fix(communication): failback probation is time-boxed and cleared on address change (review 2026-10-21 03/P-2 follow-up)

2026-10-22 08:28:11 -04:00
parent f4d328aecc
commit 4456a04e81
3 changed files with 60 additions and 2 deletions
@@ -86,6 +86,46 @@ public class SitePairChannelProviderFailbackTests
        Assert.Equal(TimeSpan.FromSeconds(1), provider.GetFailbackBackoff(Site));
    }

+    /// <summary>Verifies that probation expires: a quiet site whose NodeA dies long after the failback starts again at the initial backoff.</summary>
+    /// <returns>A task that represents the asynchronous operation.</returns>
+    [Fact]
+    public async Task ProbationOlderThanTheWindow_IsTreatedAsConfirmed_FirstProbeAtInitialBackoff()
+    {
+        using var provider = Build((_, _) => Task.FromResult(true));
+        provider.FailbackProbationWindow = TimeSpan.FromMilliseconds(100);
+        provider.UpdateSite(Site, "http://localhost:15321", "http://localhost:15322");
+
+        await CallRejectedByA(provider);
+        Assert.True(await provider.TryFailbackAsync(Site, CancellationToken.None));
+        await CallRejectedByA(provider);
+        Assert.Equal(TimeSpan.FromSeconds(2), provider.GetFailbackBackoff(Site));
+
+        // Fail back on probation, then the site goes quiet (no real call) past the window.
+        Assert.True(await provider.TryFailbackAsync(Site, CancellationToken.None));
+        await Task.Delay(300);
+
+        await CallRejectedByA(provider);
+        Assert.Equal(TimeSpan.FromSeconds(1), provider.GetFailbackBackoff(Site));
+    }
+
+    /// <summary>Verifies that an address change clears probation.</summary>
+    /// <returns>A task that represents the asynchronous operation.</returns>
+    [Fact]
+    public async Task AddressChange_ClearsProbation()
+    {
+        using var provider = Build((_, _) => Task.FromResult(true));
+        provider.UpdateSite(Site, "http://localhost:15331", "http://localhost:15332");
+
+        await CallRejectedByA(provider);
+        Assert.True(await provider.TryFailbackAsync(Site, CancellationToken.None));
+        await CallRejectedByA(provider);
+        Assert.True(await provider.TryFailbackAsync(Site, CancellationToken.None));
+
+        provider.UpdateSite(Site, "http://localhost:15333", "http://localhost:15332");
+        await CallRejectedByA(provider);
+        Assert.Equal(TimeSpan.FromSeconds(1), provider.GetFailbackBackoff(Site));
+    }
+
    /// <summary>Verifies that the production probe treats a not-ready (not-dispatched Unavailable) site as not ready.</summary>
    /// <returns>A task that represents the asynchronous operation.</returns>
    [Fact]