fix(runtime,galaxy): #869 review round 1 — confirmation off the actor scheduler, stop/async-fault tests
- Start the ack confirmation with Task.Run + ConfigureAwait(false) so it never depends on the ReceiveAsync handler's ActorTaskScheduler (the PostStop abandon-and-revert report must run after the actor stopped). - DriverInstanceActorAckConfirmationTests: a confirmation that faults after the handler returned is reported; one pending at actor stop is reported; a confirmed ack reports nothing (positive control). - Deterministic tracker matching test (Raise/Clear/Retrigger/other alarm do not confirm; case-insensitive match does). - AdminUI min/max on the confirm-timeout field; Galaxy.md documents the reconnect, UNACK_RTN-as-Clear and RPC-budget limits. Claude-Session: https://claude.ai/code/session_01GT67AD99zQQqpLCVm3p7xk
This commit is contained in:
Joseph Doherty
+152
@@ -0,0 +1,152 @@
|
||||
using System.Collections.Concurrent;
|
||||
using Akka.Actor;
|
||||
using Shouldly;
|
||||
using Xunit;
|
||||
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
|
||||
using ZB.MOM.WW.OtOpcUa.Runtime.Drivers;
|
||||
using ZB.MOM.WW.OtOpcUa.Runtime.Tests.Harness;
|
||||
|
||||
namespace ZB.MOM.WW.OtOpcUa.Runtime.Tests.Drivers;
|
||||
|
||||
/// <summary>
|
||||
/// lmxopcua#869 — <see cref="DriverInstanceActor"/> asks an <see cref="IAlarmAcknowledgeConfirmation"/> driver to
|
||||
/// confirm an ack AFTER <see cref="IAlarmSource.AcknowledgeAsync"/> returned, off its mailbox, and reports
|
||||
/// <see cref="DriverInstanceActor.AlarmAckFailed"/> to the router when the confirmation fails — including one that
|
||||
/// fails long after the ack handler returned, and one abandoned because the actor stopped.
|
||||
/// </summary>
|
||||
public sealed class DriverInstanceActorAckConfirmationTests : RuntimeActorTestBase
|
||||
{
|
||||
private static readonly TimeSpan Timeout = PresenceBudget;
|
||||
|
||||
/// <summary>A confirmation that faults asynchronously, after the ack handler returned, is reported failed.</summary>
|
||||
[Fact]
|
||||
public void A_confirmation_that_fails_later_is_reported_as_a_failed_ack()
|
||||
{
|
||||
var driver = new ConfirmingDriver();
|
||||
var actor = SpawnConnected(driver);
|
||||
var gate = new TaskCompletionSource();
|
||||
driver.Confirmation = () => gate.Task;
|
||||
var router = CreateTestProbe();
|
||||
|
||||
actor.Tell(Ack("n1"), router.Ref);
|
||||
AwaitCondition(() => driver.ConfirmCalls == 1, Timeout, TestContext.Current.CancellationToken);
|
||||
gate.SetException(new DriverOperationRefusedException("not confirmed within 10 s (BadTimeout)"));
|
||||
|
||||
var failed = router.ExpectMsg<DriverInstanceActor.AlarmAckFailed>(Timeout, cancellationToken: TestContext.Current.CancellationToken);
|
||||
failed.ConditionNodeId.ShouldBe("n1");
|
||||
failed.Reason.ShouldContain("BadTimeout");
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// A confirmation still pending when the actor stops is abandoned AND reported failed, so the host reverts the
|
||||
/// ack this incarnation can no longer confirm. (A confirmation continuation posted back to the stopped actor
|
||||
/// would dead-letter and never report.)
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public void A_confirmation_pending_when_the_actor_stops_is_reported_as_a_failed_ack()
|
||||
{
|
||||
var driver = new ConfirmingDriver();
|
||||
var actor = SpawnConnected(driver);
|
||||
driver.Confirmation = () => new TaskCompletionSource().Task; // never completes on its own
|
||||
var router = CreateTestProbe();
|
||||
|
||||
actor.Tell(Ack("n-stop"), router.Ref);
|
||||
AwaitCondition(() => driver.ConfirmCalls == 1, Timeout, TestContext.Current.CancellationToken);
|
||||
Sys.Stop(actor);
|
||||
|
||||
var failed = router.ExpectMsg<DriverInstanceActor.AlarmAckFailed>(Timeout, cancellationToken: TestContext.Current.CancellationToken);
|
||||
failed.ConditionNodeId.ShouldBe("n-stop");
|
||||
failed.Reason.ShouldContain("stopped");
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// A confirmation that succeeds reports nothing. Positive control: a later ack whose confirmation fails is
|
||||
/// reported, and it is the FIRST report the router receives — so none came for the confirmed one.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public void A_confirmed_ack_reports_nothing()
|
||||
{
|
||||
var driver = new ConfirmingDriver();
|
||||
var actor = SpawnConnected(driver);
|
||||
var router = CreateTestProbe();
|
||||
|
||||
driver.Confirmation = () => Task.Delay(20);
|
||||
actor.Tell(Ack("n-ok"), router.Ref);
|
||||
AwaitCondition(() => driver.ConfirmCalls == 1, Timeout, TestContext.Current.CancellationToken);
|
||||
|
||||
driver.Confirmation = () => Task.FromException(new DriverOperationRefusedException("unconfirmed"));
|
||||
actor.Tell(Ack("n-bad"), router.Ref);
|
||||
|
||||
router.ExpectMsg<DriverInstanceActor.AlarmAckFailed>(Timeout, cancellationToken: TestContext.Current.CancellationToken).ConditionNodeId.ShouldBe("n-bad");
|
||||
}
|
||||
|
||||
private static DriverInstanceActor.RouteAlarmAck Ack(string conditionNodeId) =>
|
||||
new("Tank.Hi", "c", "alice", ConditionNodeId: conditionNodeId);
|
||||
|
||||
/// <summary>Spawns the actor as a child of the test actor and waits for its Connected announcement.</summary>
|
||||
private IActorRef SpawnConnected(ConfirmingDriver driver)
|
||||
{
|
||||
var actor = ChildActorOf(DriverInstanceActor.Props(driver));
|
||||
actor.Tell(new DriverInstanceActor.InitializeRequested("{}"));
|
||||
FishForMessage<DriverInstanceActor.ConnectivityChanged>(c => c.Connected, Timeout);
|
||||
return actor;
|
||||
}
|
||||
|
||||
private sealed class ConfirmingDriver : IDriver, IAlarmSource, IAlarmAcknowledgeConfirmation
|
||||
{
|
||||
private int _ackCalls;
|
||||
private int _confirmCalls;
|
||||
private readonly ConcurrentQueue<AlarmAcknowledgeRequest> _acks = new();
|
||||
|
||||
public Func<Task>? Confirmation { get; set; }
|
||||
|
||||
public int AckCalls => Volatile.Read(ref _ackCalls);
|
||||
|
||||
public int ConfirmCalls => Volatile.Read(ref _confirmCalls);
|
||||
|
||||
public string DriverInstanceId => "drv-confirm";
|
||||
|
||||
public string DriverType => "Test";
|
||||
|
||||
public Task InitializeAsync(string driverConfigJson, CancellationToken cancellationToken) => Task.CompletedTask;
|
||||
|
||||
public Task ReinitializeAsync(string driverConfigJson, CancellationToken cancellationToken) => Task.CompletedTask;
|
||||
|
||||
public Task ShutdownAsync(CancellationToken cancellationToken) => Task.CompletedTask;
|
||||
|
||||
public DriverHealth GetHealth() => new(DriverState.Healthy, null, null);
|
||||
|
||||
public Task<IAlarmSubscriptionHandle> SubscribeAlarmsAsync(
|
||||
IReadOnlyList<string> sourceNodeIds, CancellationToken cancellationToken) =>
|
||||
Task.FromResult<IAlarmSubscriptionHandle>(new Handle());
|
||||
|
||||
public Task UnsubscribeAlarmsAsync(IAlarmSubscriptionHandle handle, CancellationToken cancellationToken) =>
|
||||
Task.CompletedTask;
|
||||
|
||||
public Task AcknowledgeAsync(
|
||||
IReadOnlyList<AlarmAcknowledgeRequest> acknowledgements, CancellationToken cancellationToken)
|
||||
{
|
||||
foreach (var a in acknowledgements) _acks.Enqueue(a);
|
||||
Interlocked.Increment(ref _ackCalls);
|
||||
return Task.CompletedTask;
|
||||
}
|
||||
|
||||
public Task ConfirmAcknowledgedAsync(
|
||||
IReadOnlyList<AlarmAcknowledgeRequest> acknowledgements, CancellationToken cancellationToken)
|
||||
{
|
||||
Interlocked.Increment(ref _confirmCalls);
|
||||
return (Confirmation?.Invoke() ?? Task.CompletedTask).WaitAsync(cancellationToken);
|
||||
}
|
||||
|
||||
public event EventHandler<AlarmEventArgs>? OnAlarmEvent
|
||||
{
|
||||
add { }
|
||||
remove { }
|
||||
}
|
||||
|
||||
private sealed class Handle : IAlarmSubscriptionHandle
|
||||
{
|
||||
public string DiagnosticId => "h";
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user