feat(redundancy): PeerProbeSupervisor maintains one peer OPC UA probe per driver peer

2026-06-15 13:22:38 -04:00
parent 37b32a5623
commit f41e957e07
2 changed files with 232 additions and 0 deletions
@@ -0,0 +1,105 @@
+using Akka.Actor;
+using Shouldly;
+using Xunit;
+using ZB.MOM.WW.OtOpcUa.Commons.Messages.Redundancy;
+using ZB.MOM.WW.OtOpcUa.Commons.Types;
+using ZB.MOM.WW.OtOpcUa.Runtime.Health;
+using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;
+
+namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.Health;
+
+/// <summary>
+/// Tests for <see cref="PeerProbeSupervisor"/>: it maintains exactly one peer-OPC-UA-probe child
+/// per OTHER, non-Detached driver node named in the latest <see cref="RedundancyStateChanged"/>
+/// snapshot, spawning/stopping children as the topology changes.
+/// </summary>
+public sealed class PeerProbeSupervisorTests : RuntimeActorTestBase
+{
+    private static readonly NodeId Local = NodeId.Parse("local:4053");
+    private static readonly NodeId Peer = NodeId.Parse("peer:4053");
+    private static readonly NodeId Adm = NodeId.Parse("adm:4053");
+
+    /// <summary>No-op child actor stub so we can count children without real TCP probes.</summary>
+    private sealed class NoopActor : ReceiveActor { }
+
+    private static Props NoopProps() => Akka.Actor.Props.Create(() => new NoopActor());
+
+    private static NodeRedundancyState State(NodeId id, RedundancyRole role) =>
+        new(id, role, IsClusterLeader: false, IsRoleLeaderForDriver: false, DateTime.UtcNow);
+
+    private static RedundancyStateChanged Snapshot(params NodeRedundancyState[] nodes) =>
+        new(nodes, CorrelationId.NewId());
+
+    /// <summary>Verifies one child is spawned per non-self, non-Detached peer — self and Detached
+    /// nodes are excluded.</summary>
+    [Fact]
+    public void Spawns_one_child_per_non_self_non_detached_peer()
+    {
+        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
+            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));
+
+        sup.Tell(Snapshot(
+            State(Local, RedundancyRole.Primary),
+            State(Peer, RedundancyRole.Secondary),
+            State(Adm, RedundancyRole.Detached)));
+
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
+            duration: TimeSpan.FromMilliseconds(500));
+    }
+
+    /// <summary>Verifies the child for a departed peer is stopped when the next snapshot omits it.</summary>
+    [Fact]
+    public void Stops_child_for_departed_peer()
+    {
+        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
+            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));
+
+        sup.Tell(Snapshot(
+            State(Local, RedundancyRole.Primary),
+            State(Peer, RedundancyRole.Secondary)));
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
+            duration: TimeSpan.FromMilliseconds(500));
+
+        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
+            duration: TimeSpan.FromMilliseconds(500));
+    }
+
+    /// <summary>Verifies a single-node snapshot (just the local node) spawns no children.</summary>
+    [Fact]
+    public void Single_node_snapshot_spawns_no_children()
+    {
+        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
+            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));
+
+        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
+
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
+            duration: TimeSpan.FromMilliseconds(500));
+    }
+
+    /// <summary>Verifies a previously-removed peer is respawned when it re-appears, without an
+    /// "actor name not unique" collision on the sanitized child name.</summary>
+    [Fact]
+    public void Re_adding_a_previously_removed_peer_respawns_it()
+    {
+        var sup = ActorOfAsTestActorRef<PeerProbeSupervisor>(
+            PeerProbeSupervisor.PropsForTests(Local, _ => NoopProps()));
+
+        sup.Tell(Snapshot(
+            State(Local, RedundancyRole.Primary),
+            State(Peer, RedundancyRole.Secondary)));
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
+            duration: TimeSpan.FromMilliseconds(500));
+
+        sup.Tell(Snapshot(State(Local, RedundancyRole.Primary)));
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(0),
+            duration: TimeSpan.FromMilliseconds(500));
+
+        sup.Tell(Snapshot(
+            State(Local, RedundancyRole.Primary),
+            State(Peer, RedundancyRole.Secondary)));
+        AwaitAssert(() => sup.UnderlyingActor.ChildCount.ShouldBe(1),
+            duration: TimeSpan.FromMilliseconds(500));
+    }
+}