variables before running the sample.
    // Project ID or project number of the Cloud project you want to use.
    String projectId = "YOUR_PROJECT_ID";

    // Name of the region you want to use to run the job. Regions that are
    // available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
    String region = "europe-central2";

    // The name of the job that will be created.
    // It needs to be unique for each project and region pair.
    String jobName = "JOB_NAME";

    // Name of the bucket to be mounted for your Job.
    String bucketName = "BUCKET_NAME";

    createScriptJobWithBucket(projectId, region, jobName, bucketName);
  }

  // This method shows how to create a sample Batch Job that will run
  // a simple command on Cloud Compute instances.
  public static void createScriptJobWithBucket(String projectId, String region, String jobName,
      String bucketName)
      throws IOException, ExecutionException, InterruptedException, TimeoutException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the `batchServiceClient.close()` method on the client to safely
    // clean up any remaining background resources.
    try (BatchServiceClient batchServiceClient = BatchServiceClient.create()) {

      // Define what will be done as part of the job.
      Runnable runnable =
          Runnable.newBuilder()
              .setScript(
                  Script.newBuilder()
                      .setText(
                          "echo Hello world from task ${BATCH_TASK_INDEX}. >> "
                              + "/mnt/share/output_task_${BATCH_TASK_INDEX}.txt")
                      // You can also run a script from a file. Just remember, that needs to be a
                      // script that's already on the VM that will be running the job.
                      // Using setText() and setPath() is mutually exclusive.
                      // .setPath("/tmp/test.sh")
                      .build())
              .build();

      Volume volume = Volume.newBuilder()
          .setGcs(GCS.newBuilder()
              .setRemotePath(bucketName)
              .build())
          .setMountPath("/mnt/share")
          .build();

      // We can specify what resources are requested by each task.
      ComputeResource computeResource =
          ComputeResource.newBuilder()
              // In milliseconds per cpu-second. This means the task requires 50% of a single CPUs.
              .setCpuMilli(500)
              // In MiB.
              .setMemoryMib(16)
              .build();

      TaskSpec task =
          TaskSpec.newBuilder()
              // Jobs can be divided into tasks. In this case, we have only one task.
              .addRunnables(runnable)
              .addVolumes(volume)
              .setComputeResource(computeResource)
              .setMaxRetryCount(2)
              .setMaxRunDuration(Duration.newBuilder().setSeconds(3600).build())
              .build();

      // Tasks are grouped inside a job using TaskGroups.
      // Currently, it's possible to have only one task group.
      TaskGroup taskGroup = TaskGroup.newBuilder().setTaskCount(4).setTaskSpec(task).build();

      // Policies are used to define on what kind of virtual machines the tasks will run on.
      // In this case, we tell the system to use "e2-standard-4" machine type.
      // Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
      InstancePolicy instancePolicy =
          InstancePolicy.newBuilder().setMachineType("e2-standard-4").build();

      AllocationPolicy allocationPolicy =
          AllocationPolicy.newBuilder()
              .addInstances(InstancePolicyOrTemplate.newBuilder().setPolicy(instancePolicy).build())
              .build();

      Job job =
          Job.newBuilder()
              .addTaskGroups(taskGroup)
              .setAllocationPolicy(allocationPolicy)
              .putLabels("env", "testing")
              .putLabels("type", "script")
              .putLabels("mount", "bucket")
              // We use Cloud Logging as it's an out of the box available option.
              .setLogsPolicy(
                  LogsPolicy.newBuilder().setDestination(Destination.CLOUD_LOGGING).build())
              .build();

      CreateJobRequest createJobRequest =
          CreateJobRequest.newBuilder()
              // The job's parent is the region in which the job will run.
              .setParent(String.format("projects/%s/locations/%s", projectId, region))
              .setJob(job)
              .setJobId(jobName)
              .build();

      Job result =
          batchServiceClient
              .createJobCallable()
              .futureCall(createJobRequest)
              .get(5, TimeUnit.MINUTES);

      System.out.printf("Successfully created the job: %s", result.getName());
    }
  }
}

Node.js

Para mais informações, consulte a documentação de referência da API Node.js em lote.

Para autenticar no Batch, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

/**
 * TODO(developer): Uncomment and replace these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
/**
 * The region you want to the job to run in. The regions that support Batch are listed here:
 * https://cloud.google.com/batch/docs/get-started#locations
 */
// const region = 'us-central-1';
/**
 * The name of the job that will be created.
 * It needs to be unique for each project and region pair.
 */
// const jobName = 'YOUR_JOB_NAME';
/**
 * The name of the bucket to be mounted.
 */
// const bucketName = 'YOUR_BUCKET_NAME';

// Imports the Batch library
const batchLib = require('@google-cloud/batch');
const batch = batchLib.protos.google.cloud.batch.v1;

// Instantiates a client
const batchClient = new batchLib.v1.BatchServiceClient();

// Define what will be done as part of the job.
const task = new batch.TaskSpec();
const runnable = new batch.Runnable();
runnable.script = new batch.Runnable.Script();
runnable.script.text =
  'echo Hello world from task ${BATCH_TASK_INDEX}. >> /mnt/share/output_task_${BATCH_TASK_INDEX}.txt';
// You can also run a script from a file. Just remember, that needs to be a script that's
// already on the VM that will be running the job. Using runnable.script.text and runnable.script.path is mutually
// exclusive.
// runnable.script.path = '/tmp/test.sh'
task.runnables = [runnable];

const gcsBucket = new batch.GCS();
gcsBucket.remotePath = bucketName;
const gcsVolume = new batch.Volume();
gcsVolume.gcs = gcsBucket;
gcsVolume.mountPath = '/mnt/share';
task.volumes = [gcsVolume];

// We can specify what resources are requested by each task.
const resources = new batch.ComputeResource();
resources.cpuMilli = 2000; // in milliseconds per cpu-second. This means the task requires 2 whole CPUs.
resources.memoryMib = 16;
task.computeResource = resources;

task.maxRetryCount = 2;
task.maxRunDuration = {seconds: 3600};

// Tasks are grouped inside a job using TaskGroups.
const group = new batch.TaskGroup();
group.taskCount = 4;
group.taskSpec = task;

// Policies are used to define on what kind of virtual machines the tasks will run on.
// In this case, we tell the system to use "e2-standard-4" machine type.
// Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
const allocationPolicy = new batch.AllocationPolicy();
const policy = new batch.AllocationPolicy.InstancePolicy();
policy.machineType = 'e2-standard-4';
const instances = new batch.AllocationPolicy.InstancePolicyOrTemplate();
instances.policy = policy;
allocationPolicy.instances = [instances];

const job = new batch.Job();
job.name = jobName;
job.taskGroups = [group];
job.allocationPolicy = allocationPolicy;
job.labels = {env: 'testing', type: 'script'};
// We use Cloud Logging as it's an option available out of the box
job.logsPolicy = new batch.LogsPolicy();
job.logsPolicy.destination = batch.LogsPolicy.Destination.CLOUD_LOGGING;

// The job's parent is the project and region in which the job will run
const parent = `projects/${projectId}/locations/${region}`;

async function callCreateJob() {
  // Construct request
  const request = {
    parent,
    jobId: jobName,
    job,
  };

  // Run request
  const response = await batchClient.createJob(request);
  console.log(response);
}

callCreateJob();

Python

Para mais informações, consulte a documentação de referência da API Python em lote.

Para autenticar no Batch, configure o Application Default Credentials. Para mais informações, consulte Configurar a autenticação para um ambiente de desenvolvimento local.

from google.cloud import batch_v1

def create_script_job_with_bucket(
    project_id: str, region: str, job_name: str, bucket_name: str
) -> batch_v1.Job:
    """
    This method shows how to create a sample Batch Job that will run
    a simple command on Cloud Compute instances.

    Args:
        project_id: project ID or project number of the Cloud project you want to use.
        region: name of the region you want to use to run the job. Regions that are
            available for Batch are listed on: https://cloud.google.com/batch/docs/get-started#locations
        job_name: the name of the job that will be created.
            It needs to be unique for each project and region pair.
        bucket_name: name of the bucket to be mounted for your Job.

    Returns:
        A job object representing the job created.
    """
    client = batch_v1.BatchServiceClient()

    # Define what will be done as part of the job.
    task = batch_v1.TaskSpec()
    runnable = batch_v1.Runnable()
    runnable.script = batch_v1.Runnable.Script()
    runnable.script.text = "echo Hello world from task ${BATCH_TASK_INDEX}. >> /mnt/share/output_task_${BATCH_TASK_INDEX}.txt"
    task.runnables = [runnable]

    gcs_bucket = batch_v1.GCS()
    gcs_bucket.remote_path = bucket_name
    gcs_volume = batch_v1.Volume()
    gcs_volume.gcs = gcs_bucket
    gcs_volume.mount_path = "/mnt/share"
    task.volumes = [gcs_volume]

    # We can specify what resources are requested by each task.
    resources = batch_v1.ComputeResource()
    resources.cpu_milli = 500  # in milliseconds per cpu-second. This means the task requires 50% of a single CPUs.
    resources.memory_mib = 16
    task.compute_resource = resources

    task.max_retry_count = 2
    task.max_run_duration = "3600s"

    # Tasks are grouped inside a job using TaskGroups.
    # Currently, it's possible to have only one task group.
    group = batch_v1.TaskGroup()
    group.task_count = 4
    group.task_spec = task

    # Policies are used to define on what kind of virtual machines the tasks will run on.
    # In this case, we tell the system to use "e2-standard-4" machine type.
    # Read more about machine types here: https://cloud.google.com/compute/docs/machine-types
    allocation_policy = batch_v1.AllocationPolicy()
    policy = batch_v1.AllocationPolicy.InstancePolicy()
    policy.machine_type = "e2-standard-4"
    instances = batch_v1.AllocationPolicy.InstancePolicyOrTemplate()
    instances.policy = policy
    allocation_policy.instances = [instances]

    job = batch_v1.Job()
    job.task_groups = [group]
    job.allocation_policy = allocation_policy
    job.labels = {"env": "testing", "type": "script", "mount": "bucket"}
    # We use Cloud Logging as it's an out of the box available option
    job.logs_policy = batch_v1.LogsPolicy()
    job.logs_policy.destination = batch_v1.LogsPolicy.Destination.CLOUD_LOGGING

    create_request = batch_v1.CreateJobRequest()
    create_request.job = job
    create_request.job_id = job_name
    # The job's parent is the region in which the job will run
    create_request.parent = f"projects/{project_id}/locations/{region}"

    return client.create_job(create_request)

A seguir

Para pesquisar e filtrar exemplos de código de outros produtos do Google Cloud, consulte o navegador de amostra do Google Cloud.