Как синхронно объединить два конвейера TPL DataFlow?

Вот реализация блока SynchronizedJoinBlock, аналогичного тому, который представлен в ответе Харди Хобека. Он заботится о некоторых незначительных деталях, таких как отмена, обработка исключений и обработка оставшихся элементов, когда входные блоки Target1 и Target2 помечены как завершенные. Кроме того, логика слияния не включает рекурсию, которая должна улучшить ее работу (надеюсь, я ее не измерял) и не быть восприимчивой к исключениям переполнения стека. Небольшое отклонение: на выходе будет ValueTuple<T1, T2> вместо Tuple<T1, T2> (с целью сокращения распределения).

public sealed class SynchronizedJoinBlock<T1, T2> : IReceivableSourceBlock<(T1, T2)>
{
    private readonly Func<T1, T2, int> _comparison;
    private readonly Queue<T1> _queue1 = new Queue<T1>();
    private readonly Queue<T2> _queue2 = new Queue<T2>();
    private readonly ActionBlock<T1> _input1;
    private readonly ActionBlock<T2> _input2;
    private readonly BufferBlock<(T1, T2)> _output;
    private readonly object _locker = new object();

    public SynchronizedJoinBlock(Func<T1, T2, int> comparison,
        CancellationToken cancellationToken = default)
    {
        _comparison = comparison ?? throw new ArgumentNullException(nameof(comparison));

        // Create the three internal blocks
        var options = new ExecutionDataflowBlockOptions()
        {
            CancellationToken = cancellationToken
        };
        _input1 = new ActionBlock<T1>(Add1, options);
        _input2 = new ActionBlock<T2>(Add2, options);
        _output = new BufferBlock<(T1, T2)>(options);

        // Link the input blocks with the output block
        var inputTasks = new Task[] { _input1.Completion, _input2.Completion };
        Task.WhenAny(inputTasks).Unwrap().ContinueWith(t =>
        {
            // If ANY input block fails, then the whole block has failed
            ((IDataflowBlock)_output).Fault(t.Exception.InnerException);
            if (!_input1.Completion.IsCompleted) _input1.Complete();
            if (!_input2.Completion.IsCompleted) _input2.Complete();
            ClearQueues();
        }, default, TaskContinuationOptions.OnlyOnFaulted |
            TaskContinuationOptions.RunContinuationsAsynchronously,
            TaskScheduler.Default);
        Task.WhenAll(inputTasks).ContinueWith(t =>
        {
            // If ALL input blocks succeeded, then the whole block has succeeded
            try
            {
                if (!t.IsCanceled) PostRemaining(); // Post what's left
            }
            catch (Exception ex)
            {
                ((IDataflowBlock)_output).Fault(ex);
            }
            _output.Complete();
            ClearQueues();
        }, default, TaskContinuationOptions.NotOnFaulted |
            TaskContinuationOptions.RunContinuationsAsynchronously,
            TaskScheduler.Default);
    }

    public ITargetBlock<T1> Target1 => _input1;
    public ITargetBlock<T2> Target2 => _input2;
    public Task Completion => _output.Completion;

    private void Add1(T1 value1)
    {
        lock (_locker)
        {
            _queue1.Enqueue(value1);
            FindAndPostMatched_Unsafe();
        }
    }

    private void Add2(T2 value2)
    {
        lock (_locker)
        {
            _queue2.Enqueue(value2);
            FindAndPostMatched_Unsafe();
        }
    }

    private void FindAndPostMatched_Unsafe()
    {
        while (_queue1.Count > 0 && _queue2.Count > 0)
        {
            var result = _comparison(_queue1.Peek(), _queue2.Peek());
            if (result < 0)
            {
                _output.Post((_queue1.Dequeue(), default));
            }
            else if (result > 0)
            {
                _output.Post((default, _queue2.Dequeue()));
            }
            else // result == 0
            {
                _output.Post((_queue1.Dequeue(), _queue2.Dequeue()));
            }
        }
    }

    private void PostRemaining()
    {
        lock (_locker)
        {
            while (_queue1.Count > 0)
            {
                _output.Post((_queue1.Dequeue(), default));
            }
            while (_queue2.Count > 0)
            {
                _output.Post((default, _queue2.Dequeue()));
            }
        }
    }

    private void ClearQueues()
    {
        lock (_locker)
        {
            _queue1.Clear();
            _queue2.Clear();
        }
    }

    public void Complete() => _output.Complete();

    public void Fault(Exception exception)
        => ((IDataflowBlock)_output).Fault(exception);

    public IDisposable LinkTo(ITargetBlock<(T1, T2)> target,
        DataflowLinkOptions linkOptions)
        => _output.LinkTo(target, linkOptions);

    public bool TryReceive(Predicate<(T1, T2)> filter, out (T1, T2) item)
        => _output.TryReceive(filter, out item);

    public bool TryReceiveAll(out IList<(T1, T2)> items)
        => _output.TryReceiveAll(out items);

    (T1, T2) ISourceBlock<(T1, T2)>.ConsumeMessage(
        DataflowMessageHeader messageHeader, ITargetBlock<(T1, T2)> target,
        out bool messageConsumed)
        => ((ISourceBlock<(T1, T2)>)_output).ConsumeMessage(
            messageHeader, target, out messageConsumed);

    void ISourceBlock<(T1, T2)>.ReleaseReservation(
        DataflowMessageHeader messageHeader, ITargetBlock<(T1, T2)> target)
        => ((ISourceBlock<(T1, T2)>)_output).ReleaseReservation(
            messageHeader, target);

    bool ISourceBlock<(T1, T2)>.ReserveMessage(
        DataflowMessageHeader messageHeader, ITargetBlock<(T1, T2)> target)
        => ((ISourceBlock<(T1, T2)>)_output).ReserveMessage(
            messageHeader, target);
}

Пример использования:

var joinBlock = new SynchronizedJoinBlock<(int, int), (int, int)>(
    (x, y) => Comparer<int>.Default.Compare(x.Item1, y.Item1));

var source1 = new (int, int)[] {(17, 1700), (18, 1800), (19, 1900),
    (20, 2000), (21, 2100), (22, 2200), (25, 2500), (26, 2600),
    (27, 2700), (28, 2800), (29, 2900)};

var source2 = new (int, int)[] {(15, 1500), (16, 1600), (17, 1700),
    (18, 1800), (19, 1900), (20, 2000), (21, 2100), (24, 2400),
    (25, 2500), (26, 2600)};

Array.ForEach(source1, x => joinBlock.Target1.Post(x));
Array.ForEach(source2, x => joinBlock.Target2.Post(x));

joinBlock.Target1.Complete();
joinBlock.Target2.Complete();

while (joinBlock.OutputAvailableAsync().Result)
{
    Console.WriteLine($"> Received: {joinBlock.Receive()}");
}

Выход:

Получено: ((0, 0), (15, 1500))
Получено: ((0, 0), (16, 1600))
Получено: ((17, 1700), (17, 1700) )
Получено: ((18, 1800), (18, 1800))
Получено: ((19, 1900), (19, 1900))
Получено: ((20, 2000), ( 20, 2000))
Получено: ((21, 2100), (21, 2100))
Получено: ((22, 2200), (0, 0))
Получено: ((0, 0), (24, 2400))
Получено: ((25, 2500), (25, 2500))
Получено: ((26, 2600), (26, 2600))
Получено: ((27, 2700), (0, 0))
Получено: ((28, 2800), (0, 0))
Получено: ((29, 2900), (0, 0))

Предполагается, что входящие данные упорядочены.

Этот класс имеет аналогичную структуру с классом JoinDependencyBlock, который я опубликовал некоторое время назад в несколько связанном вопросе.

Проблема с TPL DataFlow API в том, что все является внутренним / частным и / или запечатанным. Это дает не так много возможностей для расширения API.

В любом случае для вашей проблемы было бы неплохо реализовать новый класс SynchronizedJoinBlock. Фактическая бизнес-логика находится в методе GetMessagesRecursive:

    public sealed class SynchronizedJoinBlock<T1, T2>
        : IReceivableSourceBlock<Tuple<T1, T2>>
    {
        private readonly object _syncObject = new object();
        private readonly Func<T1, T2, int> _compareFunction;
        private readonly Queue<T1> _target1Messages;
        private readonly Queue<T2> _target2Messages;
        private readonly TransformManyBlock<T1, Tuple<T1, T2>> _target1;
        private readonly TransformManyBlock<T2, Tuple<T1, T2>> _target2;
        private readonly BatchedJoinBlock<Tuple<T1, T2>, Tuple<T1, T2>> _batchedJoinBlock;
        private readonly TransformManyBlock<Tuple<IList<Tuple<T1, T2>>, IList<Tuple<T1, T2>>>, Tuple<T1, T2>> _transformManyBlock;

        public ITargetBlock<T1> Target1 => _target1;

        public ITargetBlock<T2> Target2 => _target2;

        public Task Completion => _transformManyBlock.Completion;

        public SynchronizedJoinBlock(Func<T1, T2, int> compareFunction)
        {
            _compareFunction = compareFunction
                ?? throw new ArgumentNullException(nameof(compareFunction));
            _batchedJoinBlock = new BatchedJoinBlock<Tuple<T1, T2>, Tuple<T1, T2>>(1);
            _target1Messages = new Queue<T1>();
            _target2Messages = new Queue<T2>();

            Func<ICollection<Tuple<T1, T2>>> getMessagesFunction = () =>
            {
                lock (_syncObject)
                {
                    if (_target1Messages.Count > 0 && _target2Messages.Count > 0)
                    {
                        return GetMessagesRecursive(_target1Messages.Peek(), _target2Messages.Peek()).ToArray();
                    }
                    else
                    {
                        return new Tuple<T1, T2>[0];
                    }
                }
            };

            _target1 = new TransformManyBlock<T1, Tuple<T1, T2>>((element) =>
            {
                _target1Messages.Enqueue(element);
                return getMessagesFunction();
            });
            _target1.LinkTo(_batchedJoinBlock.Target1, new DataflowLinkOptions() { PropagateCompletion = true });

            _target2 = new TransformManyBlock<T2, Tuple<T1, T2>>((element) =>
            {
                _target2Messages.Enqueue(element);
                return getMessagesFunction();
            });
            _target2.LinkTo(_batchedJoinBlock.Target2, new DataflowLinkOptions() { PropagateCompletion = true });

            _transformManyBlock = new TransformManyBlock<Tuple<IList<Tuple<T1, T2>>, IList<Tuple<T1, T2>>>, Tuple<T1, T2>>(
                element => element.Item1.Concat(element.Item2)
            );
            _batchedJoinBlock.LinkTo(_transformManyBlock, new DataflowLinkOptions() { PropagateCompletion = true });
        }

        private IEnumerable<Tuple<T1, T2>> GetMessagesRecursive(T1 value1, T2 value2)
        {
            int result = _compareFunction(value1, value2);
            if (result == 0)
            {
                yield return Tuple.Create(_target1Messages.Dequeue(), _target2Messages.Dequeue());
            }
            else if (result < 0)
            {
                yield return Tuple.Create(_target1Messages.Dequeue(), default(T2));

                if (_target1Messages.Count > 0)
                {
                    foreach (var item in GetMessagesRecursive(_target1Messages.Peek(), value2))
                    {
                        yield return item;
                    }
                }
            }
            else
            {
                yield return Tuple.Create(default(T1), _target2Messages.Dequeue());

                if (_target2Messages.Count > 0)
                {
                    foreach (var item in GetMessagesRecursive(value1, _target2Messages.Peek()))
                    {
                        yield return item;
                    }
                }
            }
        }

        public void Complete()
        {
            _target1.Complete();
            _target2.Complete();
        }

        Tuple<T1, T2> ISourceBlock<Tuple<T1, T2>>.ConsumeMessage(
            DataflowMessageHeader messageHeader,
            ITargetBlock<Tuple<T1, T2>> target, out bool messageConsumed)
        {
            return ((ISourceBlock<Tuple<T1, T2>>)_transformManyBlock)
                .ConsumeMessage(messageHeader, target, out messageConsumed);
        }

        void IDataflowBlock.Fault(Exception exception)
        {
            ((IDataflowBlock)_transformManyBlock).Fault(exception);
        }

        public IDisposable LinkTo(ITargetBlock<Tuple<T1, T2>> target,
            DataflowLinkOptions linkOptions)
        {
            return _transformManyBlock.LinkTo(target, linkOptions);
        }

        void ISourceBlock<Tuple<T1, T2>>.ReleaseReservation(
            DataflowMessageHeader messageHeader, ITargetBlock<Tuple<T1, T2>> target)
        {
            ((ISourceBlock<Tuple<T1, T2>>)_transformManyBlock)
                .ReleaseReservation(messageHeader, target);
        }

        bool ISourceBlock<Tuple<T1, T2>>.ReserveMessage(
            DataflowMessageHeader messageHeader, ITargetBlock<Tuple<T1, T2>> target)
        {
            return ((ISourceBlock<Tuple<T1, T2>>)_transformManyBlock)
                .ReserveMessage(messageHeader, target);
        }

        public bool TryReceive(Predicate<Tuple<T1, T2>> filter, out Tuple<T1, T2> item)
        {
            return _transformManyBlock.TryReceive(filter, out item);
        }

        public bool TryReceiveAll(out IList<Tuple<T1, T2>> items)
        {
            return _transformManyBlock.TryReceiveAll(out items);
        }
    }