Files
mxaccessgw/src/ZB.MOM.WW.MxGateway.Tests/Gateway/Workers/WorkerClientTests.cs
T
Joseph Doherty 8769ee9765 fix(sessions): keep named-pipe socket paths inside the macOS sun_path limit (NEXT-01)
The pipe name mxaccess-gateway-{pid}-session-{32hex} plus .NET's
CoreFxPipe_ prefix overflowed the 104-byte Unix-domain-socket path limit
under the default per-user macOS TMPDIR (~49 chars), so every test that
opened a real pipe threw ArgumentOutOfRangeException at pipe creation
unless TMPDIR=/tmp was exported. Rename to mxgw-{pid}-{sessionUid} (the
session guid hex without the session- prefix; worst-case 43 chars) and
shorten the three test-fixture names the same way. Uniqueness is
unchanged: gateway pid + full session guid. The worker receives the pipe
name via its launch command line, so mixed Server/Worker deploy SHAs are
unaffected. Docs updated in the same change (gateway.md,
GatewayProcessDesign, GatewayConfiguration, Sessions, CLAUDE.md); new
regression test pins the format and the length budget.

Verified: SessionManagerTests 39/39; SessionWorkerClientFactory,
GatewayEndToEndFakeWorkerSmoke, WorkerClient, and ReconnectReplay suites
33/33 under the default macOS TMPDIR — this also retires the
previously-misdiagnosed 'macOS pipe-timeout test failures': they were
this path-length throw, not a timeout-message defect.
2026-08-10 05:54:11 -04:00

1115 lines
50 KiB
C#
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
using System.IO.Pipes;
using Google.Protobuf.WellKnownTypes;
using ZB.MOM.WW.MxGateway.Contracts;
using ZB.MOM.WW.MxGateway.Contracts.Proto;
using ZB.MOM.WW.MxGateway.Server.Metrics;
using ZB.MOM.WW.MxGateway.Server.Workers;
using ZB.MOM.WW.MxGateway.Tests.Gateway.Workers.Fakes;
using ZB.MOM.WW.MxGateway.Tests.TestSupport;
namespace ZB.MOM.WW.MxGateway.Tests.Gateway.Workers;
public sealed class WorkerClientTests
{
private const string SessionId = "session-worker-client";
private const string Nonce = "nonce-worker-client";
private const int WorkerProcessId = 4321;
private static readonly TimeSpan TestTimeout = TimeSpan.FromSeconds(5);
/// <summary>Verifies that StartAsync enters ready state after receiving worker hello and ready messages.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task StartAsync_WithWorkerHelloAndReady_EntersReadyState()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Assert.Equal(WorkerClientState.Ready, client.State);
Assert.Equal(WorkerProcessId, client.ProcessId);
}
/// <summary>
/// The <c>GatewayHello</c> carries the negotiated worker-frame maximum so the worker adopts the
/// configured limit instead of its own default (IPC-02); a regression to sending <c>0</c> means
/// "older gateway, use default" to the worker and would silently downgrade the negotiated limit.
/// The adoption half is asserted only in the Windows-only worker suite, so the gateway half is
/// pinned here, in the portable suite (TST-28). Both the default and an override are covered so
/// the assertion tracks configuration rather than a constant.
/// </summary>
/// <param name="maxMessageBytes">Configured worker-frame maximum to negotiate.</param>
/// <returns>A task that represents the asynchronous operation.</returns>
[Theory]
[InlineData(WorkerFrameProtocolOptions.DefaultMaxMessageBytes)]
[InlineData(2 * 1024 * 1024)]
public async Task StartAsync_SendsGatewayHelloWithConfiguredMaxFrameBytes(int maxMessageBytes)
{
await using FakeWorkerHarness harness =
await FakeWorkerHarness.CreateConnectedPairAsync(maxMessageBytes: maxMessageBytes);
await using WorkerClient client = harness.CreateClient();
Task startTask = client.StartAsync(CancellationToken.None);
WorkerEnvelope gatewayHello = await harness.CompleteStartupAsync().WaitAsync(TestTimeout);
await startTask.WaitAsync(TestTimeout);
Assert.NotEqual(0u, gatewayHello.GatewayHello.MaxFrameBytes);
Assert.Equal((uint)maxMessageBytes, gatewayHello.GatewayHello.MaxFrameBytes);
}
/// <summary>Verifies that InvokeAsync completes a pending command when a matching reply arrives.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task InvokeAsync_WithMatchingReply_CompletesPendingCommand()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply> invokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.WorkerCommand, commandEnvelope.BodyCase);
Assert.False(string.IsNullOrWhiteSpace(commandEnvelope.CorrelationId));
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(commandEnvelope.CorrelationId, MxCommandKind.Ping));
WorkerCommandReply reply = await invokeTask.WaitAsync(TestTimeout);
Assert.Equal(commandEnvelope.CorrelationId, reply.Reply.CorrelationId);
Assert.Equal(MxCommandKind.Ping, reply.Reply.Kind);
}
/// <summary>
/// Verifies that a command whose serialized envelope exceeds the negotiated worker-frame maximum
/// fails only that command with <see cref="WorkerClientErrorCode.CommandTooLarge"/> at the enqueue
/// boundary, leaving the client ready for subsequent commands. Without the pre-check the
/// oversized frame would reach the write loop and fault the whole session.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task InvokeAsync_WhenCommandExceedsFrameMax_FailsOnlyThatCommandAndStaysReady()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair, maxMessageBytes: 4096);
await CompleteHandshakeAsync(client, pipePair);
WorkerCommand oversized = new()
{
Command = new MxCommand
{
Kind = MxCommandKind.Write,
Write = new WriteCommand
{
ServerHandle = 1,
ItemHandle = 2,
Value = new MxValue { StringValue = new string('x', 8192) },
},
},
};
WorkerClientException exception = await Assert.ThrowsAsync<WorkerClientException>(
async () => await client.InvokeAsync(oversized, TestTimeout, CancellationToken.None));
Assert.Equal(WorkerClientErrorCode.CommandTooLarge, exception.ErrorCode);
Assert.Equal(WorkerClientState.Ready, client.State);
// A subsequent normally-sized command still round-trips: the session was not faulted.
Task<WorkerCommandReply> nextInvoke = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(commandEnvelope.CorrelationId, MxCommandKind.Ping));
WorkerCommandReply reply = await nextInvoke.WaitAsync(TestTimeout);
Assert.Equal(MxCommandKind.Ping, reply.Reply.Kind);
Assert.Equal(WorkerClientState.Ready, client.State);
}
/// <summary>Verifies that InvokeAsync ignores late replies and keeps the client ready.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task InvokeAsync_WithLateReply_IgnoresLateReplyAndKeepsClientReady()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply> timedOutInvokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TimeSpan.FromMilliseconds(50),
CancellationToken.None);
WorkerEnvelope timedOutCommand = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
WorkerClientException exception = await Assert.ThrowsAsync<WorkerClientException>(
async () => await timedOutInvokeTask);
Assert.Equal(WorkerClientErrorCode.CommandTimeout, exception.ErrorCode);
// Send the stale reply for the already-timed-out command, then the second
// command's reply. The pipe is FIFO, so the read loop processes (and discards)
// the stale reply before the second reply — no fixed Task.Delay needed.
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(timedOutCommand.CorrelationId, MxCommandKind.Ping));
Task<WorkerCommandReply> secondInvokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.GetWorkerInfo),
TestTimeout,
CancellationToken.None);
WorkerEnvelope secondCommand = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(secondCommand.CorrelationId, MxCommandKind.GetWorkerInfo));
WorkerCommandReply reply = await secondInvokeTask.WaitAsync(TestTimeout);
Assert.Equal(WorkerClientState.Ready, client.State);
Assert.Equal(MxCommandKind.GetWorkerInfo, reply.Reply.Kind);
}
/// <summary>
/// The envelope <c>sequence</c> is a monotonic per-sender counter (gateway.md), so the values
/// observed on the pipe must be strictly increasing in wire order. Stamping the sequence when
/// the envelope is constructed lets two concurrent invokes stamp 1 and 2 but enqueue 2 then 1
/// (GWC-28); stamping on the single-consumer write loop makes wire order and sequence order the
/// same thing by construction.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ConcurrentInvokesEmitStrictlyIncreasingSequencesOnTheWire()
{
const int commandCount = 32;
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply>[] invokeTasks = Enumerable.Range(0, commandCount)
.Select(_ => Task.Run(async () => await client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None)))
.ToArray();
ulong previousSequence = 0;
for (int index = 0; index < commandCount; index++)
{
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.WorkerCommand, commandEnvelope.BodyCase);
Assert.True(
commandEnvelope.Sequence > previousSequence,
$"Command {index} arrived with sequence {commandEnvelope.Sequence} after {previousSequence}; "
+ "envelope sequences must be strictly increasing in wire order.");
previousSequence = commandEnvelope.Sequence;
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(commandEnvelope.CorrelationId, MxCommandKind.Ping));
}
await Task.WhenAll(invokeTasks).WaitAsync(TestTimeout);
Assert.Equal(WorkerClientState.Ready, client.State);
}
/// <summary>Verifies that ReadEventsAsync yields events in pipe order from the worker.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadEventsAsync_WithWorkerEvents_YieldsEventsInPipeOrder()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
using CancellationTokenSource cancellationTokenSource = new(TestTimeout);
await using IAsyncEnumerator<WorkerEvent> events =
client.ReadEventsAsync(cancellationTokenSource.Token).GetAsyncEnumerator(cancellationTokenSource.Token);
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 11, MxEventFamily.OnDataChange));
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 12, MxEventFamily.OperationComplete));
Assert.True(await events.MoveNextAsync());
Assert.Equal((ulong)11, events.Current.Event.WorkerSequence);
Assert.Equal(MxEventFamily.OnDataChange, events.Current.Event.Family);
Assert.True(await events.MoveNextAsync());
Assert.Equal((ulong)12, events.Current.Event.WorkerSequence);
Assert.Equal(MxEventFamily.OperationComplete, events.Current.Event.Family);
}
/// <summary>
/// The worker event channel is single-reader: a second <see cref="WorkerClient.ReadEventsAsync"/>
/// enumerator must throw rather than silently split events between two consumers.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadEventsAsync_SecondEnumerator_Throws()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
using CancellationTokenSource cancellationTokenSource = new(TestTimeout);
// First call claims the single reader.
IAsyncEnumerable<WorkerEvent> first = client.ReadEventsAsync(cancellationTokenSource.Token);
await using IAsyncEnumerator<WorkerEvent> firstEnumerator = first.GetAsyncEnumerator(cancellationTokenSource.Token);
// A second call must fail loudly at call time rather than racing the first for events.
Assert.Throws<InvalidOperationException>(() => client.ReadEventsAsync(cancellationTokenSource.Token));
}
/// <summary>Verifies that the read loop faults the client when the event queue overflows.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenEventQueueOverflows_FaultsClient()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = 1,
EventChannelFullModeTimeout = TimeSpan.FromMilliseconds(50),
HeartbeatGrace = TimeSpan.FromSeconds(30),
HeartbeatCheckInterval = TimeSpan.FromSeconds(30),
});
await CompleteHandshakeAsync(client, pipePair);
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 11, MxEventFamily.OnDataChange));
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 12, MxEventFamily.OnDataChange));
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted,
TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>
/// Verifies that a command reply arriving on the pipe after events is dispatched promptly even
/// when the event channel is full and has no consumer — event enqueue is decoupled from the read
/// loop, so a blocked event writer cannot delay a reply. The event full-mode timeout is
/// set far above the command timeout: without the decoupling the read loop would block behind the
/// full event channel and the in-flight InvokeAsync would hit CommandTimeout.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenEventChannelFull_DispatchesCommandReplyWithoutBlocking()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = 1,
// Much larger than TestTimeout: the read loop must not block for this long behind the
// full event channel while a reply waits.
EventChannelFullModeTimeout = TimeSpan.FromSeconds(30),
HeartbeatGrace = TimeSpan.FromSeconds(60),
HeartbeatCheckInterval = TimeSpan.FromSeconds(60),
});
await CompleteHandshakeAsync(client, pipePair);
// No StreamEvents consumer is attached, so the capacity-1 event channel fills and the event
// writer blocks on the second event's timed WriteAsync.
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 11, MxEventFamily.OnDataChange));
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 12, MxEventFamily.OnDataChange));
Task<WorkerCommandReply> invokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(commandEnvelope.CorrelationId, MxCommandKind.Ping));
WorkerCommandReply reply = await invokeTask.WaitAsync(TestTimeout);
Assert.Equal(MxCommandKind.Ping, reply.Reply.Kind);
Assert.Equal(WorkerClientState.Ready, client.State);
}
/// <summary>
/// Verifies that when the client faults it kills the owned worker process.
/// The assertion waits on <see cref="FakeWorkerProcess.WaitForExitAsync"/>, which
/// completes exactly when <c>Kill</c> runs, instead of polling <c>client.State</c>.
/// Polling state is racy: <see cref="WorkerClient.SetFaulted"/> publishes the
/// <c>Faulted</c> state before it calls <c>KillOwnedProcess</c>, so a state-based
/// wait can observe <c>Faulted</c> while <c>KillCount</c> is still 0.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenClientFaults_KillsOwnedWorkerProcess()
{
await using PipePair pipePair = await PipePair.CreateAsync();
FakeWorkerProcess process = new(WorkerProcessId);
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = 1,
EventChannelFullModeTimeout = TimeSpan.FromMilliseconds(50),
HeartbeatGrace = TimeSpan.FromSeconds(30),
HeartbeatCheckInterval = TimeSpan.FromSeconds(30),
},
processHandle: CreateProcessHandle(process));
await CompleteHandshakeAsync(client, pipePair);
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 11, MxEventFamily.OnDataChange));
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: 12, MxEventFamily.OnDataChange));
// Deterministic: this completes the instant Kill() runs, with no timing window.
using CancellationTokenSource exitTimeout = new(TestTimeout);
await process.WaitForExitAsync(exitTimeout.Token);
Assert.Equal(WorkerClientState.Faulted, client.State);
Assert.Equal(1, process.KillCount);
Assert.True(process.KillEntireProcessTree);
Assert.True(process.HasExited);
}
/// <summary>
/// Verifies that a worker faulting mid-command — the pipe dropping while an
/// <see cref="WorkerClient.InvokeAsync"/> is still pending — completes the pending
/// invoke task with a <see cref="WorkerClientException"/> carrying the
/// pipe-disconnected error code rather than hanging until the command timeout.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task InvokeAsync_WhenPipeDisconnectsMidCommand_FailsPendingInvokeWithPipeDisconnected()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply> invokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
// The worker received the command but disconnects before replying.
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.WorkerCommand, commandEnvelope.BodyCase);
await pipePair.DisposeWorkerSideAsync();
WorkerClientException exception = await Assert.ThrowsAsync<WorkerClientException>(
async () => await invokeTask.WaitAsync(TestTimeout));
Assert.Equal(WorkerClientErrorCode.PipeDisconnected, exception.ErrorCode);
await WaitUntilAsync(() => client.State == WorkerClientState.Faulted, TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>
/// Verifies that a worker emitting a <c>WorkerFault</c> envelope while an
/// <see cref="WorkerClient.InvokeAsync"/> is pending completes the pending invoke
/// task with a <see cref="WorkerClientException"/> carrying the worker-faulted
/// error code.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task InvokeAsync_WhenWorkerFaultsMidCommand_FailsPendingInvokeWithWorkerFaulted()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply> invokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.WorkerCommand, commandEnvelope.BodyCase);
await pipePair.WorkerWriter.WriteAsync(CreateWorkerFaultEnvelope("scripted mid-command fault"));
WorkerClientException exception = await Assert.ThrowsAsync<WorkerClientException>(
async () => await invokeTask.WaitAsync(TestTimeout));
Assert.Equal(WorkerClientErrorCode.WorkerFaulted, exception.ErrorCode);
await WaitUntilAsync(() => client.State == WorkerClientState.Faulted, TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>Verifies that pipe disconnect faults the client.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenPipeDisconnects_FaultsClient()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
await pipePair.DisposeWorkerSideAsync();
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted,
TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>Verifies that the read loop stops the running worker metric when the pipe disconnects.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenPipeDisconnects_StopsRunningWorkerMetric()
{
await using PipePair pipePair = await PipePair.CreateAsync();
using GatewayMetrics metrics = new();
await using WorkerClient client = CreateClient(pipePair, metrics: metrics);
await CompleteHandshakeAsync(client, pipePair);
Assert.Equal(1, metrics.GetSnapshot().WorkersRunning);
await pipePair.DisposeWorkerSideAsync();
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted
&& metrics.GetSnapshot().WorkersRunning == 0,
TestTimeout);
GatewayMetricsSnapshot snapshot = metrics.GetSnapshot();
Assert.Equal(0, snapshot.WorkersRunning);
Assert.Equal(1, snapshot.WorkerExits);
}
/// <summary>Verifies that DisposeAsync returns within a bounded timeout when the pipe read is blocked.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task DisposeAsync_WhenPipeReadIsBlocked_ReturnsWithinBoundedTimeout()
{
await using PipePair pipePair = await PipePair.CreateAsync();
WorkerClient client = CreateClient(pipePair);
await CompleteHandshakeAsync(client, pipePair);
DateTimeOffset startedAt = DateTimeOffset.UtcNow;
await client.DisposeAsync().AsTask().WaitAsync(TestTimeout);
TimeSpan elapsed = DateTimeOffset.UtcNow - startedAt;
Assert.True(
elapsed < TimeSpan.FromSeconds(4),
$"DisposeAsync took {elapsed.TotalMilliseconds:N0}ms.");
}
/// <summary>Verifies that DisposeAsync kills the still-running owned worker process before disposing.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task DisposeAsync_WhenOwnedWorkerStillRuns_KillsProcessBeforeDisposing()
{
await using PipePair pipePair = await PipePair.CreateAsync();
FakeWorkerProcess process = new(WorkerProcessId);
WorkerClient client = CreateClient(pipePair, processHandle: CreateProcessHandle(process));
await client.DisposeAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(1, process.KillCount);
Assert.True(process.KillEntireProcessTree);
Assert.True(process.Disposed);
}
/// <summary>
/// Verifies that a heartbeat envelope updates the last-heartbeat timestamp and worker
/// process id. Uses a <see cref="ManualTimeProvider"/> so the timestamp advance is
/// deterministic instead of relying on a wall-clock <c>Task.Delay</c> exceeding
/// <see cref="DateTimeOffset.UtcNow"/> resolution.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task ReadLoop_WhenHeartbeatArrives_UpdatesLastHeartbeatAndWorkerProcess()
{
ManualTimeProvider clock = new(DateTimeOffset.Parse("2026-05-18T12:00:00Z", System.Globalization.CultureInfo.InvariantCulture));
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(pipePair, timeProvider: clock);
await CompleteHandshakeAsync(client, pipePair);
DateTimeOffset previousHeartbeat = client.LastHeartbeatAt;
clock.Advance(TimeSpan.FromSeconds(1));
await pipePair.WorkerWriter.WriteAsync(CreateHeartbeatEnvelope(workerProcessId: 9876));
await WaitUntilAsync(
() => client.ProcessId == 9876 && client.LastHeartbeatAt > previousHeartbeat,
TestTimeout);
Assert.Equal(WorkerClientState.Ready, client.State);
Assert.Equal(previousHeartbeat + TimeSpan.FromSeconds(1), client.LastHeartbeatAt);
}
/// <summary>
/// Verifies that the heartbeat monitor faults the client when the heartbeat expires.
/// Uses an injected <see cref="ManualTimeProvider"/> so the grace comparison is deterministic
/// instead of depending on real wall-clock advance; the monitor's
/// <see cref="WorkerClientOptions.HeartbeatCheckInterval"/> timer stays on the real clock and
/// observes the manually-advanced grace on its next tick.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task HeartbeatMonitor_WhenHeartbeatExpires_FaultsClient()
{
ManualTimeProvider clock = new(DateTimeOffset.Parse("2026-05-20T12:00:00Z", System.Globalization.CultureInfo.InvariantCulture));
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
HeartbeatGrace = TimeSpan.FromMilliseconds(80),
HeartbeatCheckInterval = TimeSpan.FromMilliseconds(20),
EventChannelCapacity = 8,
},
timeProvider: clock);
await CompleteHandshakeAsync(client, pipePair);
clock.Advance(TimeSpan.FromSeconds(2));
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted,
TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>
/// While a command is in flight on the
/// gateway↔worker pipe and the oldest pending command is younger
/// than <see cref="WorkerClientOptions.HeartbeatStuckCeiling"/>, the
/// heartbeat watchdog must NOT fault on heartbeat-expired alone — the
/// gap is more likely caused by pipe-write contention than by a hung
/// worker.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task HeartbeatMonitor_WhenCommandInFlightWithinCeiling_DoesNotFaultOnExpiredHeartbeat()
{
ManualTimeProvider clock = new(DateTimeOffset.Parse("2026-05-20T13:00:00Z", System.Globalization.CultureInfo.InvariantCulture));
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
HeartbeatGrace = TimeSpan.FromMilliseconds(80),
HeartbeatCheckInterval = TimeSpan.FromMilliseconds(20),
EventChannelCapacity = 8,
HeartbeatStuckCeiling = TimeSpan.FromSeconds(30),
},
timeProvider: clock);
await CompleteHandshakeAsync(client, pipePair);
// Begin a command that the test never replies to — keeps the
// PendingCommand alive in `_pendingCommands` for the duration.
Task<WorkerCommandReply> pendingInvoke = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.WorkerCommand, commandEnvelope.BodyCase);
// Advance well past HeartbeatGrace but well within HeartbeatStuckCeiling.
clock.Advance(TimeSpan.FromSeconds(2));
// Give the heartbeat monitor a few real check-intervals to observe the gap.
await Task.Delay(TimeSpan.FromMilliseconds(150));
Assert.Equal(WorkerClientState.Ready, client.State);
Assert.False(pendingInvoke.IsCompleted);
}
/// <summary>
/// Once the oldest pending command exceeds
/// <see cref="WorkerClientOptions.HeartbeatStuckCeiling"/>, the
/// heartbeat watchdog fires anyway — a truly stuck COM call shouldn't
/// keep the watchdog suppressed indefinitely.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task HeartbeatMonitor_WhenPendingCommandExceedsStuckCeiling_FaultsClient()
{
ManualTimeProvider clock = new(DateTimeOffset.Parse("2026-05-20T13:00:00Z", System.Globalization.CultureInfo.InvariantCulture));
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
HeartbeatGrace = TimeSpan.FromMilliseconds(80),
HeartbeatCheckInterval = TimeSpan.FromMilliseconds(20),
EventChannelCapacity = 8,
HeartbeatStuckCeiling = TimeSpan.FromMilliseconds(200),
},
timeProvider: clock);
await CompleteHandshakeAsync(client, pipePair);
Task<WorkerCommandReply> pendingInvoke = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
// Advance the clock past HeartbeatStuckCeiling. The worker pipe's
// PendingCommand.StartTimestamp uses TimeProvider.GetTimestamp(), so the
// ManualTimeProvider's GetElapsedTime sees the advanced gap.
clock.Advance(TimeSpan.FromSeconds(2));
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted,
TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
}
/// <summary>
/// A transient burst that exceeds
/// <see cref="WorkerClientOptions.EventChannelCapacity"/> must be
/// absorbed for up to <see cref="WorkerClientOptions.EventChannelFullModeTimeout"/>
/// (the channel is configured for <c>BoundedChannelFullMode.Wait</c>);
/// only when the wait elapses without progress is the worker faulted,
/// and the diagnostic must name the channel capacity, depth, and
/// actionable remediation.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task EnqueueWorkerEvent_WhenChannelFullPastTimeout_FaultsWithRichDiagnostic()
{
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = 4,
EventChannelFullModeTimeout = TimeSpan.FromMilliseconds(100),
HeartbeatGrace = TimeSpan.FromSeconds(30),
HeartbeatCheckInterval = TimeSpan.FromSeconds(1),
});
await CompleteHandshakeAsync(client, pipePair);
// Fill the 4-slot channel and write exactly one more to force the
// overflow path. The gateway never opens a StreamEvents consumer, so
// the events stay buffered. Exactly five events are written: the
// worker client faults while reading the fifth, after which its read
// loop stops — a sixth event would never be drained and its pipe
// write would block forever on a full OS pipe buffer.
for (ulong sequence = 1; sequence <= 5; sequence++)
{
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence: sequence, MxEventFamily.OnDataChange));
}
await WaitUntilAsync(
() => client.State == WorkerClientState.Faulted,
TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
// Reading the events channel after fault throws the propagated
// WorkerClientException carrying the rich diagnostic message. The
// drain is bounded by TestTimeout so a regression that leaves the
// channel uncompleted fails the test instead of hanging it.
using CancellationTokenSource drainTimeout = new(TestTimeout);
WorkerClientException fault = await Assert.ThrowsAsync<WorkerClientException>(async () =>
{
await foreach (WorkerEvent _ in client.ReadEventsAsync(drainTimeout.Token))
{
}
});
Assert.Contains("Worker event channel rejected", fault.Message);
Assert.Contains("of 4 capacity", fault.Message);
Assert.Contains("StreamEvents", fault.Message);
Assert.Contains("MxGateway:Events:QueueCapacity", fault.Message);
}
/// <summary>
/// GWC-24: the staging channel between the read loop and the event writer is bounded at
/// 2 × <see cref="WorkerClientOptions.EventChannelCapacity"/>, so a consumer that drains
/// slower than the worker produces faults the client at the bound instead of growing
/// gateway memory silently. The full-mode timeout here is far longer than the test could
/// ever wait, which proves the fault came from the staging bound and not from the timed
/// write in <c>EnqueueWorkerEventAsync</c>. A command reply interleaved before the fault
/// must still complete: the read loop never blocks behind events (the GWC-04 guarantee).
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task StagingChannelOverflowFaultsWorkerWithoutWaitingForFullModeTimeout()
{
const int capacity = 4;
const int stagingBound = 2 * capacity;
using GatewayMetrics metrics = new();
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = capacity,
// Five minutes: the timed-write fault physically cannot be the trigger.
EventChannelFullModeTimeout = TimeSpan.FromMinutes(5),
HeartbeatGrace = TimeSpan.FromSeconds(30),
HeartbeatCheckInterval = TimeSpan.FromSeconds(30),
},
metrics: metrics);
await CompleteHandshakeAsync(client, pipePair);
// The staging channel alone holds 2 × capacity, and the event writer only ever removes
// from it, so this batch cannot fault however the writer happens to be scheduled. Waiting
// on the gauge (rather than a delay) proves the read loop consumed every one of them.
ulong sequence = 1;
for (; sequence <= (ulong)stagingBound; sequence++)
{
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence, MxEventFamily.OnDataChange));
}
await WaitUntilAsync(
() => metrics.GetSnapshot().WorkerEventQueueDepth == stagingBound,
TestTimeout);
Assert.Equal(WorkerClientState.Ready, client.State);
// The event path is backed up with no consumer attached, yet a command still round-trips.
Task<WorkerCommandReply> invokeTask = client.InvokeAsync(
CreateCommand(MxCommandKind.Ping),
TestTimeout,
CancellationToken.None);
WorkerEnvelope commandEnvelope = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
await pipePair.WorkerWriter.WriteAsync(
CreateCommandReplyEnvelope(commandEnvelope.CorrelationId, MxCommandKind.Ping));
WorkerCommandReply reply = await invokeTask.WaitAsync(TestTimeout);
Assert.Equal(MxCommandKind.Ping, reply.Reply.Kind);
Assert.Equal(WorkerClientState.Ready, client.State);
// The absolute ceiling is capacity (consumer channel) + 1 (in flight in the blocked event
// writer) + 2 × capacity (staging). Push comfortably past it. The events are tiny, so the
// ones the stopped read loop never drains stay in the OS pipe buffer instead of blocking.
for (int extra = 0; extra < 3 * capacity; extra++, sequence++)
{
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence, MxEventFamily.OnDataChange));
}
await WaitUntilAsync(() => client.State == WorkerClientState.Faulted, TestTimeout);
Assert.Equal(WorkerClientState.Faulted, client.State);
using CancellationTokenSource drainTimeout = new(TestTimeout);
WorkerClientException fault = await Assert.ThrowsAsync<WorkerClientException>(async () =>
{
await foreach (WorkerEvent _ in client.ReadEventsAsync(drainTimeout.Token))
{
}
});
Assert.Equal(WorkerClientErrorCode.ProtocolViolation, fault.ErrorCode);
Assert.Contains("staging", fault.Message, StringComparison.OrdinalIgnoreCase);
Assert.Contains($"{2 * capacity}", fault.Message, StringComparison.Ordinal);
Assert.Contains("StreamEvents", fault.Message, StringComparison.Ordinal);
Assert.Contains("MxGateway:Events:QueueCapacity", fault.Message, StringComparison.Ordinal);
// The timed-write diagnostic must not be what fired.
Assert.DoesNotContain("Worker event channel rejected", fault.Message, StringComparison.Ordinal);
}
/// <summary>
/// GWC-24: the worker event queue-depth gauge counts staged *and* queued events, so a
/// backlog held in the staging channel is visible rather than invisible. Depth is
/// incremented at staging and decremented when the consumer reads, so the single counter
/// reports total undelivered events and returns to zero once drained.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WorkerEventQueueDepthGaugeCountsStagedEvents()
{
const int capacity = 4;
const int eventCount = 8;
using GatewayMetrics metrics = new();
await using PipePair pipePair = await PipePair.CreateAsync();
await using WorkerClient client = CreateClient(
pipePair,
new WorkerClientOptions
{
EventChannelCapacity = capacity,
EventChannelFullModeTimeout = TimeSpan.FromMinutes(5),
HeartbeatGrace = TimeSpan.FromSeconds(30),
HeartbeatCheckInterval = TimeSpan.FromSeconds(30),
},
metrics: metrics);
await CompleteHandshakeAsync(client, pipePair);
// Above EventChannelCapacity but below the 2× staging bound: no consumer, no fault.
for (ulong sequence = 1; sequence <= eventCount; sequence++)
{
await pipePair.WorkerWriter.WriteAsync(
CreateEventEnvelope(sequence, MxEventFamily.OnDataChange));
}
await WaitUntilAsync(
() => metrics.GetSnapshot().WorkerEventQueueDepth == eventCount,
TestTimeout);
Assert.Equal(eventCount, metrics.GetSnapshot().WorkerEventQueueDepth);
Assert.Equal(WorkerClientState.Ready, client.State);
using CancellationTokenSource drainTimeout = new(TestTimeout);
await using IAsyncEnumerator<WorkerEvent> events = client
.ReadEventsAsync(drainTimeout.Token)
.GetAsyncEnumerator(drainTimeout.Token);
for (int read = 0; read < eventCount; read++)
{
Assert.True(await events.MoveNextAsync());
}
await WaitUntilAsync(
() => metrics.GetSnapshot().WorkerEventQueueDepth == 0,
TestTimeout);
Assert.Equal(0, metrics.GetSnapshot().WorkerEventQueueDepth);
}
private static WorkerClient CreateClient(
PipePair pipePair,
WorkerClientOptions? options = null,
GatewayMetrics? metrics = null,
WorkerProcessHandle? processHandle = null,
TimeProvider? timeProvider = null,
int maxMessageBytes = WorkerFrameProtocolOptions.DefaultMaxMessageBytes)
{
WorkerFrameProtocolOptions frameOptions = new(
SessionId,
GatewayContractInfo.WorkerProtocolVersion,
maxMessageBytes);
WorkerClientConnection connection = new(
SessionId,
Nonce,
pipePair.GatewayStream,
frameOptions,
processHandle);
return new WorkerClient(connection, options, metrics, timeProvider);
}
private static WorkerProcessHandle CreateProcessHandle(FakeWorkerProcess process)
{
return new WorkerProcessHandle(
process,
new WorkerProcessCommandLine("ZB.MOM.WW.MxGateway.Worker.exe", []),
DateTimeOffset.UtcNow);
}
private static async Task CompleteHandshakeAsync(
WorkerClient client,
PipePair pipePair)
{
Task startTask = client.StartAsync(CancellationToken.None);
WorkerEnvelope gatewayHello = await pipePair.WorkerReader.ReadAsync().AsTask().WaitAsync(TestTimeout);
Assert.Equal(WorkerEnvelope.BodyOneofCase.GatewayHello, gatewayHello.BodyCase);
Assert.Equal(Nonce, gatewayHello.GatewayHello.Nonce);
Assert.Equal(GatewayContractInfo.WorkerProtocolVersion, gatewayHello.GatewayHello.SupportedProtocolVersion);
await pipePair.WorkerWriter.WriteAsync(CreateWorkerHelloEnvelope());
await pipePair.WorkerWriter.WriteAsync(CreateWorkerReadyEnvelope());
await startTask.WaitAsync(TestTimeout);
}
private static WorkerCommand CreateCommand(MxCommandKind kind)
{
return new WorkerCommand
{
Command = new MxCommand
{
Kind = kind,
},
};
}
private static WorkerEnvelope CreateWorkerHelloEnvelope()
{
return CreateWorkerEnvelope(
correlationId: string.Empty,
sequence: 1,
envelope => envelope.WorkerHello = new WorkerHello
{
ProtocolVersion = GatewayContractInfo.WorkerProtocolVersion,
Nonce = Nonce,
WorkerProcessId = WorkerProcessId,
WorkerVersion = "fake-worker",
});
}
private static WorkerEnvelope CreateWorkerReadyEnvelope()
{
return CreateWorkerEnvelope(
correlationId: string.Empty,
sequence: 2,
envelope => envelope.WorkerReady = new WorkerReady
{
WorkerProcessId = WorkerProcessId,
MxaccessProgid = "LMXProxy.LMXProxyServer.1",
MxaccessClsid = "{C30B52F5-2CB5-4760-AF0A-3A344A7EB5DC}",
});
}
private static WorkerEnvelope CreateCommandReplyEnvelope(
string correlationId,
MxCommandKind kind)
{
return CreateWorkerEnvelope(
correlationId,
sequence: 10,
envelope => envelope.WorkerCommandReply = new WorkerCommandReply
{
Reply = new MxCommandReply
{
SessionId = SessionId,
CorrelationId = correlationId,
Kind = kind,
},
});
}
private static WorkerEnvelope CreateEventEnvelope(
ulong sequence,
MxEventFamily family)
{
return CreateWorkerEnvelope(
correlationId: string.Empty,
sequence,
envelope => envelope.WorkerEvent = new WorkerEvent
{
Event = new MxEvent
{
SessionId = SessionId,
Family = family,
WorkerSequence = sequence,
},
});
}
private static WorkerEnvelope CreateWorkerFaultEnvelope(string diagnosticMessage)
{
return CreateWorkerEnvelope(
correlationId: string.Empty,
sequence: 30,
envelope => envelope.WorkerFault = new WorkerFault
{
Category = WorkerFaultCategory.MxaccessCommandFailed,
DiagnosticMessage = diagnosticMessage,
ProtocolStatus = new ProtocolStatus
{
Code = ProtocolStatusCode.WorkerUnavailable,
Message = diagnosticMessage,
},
});
}
private static WorkerEnvelope CreateHeartbeatEnvelope(int workerProcessId)
{
return CreateWorkerEnvelope(
correlationId: string.Empty,
sequence: 20,
envelope => envelope.WorkerHeartbeat = new WorkerHeartbeat
{
WorkerProcessId = workerProcessId,
State = WorkerState.Ready,
LastStaActivityTimestamp = Timestamp.FromDateTimeOffset(DateTimeOffset.UtcNow),
PendingCommandCount = 0,
OutboundEventQueueDepth = 0,
});
}
private static WorkerEnvelope CreateWorkerEnvelope(
string correlationId,
ulong sequence,
Action<WorkerEnvelope> setBody)
{
WorkerEnvelope envelope = new()
{
ProtocolVersion = GatewayContractInfo.WorkerProtocolVersion,
SessionId = SessionId,
Sequence = sequence,
CorrelationId = correlationId,
};
setBody(envelope);
return envelope;
}
private static async Task WaitUntilAsync(
Func<bool> predicate,
TimeSpan timeout)
{
using CancellationTokenSource cancellationTokenSource = new(timeout);
while (!predicate())
{
await Task.Delay(TimeSpan.FromMilliseconds(10), cancellationTokenSource.Token);
}
}
private sealed class PipePair : IAsyncDisposable
{
private readonly NamedPipeClientStream _workerStream;
private bool _workerSideDisposed;
private PipePair(
NamedPipeServerStream gatewayStream,
NamedPipeClientStream workerStream)
{
GatewayStream = gatewayStream;
_workerStream = workerStream;
WorkerReader = new WorkerFrameReader(_workerStream, new WorkerFrameProtocolOptions(SessionId));
WorkerWriter = new WorkerFrameWriter(_workerStream, new WorkerFrameProtocolOptions(SessionId));
}
/// <summary>The gateway side of the named pipe connection.</summary>
public NamedPipeServerStream GatewayStream { get; }
/// <summary>Frame reader for worker messages.</summary>
public WorkerFrameReader WorkerReader { get; }
/// <summary>Frame writer for worker messages.</summary>
public WorkerFrameWriter WorkerWriter { get; }
/// <summary>Creates a connected pipe pair for testing.</summary>
/// <returns>The connected <see cref="PipePair"/>.</returns>
public static async Task<PipePair> CreateAsync()
{
string pipeName = $"mxgw-wc-{Guid.NewGuid():N}";
NamedPipeServerStream gatewayStream = new(
pipeName,
PipeDirection.InOut,
maxNumberOfServerInstances: 1,
PipeTransmissionMode.Byte,
PipeOptions.Asynchronous);
NamedPipeClientStream workerStream = new(
".",
pipeName,
PipeDirection.InOut,
PipeOptions.Asynchronous);
Task waitForConnectionTask = gatewayStream.WaitForConnectionAsync();
await workerStream.ConnectAsync();
await waitForConnectionTask;
return new PipePair(gatewayStream, workerStream);
}
/// <summary>Disposes the worker side of the pipe.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
public async ValueTask DisposeWorkerSideAsync()
{
if (_workerSideDisposed)
{
return;
}
await _workerStream.DisposeAsync();
_workerSideDisposed = true;
}
/// <summary>Disposes the duplex stream.</summary>
/// <returns>A task that represents the asynchronous operation.</returns>
public async ValueTask DisposeAsync()
{
await DisposeWorkerSideAsync();
await GatewayStream.DisposeAsync();
}
}
}