Files
lmxopcua/tests/ZB.MOM.WW.OtOpcUa.Server.Tests/RecoveryStateManagerTests.cs
Joseph Doherty 483f55557c Phase 6.3 Stream B + Stream D (core) — ServiceLevelCalculator + RecoveryStateManager + ApplyLeaseRegistry
Lands the pure-logic heart of Phase 6.3. OPC UA node wiring (Stream C),
RedundancyCoordinator topology loader (Stream A), Admin UI + metrics (Stream E),
and client interop tests (Stream F) are follow-up work — tracked as
tasks #145-150.

New Server.Redundancy sub-namespace:

- ServiceLevelCalculator — pure 8-state matrix per decision #154. Inputs:
  role, selfHealthy, peerUa/HttpHealthy, applyInProgress, recoveryDwellMet,
  topologyValid, operatorMaintenance. Output: OPC UA Part 5 §6.3.34 Byte.
  Reserved bands (0=Maintenance, 1=NoData, 2=InvalidTopology) override
  everything; operational bands occupy 30..255.
  Key invariants:
    * Authoritative-Primary = 255, Authoritative-Backup = 100.
    * Isolated-Primary = 230 (retains authority with peer down).
    * Isolated-Backup = 80 (does NOT auto-promote — non-transparent model).
    * Primary-Mid-Apply = 200, Backup-Mid-Apply = 50; apply dominates
      peer-unreachable per Stream C.4 integration expectation.
    * Recovering-Primary = 180, Recovering-Backup = 30.
    * Standalone treats healthy as Authoritative-Primary (no peer concept).
- ServiceLevelBand enum — labels every numeric band for logs + Admin UI.
  Values match the calculator table exactly; compliance script asserts
  drift detection.
- RecoveryStateManager — holds Recovering band until (dwell ≥ 60s default)
  AND (one publish witness observed). Re-fault resets both gates so a
  flapping node doesn't shortcut through recovery twice.
- ApplyLeaseRegistry — keyed on (ConfigGenerationId, PublishRequestId) per
  decision #162. BeginApplyLease returns an IAsyncDisposable so every exit
  path (success, exception, cancellation, dispose-twice) closes the lease.
  ApplyMaxDuration watchdog (10 min default) via PruneStale tick forces
  close after a crashed publisher so ServiceLevel can't stick at mid-apply.

Tests (40 new, all pass):
- ServiceLevelCalculatorTests (27): reserved bands override; self-unhealthy
  → NoData; invalid topology demotes both nodes to 2; authoritative primary
  255; backup 100; isolated primary 230 retains authority; isolated backup
  80 does not promote; http-only unreachable triggers isolated; mid-apply
  primary 200; mid-apply backup 50; apply dominates peer-unreachable; recovering
  primary 180; recovering backup 30; standalone treats healthy as 255;
  classify round-trips every band including Unknown sentinel.
- RecoveryStateManagerTests (6): never-faulted auto-meets dwell; faulted-only
  returns true (semantics-doc test — coordinator short-circuits on
  selfHealthy=false); recovered without witness never meets; witness without
  dwell never meets; witness + dwell-elapsed meets; re-fault resets.
- ApplyLeaseRegistryTests (7): empty registry not-in-progress; begin+dispose
  closes; dispose on exception still closes; dispose twice safe; concurrent
  leases isolated; watchdog closes stale; watchdog leaves recent alone.

Full solution dotnet test: 1137 passing (Phase 6.2 shipped at 1097, Phase 6.3
B + D core = +40 = 1137). Pre-existing Client.CLI Subscribe flake unchanged.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 09:56:34 -04:00

93 lines
3.1 KiB
C#

using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Server.Redundancy;
namespace ZB.MOM.WW.OtOpcUa.Server.Tests;
[Trait("Category", "Unit")]
public sealed class RecoveryStateManagerTests
{
private static readonly DateTime T0 = new(2026, 4, 19, 12, 0, 0, DateTimeKind.Utc);
private sealed class FakeTimeProvider : TimeProvider
{
public DateTime Utc { get; set; } = T0;
public override DateTimeOffset GetUtcNow() => new(Utc, TimeSpan.Zero);
}
[Fact]
public void NeverFaulted_DwellIsAutomaticallyMet()
{
var mgr = new RecoveryStateManager();
mgr.IsDwellMet().ShouldBeTrue();
}
[Fact]
public void AfterFault_Only_IsDwellMet_Returns_True_ButCallerDoesntQueryDuringFaulted()
{
// Documented semantics: IsDwellMet is only consulted when selfHealthy=true (i.e. the
// node has recovered into Healthy). During Faulted the coordinator short-circuits on
// the self-health check and never calls IsDwellMet. So returning true here is harmless;
// the test captures the intent so a future "return false during Faulted" tweak has to
// deliberately change this test first.
var mgr = new RecoveryStateManager();
mgr.MarkFaulted();
mgr.IsDwellMet().ShouldBeTrue();
}
[Fact]
public void AfterRecovery_NoWitness_DwellNotMet_EvenAfterElapsed()
{
var clock = new FakeTimeProvider();
var mgr = new RecoveryStateManager(dwellTime: TimeSpan.FromSeconds(60), timeProvider: clock);
mgr.MarkFaulted();
mgr.MarkRecovered();
clock.Utc = T0.AddSeconds(120);
mgr.IsDwellMet().ShouldBeFalse("dwell elapsed but no publish witness — must NOT escape Recovering band");
}
[Fact]
public void AfterRecovery_WitnessButTooSoon_DwellNotMet()
{
var clock = new FakeTimeProvider();
var mgr = new RecoveryStateManager(dwellTime: TimeSpan.FromSeconds(60), timeProvider: clock);
mgr.MarkFaulted();
mgr.MarkRecovered();
mgr.RecordPublishWitness();
clock.Utc = T0.AddSeconds(30);
mgr.IsDwellMet().ShouldBeFalse("witness ok but dwell 30s < 60s");
}
[Fact]
public void AfterRecovery_Witness_And_DwellElapsed_Met()
{
var clock = new FakeTimeProvider();
var mgr = new RecoveryStateManager(dwellTime: TimeSpan.FromSeconds(60), timeProvider: clock);
mgr.MarkFaulted();
mgr.MarkRecovered();
mgr.RecordPublishWitness();
clock.Utc = T0.AddSeconds(61);
mgr.IsDwellMet().ShouldBeTrue();
}
[Fact]
public void ReFault_ResetsWitness_AndDwellClock()
{
var clock = new FakeTimeProvider();
var mgr = new RecoveryStateManager(dwellTime: TimeSpan.FromSeconds(60), timeProvider: clock);
mgr.MarkFaulted();
mgr.MarkRecovered();
mgr.RecordPublishWitness();
clock.Utc = T0.AddSeconds(61);
mgr.IsDwellMet().ShouldBeTrue();
mgr.MarkFaulted();
mgr.MarkRecovered();
clock.Utc = T0.AddSeconds(100); // re-entered Recovering, no new witness
mgr.IsDwellMet().ShouldBeFalse("new recovery needs its own witness");
}
}