这是一个替代方案BatchBlock https://learn.microsoft.com/en-us/dotnet/api/system.threading.tasks.dataflow.batchblock-1具有一些额外功能的实现。它包括一个TriggerBatch
具有此签名的方法:
public int TriggerBatch(int nextMinBatchSizeIfEmpty);
如果输入队列不为空,调用此方法将立即触发批处理,否则将设置临时MinBatchSize
这只会影响下一批。您可以使用较小的值来调用此方法nextMinBatchSizeIfEmpty
确保在当前无法生产批次的情况下,下一个批次将比配置的时间更早发生BatchSize
在块的构造函数中。
此方法返回生产批次的大小。它返回0
如果输入队列为空,或者输出队列已满,或者块已完成。
public class BatchBlockEx<T> : ITargetBlock<T>, ISourceBlock<T[]>
{
private readonly ITargetBlock<T> _input;
private readonly IPropagatorBlock<T[], T[]> _output;
private readonly Queue<T> _queue;
private readonly object _locker = new object();
private int _nextMinBatchSize = Int32.MaxValue;
public Task Completion { get; }
public int InputCount { get { lock (_locker) return _queue.Count; } }
public int OutputCount => ((BufferBlock<T[]>)_output).Count;
public int BatchSize { get; }
public BatchBlockEx(int batchSize, DataflowBlockOptions dataflowBlockOptions = null)
{
if (batchSize < 1) throw new ArgumentOutOfRangeException(nameof(batchSize));
dataflowBlockOptions = dataflowBlockOptions ?? new DataflowBlockOptions();
if (dataflowBlockOptions.BoundedCapacity != DataflowBlockOptions.Unbounded &&
dataflowBlockOptions.BoundedCapacity < batchSize)
throw new ArgumentOutOfRangeException(nameof(batchSize),
"Number must be no greater than the value specified in BoundedCapacity.");
this.BatchSize = batchSize;
_output = new BufferBlock<T[]>(dataflowBlockOptions);
_queue = new Queue<T>(batchSize);
_input = new ActionBlock<T>(async item =>
{
T[] batch = null;
lock (_locker)
{
_queue.Enqueue(item);
if (_queue.Count == batchSize || _queue.Count >= _nextMinBatchSize)
{
batch = _queue.ToArray(); _queue.Clear();
_nextMinBatchSize = Int32.MaxValue;
}
}
if (batch != null) await _output.SendAsync(batch).ConfigureAwait(false);
}, new ExecutionDataflowBlockOptions()
{
BoundedCapacity = 1,
CancellationToken = dataflowBlockOptions.CancellationToken
});
var inputContinuation = _input.Completion.ContinueWith(async t =>
{
try
{
T[] batch = null;
lock (_locker)
{
if (_queue.Count > 0)
{
batch = _queue.ToArray(); _queue.Clear();
}
}
if (batch != null) await _output.SendAsync(batch).ConfigureAwait(false);
}
finally
{
if (t.IsFaulted)
{
_output.Fault(t.Exception.InnerException);
}
else
{
_output.Complete();
}
}
}, TaskScheduler.Default).Unwrap();
this.Completion = Task.WhenAll(inputContinuation, _output.Completion);
}
public void Complete() => _input.Complete();
void IDataflowBlock.Fault(Exception ex) => _input.Fault(ex);
public int TriggerBatch(Func<T[], bool> condition, int nextMinBatchSizeIfEmpty)
{
if (nextMinBatchSizeIfEmpty < 1)
throw new ArgumentOutOfRangeException(nameof(nextMinBatchSizeIfEmpty));
int count = 0;
lock (_locker)
{
if (_queue.Count > 0)
{
T[] batch = _queue.ToArray();
if (condition == null || condition(batch))
{
bool accepted = _output.Post(batch);
if (accepted) { _queue.Clear(); count = batch.Length; }
}
_nextMinBatchSize = Int32.MaxValue;
}
else
{
_nextMinBatchSize = nextMinBatchSizeIfEmpty;
}
}
return count;
}
public int TriggerBatch(Func<T[], bool> condition)
=> TriggerBatch(condition, Int32.MaxValue);
public int TriggerBatch(int nextMinBatchSizeIfEmpty)
=> TriggerBatch(null, nextMinBatchSizeIfEmpty);
public int TriggerBatch() => TriggerBatch(null, Int32.MaxValue);
DataflowMessageStatus ITargetBlock<T>.OfferMessage(
DataflowMessageHeader messageHeader, T messageValue,
ISourceBlock<T> source, bool consumeToAccept)
{
return _input.OfferMessage(messageHeader, messageValue, source,
consumeToAccept);
}
T[] ISourceBlock<T[]>.ConsumeMessage(DataflowMessageHeader messageHeader,
ITargetBlock<T[]> target, out bool messageConsumed)
{
return _output.ConsumeMessage(messageHeader, target, out messageConsumed);
}
bool ISourceBlock<T[]>.ReserveMessage(DataflowMessageHeader messageHeader,
ITargetBlock<T[]> target)
{
return _output.ReserveMessage(messageHeader, target);
}
void ISourceBlock<T[]>.ReleaseReservation(DataflowMessageHeader messageHeader,
ITargetBlock<T[]> target)
{
_output.ReleaseReservation(messageHeader, target);
}
IDisposable ISourceBlock<T[]>.LinkTo(ITargetBlock<T[]> target,
DataflowLinkOptions linkOptions)
{
return _output.LinkTo(target, linkOptions);
}
}
另一个超载TriggerBatch
方法允许检查当前可以生产的批次,并决定是否应该触发它:
public int TriggerBatch(Func<T[], bool> condition);
The BatchBlockEx
类不支持Greedy https://learn.microsoft.com/en-us/dotnet/api/system.threading.tasks.dataflow.groupingdataflowblockoptions.greedy and MaxNumberOfGroups https://learn.microsoft.com/en-us/dotnet/api/system.threading.tasks.dataflow.groupingdataflowblockoptions.maxnumberofgroups内置选项BatchBlock
.