Question

如何从Google Cloud Function启动Cloud Dataflow作业？我想将Google Cloud Functions用作启用跨服务合成的机制。

Answer 1

我在下面列出了WordCount示例的一个非常基本的示例。请注意，您需要在Cloud Function部署中包含Java二进制文件的副本，因为它不在默认环境中。同样，您还需要使用Cloud Function打包部署jar。

module.exports = {
  wordcount: function (context, data) {
    const spawn = require('child_process').spawn;
    const child = spawn(
            'jre1.8.0_73/bin/java',
            ['-cp',
             'MY_JAR.jar',
             'com.google.cloud.dataflow.examples.WordCount',
             '--jobName=fromACloudFunction',
             '--project=MY_PROJECT',
             '--runner=BlockingDataflowPipelineRunner',
             '--stagingLocation=gs://STAGING_LOCATION',
             '--inputFile=gs://dataflow-samples/shakespeare/*',
             '--output=gs://OUTPUT_LOCATION'
            ],
            { cwd: __dirname });

    child.stdout.on('data', function(data) {
      console.log('stdout: ' + data);
    });
    child.stderr.on('data', function(data) {
      console.log('error: ' + data);
    });
    child.on('close', function(code) {
      console.log('closing code: ' + code);
    });
    context.success();
  }
}

您可以使用non-blocking runner进一步增强此示例，并让函数返回作业ID，以便您可以单独轮询作业完成情况。此模式也应该对其他SDK有效，只要它们的依赖关系可以打包到云函数中。

Answer 2

最好的启动方式是通过云功能启动，但是要小心，如果您将云功能用于Google云存储，那么对于每个上传的文件，都会启动一个数据流作业。

const { google } = require('googleapis');

const templatePath = "gs://template_dir/df_template;
const project = "<project_id>";
const tempLoc = "gs://tempLocation/";

exports.PMKafka = (data, context, callback) => {
    const file = data;

    console.log(`Event ${context.eventId}`);
    console.log(`Event Type: ${context.eventType}`);
    console.log(`Bucket Name: ${file.bucket}`);
    console.log(`File Name: ${file.name}`);
    console.log(`Metageneration: ${file.metageneration}`);
    console.log(`Created: ${file.timeCreated}`);
    console.log(`Updated: ${file.updated}`);
    console.log(`Uploaded File Name - gs://${file.bucket}/${file.name}`);

    google.auth.getApplicationDefault(function (err, authClient, projectId) {
        if (err) {
            throw err;
        }

        if (authClient.createScopedRequired && authClient.createScopedRequired()) {
            authClient = authClient.createScoped(authScope);
        }

        const dataflow = google.dataflow({ version: 'v1b3', auth: authClient });

        var inputDict= {
            inputFile: `gs://${file.bucket}/${file.name}`,
            ...
            ...
            <other_runtime_parameters>
        };

        var env = {
            tempLocation: tempLoc
        };

        var resource_opts = {
            parameters: inputDict,
            environment: env,
            jobName: config.jobNamePrefix + "-" + new Date().toISOString().toLowerCase().replace(":","-").replace(".","-")
        };

        var opts = {
            gcsPath: templatePath,
            projectId: project,
            resource: resource_opts
        }

        console.log(`Dataflow Run Time Options - ${JSON.stringify(opts)}`)

        dataflow.projects.templates.launch(opts, function (err, response) {
            if (err) {
                console.error("problem running dataflow template, error was: ", err);
                slack.publishMessage(null, null, false, err);
                return;
            }
            console.log("Dataflow template response: ", response);
            var jobid = response["data"]["job"]["id"];
            console.log("Dataflow Job ID: ", jobid);
        });
        callback();
    });
};

从云功能启动云数据流

2 个答案: