如何在流式管道中按小捆绑的 N 个元素进行批处理？

我已经按照此答案中的描述实现了 N 个元素的批处理：谷歌数据流管道中的数据存储输入可以一次处理一批 N 个条目吗？ https://stackoverflow.com/questions/35065109/can-datastore-input-in-google-dataflow-pipeline-be-processed-in-a-batch-of-n-ent?answertab=active#tab-top

    package com.example.dataflow.transform;

    import com.example.dataflow.event.ClickEvent;
    import org.apache.beam.sdk.transforms.DoFn;
    import org.apache.beam.sdk.transforms.windowing.GlobalWindow;
    import org.joda.time.Instant;

    import java.util.ArrayList;
    import java.util.List;

    public class ClickToClicksPack extends DoFn> {
        public static final int BATCH_SIZE = 10;

        private List accumulator;

        @StartBundle
        public void startBundle() {
            accumulator = new ArrayList(BATCH_SIZE);
        }

        @ProcessElement
        public void processElement(ProcessContext c) {
            ClickEvent clickEvent = c.element();
            accumulator.add(clickEvent);
            if (accumulator.size() >= BATCH_SIZE) {
                c.output(accumulator);
                accumulator = new ArrayList(BATCH_SIZE);
            }
        }

        @FinishBundle
        public void finishBundle(FinishBundleContext c) {
            if (accumulator.size() > 0) {
                ClickEvent clickEvent = accumulator.get(0);
                long time = clickEvent.getClickTimestamp().getTime();

                c.output(accumulator, new Instant(time), GlobalWindow.INSTANCE);
            }
        }
    }

但是当我在流模式下运行管道时，有很多批次只有 1 或 2 个元素。据我了解，这是因为捆绑包尺寸较小。运行一天后，批处理中的平均元素数量约为 4。我确实需要它接近 10，以便后续步骤获得更好的性能。

有没有办法控制包的大小？ 或者我应该使用“GroupIntoBatches”转换来实现此目的。在这种情况下，我不清楚应该选择什么作为键。

更新： 使用 java 线程 id 或 VM 主机名作为应用“GroupIntoBatches”转换的键是一个好主意吗？

我最终用内部的“GroupIntoBatches”进行了复合转换。 以下答案包含有关密钥选择的建议：https://stackoverflow.com/a/44956702/4888849 https://stackoverflow.com/a/44956702/4888849

在我当前的实现中，我使用随机键来实现并行性，并且我对事件进行窗口化以便定期发出结果，即使一个键的事件数少于 BATCH_SIZE 也是如此。

    package com.example.dataflow.transform;

    import com.example.dataflow.event.ClickEvent;
    import org.apache.beam.sdk.transforms.DoFn;
    import org.apache.beam.sdk.transforms.GroupIntoBatches;
    import org.apache.beam.sdk.transforms.PTransform;
    import org.apache.beam.sdk.transforms.ParDo;
    import org.apache.beam.sdk.transforms.windowing.FixedWindows;
    import org.apache.beam.sdk.transforms.windowing.Window;
    import org.apache.beam.sdk.values.KV;
    import org.apache.beam.sdk.values.PCollection;
    import org.joda.time.Duration;

    import java.util.Random;

    /**
     * Batch clicks into packs of BATCH_SIZE size
     */
    public class ClickToClicksPack extends PTransform, PCollection>> {
        public static final int BATCH_SIZE = 10;
        // Define window duration.
        // After window's end - elements are emitted even if there are less then BATCH_SIZE elements
        public static final int WINDOW_DURATION_SECONDS = 1;
        private static final int DEFAULT_SHARDS_NUMBER = 20;
        // Determine possible parallelism level
        private int shardsNumber = DEFAULT_SHARDS_NUMBER;

        public ClickToClicksPack() {
            super();
        }

        public ClickToClicksPack(int shardsNumber) {
            super();
            this.shardsNumber = shardsNumber;
        }

        @Override
        public PCollection> expand(PCollection input) {
            return input
                    // assign keys, as "GroupIntoBatches" works only with key-value pairs
                    .apply(ParDo.of(new AssignRandomKeys(shardsNumber)))
                    .apply(Window.into(FixedWindows.of(Duration.standardSeconds(WINDOW_DURATION_SECONDS))))
                    .apply(GroupIntoBatches.ofSize(BATCH_SIZE))
                    .apply(ParDo.of(new ExtractValues()));
        }

        /**
         * Assigns to clicks random integer between zero and shardsNumber
         */
        private static class AssignRandomKeys extends DoFn> {
            private int shardsNumber;
            private Random random;

            AssignRandomKeys(int shardsNumber) {
                super();
                this.shardsNumber = shardsNumber;
            }

            @Setup
            public void setup() {
                random = new Random();
            }

            @ProcessElement
            public void processElement(ProcessContext c) {
                ClickEvent clickEvent = c.element();
                KV kv = KV.of(random.nextInt(shardsNumber), clickEvent);
                c.output(kv);
            }
        }

        /**
         * Extract values from KV
         */
        private static class ExtractValues extends DoFn>, Iterable> {
            @ProcessElement
            public void processElement(ProcessContext c) {
                KV> kv = c.element();
                c.output(kv.getValue());
            }
        }
    }