fix(dcl): queue a create whose actor name belongs to a still-terminating child instead of refusing it (review 2026-10-21 follow-up L2)

2026-10-22 09:46:52 -04:00
parent 530a096111
commit e60c316f30
3 changed files with 141 additions and 13 deletions
@@ -20,6 +20,7 @@ public class ConnectionActorNameTests : TestKit
 {
    private readonly IDataConnectionFactory _factory = Substitute.For<IDataConnectionFactory>();
    private readonly ISiteHealthCollector _health = Substitute.For<ISiteHealthCollector>();
+    private volatile bool _slowDispose;
    private readonly DataConnectionOptions _options = new()
    {
        ReconnectInterval = TimeSpan.FromMilliseconds(100),
@@ -37,6 +38,13 @@ public class ConnectionActorNameTests : TestKit
            adapter.Status.Returns(ConnectionHealth.Connected);
            adapter.SubscribeAsync(Arg.Any<string>(), Arg.Any<SubscriptionCallback>(), Arg.Any<CancellationToken>())
                .Returns("sub-1");
+            // A synchronous delay inside DisposeAsync holds the stopping child in PostStop, which
+            // keeps its actor name reserved — the dispose window the L2 tests exercise.
+            adapter.DisposeAsync().Returns(_ =>
+            {
+                if (_slowDispose) Thread.Sleep(400);
+                return ValueTask.CompletedTask;
+            });
            return adapter;
        });
    }
@@ -89,4 +97,45 @@ public class ConnectionActorNameTests : TestKit
        Assert.Contains("Unknown connection", Subscribe(manager, "PLC-A").ErrorMessage);
        Assert.DoesNotContain("Unknown connection", Subscribe(manager, "PLC A").ErrorMessage ?? "");
    }
+
+    /// <summary>
+    /// Follow-up L2: a Remove immediately followed by a Create of the SAME name (a redeploy that
+    /// rebuilds the connection) lands while the stopped child is still terminating, so its actor
+    /// name is still reserved. The create used to be refused permanently as a "collision" — and
+    /// the deployment manager, having recorded the config hash, never resent it. The manager now
+    /// queues the create until the old child's Terminated arrives.
+    /// </summary>
+    [Fact]
+    public void RemoveThenCreateSameName_InsideDisposeWindow_IsCreatedOnceTheOldChildTerminates()
+    {
+        _slowDispose = true;
+        var manager = CreateManager();
+        manager.Tell(new CreateConnectionCommand("PLC1", "OpcUa", new Dictionary<string, string>(), null, 3));
+        manager.Tell(new RemoveConnectionCommand("PLC1"));
+        manager.Tell(new CreateConnectionCommand("PLC1", "OpcUa", new Dictionary<string, string>(), null, 3));
+
+        AwaitAssert(
+            () => Assert.DoesNotContain("Unknown connection", Subscribe(manager, "PLC1").ErrorMessage ?? ""),
+            TimeSpan.FromSeconds(10),
+            TimeSpan.FromMilliseconds(100));
+    }
+
+    /// <summary>
+    /// Follow-up L2: a Remove that arrives while a create is still queued behind a terminating
+    /// child cancels the queued create — the connection stays removed.
+    /// </summary>
+    [Fact]
+    public void RemoveWhileCreateQueued_CancelsTheQueuedCreate()
+    {
+        _slowDispose = true;
+        var manager = CreateManager();
+        manager.Tell(new CreateConnectionCommand("PLC2", "OpcUa", new Dictionary<string, string>(), null, 3));
+        manager.Tell(new RemoveConnectionCommand("PLC2"));
+        manager.Tell(new CreateConnectionCommand("PLC2", "OpcUa", new Dictionary<string, string>(), null, 3));
+        manager.Tell(new RemoveConnectionCommand("PLC2"));
+
+        // Let the old child terminate (and any wrongly-queued create run) before asserting.
+        Thread.Sleep(1000);
+        Assert.Contains("Unknown connection", Subscribe(manager, "PLC2").ErrorMessage);
+    }
 }