Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests/OpcUa/OpcUaPublishActorOffThreadPlanTests.cs
T
Joseph Doherty deaa31479b perf(runtime): parse + plan a deploy off the pinned OPC UA thread (B6)
Review 02 P5. OpcUaPublishActor ran the whole apply — DeploymentArtifact
.Open, ParseComposition, AddressSpacePlanner.Compute and the sink
materialisation — on the opcua-synchronized-dispatcher, so a large
artifact serialised every live value batch (and, because the node
manager lock is the SDK's, every client Publish) behind the parse.

StartRebuild now runs Open + ParseDataPlaneAuthority + ParseComposition
+ Compute in Task.Run and pipes a PlanReady (or PlanFailed) back to Self;
only ApplyPlan — the sink passes — runs on the actor thread. Rebuilds are
applied strictly in arrival order (a plan is a diff against _lastApplied,
which only the apply advances): one in flight, later ones queue in
_pendingRebuilds while value/status batches keep flowing. The apply is
closed (CompleteAddressSpaceApply) and the RebuildCompleted reply sent on
every path, PlanFailed included. The bytes-less ConfigDb fallback
(LoadArtifact / LoadLatestArtifact) is deleted: it had no production
producer and would have blocked the pinned thread on central SQL; the
dbFactory Props/ctor parameter is kept for wiring compatibility (F4).

Tests: OpcUaPublishActorOffThreadPlanTests — a value batch sent right
after a 50k-tag rebuild lands before that rebuild's first materialise
call (positive control: all 50k tags still materialise); back-to-back
rebuilds apply in arrival order (the second diffs against the first);
unreadable bytes answer degraded with nothing torn down. The rebuild /
apply-failure suites now hand the actor the artifact bytes every
production producer carries (SealArtifact records them; Rebuild(dep)).

Refs #732

Claude-Session: https://claude.ai/code/session_01Ub9hGmYLQvn9XETzw7CMsT
2026-10-22 10:47:32 -04:00

129 lines
8.7 KiB
C#

using System.Collections.Concurrent;
using System.Text.Json;
using Akka.Actor;
using Microsoft.Extensions.Logging.Abstractions;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
using ZB.MOM.WW.OtOpcUa.Commons.Types;
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>
/// Review 02 P5 — a rebuild's artifact parse + plan no longer run on the pinned OPC UA thread. The
/// observable: value batches sent right after a large rebuild land on the sink BEFORE that rebuild's first
/// materialise call, because the actor is free while the thread pool parses and plans; two rebuilds sent
/// back to back still apply in arrival order; a plan that throws still answers the requester degraded.
/// </summary>
public sealed class OpcUaPublishActorOffThreadPlanTests : RuntimeActorTestBase
{
[Fact]
public void Value_batches_keep_flowing_while_a_large_plan_computes()
{
var sink = new OrderedSink();
var applier = new AddressSpaceApplier(sink, NullLogger<AddressSpaceApplier>.Instance);
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, applier: applier));
// A value node the batch names; the sink is a recorder, so it need not exist.
var batch = new OpcUaPublishActor.AttributeValueBatchUpdate(
[new ValueWrite("Plant/Modbus/dev1/live", 1, OpcUaStatus.Good, DateTime.UtcNow, AddressSpaceRealm.Raw)]);
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), DeploymentId.NewId(), RawTagArtifact(50_000), ReportOutcome: true));
actor.Tell(batch);
var completed = ExpectMsg<OpcUaPublishActor.RebuildCompleted>(TimeSpan.FromSeconds(120));
completed.Degraded.ShouldBeFalse(completed.DegradedReason);
var calls = sink.Calls.ToList();
var batchIndex = calls.IndexOf("WV:Plant/Modbus/dev1/live");
var firstMaterialise = calls.FindIndex(c => c.StartsWith("EV:", StringComparison.Ordinal) || c.StartsWith("EF:", StringComparison.Ordinal));
batchIndex.ShouldBeGreaterThanOrEqualTo(0, "the batch must reach the sink");
firstMaterialise.ShouldBeGreaterThanOrEqualTo(0, "the plan must still be applied (positive control)");
batchIndex.ShouldBeLessThan(firstMaterialise, "the batch sent after the rebuild must land before the rebuild's materialisation — the parse/plan step no longer holds the actor thread");
calls.Count(c => c.StartsWith("EV:", StringComparison.Ordinal)).ShouldBe(50_000);
}
[Fact]
public void Back_to_back_rebuilds_apply_in_arrival_order()
{
var sink = new OrderedSink();
var applier = new AddressSpaceApplier(sink, NullLogger<AddressSpaceApplier>.Instance);
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, applier: applier));
// The first (large) plan is still computing when the second (tiny) arrives; the second must wait for
// it — its plan is a diff against what the first applies.
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), DeploymentId.NewId(), RawTagArtifact(20_000), ReportOutcome: true));
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), DeploymentId.NewId(), RawTagArtifact(2), ReportOutcome: true));
var first = ExpectMsg<OpcUaPublishActor.RebuildCompleted>(TimeSpan.FromSeconds(120));
var second = ExpectMsg<OpcUaPublishActor.RebuildCompleted>(TimeSpan.FromSeconds(120));
first.Degraded.ShouldBeFalse(first.DegradedReason);
second.Degraded.ShouldBeFalse(second.DegradedReason);
// The second composition is a strict subset (2 of the same tags), so it diffs as a PureRemove of the
// other 19,998 — which only works if it was planned AFTER the first apply, against its composition.
sink.Calls.Count(c => c.StartsWith("RV:", StringComparison.Ordinal)).ShouldBe(19_998);
}
[Fact]
public void Unreadable_bytes_answer_degraded_and_keep_the_served_space()
{
var sink = new OrderedSink();
var applier = new AddressSpaceApplier(sink, NullLogger<AddressSpaceApplier>.Instance);
var actor = Sys.ActorOf(OpcUaPublishActor.PropsForTests(sink: sink, applier: applier));
actor.Tell(new OpcUaPublishActor.RebuildAddressSpace(CorrelationId.NewId(), DeploymentId.NewId(), "not json"u8.ToArray(), ReportOutcome: true));
var completed = ExpectMsg<OpcUaPublishActor.RebuildCompleted>(PresenceBudget);
completed.Degraded.ShouldBeTrue();
completed.DegradedReason.ShouldNotBeNull().ShouldContain("threw");
sink.Calls.ShouldBeEmpty("nothing may be torn down for bytes that could not be read");
sink.Completed.ShouldBe(1, "the apply is still closed");
}
private static byte[] RawTagArtifact(int tagCount) =>
JsonSerializer.SerializeToUtf8Bytes(new
{
UnsAreas = Array.Empty<object>(),
UnsLines = Array.Empty<object>(),
Equipment = Array.Empty<object>(),
RawFolders = new[] { new { RawFolderId = "rf-1", ParentRawFolderId = (string?)null, Name = "Plant", ClusterId = "c1" } },
DriverInstances = new[] { new { DriverInstanceId = "drv-1", DriverType = "Modbus", DriverConfig = "{}", Name = "Modbus", RawFolderId = "rf-1", ClusterId = "c1" } },
Devices = new[] { new { DeviceId = "dev-1", DriverInstanceId = "drv-1", Name = "dev1", DeviceConfig = "{}" } },
TagGroups = Array.Empty<object>(),
Tags = Enumerable.Range(0, tagCount).Select(i => new
{
TagId = $"t-{i}", DeviceId = "dev-1", TagGroupId = (string?)null, Name = $"T{i}",
DataType = "Float", AccessLevel = 0, TagConfig = "{}",
}).ToArray(),
UnsTagReferences = Array.Empty<object>(),
ScriptedAlarms = Array.Empty<object>(),
});
private sealed class OrderedSink : IOpcUaAddressSpaceSink, ISurgicalAddressSpaceSink
{
public ConcurrentQueue<string> Calls { get; } = new();
public int Completed;
public void WriteValue(string nodeId, object? value, uint statusCode, DateTime ts, AddressSpaceRealm realm) => Calls.Enqueue($"WV:{nodeId}");
public void WriteValues(IReadOnlyList<ValueWrite> values) { foreach (var v in values) Calls.Enqueue($"WV:{v.NodeId}"); }
public void WriteAlarmQuality(string alarmNodeId, uint statusCode, DateTime ts, AddressSpaceRealm realm) { }
public void WriteAlarmCondition(string alarmNodeId, AlarmConditionSnapshot state, DateTime ts, AddressSpaceRealm realm) => Calls.Enqueue($"WA:{alarmNodeId}");
public void MaterialiseAlarmCondition(string alarmNodeId, string equipmentNodeId, string displayName, string alarmType, int severity, AddressSpaceRealm realm, bool isNative = false) => Calls.Enqueue($"MA:{alarmNodeId}");
public void EnsureFolder(string folderNodeId, string? parentNodeId, string displayName, AddressSpaceRealm realm) => Calls.Enqueue($"EF:{folderNodeId}");
public void EnsureVariable(string variableNodeId, string? parentFolderNodeId, string displayName, string dataType, bool writable, AddressSpaceRealm realm, string? historianTagname = null, bool isArray = false, uint? arrayLength = null, bool refuseArrayOnScalar = false) => Calls.Enqueue($"EV:{variableNodeId}");
public void RebuildAddressSpace() => Calls.Enqueue("RB");
public void CompleteAddressSpaceApply() => Interlocked.Increment(ref Completed);
public void RaiseNodesAddedModelChange(string affectedNodeId, AddressSpaceRealm realm) => Calls.Enqueue($"NA:{affectedNodeId}");
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") { }
public bool UpdateTagAttributes(string variableNodeId, bool writable, string? historianTagname, string dataType, bool isArray, uint? arrayLength, AddressSpaceRealm realm) { Calls.Enqueue($"UT:{variableNodeId}"); return true; }
public bool UpdateFolderDisplayName(string folderNodeId, string displayName, AddressSpaceRealm realm) => true;
public bool RemoveVariableNode(string variableNodeId, AddressSpaceRealm realm) { Calls.Enqueue($"RV:{variableNodeId}"); return true; }
public bool RemoveAlarmConditionNode(string alarmNodeId, AddressSpaceRealm realm) { Calls.Enqueue($"RA:{alarmNodeId}"); return true; }
public bool RemoveEquipmentSubtree(string equipmentNodeId, AddressSpaceRealm realm) { Calls.Enqueue($"RE:{equipmentNodeId}"); return true; }
}
}