fix(communication): guard per-site ClusterClient creation; add real-factory address-edit lifecycle test

This commit is contained in:
Joseph Doherty
2026-07-08 14:57:13 -04:00
parent 75cbac4478
commit f91e75bfe4
2 changed files with 97 additions and 1 deletions
@@ -0,0 +1,82 @@
using System.Collections.Immutable;
using Akka.Actor;
using Akka.Cluster.Tools.Client;
using Akka.Configuration;
using Akka.TestKit.Xunit2;
using Microsoft.Extensions.DependencyInjection;
using NSubstitute;
using Xunit;
using ZB.MOM.WW.ScadaBridge.Commons.Entities.Sites;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
using ZB.MOM.WW.ScadaBridge.Communication;
using ZB.MOM.WW.ScadaBridge.Communication.Actors;
namespace ZB.MOM.WW.ScadaBridge.Communication.Tests;
public class CentralCommunicationActorClientLifecycleTests : TestKit
{
private static readonly Config TestConfig = ConfigurationFactory.ParseString(@"
akka.actor.provider = cluster
akka.remote.dot-netty.tcp.port = 0
akka.remote.dot-netty.tcp.hostname = localhost")
.WithFallback(ClusterClientReceptionist.DefaultConfig());
public CentralCommunicationActorClientLifecycleTests() : base(TestConfig) { }
// Empty ServiceProvider with a no-op ISiteRepository so the actor's periodic
// db-refresh (fired at PreStart) resolves and returns no sites, keeping the
// logs clean; the tests drive SiteAddressCacheLoaded directly.
private static IServiceProvider EmptyProvider()
{
var siteRepo = Substitute.For<ISiteRepository>();
siteRepo.GetAllSitesAsync(Arg.Any<CancellationToken>()).Returns(new List<Site>());
var services = new ServiceCollection();
services.AddScoped(_ => siteRepo);
return services.BuildServiceProvider();
}
private static SiteAddressCacheLoaded Load(string siteId, params string[] addrs) =>
new(new Dictionary<string, IReadOnlyList<string>>
{ [siteId] = addrs.ToList().AsReadOnly() });
[Fact]
public void AddressEdit_RecreatesClient_WithoutRestartLoop()
{
var actor = Sys.ActorOf(Props.Create(() => new CentralCommunicationActor(
EmptyProvider(), new DefaultSiteClientFactory(), null)));
// First load creates the client; second load (edited NodeA address) stops
// the old one and creates a replacement in the same message handling.
// Pre-fix this throws InvalidActorNameException and restarts the actor.
EventFilter.Exception<InvalidActorNameException>().Expect(0, () =>
{
actor.Tell(Load("site-a", "akka.tcp://scadabridge@node-a:8081"));
actor.Tell(Load("site-a", "akka.tcp://scadabridge@node-a-edited:8081"));
actor.Tell(Load("site-a", "akka.tcp://scadabridge@node-a:8081")); // and back — third generation
});
// The actor must still be alive and routing (not crash-looping):
// an envelope for an unknown site produces the "No ClusterClient" warning,
// proving the Receive pipeline is healthy.
EventFilter.Warning(contains: "No ClusterClient for site").ExpectOne(() =>
actor.Tell(new SiteEnvelope("unknown-site", new object())));
}
[Fact]
public void FactoryThrow_SkipsSite_DoesNotCrashActor()
{
var throwingFactory = Substitute.For<ISiteClientFactory>();
throwingFactory.Create(Arg.Any<ActorSystem>(), Arg.Any<string>(), Arg.Any<ImmutableHashSet<ActorPath>>())
.Returns(_ => throw new InvalidOperationException("boom"));
var actor = Sys.ActorOf(Props.Create(() => new CentralCommunicationActor(
EmptyProvider(), throwingFactory, null)));
EventFilter.Error(contains: "Failed to create ClusterClient").ExpectOne(() =>
actor.Tell(Load("site-a", "akka.tcp://scadabridge@node-a:8081")));
// Actor survived — a subsequent envelope for that (unrouted) site still
// produces the healthy "No ClusterClient" warning rather than a dead actor.
EventFilter.Warning(contains: "No ClusterClient for site").ExpectOne(() =>
actor.Tell(new SiteEnvelope("site-a", new object())));
}
}