Merge branch 'fix/gwc-28-29-30-polish'
ci / java (push) Successful in 2m44s
ci / windows-x86 (push) Successful in 1m3s
ci / nightly-windev (push) Has been skipped
ci / portable (push) Successful in 17m13s

# Conflicts:
#	archreview/2026-07-12/remediation/00-tracking.md
This commit is contained in:
Joseph Doherty
2026-08-07 06:20:14 -04:00
11 changed files with 217 additions and 20 deletions
@@ -116,9 +116,12 @@ public sealed class MxAccessGatewayService(
return bulkConstraintPlan.CreateDeniedReply(request);
}
MxCommandRequest invokeRequest = request.Clone();
invokeRequest.Command = commandToInvoke;
WorkerCommand workerCommand = mapper.MapCommand(invokeRequest);
// Map from the command alone: cloning the whole request only to overwrite its command with
// commandToInvoke deep-cloned the (potentially large) original payload for nothing, since
// MapCommand reads nothing but the command (GWC-29). The one clone that matters still
// happens inside MapCommand, which is what keeps the worker-bound graph unaliased from
// commandToInvoke — the caller still reads it below via TrackCommandReply.
WorkerCommand workerCommand = mapper.MapCommand(commandToInvoke);
WorkerCommandReply workerReply = await sessionManager
.InvokeAsync(request.SessionId, workerCommand, context.CancellationToken)
.ConfigureAwait(false);
@@ -29,9 +29,27 @@ public sealed class MxAccessGrpcMapper
ArgumentNullException.ThrowIfNull(request);
ArgumentNullException.ThrowIfNull(request.Command);
return MapCommand(request.Command);
}
/// <summary>
/// Maps a gRPC MX command to a worker command. Callers that already hold the command — including
/// the constraint pipeline, whose rewritten command is not the one on the request — use this
/// overload rather than cloning a whole request to carry a single field (GWC-29); nothing outside
/// the command is read here.
/// </summary>
/// <param name="command">Command payload.</param>
/// <returns>The mapped <see cref="WorkerCommand"/> ready for worker dispatch.</returns>
public WorkerCommand MapCommand(MxCommand command)
{
ArgumentNullException.ThrowIfNull(command);
// The clone is required and must stay: the caller may hand us the gRPC-owned request command,
// and the caller keeps reading it after dispatch (TrackCommandReply). Cloning here is what makes
// WorkerClient.CreateCommandEnvelope's no-aliasing invariant true.
return new WorkerCommand
{
Command = request.Command.Clone(),
Command = command.Clone(),
EnqueueTimestamp = Timestamp.FromDateTimeOffset(_timeProvider.GetUtcNow()),
};
}
@@ -40,7 +40,9 @@ public sealed class WorkerClient : IWorkerClient
private readonly ConcurrentDictionary<string, PendingCommand> _pendingCommands = new(StringComparer.Ordinal);
private readonly SemaphoreSlim _pendingCommandSlots;
private readonly CancellationTokenSource _stopCts = new();
private long _nextSequence;
// Touched only by WriteLoopAsync — the single consumer of _outboundEnvelopes — so it needs no
// interlocking. See WriteLoopAsync for why the stamp happens there rather than at construction.
private ulong _nextSequence;
private WorkerClientState _state;
private DateTimeOffset _lastHeartbeatAt;
private int? _processId;
@@ -404,6 +406,13 @@ public sealed class WorkerClient : IWorkerClient
{
await foreach (WorkerEnvelope envelope in _outboundEnvelopes.Reader.ReadAllAsync(_stopCts.Token).ConfigureAwait(false))
{
// GWC-28: stamp the sequence at the point of writing, not when the envelope is built.
// Stamping at construction let two concurrent InvokeAsync callers take 1 and 2 and then
// enqueue in the order 2, 1 — non-monotonic on the wire, breaking gateway.md's
// "monotonic per sender" contract. This loop is the channel's single consumer
// (SingleReader = true), so wire order and stamp order are the same thing here and
// _nextSequence needs no interlocking. Mirrors the worker's WRK-04 fix.
envelope.Sequence = unchecked(++_nextSequence);
await _writer.WriteAsync(envelope, _stopCts.Token).ConfigureAwait(false);
}
}
@@ -1072,11 +1081,13 @@ public sealed class WorkerClient : IWorkerClient
string correlationId,
Action<WorkerEnvelope> setBody)
{
// Sequence is deliberately left unset here: WriteLoopAsync stamps it immediately before the
// frame goes out, so the numbers are monotonic in wire order however the callers interleave
// between construction and enqueue (GWC-28, mirroring the worker's WRK-04 fix).
WorkerEnvelope envelope = new()
{
ProtocolVersion = _connection.FrameOptions.ProtocolVersion,
SessionId = SessionId,
Sequence = (ulong)Interlocked.Increment(ref _nextSequence),
CorrelationId = correlationId,
};
setBody(envelope);
@@ -5,11 +5,24 @@ using ZB.MOM.WW.MxGateway.Contracts.Proto;
namespace ZB.MOM.WW.MxGateway.Server.Workers;
/// <summary>
/// Reads length-prefixed WorkerEnvelope protobuf frames from a stream.
/// </summary>
/// <remarks>
/// <see cref="ReadAsync"/> is not reentrant: the reader keeps a per-instance length-prefix scratch
/// buffer, so exactly one consumer may be inside a read at a time. That matches how the reader is
/// used — a single read loop per <c>WorkerClient</c>, with handshake reads completing before the
/// loop starts.
/// </remarks>
public sealed class WorkerFrameReader
{
private readonly WorkerFrameProtocolOptions _options;
private readonly Stream _stream;
// Reused across frames rather than allocated per read (GWC-30). Safe because ReadAsync is
// single-consumer by construction; the prefix is fully overwritten by every read.
private readonly byte[] _lengthPrefix = new byte[sizeof(uint)];
/// <summary>
/// Initializes a new instance of <see cref="WorkerFrameReader"/>.
/// </summary>
@@ -30,10 +43,9 @@ public sealed class WorkerFrameReader
/// <returns>Parsed worker envelope.</returns>
public async ValueTask<WorkerEnvelope> ReadAsync(CancellationToken cancellationToken = default)
{
byte[] lengthPrefix = new byte[sizeof(uint)];
await ReadExactlyOrThrowAsync(lengthPrefix, cancellationToken).ConfigureAwait(false);
await ReadExactlyOrThrowAsync(_lengthPrefix, cancellationToken).ConfigureAwait(false);
uint payloadLength = BinaryPrimitives.ReadUInt32LittleEndian(lengthPrefix);
uint payloadLength = BinaryPrimitives.ReadUInt32LittleEndian(_lengthPrefix);
if (payloadLength == 0)
{
throw new WorkerFrameProtocolException(