Page History

    /**
     * The ElementConverter provides a mapping between for the elements of a
     * stream to request entries that can be sent to the destination.
     * <p>
     * The resulting request entry is buffered by the AsyncSinkWriter and sent
     * to the destination when the {@code submitRequestEntries} method is
     * invoked.
     */
    private final ElementConverter<InputT, RequestEntryT> elementConverter;


    /**
     * Buffer to hold request entries that should be persisted into the
     * destination.
     * <p>
     * A request entry contain all relevant details to make a call to the
     * destination. Eg, for Kinesis Data Streams a request entry contains the
     * payload and partition key.
     * <p>
     * It seems more natural to buffer InputT, ie, the events that should be
     * persisted, rather than RequestEntryT. However, in practice, the response
     * of a failed request call can make it very hard, if not impossible, to
     * reconstruct the original event. It is much easier, to just construct a
     * new (retry) request entry from the response and add that back to the
     * queue for later retry.
     */
    private final Deque<RequestEntryT> bufferedRequestEntries = new ConcurrentLinkedDeque<>ArrayDeque<>(...);


    /**
     * Tracks all pending async calls that have been executed since the last
     * checkpoint. Calls that already completed (successfully or unsuccessfully) are
     * are automatically removeddecrementing from the queuecounter. Any request entry that was not
     * successfully persisted needneeds to be handled and retried by the logic in
     * {@code submitRequestsToApi}.
     * <p>
     * There is a limit on the number of concurrent (async) requests that can be
     * handled by the client library. This limit is enforced by checking the
     * size of this queue before issuing new requests.
     * <p>
     * To complete a checkpoint, we need to make sure that no requests are in
     * flight, as they may fail, which could then lead to data loss.
     */
    private Queue<CompletableFuture<?>> inFlightRequests = new ConcurrentLinkedQueue<>(...);

int inFlightRequestsCount;


    @Override
    public void write(InputT element, Context context) throws IOException, InterruptedException {
        
// blocks if too many elements have  bufferedRequestEntries.putLast(elementConverter.apply(element, context));

		
been buffered
    }


    /**
     * The entire request may fail or single request entries that are part of
while (bufferedRequestEntries.size() >= MAX_BUFFERED_REQUESTS_ENTRIES) {
            mailboxExecutor.yield();
      * the request}

 may not be persisted successfully, eg, because of network bufferedRequestEntries.add(elementConverter.apply(element, context));

     * issues or service side throttling. All request entries that failed with// blocks if too many async requests are in flight
     * transient failures needflush();
 to be re-queued with this method so that aren't }


    /**
     * lost and can be retried later. Persists buffered RequestsEntries into the destination by invoking {@code
     * <p>
     * Request entries that are causing the same error in a reproducible manner,submitRequestEntries} with batches according to the user specified
     * buffering hints.
     *
     * eg, ill-formed request entries, must not be re-queued but the error needsThe method blocks if too many async requests are in flight.
     */
 to be handled in the logic of {@code submitRequestEntries}. Otherwiseprivate void flush() throws InterruptedException {
     * these request entries will be retried indefinitely, always causing the
while (bufferedRequestEntries.size() >= MAX_BATCH_SIZE) {

        * same error.
  // create a */
batch of request entries protectedthat voidshould requeueFailedRequestEntry(RequestEntryT requestEntry) {be persisted in the destination
        bufferedRequestEntries.offerFirst(requestEntry);
    }


ArrayList<RequestEntryT> batch =  /**new ArrayList<>(MAX_BATCH_SIZE);

     * In-flight requests may fail, but they will be retried if the sink iswhile (batch.size() <= MAX_BATCH_SIZE && !bufferedRequestEntries.isEmpty()) {
     * still healthy.
     * <p>
   try {
 * To not lose any requests, there cannot be any outstanding in-flight
     * requests when a commit is initialized. To this end, all in-flight
 batch.add(bufferedRequestEntries.remove());
             * requests need to} becatch completed(NoSuchElementException ase) part{
 of the pre commit.
     */
    @Override
    public List<Collection<CompletableFuture<?>>> prepareCommit(boolean flush) throws IOException {

        // reuse current inFlightRequests as commitable and create an empty queue 
 // if there are not enough elements, just create a smaller batch
                   // tobreak;
 avoid copy and clearing
        List<Collection<CompletableFuture<?>>>  committable = Collections.singletonList(inFlightRequests);

 }
        // all in-flight requests are}

 handled by the AsyncSinkCommiter and new 
     ResultFuture<RequestEntryT> requestResult =
 // elements cannot be added to the queue during a commit, so it's save to 
    failedRequestEntries -> mailboxExecutor.execute(
  // create a new queue
        inFlightRequests = new ConcurrentLinkedQueue<>();

        return committable;
  ()  }


-> completeRequest(failedRequestEntries),
     /**
     * All in-flight requests have been completed, but there may still be
     * request entries"Mark in-flight therequest internalas buffercompleted thatand arerequeue yet%d to be sent to the
request entries",
          * endpoint. These request entries are stored in the snapshot state so that
     * they don't get lost in case of a failure/restart of the application.
     */ failedRequestEntries.size());

            while (inFlightRequestsCount >= MAX_IN_FLIGHT_REQUESTS) {
    @Override
    public List<Collection<RequestEntryT>> snapshotState() throws IOException {
      mailboxExecutor.yield();
            }

            inFlightRequestsCount++;
          return  Collections.singletonList(bufferedRequestEntries);submitRequestEntries(batch, requestResult);
        }
    }

    /**
     * Marks an in-flight request as completed and prepends failed requestEntries back to the
     * internal requestEntry buffer for later retry.
     *
     * @param failedRequestEntries requestEntries that need to be retried
     */
    private void completeRequest(Collection<RequestEntryT> failedRequestEntries) {
        inFlightRequestsCount--;

        // By just iterating through failedRequestEntries, it reverses the order of the
        // failedRequestEntries. It doesn't make a difference for kinesis:putRecords, as the api
        // does not make any order guarantees, but may cause avoidable reorderings for other
        // destinations.
        failedRequestEntries.forEach(bufferedRequestEntries::addFirst);
    }


    /**
     * In flight requests will be retried if the sink is still healthy. But if in-flight requests
     * fail after a checkpoint has been triggered and Flink needs to recover from the checkpoint,
     * the (failed) in-flight requests are gone and cannot be retried. Hence, there cannot be any
     * outstanding in-flight requests when a commit is initialized.
     *
     * <p>To this end, all in-flight requests need to completed before proceeding with the commit.
     */
    @Override
    public List<Void> prepareCommit(boolean flush) throws IOException, InterruptedException {
        if (flush) {
            flush();
        }

        // wait until all in-flight requests completed
        while (inFlightRequestsCount > 0) {
            mailboxExecutor.yield();
        }

        return Collections.emptyList();
    }


    /**
     * All in-flight requests have been completed, but there may still be
     * request entries in the internal buffer that are yet to be sent to the
     * endpoint. These request entries are stored in the snapshot state so that
     * they don't get lost in case of a failure/restart of the application.
     */
    @Override
    public List<Collection<RequestEntryT>> snapshotState() throws IOException {
        return Collections.singletonList(bufferedRequestEntries);
    }

private class AmazonKinesisDataStreamWriter extends AsyncSinkWriter<InputT
new ElementConverter<InputT, PutRecordsRequestEntry>() {

    @Override
    publicprotected PutRecordsRequestEntryvoid applysubmitRequestEntries(InputTList<PutRecordsRequestEntry> elementrequestEntries, SinkWriter.ContextResultFuture<PutRecordsRequestEntry> contextrequestResult) {
        return PutRecordsRequestEntry
        // create a      .builder()batch request
        PutRecordsRequest batchRequest       .data(SdkBytes.fromUtf8String(element.toString()))= PutRecordsRequest
                .partitionKey(String.valueOf(element.hashCodebuilder()))
                .build();
    }
}

...
}