feat(redundancy): gate scripted-alarm alerts publish on Primary (A1)
This commit is contained in:
Joseph Doherty
@@ -280,7 +280,7 @@ public sealed class DriverHostActor : ReceiveActor, IWithTimers
|
||||
var engine = new ScriptedAlarmEngine(
|
||||
upstream, store, new ScriptLoggerFactory(_scriptRootLogger.Logger), _scriptRootLogger.Logger);
|
||||
_scriptedAlarmHost = Context.ActorOf(
|
||||
ScriptedAlarmHostActor.Props(_opcUaPublishActor, _dependencyMux, upstream, engine),
|
||||
ScriptedAlarmHostActor.Props(_opcUaPublishActor, _dependencyMux, upstream, engine, _localNode),
|
||||
"scripted-alarm-host");
|
||||
}
|
||||
|
||||
|
||||
@@ -2,7 +2,9 @@ using Akka.Actor;
|
||||
using Akka.Cluster.Tools.PublishSubscribe;
|
||||
using Akka.Event;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Alerts;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Redundancy;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.OpcUa;
|
||||
using ZB.MOM.WW.OtOpcUa.Commons.Types;
|
||||
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
|
||||
using ZB.MOM.WW.OtOpcUa.Core.ScriptedAlarms;
|
||||
using ZB.MOM.WW.OtOpcUa.OpcUaServer;
|
||||
@@ -95,10 +97,17 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
private readonly IActorRef? _mux;
|
||||
private readonly DependencyMuxTagUpstreamSource _upstream;
|
||||
private readonly ScriptedAlarmEngine _engine;
|
||||
private readonly NodeId? _localNode;
|
||||
private readonly ILoggingAdapter _log = Context.GetLogger();
|
||||
private readonly CancellationTokenSource _cts = new();
|
||||
private readonly EventHandler<ScriptedAlarmEvent> _onEngineEvent;
|
||||
|
||||
/// <summary>Cached local <see cref="RedundancyRole"/> from the latest <see cref="RedundancyStateChanged"/>
|
||||
/// snapshot (null = unknown until the first snapshot arrives, or no <see cref="_localNode"/> wired). The
|
||||
/// cluster-wide <c>alerts</c> publish in <see cref="OnEngineEmission"/> is gated on this: only the Primary
|
||||
/// publishes (default-emit while unknown so single-node deploys + the boot window never drop transitions).</summary>
|
||||
private RedundancyRole? _localRole;
|
||||
|
||||
/// <summary>Monotonic load generation, bumped on every <see cref="OnApply"/>. The continuation that
|
||||
/// pipes back an <see cref="AlarmsLoaded"/> captures the generation it was started under; a stale
|
||||
/// completion (an earlier generation arriving after a newer apply) is discarded in
|
||||
@@ -118,23 +127,31 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
/// <param name="upstream">The mux-fed upstream the engine reads + subscribes from. MUST be the
|
||||
/// same instance the <paramref name="engine"/> was constructed around.</param>
|
||||
/// <param name="engine">The scripted-alarm engine this host owns + disposes.</param>
|
||||
/// <param name="localNode">The local cluster node id, used to read this node's <see cref="RedundancyRole"/>
|
||||
/// from the <c>redundancy-state</c> topic so only the Primary publishes the cluster-wide <c>alerts</c>
|
||||
/// transition. Null (the default) leaves the role unknown ⇒ default-emit (single-node deploys + tests).</param>
|
||||
public static Props Props(
|
||||
IActorRef publishActor,
|
||||
IActorRef? mux,
|
||||
DependencyMuxTagUpstreamSource upstream,
|
||||
ScriptedAlarmEngine engine) =>
|
||||
Akka.Actor.Props.Create(() => new ScriptedAlarmHostActor(publishActor, mux, upstream, engine));
|
||||
ScriptedAlarmEngine engine,
|
||||
NodeId? localNode = null) =>
|
||||
Akka.Actor.Props.Create(() => new ScriptedAlarmHostActor(publishActor, mux, upstream, engine, localNode));
|
||||
|
||||
/// <summary>Initializes a new instance of the <see cref="ScriptedAlarmHostActor"/> class.</summary>
|
||||
/// <param name="publishActor">The OPC UA publish actor emissions are bridged to.</param>
|
||||
/// <param name="mux">Optional dependency multiplexer the host registers dependency interest with.</param>
|
||||
/// <param name="upstream">The mux-fed upstream the engine reads + subscribes from (same instance the engine wraps).</param>
|
||||
/// <param name="engine">The scripted-alarm engine this host owns + disposes.</param>
|
||||
/// <param name="localNode">The local cluster node id, used to read this node's <see cref="RedundancyRole"/>
|
||||
/// from the <c>redundancy-state</c> topic so only the Primary publishes the cluster-wide <c>alerts</c>
|
||||
/// transition. Null leaves the role unknown ⇒ default-emit (single-node deploys + tests).</param>
|
||||
public ScriptedAlarmHostActor(
|
||||
IActorRef publishActor,
|
||||
IActorRef? mux,
|
||||
DependencyMuxTagUpstreamSource upstream,
|
||||
ScriptedAlarmEngine engine)
|
||||
ScriptedAlarmEngine engine,
|
||||
NodeId? localNode = null)
|
||||
{
|
||||
ArgumentNullException.ThrowIfNull(publishActor);
|
||||
ArgumentNullException.ThrowIfNull(upstream);
|
||||
@@ -143,6 +160,7 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
_mux = mux;
|
||||
_upstream = upstream;
|
||||
_engine = engine;
|
||||
_localNode = localNode;
|
||||
|
||||
// OnEvent fires on the engine's worker thread. NEVER touch Context / actor state here —
|
||||
// marshal onto the actor thread via the thread-safe Self.Tell. Keep the handler in a field
|
||||
@@ -155,6 +173,9 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
Receive<AlarmsLoaded>(OnAlarmsLoaded);
|
||||
Receive<VirtualTagActor.DependencyValueChanged>(OnDependencyChanged);
|
||||
Receive<EngineEmission>(OnEngineEmission);
|
||||
// Cluster redundancy snapshots (published on the `redundancy-state` topic, subscribed in PreStart)
|
||||
// cache this node's role so OnEngineEmission can gate the cluster-wide alerts publish to the Primary.
|
||||
Receive<RedundancyStateChanged>(OnRedundancyStateChanged);
|
||||
// Inbound OPC UA Part 9 alarm method calls arrive as AlarmCommands on the cluster
|
||||
// `alarm-commands` DPS topic (T18 publishes them after the AlarmAck role gate). The topic is a
|
||||
// cluster-wide broadcast — every host node receives every command — so OnAlarmCommand filters to
|
||||
@@ -275,9 +296,37 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
User: TransitionUser(e),
|
||||
TimestampUtc: e.TimestampUtc);
|
||||
|
||||
// Warm-standby dedup: only the Primary (driver-role leader) publishes the cluster-wide
|
||||
// transition. Default-emit until told we are Secondary/Detached so single-node deploys + the
|
||||
// boot window never drop transitions. The OPC UA node write above + inbound command processing
|
||||
// stay ungated (the secondary keeps its address space + engine state warm for failover).
|
||||
if (_localRole is RedundancyRole.Secondary or RedundancyRole.Detached)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
_mediator.Tell(new Publish(AlertsTopic, evt));
|
||||
}
|
||||
|
||||
/// <summary>Caches this node's <see cref="RedundancyRole"/> from a cluster redundancy snapshot so
|
||||
/// <see cref="OnEngineEmission"/> can gate the cluster-wide <c>alerts</c> publish to the Primary. A
|
||||
/// snapshot that doesn't mention <see cref="_localNode"/> (or no local node wired) leaves the cached
|
||||
/// role unchanged ⇒ default-emit. Mirrors <see cref="OpcUaPublishActor"/>'s handler.</summary>
|
||||
/// <param name="msg">The cluster redundancy snapshot.</param>
|
||||
private void OnRedundancyStateChanged(RedundancyStateChanged msg)
|
||||
{
|
||||
if (_localNode is null)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
var local = msg.Nodes.FirstOrDefault(n => n.NodeId == _localNode.Value);
|
||||
if (local is not null)
|
||||
{
|
||||
_localRole = local.Role;
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Drives an inbound OPC UA Part 9 alarm method call (delivered as an <see cref="AlarmCommand"/>
|
||||
/// on the cluster <c>alarm-commands</c> topic) onto the matching <see cref="ScriptedAlarmEngine"/>
|
||||
@@ -386,6 +435,10 @@ public sealed class ScriptedAlarmHostActor : ReceiveActor
|
||||
// the node manager's condition handlers, T18) land here as AlarmCommands. The Subscribe is sent
|
||||
// from Self so the SubscribeAck returns to this actor (handled as a no-op in the ctor wiring).
|
||||
_mediator.Tell(new Subscribe(AlarmCommandsTopic, Self));
|
||||
// Also subscribe to the `redundancy-state` topic so cluster role changes land as
|
||||
// RedundancyStateChanged and cache this node's role — OnEngineEmission gates the cluster-wide
|
||||
// alerts publish to the Primary so a 2-node single-cluster deploy doesn't double-emit transitions.
|
||||
_mediator.Tell(new Subscribe(OpcUaPublishActor.RedundancyStateTopic, Self));
|
||||
base.PreStart();
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user