0742946108
HistorianAdapterActor now subscribes to the redundancy-state DPS topic,
caches the local node's RedundancyRole, and SKIPS the durable-sink enqueue
when the local node is Secondary or Detached. Unknown/null role default-writes
so single-node deploys and the boot window never silently drop historization.
GetStatus stays ungated.
PREMISE: verified the actor is registered but FED BY NOTHING in production —
there is no AlarmHistorianEvent producer and nothing resolves its registry key
to Tell it. This is a FORWARD-LOOKING / DEFENSIVE guard, not a fix for a live
double-write: the moment a per-node feeder lands (engine -> historian, expected
as a per-node cluster broadcast like the alerts topic), only the Primary will
write to the durable sink (exactly-once across all alarm sources).
Mirrors the sibling A1 treatment of ScriptedAlarmHostActor (06c4155) and
OpcUaPublishActor's redundancy-state handler. localNode threaded through
HistorianAdapterActor.Props from ServiceCollectionExtensions (roleInfo.LocalNode).
128 lines
6.3 KiB
C#
128 lines
6.3 KiB
C#
using Akka.Actor;
|
|
using Akka.Cluster.Tools.PublishSubscribe;
|
|
using Akka.Event;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Redundancy;
|
|
using ZB.MOM.WW.OtOpcUa.Commons.Types;
|
|
using ZB.MOM.WW.OtOpcUa.Core.AlarmHistorian;
|
|
using ZB.MOM.WW.OtOpcUa.Runtime.OpcUa;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Runtime.Historian;
|
|
|
|
/// <summary>
|
|
/// Thin actor wrapper around <see cref="IAlarmHistorianSink"/>. Engine code (ScriptedAlarmActor,
|
|
/// Galaxy native alarm bridge, AB CIP ALMD reader) tells <see cref="AlarmHistorianEvent"/>s to this
|
|
/// actor; the actor enqueues them on the sink fire-and-forget. Production deployments register
|
|
/// <see cref="SqliteStoreAndForwardSink"/> against <c>IAlarmHistorianSink</c>; the sink owns the
|
|
/// durable queue + drain-to-Wonderware-pipe loop. The actor here owns nothing operational beyond
|
|
/// the message contract — its job is to keep the engine actors on Akka's mailbox without blocking
|
|
/// them on disk I/O or pipe handshakes.
|
|
///
|
|
/// Query queue depth + drain health via <see cref="GetStatus"/>.
|
|
/// </summary>
|
|
public sealed class HistorianAdapterActor : ReceiveActor
|
|
{
|
|
public sealed record GetStatus
|
|
{
|
|
public static readonly GetStatus Instance = new();
|
|
}
|
|
|
|
private readonly IAlarmHistorianSink _sink;
|
|
private readonly NodeId? _localNode;
|
|
private readonly ILoggingAdapter _log = Context.GetLogger();
|
|
private IActorRef? _mediator;
|
|
|
|
/// <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
|
|
/// durable sink enqueue in the <see cref="AlarmHistorianEvent"/> handler is gated on this: only the
|
|
/// Primary historizes (default-write while unknown so single-node deploys + the boot window never drop
|
|
/// historization).</summary>
|
|
private RedundancyRole? _localRole;
|
|
|
|
/// <summary>Creates the props for a HistorianAdapterActor instance.</summary>
|
|
/// <param name="sink">The alarm historian sink implementation, or null to use a null sink.</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 historizes to the durable sink. Null (the
|
|
/// default) leaves the role unknown ⇒ default-write (single-node deploys + tests).</param>
|
|
/// <returns>Props configured for creating a HistorianAdapterActor.</returns>
|
|
public static Props Props(IAlarmHistorianSink? sink = null, NodeId? localNode = null) =>
|
|
Akka.Actor.Props.Create(() => new HistorianAdapterActor(sink ?? NullAlarmHistorianSink.Instance, localNode));
|
|
|
|
/// <summary>Initializes a new instance of the HistorianAdapterActor class.</summary>
|
|
/// <param name="sink">The alarm historian sink to forward enqueued events to.</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 historizes to the durable sink. Null leaves
|
|
/// the role unknown ⇒ default-write (single-node deploys + tests).</param>
|
|
public HistorianAdapterActor(IAlarmHistorianSink sink, NodeId? localNode = null)
|
|
{
|
|
_sink = sink;
|
|
_localNode = localNode;
|
|
|
|
Receive<AlarmHistorianEvent>(evt =>
|
|
{
|
|
// Warm-standby dedup (forward-looking): only the Primary historizes to the durable sink so a
|
|
// future per-node feeder writes exactly once. Default-write until told Secondary/Detached so
|
|
// single-node deploys + the boot window never drop historization. (Currently the actor has no
|
|
// production feeder — this is a defensive guard for when engine→historian wiring lands.)
|
|
if (_localRole is RedundancyRole.Secondary or RedundancyRole.Detached)
|
|
{
|
|
return;
|
|
}
|
|
|
|
// Fire-and-forget: SqliteStoreAndForwardSink persists to local SQLite synchronously
|
|
// inside EnqueueAsync (it returns once the row is committed), so we don't block on
|
|
// network/pipe latency. Failures are surfaced via GetStatus's LastError + drain state.
|
|
_ = EnqueueAsync(evt);
|
|
});
|
|
|
|
Receive<GetStatus>(_ => Sender.Tell(_sink.GetStatus()));
|
|
|
|
// Cluster redundancy snapshots (published on the `redundancy-state` topic, subscribed in PreStart)
|
|
// cache this node's role so the AlarmHistorianEvent handler can gate the durable sink enqueue to the
|
|
// Primary. The PubSub Subscribe is acked back to Self (no-op below).
|
|
Receive<RedundancyStateChanged>(OnRedundancyStateChanged);
|
|
Receive<SubscribeAck>(_ => { });
|
|
}
|
|
|
|
/// <summary>Subscribes to the <c>redundancy-state</c> topic so cluster role changes land as
|
|
/// <see cref="RedundancyStateChanged"/> and cache this node's role — the historian enqueue is gated to
|
|
/// the Primary so a future per-node feeder doesn't double-write across the warm-redundant pair.</summary>
|
|
protected override void PreStart()
|
|
{
|
|
_mediator = DistributedPubSub.Get(Context.System).Mediator;
|
|
_mediator.Tell(new Subscribe(OpcUaPublishActor.RedundancyStateTopic, Self));
|
|
base.PreStart();
|
|
}
|
|
|
|
/// <summary>Caches this node's <see cref="RedundancyRole"/> from a cluster redundancy snapshot so the
|
|
/// <see cref="AlarmHistorianEvent"/> handler can gate the durable sink enqueue to the Primary. A snapshot
|
|
/// that doesn't mention <see cref="_localNode"/> (or no local node wired) leaves the cached role unchanged
|
|
/// ⇒ default-write. 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;
|
|
}
|
|
}
|
|
|
|
private async Task EnqueueAsync(AlarmHistorianEvent evt)
|
|
{
|
|
try
|
|
{
|
|
await _sink.EnqueueAsync(evt, CancellationToken.None);
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
_log.Error(ex, "Historian sink rejected event for {AlarmId} at {Ts}",
|
|
evt.AlarmId, evt.TimestampUtc);
|
|
}
|
|
}
|
|
}
|