acfb4fbaca
v2-ci / unit-tests (push) Has been cancelled
IOpcUaEndpointState (review-remediation lane C3) recorded whether the SDK started, but only the health check read it: a fused node whose endpoint failed (port 4840 taken, ...) still advertised 250/240 and stayed driver Primary, so the Primary-gated data plane ran on a node no client could reach while the reachable peer refused writes as Secondary. - Move IOpcUaEndpointState/OpcUaEndpointState/OpcUaEndpointStatus from Host to Commons.OpcUa so the Runtime can consume it. - ServiceLevelCalculator: new NodeHealthInputs.EndpointListening (default true). false -> 0, ahead of every other input including the +10 Primary bonus. - OpcUaPublishActor: takes the endpoint state, feeds EndpointListening (Failed only; NotStarted / Stopped are boot/shutdown windows) on the DB-backed and DB-less paths, and the legacy role-only seam returns 0 for a failed endpoint too. - New OpcUaEndpointStepDownActor (one per driver node): a Primary (ClusterActiveNode.SelfIsActive, the election's own primitive) with a Failed endpoint gracefully Leaves its mesh - the manual failover mechanism - so the peer becomes the oldest Up driver member, hosts the singletons and is Primary. The election itself is not bent. Guarded on a peer having recently reported its own endpoint listening (EndpointReport on the new opcua-endpoint-state DPS topic), so a pair with both endpoints failed does not bounce the role and restart nodes forever, and a lone node never shuts itself down. - Runtime now references ZB.MOM.WW.Health.Akka (ClusterActiveNode). - Docs: Redundancy.md tier table + new "Endpoint start failure: Primary step-down" section; cluster-topology rule; HealthEndpoints / OpcUaEndpointHealthCheck comments (F-C1 landed). Tests: ServiceLevelCalculatorTests (+5), OpcUaPublishActorEndpointStateTests (7: DB-less, DB-backed, legacy seam, NotStarted/Stopped do not demote, a later failure demotes on the next tick), OpcUaEndpointStepDownActorTests (3, real two-node mesh: holds while the peer is not listening then leaves and the peer becomes Primary; failed Secondary and healthy Primary never leave). Each was mutation-checked: removing the calculator/legacy guard, the Leave, the peer-listening guard or the Primary guard fails the corresponding tests.
120 lines
5.0 KiB
C#
120 lines
5.0 KiB
C#
using Akka.Cluster;
|
|
using Shouldly;
|
|
using Xunit;
|
|
using ZB.MOM.WW.OtOpcUa.Cluster.Redundancy;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Cluster.Tests;
|
|
|
|
/// <summary>
|
|
/// Unit tests for <see cref="ServiceLevelCalculator"/> — the pure ServiceLevel tiering logic.
|
|
/// Moved from ControlPlane.Tests to Cluster.Tests because the type lives in Core.Cluster.
|
|
/// See code-reviews/Cluster/findings.md Cluster-005.
|
|
/// </summary>
|
|
public sealed class ServiceLevelCalculatorTests
|
|
{
|
|
/// <summary>Non-Up member statuses produce ServiceLevel 0 regardless of other inputs.</summary>
|
|
[Theory]
|
|
[InlineData(MemberStatus.Down)]
|
|
[InlineData(MemberStatus.Removed)]
|
|
[InlineData(MemberStatus.Exiting)]
|
|
[InlineData(MemberStatus.Leaving)]
|
|
public void NotUp_returns_zero(MemberStatus status)
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(status,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: false, IsDriverPrimary: true));
|
|
sl.ShouldBe((byte)0);
|
|
}
|
|
|
|
/// <summary>Up + DB reachable + probe ok + not stale + not leader = tier 240 (healthy follower).</summary>
|
|
[Fact]
|
|
public void Fully_healthy_non_leader_returns_240()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: false, IsDriverPrimary: false));
|
|
sl.ShouldBe((byte)240);
|
|
}
|
|
|
|
/// <summary>Up + DB reachable + probe ok + not stale + is leader = tier 250 (healthy leader, +10 bonus).</summary>
|
|
[Fact]
|
|
public void Fully_healthy_role_leader_returns_250()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: false, IsDriverPrimary: true));
|
|
sl.ShouldBe((byte)250);
|
|
}
|
|
|
|
/// <summary>DB reachable but data stale = tier 200 (stale).</summary>
|
|
[Fact]
|
|
public void Db_reachable_but_stale_returns_200()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: true, IsDriverPrimary: false));
|
|
sl.ShouldBe((byte)200);
|
|
}
|
|
|
|
/// <summary>DB unreachable AND stale = tier 100 (critically degraded).</summary>
|
|
[Fact]
|
|
public void Db_unreachable_and_stale_returns_100()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: false, OpcUaProbeOk: false, Stale: true, IsDriverPrimary: false));
|
|
sl.ShouldBe((byte)100);
|
|
}
|
|
|
|
/// <summary>OPC UA probe failed while not stale falls through to the catch-all 0.</summary>
|
|
[Fact]
|
|
public void Opcua_probe_fail_when_not_stale_returns_zero()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: true, OpcUaProbeOk: false, Stale: false, IsDriverPrimary: false));
|
|
sl.ShouldBe((byte)0);
|
|
}
|
|
|
|
/// <summary>Joining is treated identically to Up for grading (node is joining the cluster).</summary>
|
|
[Fact]
|
|
public void Joining_member_is_treated_like_Up()
|
|
{
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Joining,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: false, IsDriverPrimary: false));
|
|
sl.ShouldBe((byte)240);
|
|
}
|
|
|
|
/// <summary>Leader bonus is clamped to 255 even if a hypothetical basis would overflow.</summary>
|
|
[Fact]
|
|
public void Result_is_clamped_to_255()
|
|
{
|
|
// basis 240 + 10 = 250, already within byte range; confirms Clamp is in path
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: true, OpcUaProbeOk: true, Stale: false, IsDriverPrimary: true));
|
|
((int)sl).ShouldBeLessThanOrEqualTo(255);
|
|
}
|
|
|
|
/// <summary>
|
|
/// lmxopcua#762: a node whose own OPC UA endpoint failed to start computes 0 — whatever every other input
|
|
/// says, and in particular without the +10 Primary bonus that used to keep a dead endpoint at 250.
|
|
/// </summary>
|
|
[Theory]
|
|
[InlineData(true, true, false, true)] // would be 250
|
|
[InlineData(true, true, false, false)] // would be 240
|
|
[InlineData(true, true, true, true)] // would be 210
|
|
[InlineData(false, true, true, false)] // would be 100
|
|
public void Endpoint_not_listening_returns_zero(bool dbReachable, bool probeOk, bool stale, bool primary)
|
|
{
|
|
var healthy = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: dbReachable, OpcUaProbeOk: probeOk, Stale: stale, IsDriverPrimary: primary));
|
|
healthy.ShouldBeGreaterThan((byte)0, "positive control: the same inputs with a listening endpoint must not already be 0");
|
|
|
|
var sl = ServiceLevelCalculator.Compute(new(MemberStatus.Up,
|
|
DbReachable: dbReachable, OpcUaProbeOk: probeOk, Stale: stale, IsDriverPrimary: primary,
|
|
EndpointListening: false));
|
|
sl.ShouldBe((byte)0);
|
|
}
|
|
|
|
/// <summary>The endpoint input defaults to listening, so callers with no endpoint fact keep the old tiering.</summary>
|
|
[Fact]
|
|
public void Endpoint_listening_defaults_to_true()
|
|
{
|
|
new NodeHealthInputs(MemberStatus.Up, true, true, false, true).EndpointListening.ShouldBeTrue();
|
|
}
|
|
}
|