Files
ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.PerformanceTests/Failover/FailoverTimingTests.cs
T

69 lines
3.2 KiB
C#

using System.Diagnostics;
using Akka.Actor;
using Akka.Cluster.Tools.Singleton;
using Xunit.Abstractions;
using ZB.MOM.WW.ScadaBridge.IntegrationTests.Cluster;
namespace ZB.MOM.WW.ScadaBridge.PerformanceTests.Failover;
/// <summary>
/// Failover-timing measurement on the real two-node in-process rig
/// (TwoNodeClusterFixture, production BuildHocon) at PRODUCTION timings:
/// 2s heartbeat / 10s failure-detection threshold / 15s SBR stable-after —
/// the CLAUDE.md "total failover ~25s" design envelope.
///
/// Measures the SURVIVABLE direction only: hard-crash of the YOUNGER node,
/// timed to the survivor's member REMOVAL (detection + stable-after + gossip)
/// with singleton continuity asserted on the oldest. The oldest/active-node
/// crash is NOT a recovery to time — two-node keep-oldest makes the younger
/// survivor down itself (total outage; registered deferred user decision,
/// see SbrFailoverTests XML doc + master tracker 2026-07-08). Covers overall
/// review P2-10 / report-08 NF2 and report-01 round-2 N1's measurement ask.
/// </summary>
public class FailoverTimingTests(ITestOutputHelper output)
{
private sealed class EchoActor : ReceiveActor
{
public EchoActor() => ReceiveAny(msg => Sender.Tell(msg));
}
[Trait("Category", "Performance")]
[Fact]
public async Task HardKillOfYoungerNode_SbrRemovalWithinDesignEnvelope()
{
await using var cluster = await TwoNodeClusterFixture.StartAsync(
stableAfter: TimeSpan.FromSeconds(15),
heartbeatInterval: TimeSpan.FromSeconds(2),
failureDetectionThreshold: TimeSpan.FromSeconds(10));
// Singleton on the oldest (NodeA) — the continuity probe.
var manager = cluster.NodeA.ActorOf(ClusterSingletonManager.Props(
Props.Create(() => new EchoActor()),
PoisonPill.Instance,
ClusterSingletonManagerSettings.Create(cluster.NodeA).WithSingletonName("timing-probe")),
"timing-probe-singleton");
var proxyA = cluster.NodeA.ActorOf(ClusterSingletonProxy.Props(
"/user/timing-probe-singleton",
ClusterSingletonProxySettings.Create(cluster.NodeA).WithSingletonName("timing-probe")),
"timing-probe-proxy");
Assert.Equal("ping", await proxyA.Ask<string>("ping", TimeSpan.FromSeconds(30)));
var victim = Akka.Cluster.Cluster.Get(cluster.NodeB).SelfAddress;
var sw = Stopwatch.StartNew();
await TwoNodeClusterFixture.CrashNode(cluster.NodeB);
await TwoNodeClusterFixture.WaitForMemberRemoved(cluster.NodeA, victim, TimeSpan.FromSeconds(60));
sw.Stop();
output.WriteLine(
$"MEASURED: crash -> member removed on survivor: {sw.Elapsed.TotalSeconds:F1}s " +
"(design ~25s = 10s detection + 15s stable-after; +gossip margin)");
// Design envelope: >= stable-after (SBR must not act early), <= 25s design + 15s margin.
Assert.InRange(sw.Elapsed, TimeSpan.FromSeconds(15), TimeSpan.FromSeconds(40));
// Singleton continuity on the surviving oldest node.
Assert.Equal("ping-after-crash",
await proxyA.Ask<string>("ping-after-crash", TimeSpan.FromSeconds(10)));
}
}