fix(comm): single-gRPC-endpoint sites can go live (flip degenerates to same-node reconnect) (plan R2-02 T15)

This commit is contained in:
Joseph Doherty
2026-07-13 10:26:43 -04:00
parent 41ffe42de3
commit c83b51fe9c
2 changed files with 54 additions and 2 deletions
@@ -294,7 +294,9 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
return null;
}
if (string.IsNullOrWhiteSpace(site.GrpcNodeAAddress) || string.IsNullOrWhiteSpace(site.GrpcNodeBAddress))
var nodeA = site.GrpcNodeAAddress;
var nodeB = site.GrpcNodeBAddress;
if (string.IsNullOrWhiteSpace(nodeA) && string.IsNullOrWhiteSpace(nodeB))
{
_logger.LogWarning(
"Live alarm cache: site {SiteId} ({SiteIdentifier}) has no gRPC node addresses; " +
@@ -302,7 +304,13 @@ public sealed class SiteAlarmLiveCacheService : ISiteAlarmLiveCache
return null;
}
return (site.SiteIdentifier, site.GrpcNodeAAddress!, site.GrpcNodeBAddress!);
// Single-endpoint site (review 02 round 2, N9): reuse the sole configured
// endpoint for both slots — the aggregator's NodeA↔NodeB failover flip
// degenerates to a reconnect against the same node, which is exactly the
// right behavior for a one-node site.
var grpcA = !string.IsNullOrWhiteSpace(nodeA) ? nodeA! : nodeB!;
var grpcB = !string.IsNullOrWhiteSpace(nodeB) ? nodeB! : nodeA!;
return (site.SiteIdentifier, grpcA, grpcB);
}
// ── Snapshot fan-out (the seed / reconcile) ─────────────────────────────────
@@ -258,4 +258,48 @@ public class SiteAlarmLiveCacheServiceTests : TestKit
Assert.False(service.IsLive(999));
Assert.Empty(service.GetCurrentAlarms(999));
}
// ── R2 T15: single-endpoint sites can go live (N9) ──
[Fact]
public void SiteWithOnlyNodeAEndpoint_StartsAnAggregator_AgainstThatEndpoint()
{
var site = new Site("Three", "site-3")
{
Id = 3,
GrpcNodeAAddress = "http://only-node:8083",
GrpcNodeBAddress = null, // single-endpoint site — pre-fix: never goes live
};
var siteRepo = Substitute.For<ISiteRepository>();
siteRepo.GetSiteByIdAsync(3, Arg.Any<CancellationToken>()).Returns(site);
var instanceRepo = Substitute.For<ITemplateEngineRepository>();
instanceRepo.GetInstancesBySiteIdAsync(3, Arg.Any<CancellationToken>())
.Returns(new List<Instance>());
var services = new ServiceCollection();
services.AddScoped(_ => siteRepo);
services.AddScoped(_ => instanceRepo);
var provider = services.BuildServiceProvider();
var options = Options.Create(new CommunicationOptions
{
LiveAlarmCacheLinger = TimeSpan.FromSeconds(30),
LiveAlarmCacheReconcileInterval = TimeSpan.FromMinutes(10),
});
var comm = new CommunicationService(Options.Create(new CommunicationOptions()),
NullLogger<CommunicationService>.Instance);
var factory = new CountingFactory();
var service = new SiteAlarmLiveCacheService(
provider, comm, factory, options, NullLogger<SiteAlarmLiveCacheService>.Instance);
service.SetActorSystem(Sys);
using var sub = service.Subscribe(3, () => { });
// Pre-fix: ResolveSiteAsync required BOTH endpoints and bailed → never live, no client.
AwaitCondition(() => service.IsLive(3), TimeSpan.FromSeconds(5));
Assert.True(factory.GetOrCreateCount >= 1); // a client was created for the single endpoint
}
}