fix(runtime): restart driver no longer throws 'actor name is not unique'
v2-ci / build (push) Failing after 42s
v2-ci / unit-tests (tests/Core/ZB.MOM.WW.OtOpcUa.Cluster.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Security.Tests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.Host.IntegrationTests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests) (push) Has been skipped
v2-ci / build (push) Failing after 42s
v2-ci / unit-tests (tests/Core/ZB.MOM.WW.OtOpcUa.Cluster.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Security.Tests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.Host.IntegrationTests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests) (push) Has been skipped
HandleRestartDriver stopped + respawned the child within one synchronous message handler, reusing the base actor name drv-<id>. Context.Stop is async (the child processes its own stop on its own mailbox), so the old child was ALWAYS still registered when the respawn ran — Context.ActorOf threw InvalidActorNameException deterministically on every AdminUI Restart press, crashing + restarting the host. Fix: a monotonic _childSpawnGeneration counter (single-threaded actor) feeds a -g<gen> suffix on every spawned child name, so a respawn can never collide with the still-terminating predecessor. Children are tracked by the _children dict (by IActorRef), never by actor path, so the suffix is invisible to callers. This also closes the same-shaped latent race in the reconcile path (a removed- then-readded instance, and a driver-type-change ToStop+ToSpawn in one plan). Regression test RestartDriver_respawns_the_child_without_an_actor_name_collision (verified: FAILS on the old code with the exact InvalidActorNameException, PASSES with the fix). Runtime.Tests 238/238 green. Code-reviewed (approved).
This commit is contained in:
@@ -88,6 +88,11 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
|
||||
private readonly Dictionary<string, ChildEntry> _children = new(StringComparer.Ordinal);
|
||||
|
||||
// Monotonic counter feeding the child actor-name suffix (see ActorNameFor / SpawnChild). Single-
|
||||
// threaded actor, so a plain increment is safe; it only ever grows, guaranteeing a unique name per
|
||||
// spawn so a restart's respawn never collides with the still-terminating old child.
|
||||
private long _childSpawnGeneration;
|
||||
|
||||
/// <summary>
|
||||
/// Driver live-value routing map: <c>(DriverInstanceId, FullName) → folder-scoped equipment
|
||||
/// NodeId(s)</c>. Rebuilt every apply by <see cref="PushDesiredSubscriptions"/> from the
|
||||
@@ -984,6 +989,13 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
// identity for pre-PR artifacts that don't carry it yet (older deploys persisted before
|
||||
// ClusterId was added to DriverInstanceSpec).
|
||||
var clusterId = !string.IsNullOrEmpty(spec.ClusterId) ? spec.ClusterId : _localNode.Value;
|
||||
// A fresh generation-suffixed name on EVERY spawn so a respawn can never collide with a child
|
||||
// still tearing down: Akka frees a stopped actor's name only after it FULLY terminates (async),
|
||||
// but HandleRestartDriver stops + respawns within one (synchronous) message handler — the old
|
||||
// child is still registered, so reusing the base name throws InvalidActorNameException
|
||||
// ("actor name is not unique"). Children are tracked by the _children dict (by IActorRef), never
|
||||
// by path, so the suffix is invisible to every caller.
|
||||
var actorName = ActorNameFor(spec.DriverInstanceId, _childSpawnGeneration++);
|
||||
if (stub)
|
||||
{
|
||||
child = Context.ActorOf(
|
||||
@@ -993,7 +1005,7 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
startStubbed: true,
|
||||
healthPublisher: _healthPublisher,
|
||||
clusterId: clusterId),
|
||||
ActorNameFor(spec.DriverInstanceId));
|
||||
actorName);
|
||||
}
|
||||
else
|
||||
{
|
||||
@@ -1002,7 +1014,7 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
driver!,
|
||||
healthPublisher: _healthPublisher,
|
||||
clusterId: clusterId),
|
||||
ActorNameFor(spec.DriverInstanceId));
|
||||
actorName);
|
||||
child.Tell(new DriverInstanceActor.InitializeRequested(spec.DriverConfig));
|
||||
}
|
||||
|
||||
@@ -1028,11 +1040,13 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
_log.Info("DriverHost {Node}: stopped driver child {Id}", _localNode, driverInstanceId);
|
||||
}
|
||||
|
||||
private static string ActorNameFor(string driverInstanceId)
|
||||
private static string ActorNameFor(string driverInstanceId, long generation)
|
||||
{
|
||||
// Akka actor names cannot contain '/', ':', or whitespace. Mangle defensively.
|
||||
// Akka actor names cannot contain '/', ':', or whitespace. Mangle defensively. The monotonic
|
||||
// generation suffix guarantees a never-before-used name on every spawn (see SpawnChild) so a
|
||||
// restart's respawn can never collide with the still-terminating predecessor.
|
||||
var chars = driverInstanceId.Select(c => char.IsLetterOrDigit(c) || c is '-' or '_' or '.' ? c : '_').ToArray();
|
||||
return "drv-" + new string(chars);
|
||||
return "drv-" + new string(chars) + "-g" + generation;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
|
||||
Reference in New Issue
Block a user