perf(worker): event hot-path allocation + flush cuts (WRK-06/11/12, IPC-15)
WRK-06: MxStatusProxyConverter caches the four resolved FieldInfo per status type in a static ConcurrentDictionary (the GetField metadata scan ran 4x per status per event on the STA path). GetValue+Convert.ToInt32 still run per event (late-bound RCW). Exceptions byte-identical: missing-field message unchanged (ResolveField, not cached on throw via GetOrAdd); null-value message unchanged. WRK-11: MxAccessEventQueue.Enqueue takes ownership of the passed MxEvent - stamps WorkerSequence/WorkerTimestamp on it in place and enqueues it, no Clone(). Audited all 3 callers (base/alarm event sinks, provider-mode handler): each builds a fresh event per Enqueue, none reuse it. MxAccessValueCache.Set now deep-copies its retained Value/SourceTimestamp/Statuses so the cache snapshot never aliases the queue-owned (later serialized) event. Net: alarm/other events clone nothing (was full clone); data-change clones payload-only. WRK-12: WorkerFrameWriter coalesces the flush across a drained batch - each frame is written but not flushed individually; one FlushAsync after the batch, then all written frames complete. Preserves the written+flushed completion contract; a burst of N events costs 1 flush, not N. On write failure the whole in-flight batch + queue fail so no caller hangs. IPC-15 (doc): the multi-event WorkerEnvelope body remains unimplemented (wire still carries one event per worker_event frame); gateway.md Performance section now distinguishes the shipped flush-coalescing from that deferred proto change. net48-safe (no init/records; readonly struct cache entry). Worker builds x86 only - verification on windev. Tests added: converter cache-reuse, queue ownership-transfer, value-cache snapshot independence, writer batch-flush-once. Claude-Session: https://claude.ai/code/session_01DMXXvNuPekkkrTEyPNxEkW
This commit is contained in:
@@ -1,4 +1,5 @@
|
||||
using System;
|
||||
using System.Collections.Concurrent;
|
||||
using System.Collections.Generic;
|
||||
using System.Globalization;
|
||||
using System.Reflection;
|
||||
@@ -9,6 +10,17 @@ namespace ZB.MOM.WW.MxGateway.Worker.Conversion;
|
||||
/// <summary>Converts MXAccess MXSTATUS_PROXY COM objects to protobuf MxStatusProxy messages.</summary>
|
||||
public sealed class MxStatusProxyConverter
|
||||
{
|
||||
/// <summary>
|
||||
/// Per-type cache of the four resolved <see cref="FieldInfo"/> objects a
|
||||
/// status conversion needs. The status type is stable (the interop
|
||||
/// <c>MXSTATUS_PROXY</c> struct in production; a fixed test double in
|
||||
/// tests), so the expensive <see cref="Type.GetField(string, BindingFlags)"/>
|
||||
/// metadata scan is resolved once per type and reused. Keyed by
|
||||
/// <see cref="Type"/> so a plain-CLR test double and the real interop
|
||||
/// struct each get their own entry, keeping the converter interop-agnostic.
|
||||
/// </summary>
|
||||
private static readonly ConcurrentDictionary<Type, StatusFields> FieldCache = new();
|
||||
|
||||
/// <summary>Converts a single status object to a protobuf message, reflecting all fields and diagnostics.</summary>
|
||||
/// <param name="status">COM status object to convert.</param>
|
||||
/// <returns>The converted protobuf status message.</returns>
|
||||
@@ -20,10 +32,11 @@ public sealed class MxStatusProxyConverter
|
||||
}
|
||||
|
||||
Type statusType = status.GetType();
|
||||
int success = ReadInt32Field(status, statusType, "success");
|
||||
int rawCategory = ReadInt32Field(status, statusType, "category");
|
||||
int rawDetectedBy = ReadInt32Field(status, statusType, "detectedBy");
|
||||
int detail = ReadInt32Field(status, statusType, "detail");
|
||||
StatusFields fields = GetFields(statusType);
|
||||
int success = ReadInt32Field(status, statusType, fields.Success);
|
||||
int rawCategory = ReadInt32Field(status, statusType, fields.Category);
|
||||
int rawDetectedBy = ReadInt32Field(status, statusType, fields.DetectedBy);
|
||||
int detail = ReadInt32Field(status, statusType, fields.Detail);
|
||||
|
||||
return new MxStatusProxy
|
||||
{
|
||||
@@ -82,6 +95,43 @@ public sealed class MxStatusProxyConverter
|
||||
|
||||
private static int ReadInt32Field(
|
||||
object value,
|
||||
Type valueType,
|
||||
FieldInfo field)
|
||||
{
|
||||
object? fieldValue = field.GetValue(value);
|
||||
if (fieldValue is null)
|
||||
{
|
||||
throw new MxStatusConversionException(
|
||||
$"Status object field '{field.Name}' on type '{valueType.FullName}' is null.");
|
||||
}
|
||||
|
||||
return System.Convert.ToInt32(fieldValue, CultureInfo.InvariantCulture);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Resolves (and caches) the four <see cref="FieldInfo"/> objects for the
|
||||
/// given status type. The first resolution for a type performs the
|
||||
/// reflection scan; every subsequent conversion of that type reuses the
|
||||
/// cached entry. A type missing a required field throws the same
|
||||
/// <see cref="MxStatusConversionException"/> the per-field lookup used to
|
||||
/// throw — and, because <see cref="ConcurrentDictionary{TKey,TValue}.GetOrAdd(TKey, Func{TKey, TValue})"/>
|
||||
/// does not store a value when the factory throws, a bad type keeps
|
||||
/// failing identically on every call rather than being cached.
|
||||
/// </summary>
|
||||
/// <param name="statusType">Runtime type of the status object being converted.</param>
|
||||
/// <returns>The resolved field set for <paramref name="statusType"/>.</returns>
|
||||
private static StatusFields GetFields(Type statusType)
|
||||
{
|
||||
return FieldCache.GetOrAdd(
|
||||
statusType,
|
||||
type => new StatusFields(
|
||||
ResolveField(type, "success"),
|
||||
ResolveField(type, "category"),
|
||||
ResolveField(type, "detectedBy"),
|
||||
ResolveField(type, "detail")));
|
||||
}
|
||||
|
||||
private static FieldInfo ResolveField(
|
||||
Type valueType,
|
||||
string fieldName)
|
||||
{
|
||||
@@ -92,14 +142,7 @@ public sealed class MxStatusProxyConverter
|
||||
$"Status object type '{valueType.FullName}' does not expose required field '{fieldName}'.");
|
||||
}
|
||||
|
||||
object? fieldValue = field.GetValue(value);
|
||||
if (fieldValue is null)
|
||||
{
|
||||
throw new MxStatusConversionException(
|
||||
$"Status object field '{fieldName}' on type '{valueType.FullName}' is null.");
|
||||
}
|
||||
|
||||
return System.Convert.ToInt32(fieldValue, CultureInfo.InvariantCulture);
|
||||
return field;
|
||||
}
|
||||
|
||||
private static MxStatusCategory MapCategory(int rawCategory)
|
||||
@@ -134,4 +177,32 @@ public sealed class MxStatusProxyConverter
|
||||
_ => MxStatusSource.Unknown,
|
||||
};
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// The four resolved status fields cached per type. Plain readonly struct
|
||||
/// (not a record) so it compiles under the worker's net48 target, which
|
||||
/// lacks <c>IsExternalInit</c>.
|
||||
/// </summary>
|
||||
private readonly struct StatusFields
|
||||
{
|
||||
public StatusFields(
|
||||
FieldInfo success,
|
||||
FieldInfo category,
|
||||
FieldInfo detectedBy,
|
||||
FieldInfo detail)
|
||||
{
|
||||
Success = success;
|
||||
Category = category;
|
||||
DetectedBy = detectedBy;
|
||||
Detail = detail;
|
||||
}
|
||||
|
||||
public FieldInfo Success { get; }
|
||||
|
||||
public FieldInfo Category { get; }
|
||||
|
||||
public FieldInfo DetectedBy { get; }
|
||||
|
||||
public FieldInfo Detail { get; }
|
||||
}
|
||||
}
|
||||
|
||||
@@ -112,36 +112,77 @@ public sealed class WorkerFrameWriter
|
||||
// Runs only under _writeLock. Drains control frames before event frames, stamping and writing each.
|
||||
// The stream write itself is not cancellable: a frame is written atomically or fails, never left
|
||||
// half-written on the pipe because a caller gave up waiting.
|
||||
//
|
||||
// Flushes are coalesced across the whole drained batch (WRK-12 / IPC-15): each frame is written to
|
||||
// the stream but not flushed individually; a single FlushAsync runs after the batch, then every
|
||||
// successfully-written frame is completed. A caller's Completion therefore still signals only after
|
||||
// its bytes have been written AND flushed, so the "written and flushed" contract is unchanged — but
|
||||
// a burst of N events now costs one flush syscall instead of N.
|
||||
private async Task DrainQueuedFramesAsync()
|
||||
{
|
||||
List<PendingFrame> written = new List<PendingFrame>();
|
||||
while (true)
|
||||
{
|
||||
PendingFrame? frame = DequeueNext();
|
||||
if (frame is null)
|
||||
{
|
||||
return;
|
||||
break;
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
await WriteFrameAsync(frame.Envelope).ConfigureAwait(false);
|
||||
frame.Completion.TrySetResult(true);
|
||||
written.Add(frame);
|
||||
}
|
||||
catch (WorkerFrameProtocolException exception) when (IsPerFrameRejection(exception))
|
||||
{
|
||||
// Validation, empty-payload, and oversized-frame errors are specific to this frame and
|
||||
// do not damage the stream; fail only this frame and keep draining the rest.
|
||||
// do not damage the stream; fail only this frame and keep draining the rest. Nothing was
|
||||
// written for it, so it needs no flush.
|
||||
frame.Completion.TrySetException(exception);
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
// A stream write/flush failure means the pipe is broken; fail this frame and every frame
|
||||
// still queued so no caller awaits forever, then stop draining.
|
||||
// A stream write failure means the pipe is broken; fail this frame, every frame already
|
||||
// written this batch but not yet flushed, and every frame still queued so no caller
|
||||
// awaits forever, then stop draining.
|
||||
frame.Completion.TrySetException(exception);
|
||||
FailFrames(written, exception);
|
||||
FailAllQueued(exception);
|
||||
return;
|
||||
}
|
||||
}
|
||||
|
||||
if (written.Count == 0)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
await _stream.FlushAsync(CancellationToken.None).ConfigureAwait(false);
|
||||
}
|
||||
catch (Exception exception)
|
||||
{
|
||||
// The batch reached the stream but the flush that guarantees delivery failed: the pipe is
|
||||
// broken. Fail every frame in the batch (the queue was already drained) so no caller treats
|
||||
// an unflushed write as delivered.
|
||||
FailFrames(written, exception);
|
||||
return;
|
||||
}
|
||||
|
||||
foreach (PendingFrame frame in written)
|
||||
{
|
||||
frame.Completion.TrySetResult(true);
|
||||
}
|
||||
}
|
||||
|
||||
private static void FailFrames(List<PendingFrame> frames, Exception exception)
|
||||
{
|
||||
foreach (PendingFrame frame in frames)
|
||||
{
|
||||
frame.Completion.TrySetException(exception);
|
||||
}
|
||||
}
|
||||
|
||||
private static bool IsPerFrameRejection(WorkerFrameProtocolException exception)
|
||||
@@ -211,14 +252,14 @@ public sealed class WorkerFrameWriter
|
||||
|
||||
// Serialize once into a single buffer that carries the 4-byte length prefix followed by the
|
||||
// payload, then issue one stream write. This avoids a second serialization pass, a separate
|
||||
// prefix array, and a separate prefix write.
|
||||
// prefix array, and a separate prefix write. The flush is deferred to the end of the drained
|
||||
// batch (see DrainQueuedFramesAsync) so a burst of frames shares one flush.
|
||||
int frameLength = sizeof(uint) + payloadLength;
|
||||
byte[] frame = new byte[frameLength];
|
||||
WriteUInt32LittleEndian(frame, (uint)payloadLength);
|
||||
envelope.WriteTo(new Span<byte>(frame, sizeof(uint), payloadLength));
|
||||
|
||||
await _stream.WriteAsync(frame, 0, frameLength, CancellationToken.None).ConfigureAwait(false);
|
||||
await _stream.FlushAsync(CancellationToken.None).ConfigureAwait(false);
|
||||
}
|
||||
|
||||
private static void WriteUInt32LittleEndian(
|
||||
|
||||
@@ -8,6 +8,17 @@ namespace ZB.MOM.WW.MxGateway.Worker.MxAccess;
|
||||
/// <summary>
|
||||
/// Thread-safe queue for MxAccess events with capacity overflow and fault tracking.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// Ownership invariant: <see cref="Enqueue"/> takes ownership of the
|
||||
/// <see cref="MxEvent"/> passed to it — it stamps the worker sequence and
|
||||
/// timestamp on that same instance and enqueues it directly, without
|
||||
/// cloning (WRK-11). Every caller must therefore pass a freshly built
|
||||
/// <see cref="MxEvent"/> that it does not retain, reuse, or mutate after the
|
||||
/// call returns. All production callers (MxAccessBaseEventSink,
|
||||
/// MxAccessAlarmEventSink, AlarmCommandHandler) build a new event per
|
||||
/// Enqueue via the mapper and satisfy this; the value cache stores its own
|
||||
/// independent snapshot (see <see cref="MxAccessValueCache.Set"/>).
|
||||
/// </remarks>
|
||||
public sealed class MxAccessEventQueue
|
||||
{
|
||||
/// <summary>
|
||||
@@ -110,8 +121,11 @@ public sealed class MxAccessEventQueue
|
||||
|
||||
/// <summary>
|
||||
/// Enqueues an MxAccess event, assigning a sequence number and timestamp.
|
||||
/// Takes ownership of <paramref name="mxEvent"/>: the sequence and timestamp
|
||||
/// are stamped on that same instance and it is enqueued without cloning, so
|
||||
/// the caller must pass a freshly built event it does not reuse afterwards.
|
||||
/// </summary>
|
||||
/// <param name="mxEvent">MXAccess event to enqueue.</param>
|
||||
/// <param name="mxEvent">Freshly built MXAccess event to enqueue; ownership transfers to the queue.</param>
|
||||
public void Enqueue(MxEvent mxEvent)
|
||||
{
|
||||
if (mxEvent is null)
|
||||
@@ -132,13 +146,17 @@ public sealed class MxAccessEventQueue
|
||||
throw new MxAccessEventQueueOverflowException(capacity);
|
||||
}
|
||||
|
||||
MxEvent queuedEvent = mxEvent.Clone();
|
||||
queuedEvent.WorkerSequence = ++lastEventSequence;
|
||||
queuedEvent.WorkerTimestamp = Timestamp.FromDateTime(DateTime.UtcNow);
|
||||
// WRK-11: stamp the sequence/timestamp on the caller's own event and
|
||||
// enqueue that same instance under the lock instead of cloning. See
|
||||
// the ownership invariant on the class summary — the caller hands the
|
||||
// event over exclusively, so a defensive Clone() here is pure
|
||||
// overhead on the hottest path.
|
||||
mxEvent.WorkerSequence = ++lastEventSequence;
|
||||
mxEvent.WorkerTimestamp = Timestamp.FromDateTime(DateTime.UtcNow);
|
||||
|
||||
WorkerEvent workerEvent = new()
|
||||
{
|
||||
Event = queuedEvent,
|
||||
Event = mxEvent,
|
||||
};
|
||||
events.Enqueue(workerEvent);
|
||||
}
|
||||
|
||||
@@ -40,6 +40,20 @@ public sealed class MxAccessValueCache
|
||||
throw new ArgumentNullException(nameof(mxEvent));
|
||||
}
|
||||
|
||||
// WRK-11: the event sink no longer clones before enqueue, so the passed
|
||||
// mxEvent is the very instance handed to the outbound queue. Deep-copy
|
||||
// the value/timestamp/statuses payload we retain here so the cache's
|
||||
// snapshot stays independent of the enqueued (and later serialized)
|
||||
// event — the two must never share mutable protobuf sub-messages.
|
||||
// Value is always set for OnDataChange; SourceTimestamp may be unset when
|
||||
// the source timestamp could not be parsed, so both are cloned only when
|
||||
// present. The null-forgiving result matches CachedValue's non-null-
|
||||
// annotated parameters, which already accepted a runtime-null value or
|
||||
// timestamp before WRK-11 (the ternary keeps the compiler's null-state
|
||||
// from poisoning to maybe-null, which a plain null check would do).
|
||||
MxValue cachedValue = mxEvent.Value is null ? null! : mxEvent.Value.Clone();
|
||||
Timestamp cachedTimestamp = mxEvent.SourceTimestamp is null ? null! : mxEvent.SourceTimestamp.Clone();
|
||||
|
||||
long key = CreateItemKey(serverHandle, itemHandle);
|
||||
lock (syncRoot)
|
||||
{
|
||||
@@ -49,10 +63,10 @@ public sealed class MxAccessValueCache
|
||||
|
||||
entries[key] = new CachedValue(
|
||||
nextVersion,
|
||||
mxEvent.Value,
|
||||
cachedValue,
|
||||
mxEvent.Quality,
|
||||
mxEvent.SourceTimestamp,
|
||||
mxEvent.Statuses);
|
||||
cachedTimestamp,
|
||||
mxEvent.Statuses.Clone());
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user