fix(communication): cancel-only CTS replacement, deferred channel disposal, single-endpoint debug stream (arch-review 2026-08-19 P3-1 + P3-2 + P3-3)

2026-08-19 14:38:33 -04:00
parent fd4cb30273
commit 412406e7c5
8 changed files with 566 additions and 50 deletions
@@ -0,0 +1,105 @@
+using Grpc.Net.Client;
+using Microsoft.Extensions.Logging.Abstractions;
+using Microsoft.Extensions.Options;
+using ZB.MOM.WW.ScadaBridge.Communication.Grpc;
+
+namespace ZB.MOM.WW.ScadaBridge.Communication.Tests.Grpc;
+
+/// <summary>
+/// Arch-review 2026-08-19 P3-2 — a channel replaced by the 60 s DB address refresh (or an admin
+/// edit) must not be disposed out from under an in-flight <see cref="SitePairChannelProvider.ExecuteAsync{T}"/>
+/// call. <c>ExecuteAsync</c> reads the channel under the pair gate but runs the RPC outside it, so an
+/// inline dispose aborted whatever was running — a multi-minute <c>DeployArtifactsCommand</c>
+/// included — with a status the cross-node retry deliberately never engages on.
+/// </summary>
+public class SitePairChannelProviderDisposalTests
+{
+    private static SitePairChannelProvider Build() => new(
+        new NoKeyProvider(),
+        Options.Create(new CommunicationOptions()),
+        NullLogger<SitePairChannelProvider>.Instance);
+
+    [Fact]
+    public async Task UpdateSite_WhileCallInFlight_ParksTheOldChannelAndLetsTheCallComplete()
+    {
+        using var provider = Build();
+        provider.UpdateSite("site-1", "http://localhost:15101", nodeBEndpoint: null);
+
+        var entered = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
+        var release = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
+        GrpcChannel? inFlightChannel = null;
+
+        // A long-running command (deploy) against the site's current channel.
+        var call = provider.ExecuteAsync("site-1", async (channel, ct) =>
+        {
+            inFlightChannel = channel;
+            entered.SetResult();
+            await release.Task;
+            // A disposed GrpcChannel throws here — this is the assertion that the address
+            // refresh did not pull the channel out from under the call.
+            _ = channel.CreateCallInvoker();
+            return 42;
+        }, CancellationToken.None);
+
+        await entered.Task.WaitAsync(TimeSpan.FromSeconds(5));
+
+        // The DB refresh tick re-points the site at a new address, mid-call.
+        provider.UpdateSite("site-1", "http://localhost:15102", nodeBEndpoint: null);
+
+        // The superseded channel is PARKED, not disposed synchronously.
+        Assert.Equal(1, provider.ParkedChannelCount);
+
+        release.SetResult();
+        Assert.Equal(42, await call.WaitAsync(TimeSpan.FromSeconds(5)));
+
+        // Once the grace window elapses the park drains and the channel really is disposed —
+        // deferred disposal, not a leak.
+        provider.SweepGraveyard(force: true);
+        Assert.Equal(0, provider.ParkedChannelCount);
+        Assert.Throws<ObjectDisposedException>(() => inFlightChannel!.CreateCallInvoker());
+    }
+
+    [Fact]
+    public void RemoveSite_ParksBothChannelsRatherThanDisposingThemInline()
+    {
+        using var provider = Build();
+        provider.UpdateSite("site-1", "http://localhost:15111", "http://localhost:15112");
+
+        provider.RemoveSite("site-1");
+
+        // Same hazard as UpdateSite: an admin deleting a site while a command is in flight.
+        Assert.Equal(2, provider.ParkedChannelCount);
+
+        provider.SweepGraveyard(force: true);
+        Assert.Equal(0, provider.ParkedChannelCount);
+    }
+
+    [Fact]
+    public void UpdateSite_UnchangedEndpoints_ParksNothing()
+    {
+        using var provider = Build();
+        provider.UpdateSite("site-1", "http://localhost:15121", "http://localhost:15122");
+        provider.UpdateSite("site-1", "http://localhost:15121", "http://localhost:15122");
+
+        Assert.Equal(0, provider.ParkedChannelCount);
+    }
+
+    [Fact]
+    public void Dispose_DrainsParkedChannelsRegardlessOfRemainingGrace()
+    {
+        var provider = Build();
+        provider.UpdateSite("site-1", "http://localhost:15131", nodeBEndpoint: null);
+        provider.UpdateSite("site-1", "http://localhost:15132", nodeBEndpoint: null);
+        Assert.Equal(1, provider.ParkedChannelCount);
+
+        provider.Dispose();
+
+        Assert.Equal(0, provider.ParkedChannelCount);
+    }
+
+    private sealed class NoKeyProvider : ISitePskProvider
+    {
+        public ValueTask<string> GetAsync(string siteId, CancellationToken ct) => new("k");
+        public void Invalidate(string siteId) { }
+    }
+}