Files
lmxopcua/tests/ZB.MOM.WW.OtOpcUa.Server.Tests/ServiceLevelCalculatorTests.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

218 lines
7.4 KiB
C#

using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Configuration.Enums;
using ZB.MOM.WW.OtOpcUa.Server.Redundancy;
namespace ZB.MOM.WW.OtOpcUa.Server.Tests;
[Trait("Category", "Unit")]
public sealed class ServiceLevelCalculatorTests
{
// --- Reserved bands (0, 1, 2) ---
[Fact]
public void OperatorMaintenance_Overrides_Everything()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true,
operatorMaintenance: true);
v.ShouldBe((byte)ServiceLevelBand.Maintenance);
}
[Fact]
public void UnhealthySelf_ReturnsNoData()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: false, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)ServiceLevelBand.NoData);
}
[Fact]
public void InvalidTopology_Demotes_BothNodes_To_2()
{
var primary = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: false);
var secondary = ServiceLevelCalculator.Compute(
RedundancyRole.Secondary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: false);
primary.ShouldBe((byte)ServiceLevelBand.InvalidTopology);
secondary.ShouldBe((byte)ServiceLevelBand.InvalidTopology);
}
// --- Operational bands (authoritative) ---
[Fact]
public void Authoritative_Primary_Is_255()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)ServiceLevelBand.AuthoritativePrimary);
v.ShouldBe((byte)255);
}
[Fact]
public void Authoritative_Backup_Is_100()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Secondary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)100);
}
// --- Isolated bands ---
[Fact]
public void IsolatedPrimary_PeerUnreachable_Is_230_RetainsAuthority()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: false, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)230);
}
[Fact]
public void IsolatedBackup_PrimaryUnreachable_Is_80_DoesNotPromote()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Secondary,
selfHealthy: true, peerUaHealthy: false, peerHttpHealthy: false,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)80, "Backup isolates at 80 — doesn't auto-promote to 255");
}
[Fact]
public void HttpOnly_Unreachable_TriggersIsolated()
{
// Either probe failing marks peer unreachable — UA probe is authoritative but HTTP is
// the fast-fail short-circuit; either missing means "not a valid peer right now".
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: false,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)230);
}
// --- Apply-mid bands ---
[Fact]
public void PrimaryMidApply_Is_200()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: true, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)200);
}
[Fact]
public void BackupMidApply_Is_50()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Secondary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: true, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)50);
}
[Fact]
public void ApplyInProgress_Dominates_PeerUnreachable()
{
// Per Stream C.4 integration-test expectation: mid-apply + peer down → apply wins (200).
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: false, peerHttpHealthy: false,
applyInProgress: true, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)200);
}
// --- Recovering bands ---
[Fact]
public void RecoveringPrimary_Is_180()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Primary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: false, topologyValid: true);
v.ShouldBe((byte)180);
}
[Fact]
public void RecoveringBackup_Is_30()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Secondary,
selfHealthy: true, peerUaHealthy: true, peerHttpHealthy: true,
applyInProgress: false, recoveryDwellMet: false, topologyValid: true);
v.ShouldBe((byte)30);
}
// --- Standalone node (no peer) ---
[Fact]
public void Standalone_IsAuthoritativePrimary_WhenHealthy()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Standalone,
selfHealthy: true, peerUaHealthy: false, peerHttpHealthy: false,
applyInProgress: false, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)255, "Standalone has no peer — treat healthy as authoritative");
}
[Fact]
public void Standalone_MidApply_Is_200()
{
var v = ServiceLevelCalculator.Compute(
RedundancyRole.Standalone,
selfHealthy: true, peerUaHealthy: false, peerHttpHealthy: false,
applyInProgress: true, recoveryDwellMet: true, topologyValid: true);
v.ShouldBe((byte)200);
}
// --- Classify round-trip ---
[Theory]
[InlineData((byte)0, ServiceLevelBand.Maintenance)]
[InlineData((byte)1, ServiceLevelBand.NoData)]
[InlineData((byte)2, ServiceLevelBand.InvalidTopology)]
[InlineData((byte)30, ServiceLevelBand.RecoveringBackup)]
[InlineData((byte)50, ServiceLevelBand.BackupMidApply)]
[InlineData((byte)80, ServiceLevelBand.IsolatedBackup)]
[InlineData((byte)100, ServiceLevelBand.AuthoritativeBackup)]
[InlineData((byte)180, ServiceLevelBand.RecoveringPrimary)]
[InlineData((byte)200, ServiceLevelBand.PrimaryMidApply)]
[InlineData((byte)230, ServiceLevelBand.IsolatedPrimary)]
[InlineData((byte)255, ServiceLevelBand.AuthoritativePrimary)]
[InlineData((byte)123, ServiceLevelBand.Unknown)]
public void Classify_RoundTrips_EveryBand(byte value, ServiceLevelBand expected)
{
ServiceLevelCalculator.Classify(value).ShouldBe(expected);
}
}