feat(dashboard): in-process snapshot feed replaces the pages' loopback /hubs/snapshot hop

This commit is contained in:
Joseph Doherty
2026-08-15 20:16:29 -04:00
parent e23f816bfb
commit e245237c2b
5 changed files with 637 additions and 45 deletions
@@ -0,0 +1,333 @@
using System.Runtime.CompilerServices;
using System.Threading.Channels;
using ZB.MOM.WW.MxGateway.Server.Dashboard;
namespace ZB.MOM.WW.MxGateway.Tests.Gateway.Dashboard;
/// <summary>
/// Covers the in-process snapshot fan-out that replaced the dashboard pages'
/// loopback <c>/hubs/snapshot</c> connections. The invariants under test are the
/// ones that make the feed cheaper than the hub hop: exactly one underlying
/// <see cref="IDashboardSnapshotService.WatchSnapshotsAsync"/> enumeration for any
/// number of viewers, nothing at all while nobody is watching, and a slow viewer
/// that can neither buffer without bound nor stall the others.
/// </summary>
public sealed class DashboardSnapshotFeedTests
{
private static readonly TimeSpan TestTimeout = TimeSpan.FromSeconds(5);
/// <summary>
/// With no page subscribed, the feed must not touch the snapshot service at
/// all — no timer, no snapshot build. This is the whole point of the idle
/// gate: an unattended gateway does no dashboard work.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WatchAsync_WithNoSubscribers_NeverEnumeratesUnderlyingWatch()
{
FakeSnapshotService service = new();
DashboardSnapshotFeed feed = new(service);
// Obtaining the enumerable without enumerating it must not subscribe
// either: the pump starts on the first MoveNextAsync, not before.
_ = feed.WatchAsync(CancellationToken.None);
await Task.Delay(TimeSpan.FromMilliseconds(100));
Assert.Equal(0, service.EnumerationCount);
}
/// <summary>
/// Two viewers share one underlying enumeration and both see the same
/// pushed snapshot. Before the feed, each page opened its own SignalR
/// connection and the publisher pulled its own snapshot stream.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WatchAsync_WithTwoSubscribers_SharesASingleUnderlyingEnumeration()
{
FakeSnapshotService service = new();
DashboardSnapshotFeed feed = new(service);
using CancellationTokenSource firstCancellation = new();
using CancellationTokenSource secondCancellation = new();
IAsyncEnumerator<DashboardSnapshot> first =
feed.WatchAsync(firstCancellation.Token).GetAsyncEnumerator(firstCancellation.Token);
Task<bool> firstMove = first.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 1);
IAsyncEnumerator<DashboardSnapshot> second =
feed.WatchAsync(secondCancellation.Token).GetAsyncEnumerator(secondCancellation.Token);
Task<bool> secondMove = second.MoveNextAsync().AsTask();
// Push until both have observed a snapshot: a subscriber only becomes
// visible to the pump once its MoveNextAsync has registered the channel,
// so a single push could race the second registration.
await PushUntilAsync(service, Task.WhenAll(firstMove, secondMove));
Assert.True(await firstMove.WaitAsync(TestTimeout));
Assert.True(await secondMove.WaitAsync(TestTimeout));
Assert.StartsWith("push-", first.Current.GatewayVersion, StringComparison.Ordinal);
Assert.StartsWith("push-", second.Current.GatewayVersion, StringComparison.Ordinal);
Assert.Equal(1, service.EnumerationCount);
await firstCancellation.CancelAsync();
await secondCancellation.CancelAsync();
await DrainAsync(first, firstMove);
await DrainAsync(second, secondMove);
}
/// <summary>
/// The last viewer leaving must cancel the underlying enumeration (idle
/// gate re-armed), and the next viewer must restart it — the rapid
/// unsubscribe/resubscribe path a page navigation exercises.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WatchAsync_WhenLastSubscriberLeaves_CancelsPumpAndRestartsForTheNext()
{
FakeSnapshotService service = new();
DashboardSnapshotFeed feed = new(service);
using CancellationTokenSource firstCancellation = new();
IAsyncEnumerator<DashboardSnapshot> first =
feed.WatchAsync(firstCancellation.Token).GetAsyncEnumerator(firstCancellation.Token);
Task<bool> firstMove = first.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 1);
await firstCancellation.CancelAsync();
await DrainAsync(first, firstMove);
await WaitUntilAsync(() => service.CompletedEnumerationCount >= 1);
Assert.True(service.LastEnumerationWasCancelled);
using CancellationTokenSource secondCancellation = new();
IAsyncEnumerator<DashboardSnapshot> second =
feed.WatchAsync(secondCancellation.Token).GetAsyncEnumerator(secondCancellation.Token);
Task<bool> secondMove = second.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 2);
Assert.Equal(2, service.EnumerationCount);
await secondCancellation.CancelAsync();
await DrainAsync(second, secondMove);
}
/// <summary>
/// A viewer that is not reading must not stall the pump or accumulate
/// snapshots: its bounded channel drops the oldest, so its next read is the
/// newest snapshot the pump has broadcast, not a backlog head. The fast
/// reader's progress is what makes the assertion deterministic — once it has
/// seen the third snapshot the pump has provably broadcast all three.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WatchAsync_WithASlowSubscriber_KeepsOnlyTheNewestSnapshot()
{
FakeSnapshotService service = new();
DashboardSnapshotFeed feed = new(service);
using CancellationTokenSource fastCancellation = new();
using CancellationTokenSource slowCancellation = new();
IAsyncEnumerator<DashboardSnapshot> fast =
feed.WatchAsync(fastCancellation.Token).GetAsyncEnumerator(fastCancellation.Token);
Task<bool> fastMove = fast.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 1);
// The slow subscriber registers but never advances until the very end.
IAsyncEnumerator<DashboardSnapshot> slow =
feed.WatchAsync(slowCancellation.Token).GetAsyncEnumerator(slowCancellation.Token);
Task<bool> slowMove = slow.MoveNextAsync().AsTask();
await PushUntilAsync(service, Task.WhenAll(fastMove, slowMove));
Assert.True(await fastMove.WaitAsync(TestTimeout));
Assert.True(await slowMove.WaitAsync(TestTimeout));
service.Push(CreateSnapshot("s1"));
service.Push(CreateSnapshot("s2"));
service.Push(CreateSnapshot("s3"));
// Drain the fast reader until it sees s3; that proves the pump broadcast
// all three to every subscriber, so the slow channel now holds exactly s3.
string fastLatest = fast.Current.GatewayVersion;
while (fastLatest != "s3")
{
Assert.True(await fast.MoveNextAsync().AsTask().WaitAsync(TestTimeout));
fastLatest = fast.Current.GatewayVersion;
}
Assert.True(await slow.MoveNextAsync().AsTask().WaitAsync(TestTimeout));
Assert.Equal("s3", slow.Current.GatewayVersion);
await fastCancellation.CancelAsync();
await slowCancellation.CancelAsync();
await DrainAsync(fast, Task.FromResult(true));
await DrainAsync(slow, Task.FromResult(true));
}
/// <summary>
/// A fault in the underlying watch is surfaced to the current viewers rather
/// than silently hanging them, and it resets the feed so the next viewer
/// starts a fresh pump instead of attaching to a dead one.
/// </summary>
/// <returns>A task that represents the asynchronous operation.</returns>
[Fact]
public async Task WatchAsync_WhenUnderlyingWatchFaults_PropagatesAndRestartsForTheNextSubscriber()
{
FakeSnapshotService service = new();
DashboardSnapshotFeed feed = new(service);
using CancellationTokenSource firstCancellation = new();
IAsyncEnumerator<DashboardSnapshot> first =
feed.WatchAsync(firstCancellation.Token).GetAsyncEnumerator(firstCancellation.Token);
Task<bool> firstMove = first.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 1);
service.Fault(new InvalidOperationException("simulated snapshot source failure"));
InvalidOperationException failure =
await Assert.ThrowsAsync<InvalidOperationException>(() => firstMove.WaitAsync(TestTimeout));
Assert.Equal("simulated snapshot source failure", failure.Message);
await first.DisposeAsync();
using CancellationTokenSource secondCancellation = new();
IAsyncEnumerator<DashboardSnapshot> second =
feed.WatchAsync(secondCancellation.Token).GetAsyncEnumerator(secondCancellation.Token);
Task<bool> secondMove = second.MoveNextAsync().AsTask();
await WaitUntilAsync(() => service.EnumerationCount >= 2);
await PushUntilAsync(service, secondMove);
Assert.True(await secondMove.WaitAsync(TestTimeout));
await secondCancellation.CancelAsync();
await DrainAsync(second, secondMove);
}
/// <summary>Builds a snapshot whose version string identifies it in assertions.</summary>
/// <param name="version">Identity marker carried in <c>GatewayVersion</c>.</param>
/// <returns>A snapshot carrying the supplied identity marker.</returns>
private static DashboardSnapshot CreateSnapshot(string version)
{
return new DashboardSnapshot(
GeneratedAt: DateTimeOffset.UnixEpoch,
GatewayStartedAt: DateTimeOffset.UnixEpoch,
GatewayUptime: TimeSpan.Zero,
GatewayStatus: "Healthy",
GatewayVersion: version,
Sessions: Array.Empty<DashboardSessionSummary>(),
Workers: Array.Empty<DashboardWorkerSummary>(),
Metrics: Array.Empty<DashboardMetricSummary>(),
Faults: Array.Empty<DashboardFaultSummary>(),
ApiKeys: Array.Empty<DashboardApiKeySummary>(),
Configuration: null!,
Galaxy: null!);
}
/// <summary>
/// Pushes snapshots until the supplied task completes, so a test never
/// depends on a single push landing after a subscriber has registered.
/// </summary>
/// <param name="service">Fake snapshot source to push through.</param>
/// <param name="until">Task whose completion stops the pushes.</param>
/// <returns>A task that represents the asynchronous operation.</returns>
private static async Task PushUntilAsync(FakeSnapshotService service, Task until)
{
using CancellationTokenSource cancellation = new(TestTimeout);
int sequence = 0;
while (!until.IsCompleted)
{
service.Push(CreateSnapshot($"push-{sequence++}"));
await Task.Delay(TimeSpan.FromMilliseconds(5), cancellation.Token);
}
}
/// <summary>
/// Observes the cancellation of a pending enumeration and disposes the
/// enumerator, mirroring how <c>await foreach</c> unwinds a cancelled watch.
/// </summary>
/// <param name="enumerator">Enumerator to unwind.</param>
/// <param name="pending">The in-flight move, if any.</param>
/// <returns>A task that represents the asynchronous operation.</returns>
private static async Task DrainAsync(IAsyncEnumerator<DashboardSnapshot> enumerator, Task pending)
{
try
{
await pending.WaitAsync(TestTimeout);
}
catch (OperationCanceledException)
{
}
try
{
await enumerator.DisposeAsync();
}
catch (OperationCanceledException)
{
}
}
private static async Task WaitUntilAsync(Func<bool> predicate)
{
using CancellationTokenSource cancellation = new(TestTimeout);
while (!predicate())
{
await Task.Delay(TimeSpan.FromMilliseconds(5), cancellation.Token);
}
}
/// <summary>
/// Snapshot source under the feed's control: counts enumerations, records how
/// each one ended, and lets the test drive snapshots (or a fault) into the
/// live enumeration.
/// </summary>
private sealed class FakeSnapshotService : IDashboardSnapshotService
{
private readonly Channel<object> _pushes = Channel.CreateUnbounded<object>();
private int _enumerationCount;
private int _completedEnumerationCount;
private volatile bool _lastEnumerationWasCancelled;
/// <summary>Gets the number of times the feed started enumerating this source.</summary>
public int EnumerationCount => Volatile.Read(ref _enumerationCount);
/// <summary>Gets the number of enumerations that have finished (cancelled, faulted, or completed).</summary>
public int CompletedEnumerationCount => Volatile.Read(ref _completedEnumerationCount);
/// <summary>Gets a value indicating whether the most recently finished enumeration ended cancelled.</summary>
public bool LastEnumerationWasCancelled => _lastEnumerationWasCancelled;
/// <summary>Queues a snapshot for the live enumeration to yield.</summary>
/// <param name="snapshot">Snapshot to yield.</param>
public void Push(DashboardSnapshot snapshot) => _pushes.Writer.TryWrite(snapshot);
/// <summary>Queues a failure for the live enumeration to throw.</summary>
/// <param name="error">Exception to throw from the enumeration.</param>
public void Fault(Exception error) => _pushes.Writer.TryWrite(error);
/// <inheritdoc />
public DashboardSnapshot GetSnapshot() => CreateSnapshot("current");
/// <inheritdoc />
public async IAsyncEnumerable<DashboardSnapshot> WatchSnapshotsAsync(
[EnumeratorCancellation] CancellationToken cancellationToken)
{
Interlocked.Increment(ref _enumerationCount);
try
{
await foreach (object item in _pushes.Reader.ReadAllAsync(cancellationToken).ConfigureAwait(false))
{
if (item is Exception error)
{
throw error;
}
yield return (DashboardSnapshot)item;
}
}
finally
{
_lastEnumerationWasCancelled = cancellationToken.IsCancellationRequested;
Interlocked.Increment(ref _completedEnumerationCount);
}
}
}
}