Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/OpcUa/OpcUaPublishActorApplyFailureTests.cs
T
Joseph Doherty db751d12a5
v2-ci / build (pull_request) Successful in 4m49s
v2-ci / unit-tests (pull_request) Failing after 3h11m25s
feat(alarms): condition Quality tracks source connectivity (#477)
Part 9 ConditionType.Quality was never assigned; default(StatusCode)==Good
so every native + scripted condition reported Good unconditionally — a
comms-lost device still showed a healthy, inactive, Good condition (a
wrong-VALUE bug, distinct from the null-value #473/#475). Clients (and HMIs
bucketing on IsGood) could not tell "genuinely inactive" from "lost contact".

Layer 1 — make Quality a real, plumbed field:
- AlarmConditionSnapshot gains OpcUaQuality Quality (default Good).
- MaterialiseAlarmCondition sets it (native BadWaitingForInitialData, scripted Good).
- WriteAlarmCondition projects snapshot.Quality; the delta-gate gains a Quality
  member so a quality-bucket change fires a Part 9 event.

Layer 2 — drive native quality from driver connectivity (a comms-lost driver
emits no alarm transitions, and an alarm-bearing raw tag has no value variable,
so quality can't come from either existing channel):
- DriverInstanceActor Tells parent ConnectivityChanged on Connected/Reconnecting.
- DriverHostActor fans it to every native condition the driver owns as
  OpcUaPublishActor.AlarmQualityUpdate (Good on connect, Bad on disconnect).
- New dedicated IOpcUaAddressSpaceSink.WriteAlarmQuality sets ONLY Quality and
  fires only on a bucket change — never touches Active/Acked/Retain (an active
  alarm that loses comms stays active). Not a full-snapshot re-projection, so it
  can't clobber severity/message and works for a never-fired condition.
  Forwarded through DeferredAddressSpaceSink (F10b trap; auto-verified by the
  reflection forwarding guard). Ungated by redundancy role; no /alerts row.

Scripted conditions stay Good; worst-of-input quality deferred to #478 (Layer 3).

Tests: node-level (materialise/project/no-clobber/unknown-node no-op),
NativeAlarmProjector, DriverInstanceActor connectivity emission, DriverHostActor
fan-out, OpcUaPublishActor routing, and the wire-level guard
(Condition_event_Quality_tracks_source_connectivity_on_the_wire) — RED-verified
against a simulated pre-fix always-Good server. Existing DriverInstanceActor
parent probes ignore the new ConnectivityChanged.

Docs: docs/AlarmTracking.md §"Condition source-data Quality (#477)";
design doc docs/plans/2026-07-17-alarm-condition-quality-477-design.md.
2026-07-17 15:10:04 -04:00

189 lines
9.9 KiB
C#

using System.Diagnostics.Metrics;
using System.Text.Json;
using Akka.Actor;
using Microsoft.EntityFrameworkCore;
using Microsoft.Extensions.Logging.Abstractions;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.Observability;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
using ZB.MOM.WW.OtOpcUa.Commons.Types;
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.OpcUaServer;
using ZB.MOM.WW.OtOpcUa.Runtime.OpcUa;
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;
namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.OpcUa;
/// <summary>
/// archreview 01/S-1: when the applier reports a degraded apply (a rebuild that threw, or per-node
/// materialise failures), <see cref="OpcUaPublishActor.HandleRebuild"/> must surface it — increment the
/// <c>otopcua.opcua.apply.failed</c> meter and log at Error — instead of the optimistic Info line. The
/// happy path must stay Info-only (zero increments).
/// </summary>
public sealed class OpcUaPublishActorApplyFailureTests : RuntimeActorTestBase
{
/// <summary>A rebuild whose sink throws increments otopcua.opcua.apply.failed (kind=rebuild). R2-07 — a
/// pure-add no longer rebuilds, so the degraded-rebuild path is exercised via a rebuild-forcing change:
/// a first PureAdd deploy establishes the applied composition, then a rename (ChangedEquipment ⇒ Rebuild)
/// drives the throwing SafeRebuild.</summary>
[Fact]
public void Rebuild_when_sink_throws_increments_apply_failed_meter()
{
using var recorder = new MeterRecorder("otopcua.opcua.apply.failed");
var db = NewInMemoryDbFactory();
var sink = new ThrowOnRebuildSink();
var applier = new AddressSpaceApplier(sink, NullLogger<AddressSpaceApplier>.Instance);
var dep1 = SeedEquipmentDeployment(db, ("eq-1", "eq-1"));
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, dbFactory: db, applier: applier));
// First deploy: PureAdd — no rebuild, so the throwing sink is not hit yet.
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), new DeploymentId(dep1)));
Thread.Sleep(200);
recorder.Total.ShouldBe(0);
// Second deploy: eq-1 RENAMED ⇒ ChangedEquipment ⇒ Rebuild ⇒ the sink's RebuildAddressSpace throws.
var dep2 = SeedEquipmentDeployment(db, ("eq-1", "eq-1-renamed"));
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), new DeploymentId(dep2)));
AwaitAssert(() =>
{
recorder.Total.ShouldBeGreaterThanOrEqualTo(1);
recorder.WithTag("kind", "rebuild").ShouldBeGreaterThanOrEqualTo(1);
}, duration: TimeSpan.FromSeconds(2));
}
/// <summary>A clean rebuild does NOT increment the apply-failed meter (Info-only happy path).</summary>
[Fact]
public void Rebuild_happy_path_does_not_increment_apply_failed_meter()
{
using var recorder = new MeterRecorder("otopcua.opcua.apply.failed");
var db = NewInMemoryDbFactory();
var sink = new NoopSink();
var applier = new AddressSpaceApplier(sink, NullLogger<AddressSpaceApplier>.Instance);
SeedEquipmentDeployment(db, ("eq-1", "eq-1"));
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, dbFactory: db, applier: applier));
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId()));
// Give the actor time to process, then confirm the failed meter never fired.
Thread.Sleep(400);
recorder.Total.ShouldBe(0);
}
private void AwaitAssert(Action assertion, TimeSpan duration)
{
var deadline = DateTime.UtcNow + duration;
Exception? last = null;
while (DateTime.UtcNow < deadline)
{
try { assertion(); return; }
catch (Exception ex) { last = ex; Thread.Sleep(25); }
}
if (last is not null) throw last;
}
private static Guid SeedEquipmentDeployment(IDbContextFactory<OtOpcUaConfigDbContext> dbFactory, params (string Id, string Name)[] equipment)
{
var artifact = JsonSerializer.SerializeToUtf8Bytes(new
{
Equipment = equipment.Select(e => new
{
EquipmentId = e.Id,
MachineCode = e.Id.ToUpperInvariant(),
UnsLineId = "line-1",
Name = e.Name,
}).ToArray(),
DriverInstances = Array.Empty<object>(),
ScriptedAlarms = Array.Empty<object>(),
});
var id = Guid.NewGuid();
using var ctx = dbFactory.CreateDbContext();
ctx.Deployments.Add(new Deployment
{
DeploymentId = id,
RevisionHash = new string('a', 64),
Status = DeploymentStatus.Sealed,
CreatedBy = "test",
SealedAtUtc = DateTime.UtcNow,
ArtifactBlob = artifact,
});
ctx.SaveChanges();
return id;
}
/// <summary>A sink whose RebuildAddressSpace throws (drives the applier's SafeRebuild catch → RebuildFailed).</summary>
private sealed class ThrowOnRebuildSink : IOpcUaAddressSpaceSink
{
public void WriteValue(string nodeId, object? value, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) { }
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, AddressSpaceRealm realm, string? historianTagname = null, bool isArray = false, uint? arrayLength = null) { }
public void RebuildAddressSpace() => throw new InvalidOperationException("simulated rebuild fault");
public void RaiseNodesAddedModelChange(string affectedNodeId, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WireAlarmNotifiers(string alarmNodeId, AddressSpaceRealm alarmRealm, IReadOnlyList<string> notifierFolderNodeIds, AddressSpaceRealm notifierFolderRealm) { }
public void AddReference(string sourceNodeId, AddressSpaceRealm sourceRealm, string targetNodeId, AddressSpaceRealm targetRealm, string referenceType = "Organizes") { }
}
/// <summary>A no-op sink — a clean apply (no failures).</summary>
private sealed class NoopSink : IOpcUaAddressSpaceSink
{
public void WriteValue(string nodeId, object? value, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WriteAlarmQuality(string alarmNodeId, OpcUaQuality quality, DateTime sourceTimestampUtc, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) { }
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, AddressSpaceRealm realm, string? historianTagname = null, bool isArray = false, uint? arrayLength = null) { }
public void RebuildAddressSpace() { }
public void RaiseNodesAddedModelChange(string affectedNodeId, AddressSpaceRealm realm = AddressSpaceRealm.Uns) { }
public void WireAlarmNotifiers(string alarmNodeId, AddressSpaceRealm alarmRealm, IReadOnlyList<string> notifierFolderNodeIds, AddressSpaceRealm notifierFolderRealm) { }
public void AddReference(string sourceNodeId, AddressSpaceRealm sourceRealm, string targetNodeId, AddressSpaceRealm targetRealm, string referenceType = "Organizes") { }
}
/// <summary>Listens to a single instrument by name on the central meter and tallies value + tags.</summary>
private sealed class MeterRecorder : IDisposable
{
private readonly string _name;
private readonly MeterListener _listener;
private long _total;
private readonly List<KeyValuePair<string, object?>[]> _tagSets = new();
private readonly object _gate = new();
public MeterRecorder(string instrumentName)
{
_name = instrumentName;
_listener = new MeterListener
{
InstrumentPublished = (instrument, listener) =>
{
if (instrument.Meter.Name == OtOpcUaTelemetry.MeterName && instrument.Name == _name)
listener.EnableMeasurementEvents(instrument);
}
};
_listener.SetMeasurementEventCallback<long>((_, value, tags, _) =>
{
lock (_gate)
{
_total += value;
_tagSets.Add(tags.ToArray());
}
});
_listener.Start();
}
public long Total { get { lock (_gate) return _total; } }
public int WithTag(string key, string value)
{
lock (_gate) return _tagSets.Count(set => set.Any(t => t.Key == key && Equals(t.Value, value)));
}
public void Dispose() => _listener.Dispose();
}
}