fix(site-runtime): retry the startup deployed-config load on SQLite failure (S5) — no more silent zero-instance node

2026-07-09 00:17:36 -04:00
parent b126fda22e
commit 2dabbbdde0
2 changed files with 107 additions and 4 deletions
@@ -15,6 +15,7 @@ using ZB.MOM.WW.ScadaBridge.SiteRuntime.Persistence;
 using ZB.MOM.WW.ScadaBridge.SiteRuntime.Scripts;
 using ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.TestSupport;
 using System.Text.Json;
+using System.Threading;

 namespace ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.Actors;

@@ -266,6 +267,46 @@ public class DeploymentManagerActorTests : TestKit, IDisposable
        Assert.DoesNotContain(configs, c => c.InstanceUniqueName == "bad-instance");
    }

+    // ── S5: startup deployed-config load is retried on transient failure ──
+
+    [Fact]
+    public void StartupLoadFailure_IsRetried_UntilSuccess()
+    {
+        // The first startup load throws (transient SQLite failure); the second
+        // succeeds and returns one enabled config. The DM must retry rather than
+        // stall as a silent zero-instance node — so the Instance Actor eventually
+        // exists.
+        var calls = 0;
+        Func<Task<List<DeployedInstance>>> loader = () =>
+            Interlocked.Increment(ref calls) == 1
+                ? Task.FromException<List<DeployedInstance>>(new IOException("db locked"))
+                : Task.FromResult(new List<DeployedInstance>
+                {
+                    new()
+                    {
+                        InstanceUniqueName = "inst-1",
+                        ConfigJson = MakeConfigJson("inst-1"),
+                        DeploymentId = "d1",
+                        RevisionHash = "h1",
+                        IsEnabled = true
+                    }
+                });
+
+        var dm = ActorOf(Props.Create(() => new DeploymentManagerActor(
+            _storage, _compilationService, _sharedScriptLibrary, null,
+            new SiteRuntimeOptions(), NullLogger<DeploymentManagerActor>.Instance,
+            null, null, null, null, null, null,
+            TimeSpan.FromMilliseconds(200), loader)));
+
+        AwaitAssert(() =>
+        {
+            Assert.True(Volatile.Read(ref calls) >= 2,
+                $"expected the load to be retried; calls={Volatile.Read(ref calls)}");
+            Sys.ActorSelection(dm.Path / "inst-1").Tell(new Identify(1));
+            Assert.NotNull(ExpectMsg<ActorIdentity>(TimeSpan.FromSeconds(1)).Subject);
+        }, TimeSpan.FromSeconds(10));
+    }
+
    // ── M1.6: site event log `deployment` category ─────────────────────────

    [Fact]