fix(r2-04): surface degraded address-space applies (Error log + otopcua.opcua.apply.failed)
This commit is contained in:
Joseph Doherty
+170
@@ -0,0 +1,170 @@
|
||||
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).</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);
|
||||
SeedEquipmentDeployment(db, "eq-1");
|
||||
|
||||
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, dbFactory: db, applier: applier));
|
||||
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId()));
|
||||
|
||||
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");
|
||||
|
||||
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 void SeedEquipmentDeployment(IDbContextFactory<OtOpcUaConfigDbContext> dbFactory, params string[] equipmentIds)
|
||||
{
|
||||
var artifact = JsonSerializer.SerializeToUtf8Bytes(new
|
||||
{
|
||||
Equipment = equipmentIds.Select(id => new
|
||||
{
|
||||
EquipmentId = id,
|
||||
MachineCode = id.ToUpperInvariant(),
|
||||
UnsLineId = "line-1",
|
||||
Name = id,
|
||||
}).ToArray(),
|
||||
DriverInstances = Array.Empty<object>(),
|
||||
ScriptedAlarms = Array.Empty<object>(),
|
||||
});
|
||||
|
||||
using var ctx = dbFactory.CreateDbContext();
|
||||
ctx.Deployments.Add(new Deployment
|
||||
{
|
||||
DeploymentId = Guid.NewGuid(),
|
||||
RevisionHash = new string('a', 64),
|
||||
Status = DeploymentStatus.Sealed,
|
||||
CreatedBy = "test",
|
||||
SealedAtUtc = DateTime.UtcNow,
|
||||
ArtifactBlob = artifact,
|
||||
});
|
||||
ctx.SaveChanges();
|
||||
}
|
||||
|
||||
/// <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) { }
|
||||
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc) { }
|
||||
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, bool isNative = false) { }
|
||||
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName) { }
|
||||
public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, string? historianTagname = null, bool isArray = false, uint? arrayLength = null) { }
|
||||
public void RebuildAddressSpace() => throw new InvalidOperationException("simulated rebuild fault");
|
||||
public void RaiseNodesAddedModelChange(string affectedNodeId) { }
|
||||
}
|
||||
|
||||
/// <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) { }
|
||||
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime occurredUtc) { }
|
||||
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, bool isNative = false) { }
|
||||
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName) { }
|
||||
public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, string? historianTagname = null, bool isArray = false, uint? arrayLength = null) { }
|
||||
public void RebuildAddressSpace() { }
|
||||
public void RaiseNodesAddedModelChange(string affectedNodeId) { }
|
||||
}
|
||||
|
||||
/// <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();
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user