使用 DoFn 使用 Cloud Dataflow 从 PubSub 写入 Google Cloud Storage

Question

我正在尝试使用 Google 云数据流将 Google PubSub 消息写入 Google 云存储。我知道 TextIO/AvroIO 不支持流媒体管道。但是，我在 [1] 中读到，可以在作者的评论中从 ParDo/DoFn 的流式管道中写入 GCS。我通过尽可能密切地关注他们的文章来构建管道。

我的目标是这种行为：

在与 dataflow-requests/[isodate-time]/[paneIndex] 中发布消息的时间相对应的路径下，将最多 100 条消息分批写入 GCS 中的对象（每个 window 窗格一个）。 39=]

我得到不同的结果：

每小时只有一个窗格 window。因此，我每小时 'bucket' 只得到一个文件（它实际上是 GCS 中的一个对象路径）。将 MAX_EVENTS_IN_FILE 减少到 10 没有任何区别，仍然只有一个 pane/file.
每个 GCS 对象中只有一条消息被写出
管道在写入 GCS 时偶尔会引发 CRC 错误。

如何解决这些问题并获得我期望的行为？

示例日志输出：

21:30:06.977 writing pane 0 to blob dataflow-requests/2016-04-08T20:59:59.999Z/0
21:30:06.977 writing pane 0 to blob dataflow-requests/2016-04-08T20:59:59.999Z/0
21:30:07.773 sucessfully write pane 0 to blob dataflow-requests/2016-04-08T20:59:59.999Z/0
21:30:07.846 sucessfully write pane 0 to blob dataflow-requests/2016-04-08T20:59:59.999Z/0
21:30:07.847 writing pane 0 to blob dataflow-requests/2016-04-08T20:59:59.999Z/0

这是我的代码：

package com.example.dataflow;

import com.google.cloud.dataflow.sdk.Pipeline;
import com.google.cloud.dataflow.sdk.io.PubsubIO;
import com.google.cloud.dataflow.sdk.options.DataflowPipelineOptions;
import com.google.cloud.dataflow.sdk.options.PipelineOptions;
import com.google.cloud.dataflow.sdk.options.PipelineOptionsFactory;
import com.google.cloud.dataflow.sdk.transforms.DoFn;
import com.google.cloud.dataflow.sdk.transforms.ParDo;
import com.google.cloud.dataflow.sdk.transforms.windowing.*;
import com.google.cloud.dataflow.sdk.values.PCollection;
import com.google.gcloud.storage.BlobId;
import com.google.gcloud.storage.BlobInfo;
import com.google.gcloud.storage.Storage;
import com.google.gcloud.storage.StorageOptions;
import org.joda.time.Duration;
import org.joda.time.format.ISODateTimeFormat;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.IOException;

public class PubSubGcsSSCCEPipepline {

    private static final Logger LOG = LoggerFactory.getLogger(PubSubGcsSSCCEPipepline.class);

    public static final String BUCKET_PATH = "dataflow-requests";

    public static final String BUCKET_NAME = "myBucketName";

    public static final Duration ONE_DAY = Duration.standardDays(1);
    public static final Duration ONE_HOUR = Duration.standardHours(1);
    public static final Duration TEN_SECONDS = Duration.standardSeconds(10);

    public static final int MAX_EVENTS_IN_FILE = 100;

    public static final String PUBSUB_SUBSCRIPTION = "projects/myProjectId/subscriptions/requests-dataflow";

    private static class DoGCSWrite extends DoFn<String, Void>
        implements DoFn.RequiresWindowAccess {

        public transient Storage storage;

        { init(); }

        public void init() { storage = StorageOptions.defaultInstance().service(); }

        private void readObject(java.io.ObjectInputStream in)
                throws IOException, ClassNotFoundException {
            init();
        }

        @Override
        public void processElement(ProcessContext c) throws Exception {
            String isoDate = ISODateTimeFormat.dateTime().print(c.window().maxTimestamp());
            String blobName = String.format("%s/%s/%s", BUCKET_PATH, isoDate, c.pane().getIndex());

            BlobId blobId = BlobId.of(BUCKET_NAME, blobName);
            LOG.info("writing pane {} to blob {}", c.pane().getIndex(), blobName);
            storage.create(BlobInfo.builder(blobId).contentType("text/plain").build(), c.element().getBytes());
            LOG.info("sucessfully write pane {} to blob {}", c.pane().getIndex(), blobName);
        }
    }

    public static void main(String[] args) {
        PipelineOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().create();
        options.as(DataflowPipelineOptions.class).setStreaming(true);
        Pipeline p = Pipeline.create(options);

        PubsubIO.Read.Bound<String> readFromPubsub = PubsubIO.Read.named("ReadFromPubsub")
                .subscription(PUBSUB_SUBSCRIPTION);

        PCollection<String> streamData = p.apply(readFromPubsub);

        PCollection<String> windows = streamData.apply(Window.<String>into(FixedWindows.of(ONE_HOUR))
                .withAllowedLateness(ONE_DAY)
                .triggering(AfterWatermark.pastEndOfWindow()
                        .withEarlyFirings(AfterPane.elementCountAtLeast(MAX_EVENTS_IN_FILE))
                        .withLateFirings(AfterFirst.of(AfterPane.elementCountAtLeast(MAX_EVENTS_IN_FILE),
                                AfterProcessingTime.pastFirstElementInPane()
                                        .plusDelayOf(TEN_SECONDS))))
                .discardingFiredPanes());

        windows.apply(ParDo.of(new DoGCSWrite()));

        p.run();
    }


}

[1] https://labs.spotify.com/2016/03/10/spotifys-event-delivery-the-road-to-the-cloud-part-iii/

感谢 Sam McVeety 提供的解决方案。这是任何阅读者的更正代码：

package com.example.dataflow;

import com.google.cloud.dataflow.sdk.Pipeline;
import com.google.cloud.dataflow.sdk.io.PubsubIO;
import com.google.cloud.dataflow.sdk.options.DataflowPipelineOptions;
import com.google.cloud.dataflow.sdk.options.PipelineOptions;
import com.google.cloud.dataflow.sdk.options.PipelineOptionsFactory;
import com.google.cloud.dataflow.sdk.transforms.*;
import com.google.cloud.dataflow.sdk.transforms.windowing.*;
import com.google.cloud.dataflow.sdk.values.KV;
import com.google.cloud.dataflow.sdk.values.PCollection;
import com.google.gcloud.WriteChannel;
import com.google.gcloud.storage.BlobId;
import com.google.gcloud.storage.BlobInfo;
import com.google.gcloud.storage.Storage;
import com.google.gcloud.storage.StorageOptions;
import org.joda.time.Duration;
import org.joda.time.format.ISODateTimeFormat;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import java.io.IOException;
import java.nio.ByteBuffer;
import java.util.Iterator;

public class PubSubGcsSSCCEPipepline {

    private static final Logger LOG = LoggerFactory.getLogger(PubSubGcsSSCCEPipepline.class);

    public static final String BUCKET_PATH = "dataflow-requests";

    public static final String BUCKET_NAME = "myBucketName";

    public static final Duration ONE_DAY = Duration.standardDays(1);
    public static final Duration ONE_HOUR = Duration.standardHours(1);
    public static final Duration TEN_SECONDS = Duration.standardSeconds(10);

    public static final int MAX_EVENTS_IN_FILE = 100;

    public static final String PUBSUB_SUBSCRIPTION = "projects/myProjectId/subscriptions/requests-dataflow";

    private static class DoGCSWrite extends DoFn<Iterable<String>, Void>
        implements DoFn.RequiresWindowAccess {

        public transient Storage storage;

        { init(); }

        public void init() { storage = StorageOptions.defaultInstance().service(); }

        private void readObject(java.io.ObjectInputStream in)
                throws IOException, ClassNotFoundException {
            init();
        }

        @Override
        public void processElement(ProcessContext c) throws Exception {
            String isoDate = ISODateTimeFormat.dateTime().print(c.window().maxTimestamp());
            long paneIndex = c.pane().getIndex();
            String blobName = String.format("%s/%s/%s", BUCKET_PATH, isoDate, paneIndex);

            BlobId blobId = BlobId.of(BUCKET_NAME, blobName);

            LOG.info("writing pane {} to blob {}", paneIndex, blobName);
            WriteChannel writer = storage.writer(BlobInfo.builder(blobId).contentType("text/plain").build());
            LOG.info("blob stream opened for pane {} to blob {} ", paneIndex, blobName);
            int i=0;
            for (Iterator<String> it = c.element().iterator(); it.hasNext();) {
                i++;
                writer.write(ByteBuffer.wrap(it.next().getBytes()));
                LOG.info("wrote {} elements to blob {}", i, blobName);
            }
            writer.close();
            LOG.info("sucessfully write pane {} to blob {}", paneIndex, blobName);
        }
    }

    public static void main(String[] args) {
        PipelineOptions options = PipelineOptionsFactory.fromArgs(args).withValidation().create();
        options.as(DataflowPipelineOptions.class).setStreaming(true);
        Pipeline p = Pipeline.create(options);

        PubsubIO.Read.Bound<String> readFromPubsub = PubsubIO.Read.named("ReadFromPubsub")
                .subscription(PUBSUB_SUBSCRIPTION);

        PCollection<String> streamData = p.apply(readFromPubsub);
        PCollection<KV<String, String>> keyedStream =
                streamData.apply(WithKeys.of(new SerializableFunction<String, String>() {
                    public String apply(String s) { return "constant"; } }));

        PCollection<KV<String, Iterable<String>>> keyedWindows = keyedStream
                .apply(Window.<KV<String, String>>into(FixedWindows.of(ONE_HOUR))
                        .withAllowedLateness(ONE_DAY)
                        .triggering(AfterWatermark.pastEndOfWindow()
                                .withEarlyFirings(AfterPane.elementCountAtLeast(MAX_EVENTS_IN_FILE))
                                .withLateFirings(AfterFirst.of(AfterPane.elementCountAtLeast(MAX_EVENTS_IN_FILE),
                                        AfterProcessingTime.pastFirstElementInPane()
                                                .plusDelayOf(TEN_SECONDS))))
                        .discardingFiredPanes())
                .apply(GroupByKey.create());


        PCollection<Iterable<String>> windows = keyedWindows
                .apply(Values.<Iterable<String>>create());


        windows.apply(ParDo.of(new DoGCSWrite()));

        p.run();
    }

}

Answer 1

这里有一个问题，您需要 GroupByKey 才能适当地聚合窗格。 Spotify 示例将此引用为 "Materialization of panes is done in “Aggregate Events” transform which is nothing else than a GroupByKey transform"，但这是一个微妙的点。您需要提供一个密钥才能执行此操作，在您的情况下，常数值似乎会起作用。

  PCollection<String> streamData = p.apply(readFromPubsub);
  PCollection<KV<String, String>> keyedStream =
        streamData.apply(WithKeys.of(new SerializableFunction<String, String>() {
           public Integer apply(String s) { return "constant"; } }));

此时，您可以应用窗口函数，然后应用最终的 GroupByKey 以获得所需的行为：

  PCollection<String, Iterable<String>> keyedWindows = keyedStream.apply(...)
       .apply(GroupByKey.create());
  PCollection<Iterable<String>> windows = keyedWindows
       .apply(Values.<Iterable<String>>create());

现在 processElement 中的元素将是 Iterable<String>，大小为 100 或更大。

我们已提交 https://issues.apache.org/jira/browse/BEAM-184 以使此行为更清楚。

Answer 2

从 Beam 2.0 开始，TextIO/AvroIO do 支持编写无限集合 - 请参阅 documentation，特别是，您必须指定 withWindowedWrites().

使用 DoFn 使用 Cloud Dataflow 从 PubSub 写入 Google Cloud Storage

Writing to Google Cloud Storage from PubSub using Cloud Dataflow using DoFn

google-cloud-storage

google-cloud-pubsub

google-cloud-dataflow