Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests/ClusterNodeAddressReconcilerActorTests.cs
T
Joseph Doherty 2535df019b fix(mesh): scope ClusterNode address reconcile to the admin node's own cluster
Phase 6 splits the fleet into one mesh per Cluster, so an admin (central)
node's Cluster.State.Members shows only its own pair — it no longer sees
site members via gossip. The ClusterNodeAddressReconciler singleton compared
live membership against EVERY ClusterNode row fleet-wide, so post-split every
foreign-cluster row would log EnabledRowNotInCluster forever.

Scope the actor's two DB queries to rows whose ClusterId matches the admin
node's own (IClusterRoleInfo.ClusterId, sourced at registration). A legacy
admin node with no cluster role (null ClusterId) still reconciles the whole
fleet — it genuinely sees every member via gossip. The pure Reconcile
function and AddressMismatchKind semantics are unchanged; scoping lives
entirely in the actor's queries.

Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
2026-07-24 01:39:06 -04:00

155 lines
6.5 KiB
C#

using Akka.Actor;
using Microsoft.EntityFrameworkCore;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Configuration;
using ZB.MOM.WW.OtOpcUa.Configuration.Entities;
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
using ZB.MOM.WW.OtOpcUa.ControlPlane.Fleet;
using ZB.MOM.WW.OtOpcUa.ControlPlane.Tests.Harness;
namespace ZB.MOM.WW.OtOpcUa.ControlPlane.Tests;
/// <summary>
/// Proves the reconciler is actually wired to something — subscribes to membership, reads the DB,
/// and emits. <see cref="ClusterNodeAddressReconcilerTests"/> covers the comparison logic, which a
/// dormant actor would leave perfectly correct and completely inert.
/// </summary>
public sealed class ClusterNodeAddressReconcilerActorTests : ControlPlaneActorTestBase
{
/// <summary>
/// An enabled row with no matching driver member is warned about. The harness ActorSystem
/// joins as <c>admin</c> with no driver members, so the seeded row is unmatched by
/// construction.
/// </summary>
[Fact]
public void Enabled_row_with_no_matching_member_is_logged()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "site-a-1:4053", enabled: true);
EventFilter.Warning(contains: "site-a-1:4053").ExpectOne(TimeSpan.FromSeconds(10), () =>
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(dbFactory)));
}
/// <summary>
/// The finding set is logged once, not once per sweep. A check that reprints the same warning
/// every five minutes trains operators to filter it out, which costs more than it catches —
/// so this runs a deliberately fast sweep and asserts the count stays at one.
/// </summary>
[Fact]
public void Unchanged_findings_are_not_repeated_on_every_sweep()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "site-a-1:4053", enabled: true);
// ~6 sweeps inside the window; without the change-detection guard this logs 6 times.
EventFilter.Warning(contains: "site-a-1:4053").Expect(1, TimeSpan.FromSeconds(3), () =>
{
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(
dbFactory, sweepInterval: TimeSpan.FromMilliseconds(400)));
// Hold the filter open past several sweeps rather than returning immediately.
ExpectNoMsg(TimeSpan.FromSeconds(2.5));
});
}
/// <summary>
/// A disabled row is silence — the maintenance hatch must not trade a failed deployment for a
/// permanent warning. Positive control for the test above: same setup, one flag flipped.
/// </summary>
[Fact]
public void Disabled_row_produces_no_warning()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "site-a-1:4053", enabled: false);
EventFilter.Warning(contains: "site-a-1:4053").Expect(0, TimeSpan.FromSeconds(2), () =>
{
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(
dbFactory, sweepInterval: TimeSpan.FromMilliseconds(400)));
ExpectNoMsg(TimeSpan.FromSeconds(1.5));
});
}
/// <summary>
/// Per-cluster mesh Phase 6: an admin node scoped to its OWN cluster ignores rows in a cluster
/// its mesh can no longer see. Scoped to <c>MAIN</c>, a <c>SITE-A</c> enabled row is filtered
/// out before <see cref="ClusterNodeAddressReconciler.Reconcile"/> ever sees it, so it produces
/// no <see cref="AddressMismatchKind.EnabledRowNotInCluster"/> warning. This is the false
/// positive the split would otherwise print forever.
/// </summary>
[Fact]
public void Row_in_a_foreign_cluster_is_ignored_when_scoped()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "site-a-1:4053", enabled: true, clusterId: "SITE-A");
EventFilter.Warning(contains: "site-a-1:4053").Expect(0, TimeSpan.FromSeconds(2), () =>
{
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(
dbFactory, ownClusterId: "MAIN", sweepInterval: TimeSpan.FromMilliseconds(400)));
ExpectNoMsg(TimeSpan.FromSeconds(1.5));
});
}
/// <summary>
/// Scoping does not silence the admin node's own cluster. Scoped to <c>MAIN</c>, an enabled
/// <c>MAIN</c> row with no matching driver member is still warned about — proving the filter
/// keeps in-cluster rows (and with them, within-cluster drift detection).
/// </summary>
[Fact]
public void Enabled_row_in_own_cluster_is_still_logged_when_scoped()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "main-1:4053", enabled: true, clusterId: "MAIN");
EventFilter.Warning(contains: "main-1:4053").ExpectOne(TimeSpan.FromSeconds(10), () =>
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(dbFactory, ownClusterId: "MAIN")));
}
/// <summary>
/// Legacy backward-compat: an admin node with no cluster role (null <c>ownClusterId</c>) still
/// reconciles the WHOLE fleet — such a node genuinely sees every member via gossip. A
/// <c>SITE-A</c> enabled row with no member is warned about, exactly as before the Phase 6 scope.
/// </summary>
[Fact]
public void Foreign_cluster_row_is_still_logged_when_unscoped()
{
var dbFactory = NewInMemoryDbFactory();
SeedNode(dbFactory, "site-a-1:4053", enabled: true, clusterId: "SITE-A");
EventFilter.Warning(contains: "site-a-1:4053").ExpectOne(TimeSpan.FromSeconds(10), () =>
Sys.ActorOf(ClusterNodeAddressReconcilerActor.Props(dbFactory, ownClusterId: null)));
}
private static void SeedNode(
IDbContextFactory<OtOpcUaConfigDbContext> dbFactory, string nodeId, bool enabled,
string clusterId = "SITE-A")
{
using var db = dbFactory.CreateDbContext();
if (!db.ServerClusters.Any(c => c.ClusterId == clusterId))
{
db.ServerClusters.Add(new ServerCluster
{
ClusterId = clusterId,
Name = clusterId,
Enterprise = "zb",
Site = clusterId.ToLowerInvariant(),
NodeCount = 2,
RedundancyMode = RedundancyMode.Warm,
CreatedBy = "test",
});
}
db.ClusterNodes.Add(new ClusterNode
{
NodeId = nodeId,
ClusterId = clusterId,
Host = nodeId.Split(':')[0],
ApplicationUri = $"urn:OtOpcUa:{nodeId}",
Enabled = enabled,
CreatedBy = "test",
});
db.SaveChanges();
}
}