[java] 알 수없는 크기의 불균형 분배기를 재조정 할 수 있습니까?

많은 실험을 거친 후에도 여전히 크기 추정을 통해 병렬 처리를 추가 할 수 없었습니다. 기본적으로, 이외의 값은 Long.MAX_VALUE다른 손에있는 동안 (및 분할없이)는 spliterator 너무 일찍 종료하게하는 경향이 Long.MAX_VALUE추정 원인이됩니다 trySplit그것을 반환 할 때까지 끊임없이 호출 할 null.

내가 찾은 해결책은 스플리터간에 리소스를 내부적으로 공유하고 서로간에 균형을 조정하는 것입니다.

작업 코드 :

public class AwsS3LineSpliterator<LINE> extends AbstractSpliterator<AwsS3LineInput<LINE>> {

    public final static class AwsS3LineInput<LINE> {
        final public S3ObjectSummary s3ObjectSummary;
        final public LINE lineItem;
        public AwsS3LineInput(S3ObjectSummary s3ObjectSummary, LINE lineItem) {
            this.s3ObjectSummary = s3ObjectSummary;
            this.lineItem = lineItem;
        }
    }

    private final class InputStreamHandler {
        final S3ObjectSummary file;
        final InputStream inputStream;
        InputStreamHandler(S3ObjectSummary file, InputStream is) {
            this.file = file;
            this.inputStream = is;
        }
    }

    private final Iterator<S3ObjectSummary> incomingFiles;

    private final Function<S3ObjectSummary, InputStream> fileOpener;

    private final Function<InputStream, LINE> lineReader;

    private final Deque<S3ObjectSummary> unopenedFiles;

    private final Deque<InputStreamHandler> openedFiles;

    private final Deque<AwsS3LineInput<LINE>> sharedBuffer;

    private final int maxBuffer;

    private AwsS3LineSpliterator(Iterator<S3ObjectSummary> incomingFiles, Function<S3ObjectSummary, InputStream> fileOpener,
            Function<InputStream, LINE> lineReader,
            Deque<S3ObjectSummary> unopenedFiles, Deque<InputStreamHandler> openedFiles, Deque<AwsS3LineInput<LINE>> sharedBuffer,
            int maxBuffer) {
        super(Long.MAX_VALUE, 0);
        this.incomingFiles = incomingFiles;
        this.fileOpener = fileOpener;
        this.lineReader = lineReader;
        this.unopenedFiles = unopenedFiles;
        this.openedFiles = openedFiles;
        this.sharedBuffer = sharedBuffer;
        this.maxBuffer = maxBuffer;
    }

    public AwsS3LineSpliterator(Iterator<S3ObjectSummary> incomingFiles, Function<S3ObjectSummary, InputStream> fileOpener, Function<InputStream, LINE> lineReader, int maxBuffer) {
        this(incomingFiles, fileOpener, lineReader, new ConcurrentLinkedDeque<>(), new ConcurrentLinkedDeque<>(), new ArrayDeque<>(maxBuffer), maxBuffer);
    }

    @Override
    public boolean tryAdvance(Consumer<? super AwsS3LineInput<LINE>> action) {
        AwsS3LineInput<LINE> lineInput;
        synchronized(sharedBuffer) {
            lineInput=sharedBuffer.poll();
        }
        if(lineInput != null) {
            action.accept(lineInput);
            return true;
        }
        InputStreamHandler handle = openedFiles.poll();
        if(handle == null) {
            S3ObjectSummary unopenedFile = unopenedFiles.poll();
            if(unopenedFile == null) {
                return false;
            }
            handle = new InputStreamHandler(unopenedFile, fileOpener.apply(unopenedFile));
        }
        for(int i=0; i < maxBuffer; ++i) {
            LINE line = lineReader.apply(handle.inputStream);
            if(line != null) {
                synchronized(sharedBuffer) {
                    sharedBuffer.add(new AwsS3LineInput<LINE>(handle.file, line));
                }
            }
            else {
                return tryAdvance(action);
            }
        }
        openedFiles.addFirst(handle);
        return tryAdvance(action);
    }

    @Override
    public Spliterator<AwsS3LineInput<LINE>> trySplit() {
        synchronized(incomingFiles) {
            if (incomingFiles.hasNext()) {
                unopenedFiles.add(incomingFiles.next());
                return new AwsS3LineSpliterator<LINE>(incomingFiles, fileOpener, lineReader, unopenedFiles, openedFiles, sharedBuffer, maxBuffer);
            } else {
                return null;
            }
        }
    }
}

답변