Files
lmxopcua/src/Drivers/ZB.MOM.WW.OtOpcUa.Driver.Galaxy/Runtime/EventPump.cs
T
Joseph Doherty 0b90379f70 fix(telemetry): export the Galaxy driver's spans and galaxy.events.* counters (#892)
ZbTelemetryOptions.Meters/ActivitySources are strict allowlists. The host named only
ZB.MOM.WW.OtOpcUa and the LocalDb meter, so the in-process Galaxy driver's galaxy.* spans
and its event pump's galaxy.events.* counters (both on "ZB.MOM.WW.OtOpcUa.Driver.Galaxy")
were silently dropped from /metrics and OTLP. Found exercising OTLP end to end against a
collector (scadaproj#13).

- Galaxy driver: public GalaxyDriverTelemetryNames (MeterName / ActivitySourceName);
  GalaxyTelemetry and EventPump reference it.
- Host: ObservabilityExtensions.ObservedMeters / ObservedActivitySources include it.
- Host.IntegrationTests: ObservabilityAllowlistTests assert on the listener side (span
  sampled, instrument enabled) with an unregistered-name negative control; dropping the
  Galaxy entries fails 3 of 8.

Claude-Session: https://claude.ai/code/session_01GT67ACmpMR7b9LGRPLijMi
2026-11-12 20:31:14 -05:00

619 lines
32 KiB
C#

using System.Diagnostics.Metrics;
using System.Threading.Channels;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Logging.Abstractions;
using ZB.MOM.WW.MxGateway.Client;
using ZB.MOM.WW.MxGateway.Contracts.Proto;
using ZB.MOM.WW.OtOpcUa.Core.Abstractions;
namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Runtime;
/// <summary>
/// Long-running consumer of <see cref="IGalaxySubscriber.StreamEventsAsync"/>. Translates
/// each <see cref="MxEvent"/> with family <see cref="MxEventFamily.OnDataChange"/> into
/// <see cref="DataChangeEventArgs"/> and dispatches one event per registered driver
/// subscription that includes the changed item handle (fan-out via
/// <see cref="SubscriptionRegistry.ResolveSubscribers"/>).
/// </summary>
/// <remarks>
/// <para>
/// One pump per connected <see cref="GalaxyMxSession"/>. Reconnect lives in the
/// <see cref="ReconnectSupervisor"/>; on transport failure here we log and invoke
/// the optional <c>onStreamFault</c> callback so the owner (GalaxyDriver) can
/// forward the fault to <see cref="ReconnectSupervisor.ReportTransportFailure"/>
/// and the supervisor can drive reopen → replay.
/// </para>
/// <para>
/// PR 6.2 — the network-read loop and the listener-fanout loop are decoupled by a
/// bounded <see cref="Channel{T}"/>. When a listener is slow enough to fill the
/// channel, new events are dropped (newest-dropped semantics: producer's
/// <c>TryWrite</c> fails) rather than back-pressuring the gw stream. Three counters
/// on the <c>ZB.MOM.WW.OtOpcUa.Driver.Galaxy</c> meter expose received / dispatched
/// / dropped totals so ops sees pressure before it manifests as user-visible loss.
/// </para>
/// </remarks>
internal sealed class EventPump : IAsyncDisposable
{
public const string MeterName = GalaxyDriverTelemetryNames.MeterName;
private const int DefaultChannelCapacity = 50_000;
// Single static meter so a host-level MeterListener catches all pump instances.
private static readonly Meter Meter = new(MeterName);
private static readonly Counter<long> EventsReceived =
Meter.CreateCounter<long>("galaxy.events.received", unit: "{event}",
description: "MxEvents read from the gateway StreamEvents stream.");
private static readonly Counter<long> EventsDispatched =
Meter.CreateCounter<long>("galaxy.events.dispatched", unit: "{event}",
description: "MxEvents passed through the bounded channel and into OnDataChange.");
private static readonly Counter<long> EventsDropped =
Meter.CreateCounter<long>("galaxy.events.dropped", unit: "{event}",
description: "MxEvents dropped because the bounded channel was full (newest-dropped).");
private static readonly Counter<long> ReplayGapsObserved =
Meter.CreateCounter<long>("galaxy.events.replay_gaps", unit: "{gap}",
description: "Replay-gap sentinels received — the gateway evicted events we can never see.");
private static readonly Counter<long> StreamAttachedAcks =
Meter.CreateCounter<long>("galaxy.events.stream_attached", unit: "{ack}",
description: "Stream-attached sentinels received — the gateway confirmed the event stream is registered (#877).");
private static readonly Counter<long> ValuesUndecodable =
Meter.CreateCounter<long>("galaxy.events.undecodable", unit: "{event}",
description: "Data-change events carrying a value kind this driver cannot represent.");
private static readonly Counter<long> EarlyEventsParked =
Meter.CreateCounter<long>("galaxy.events.early_parked", unit: "{event}",
description: "Data-change events that arrived before their SubscribeBulk reply registered the item handle, parked for replay (#859).");
private static readonly Counter<long> EarlyEventsReplayed =
Meter.CreateCounter<long>("galaxy.events.early_replayed", unit: "{event}",
description: "Parked early data-change events replayed once their item handle was registered (#859).");
private static readonly Counter<long> EarlyEventsOverflowed =
Meter.CreateCounter<long>("galaxy.events.early_overflow", unit: "{event}",
description: "Early data-change events dropped because the parking bound was reached (#859).");
private readonly IGalaxySubscriber _subscriber;
private readonly SubscriptionRegistry _registry;
private readonly ILogger _logger;
private readonly Func<long, ISubscriptionHandle> _handleFactory;
private readonly Action<Exception>? _onStreamFault;
private readonly Action<ReplayGap>? _onReplayGap;
private readonly Channel<MxEvent> _channel;
private readonly KeyValuePair<string, object?> _clientTag;
private readonly CancellationTokenSource _cts = new();
private Task? _loop;
private Task? _dispatchLoop;
private bool _disposed;
/// <summary>
/// Value kinds already warned about. Bounded by the <c>MxValue</c> oneof enum, so a
/// broken producer cannot flood the log, while a SECOND unrepresentable kind appearing
/// later still gets its own line — warn-once-per-pump would have swallowed it.
/// </summary>
private readonly HashSet<MxValue.KindOneofCase> _undecodableKindsWarned = [];
/// <summary>Occurs when a data change event is received from the Galaxy subscriber.</summary>
public event EventHandler<DataChangeEventArgs>? OnDataChange;
/// <summary>Initializes a new instance of the EventPump class.</summary>
/// <param name="subscriber">The Galaxy subscriber to consume events from.</param>
/// <param name="registry">The subscription registry for resolving subscribers.</param>
/// <param name="logger">The logger instance; if null, uses NullLogger.</param>
/// <param name="handleFactory">The factory for creating subscription handles; if null, uses GalaxySubscriptionHandle.</param>
/// <param name="channelCapacity">The bounded channel capacity for buffering events.</param>
/// <param name="clientName">The client name for metric tagging; if null, uses "&lt;unknown&gt;".</param>
/// <param name="onStreamFault">Optional callback invoked when the stream faults.</param>
/// <param name="onReplayGap">
/// Optional callback invoked when the gateway reports a replay gap. The contract
/// obliges the client to re-snapshot; see <see cref="HandleReplayGap"/>.
/// </param>
public EventPump(
IGalaxySubscriber subscriber,
SubscriptionRegistry registry,
ILogger? logger = null,
Func<long, ISubscriptionHandle>? handleFactory = null,
int channelCapacity = DefaultChannelCapacity,
string? clientName = null,
Action<Exception>? onStreamFault = null,
Action<ReplayGap>? onReplayGap = null)
{
_subscriber = subscriber ?? throw new ArgumentNullException(nameof(subscriber));
_registry = registry ?? throw new ArgumentNullException(nameof(registry));
_logger = logger ?? NullLogger.Instance;
_handleFactory = handleFactory ?? (id => new GalaxySubscriptionHandle(id));
_onStreamFault = onStreamFault;
_onReplayGap = onReplayGap;
if (channelCapacity < 1)
{
throw new ArgumentOutOfRangeException(nameof(channelCapacity),
"channelCapacity must be >= 1; recommended 50_000 for 50k-tag deployments.");
}
_channel = Channel.CreateBounded<MxEvent>(new BoundedChannelOptions(channelCapacity)
{
// Newest-dropped semantics: we use FullMode.Wait but never call the
// awaitable WriteAsync — only the synchronous TryWrite below in
// RunAsync. With Wait + TryWrite, a full channel makes TryWrite return
// false immediately, which we account for via the EventsDropped counter.
// We deliberately do NOT use BoundedChannelFullMode.DropWrite — that
// would silently discard the new event inside Channel<T> without
// surfacing the drop on a counter (keep this comment and the FullMode
// value consistent).
FullMode = BoundedChannelFullMode.Wait,
SingleReader = true,
// Not single-writer: besides the stream read loop, a registration that promotes
// parked early events (#859) writes the WakeSentinel from the subscribing thread.
SingleWriter = false,
});
_clientTag = new KeyValuePair<string, object?>("galaxy.client", clientName ?? "<unknown>");
// One pump per gateway session. The owner calls SubscriptionRegistry.StartNewSession() BEFORE
// creating the pump for a new session (reconnect); this pump binds to that session and never
// parks or replays under any other (#859 review — item handles are reused across sessions).
_session = _registry.CurrentSession;
_registry.ParkedEventsReady += WakeForReadyEvents;
}
private readonly int _session;
/// <summary>
/// The registry session this pump was created for (#865). A pump of an older session was opened
/// against a gateway session a reconnect replaced; its stream will never carry the new session's events.
/// </summary>
internal int Session => _session;
/// <summary>True once the stream loop has exited (faulted, completed by the gateway, or disposed).</summary>
internal bool HasEnded => Volatile.Read(ref _ended);
// Set at the very start of the stream loop's finally — before StreamRequested is completed there — so a
// waiter released by a dying loop always sees it ended (the loop task itself completes only later).
private bool _ended;
private readonly TaskCompletionSource _streamRequested = new(TaskCreationOptions.RunContinuationsAsynchronously);
/// <summary>
/// Completes once the stream loop has STARTED its <c>StreamEvents</c> call (the first
/// <c>MoveNextAsync</c> runs the subscriber's iterator synchronously up to the gRPC call creation) —
/// or once the loop has ended without getting that far, so a waiter never hangs on a dead pump.
/// #865: the gateway does not replay a fresh stream, so a caller whose only expected event is the
/// initial value of an advise it is about to make waits on this first.
/// </summary>
/// <remarks>
/// ⚠️ This NARROWS the stream-attach race, it does not close it: the HTTP/2 request is sent
/// asynchronously and the gateway attaches the subscriber after auth, concurrently with any other
/// RPC. In practice the attach wins (an advise's initial value needs a worker IPC round trip plus an
/// MXAccess advise). A gateway with the <c>stream-events-attached-ack</c> capability (mxaccessgw#227)
/// closes it: wait on <see cref="StreamAttached"/> when <see cref="AttachAckExpected"/> (#877).
/// </remarks>
public Task StreamRequested => _streamRequested.Task;
private readonly TaskCompletionSource _streamAttached = new(TaskCreationOptions.RunContinuationsAsynchronously);
private volatile bool _attachAckExpected;
/// <summary>
/// #877 — true when this pump's stream was requested WITH the gateway's stream-attached acknowledgement
/// (the subscriber reported <see cref="IGalaxySubscriber.SupportsStreamAttachedAck"/> when the stream was
/// opened). Set before <see cref="StreamRequested"/> completes, so a caller that awaited that first reads
/// the final value.
/// </summary>
public bool AttachAckExpected => _attachAckExpected;
/// <summary>
/// #877 — completes when the gateway's stream-attached sentinel arrives: the stream is registered on the
/// gateway session, so every event the session publishes from then on (an advise's initial value
/// included) reaches this stream. This CLOSES the attach race that <see cref="StreamRequested"/> only
/// narrows. Also completes once the loop has ended, so a waiter never hangs on a dead pump — check
/// <see cref="HasEnded"/> afterwards. Never completes for a stream opened without the ack
/// (<see cref="AttachAckExpected"/> false) while it is alive: callers wait on it only when expected.
/// One pump owns exactly one stream; a reconnect replaces the pump, so every new stream starts with a
/// fresh, uncompleted signal.
/// </summary>
public Task StreamAttached => _streamAttached.Task;
/// <summary>True once the stream-attached sentinel itself arrived (not merely the loop ending).</summary>
internal bool StreamAttachedReceived => Volatile.Read(ref _attachAckReceived);
private bool _attachAckReceived;
/// <summary>
/// Marker written into the channel to wake the dispatch loop after a registration promoted
/// parked early events (#859). Never dispatched itself; compared by reference.
/// </summary>
private static readonly MxEvent WakeSentinel = new();
/// <summary>
/// Wakes the dispatch loop so promoted early events replay even if no further event arrives.
/// Runs on the registering thread, possibly under the driver's <c>_registryGate</c> or the probe
/// watcher's <c>_syncLock</c> — safe because the channel keeps the default
/// <c>AllowSynchronousContinuations = false</c>, so the write never runs the dispatch loop inline.
/// A failed write is harmless: the channel is either full (the loop is busy and replays the
/// ready queue before its next dispatch) or completed (the pump is dead; its held events
/// belong to a session the next StartNewSession discards).
/// </summary>
private void WakeForReadyEvents() => _channel.Writer.TryWrite(WakeSentinel);
/// <summary>
/// Start consuming the event stream on a background task. Idempotent — second
/// calls are no-ops while the loop is running.
/// </summary>
public void Start()
{
ObjectDisposedException.ThrowIf(_disposed, this);
if (_loop is not null) return;
_loop = Task.Run(() => RunAsync(_cts.Token));
_dispatchLoop = Task.Run(() => DispatchLoopAsync(_cts.Token));
}
private async Task RunAsync(CancellationToken ct)
{
IAsyncEnumerator<MxEvent>? enumerator = null;
try
{
// #877: read the capability BEFORE opening the stream — the subscriber requests the ack from the
// same session state — and publish it before StreamRequested releases a waiter.
_attachAckExpected = _subscriber.SupportsStreamAttachedAck;
enumerator = _subscriber.StreamEventsAsync(ct).GetAsyncEnumerator(ct);
// Start the first MoveNext BEFORE awaiting it: that synchronous step issues the RPC, which is
// the moment StreamRequested reports (#865).
var next = enumerator.MoveNextAsync();
if (next.IsCompleted)
{
// Already decided (an item, an immediate end, or a fault): consume it now, so a stream that
// ended or faulted at once is seen as ended (finally) BEFORE StreamRequested releases anyone.
var hasFirst = await next.ConfigureAwait(false);
if (!hasFirst) Volatile.Write(ref _ended, true);
_streamRequested.TrySetResult();
next = new ValueTask<bool>(hasFirst);
}
else
{
_streamRequested.TrySetResult();
}
for (; await next.ConfigureAwait(false); next = enumerator.MoveNextAsync())
{
var ev = enumerator.Current;
if (ct.IsCancellationRequested) break;
// #877: the stream-attached sentinel is a control signal (family UNSPECIFIED, no body,
// worker_sequence 0). It is handled before anything else: it is never dispatched, never
// counted as a received/unknown event, and never touches a resume cursor (this driver
// keeps none — it always opens fresh streams — and a 0 sequence must never become one).
if (ev.StreamAttached is not null)
{
HandleStreamAttached(ev.StreamAttached);
continue;
}
EventsReceived.Add(1, _clientTag);
// The replay-gap sentinel is a control signal, not data, and is handled HERE
// rather than in the dispatch loop for one reason: everything past this point
// is subject to newest-dropped channel pressure, and a dropped "you have
// missed events" signal is the one loss that cannot be recovered from later.
// It carries no item payload, so there is nothing to fan out downstream.
if (ev.ReplayGap is { } gap)
{
HandleReplayGap(gap);
continue;
}
// Newest-dropped: TryWrite fast-paths the common case (channel has room).
// When full we count the drop and continue reading the gw stream so
// back-pressure doesn't propagate upstream.
if (!_channel.Writer.TryWrite(ev))
{
EventsDropped.Add(1, _clientTag);
}
}
// Falling out of the loop without an exception means the SERVER completed the
// stream — a closed or evicted gateway session, not a transport failure. That is
// just as fatal to this driver as a fault (the pump is now dead and no further
// data-change events can ever arrive) but it raises nothing, so without this the
// pump exits silently, the supervisor is never told, GetHealth() keeps reporting
// Healthy, and the comms-loss watchdog never trips either — it requires a
// non-Healthy state. The result is a driver that is permanently, invisibly deaf.
if (!ct.IsCancellationRequested)
{
var cause = new InvalidOperationException(
"The gateway completed the StreamEvents stream without an error. The session was " +
"closed or evicted server-side; the event pump cannot receive further events.");
_logger.LogWarning(
"Galaxy EventPump stream was completed by the gateway — notifying reconnect supervisor.");
NotifyStreamFault(cause);
}
}
catch (Exception) when (ct.IsCancellationRequested)
{
// Clean shutdown — no log. A cancelled gRPC stream may surface as RpcException(Cancelled)
// rather than OperationCanceledException; either way the pump was told to stop, so this
// is not a transport fault and must not wake the reconnect supervisor mid-teardown.
}
catch (Exception ex)
{
_logger.LogWarning(ex,
"Galaxy EventPump loop ended with an exception — notifying reconnect supervisor.");
// The gw StreamEvents stream faulted. Signal the reconnect supervisor so it
// drives reopen → replay. Without this the stream silently dies and a
// transient gateway drop permanently stops data-change notifications.
NotifyStreamFault(ex);
}
finally
{
Volatile.Write(ref _ended, true);
// A loop that died before issuing the RPC must not strand a StreamRequested waiter.
_streamRequested.TrySetResult();
// Nor one waiting for an attach acknowledgement that can no longer arrive (#877).
_streamAttached.TrySetResult();
if (enumerator is not null)
{
try { await enumerator.DisposeAsync().ConfigureAwait(false); }
catch (Exception ex) when (ct.IsCancellationRequested || ex is OperationCanceledException)
{
// Disposing a cancelled stream may surface its cancellation — shutdown noise.
}
catch (Exception ex)
{
_logger.LogDebug(ex, "Galaxy EventPump stream enumerator dispose failed.");
}
}
// Tell the dispatch loop the producer is done so it drains and exits.
_channel.Writer.TryComplete();
}
}
/// <summary>
/// Logs the first occurrence of each unrepresentable value kind. The dispatch loop is
/// single-reader, so the set needs no lock — but it is only ever touched from there.
/// </summary>
private void WarnUndecodableOnce(MxEvent ev)
{
var kind = ev.Value?.KindCase ?? MxValue.KindOneofCase.None;
if (!_undecodableKindsWarned.Add(kind)) return;
_logger.LogWarning(
"Galaxy event for item handle {ItemHandle} carried a value kind this driver cannot " +
"represent ({KindCase}) — publishing BadTypeMismatch. This means the gateway is sending " +
"a wire type MxValueDecoder has no mapping for; readings of this kind are being lost. " +
"Further occurrences of {KindCase} are counted on galaxy.events.undecodable, not logged.",
ev.ItemHandle, kind, kind);
}
private void NotifyStreamFault(Exception cause)
{
if (_onStreamFault is null) return;
try { _onStreamFault(cause); }
catch (Exception cbEx)
{
_logger.LogWarning(cbEx,
"Galaxy EventPump stream-fault callback threw — supervisor may not have been notified.");
}
}
/// <summary>
/// Handles the gateway's replay-gap sentinel: events between the sequence we asked to
/// resume after and the oldest the gateway still retains were evicted and can never be
/// delivered. The contract is explicit that a client "MUST treat a present replay_gap as
/// 'you missed events — discard local state and re-snapshot'".
/// </summary>
/// <remarks>
/// ⚠️ <b>This is unreachable in the current configuration and that is deliberate.</b>
/// The gateway emits the sentinel only on a stream opened with
/// <c>after_worker_sequence &gt; 0</c>; <c>GatewayGalaxySubscriber</c> passes 0, which the
/// gateway treats as "fresh stream, not a resume: plain attach, no replay, no sentinel".
/// It is implemented anyway because the alternative — the sentinel falling through the
/// family switch into the default drop, which is what happened before, since a sentinel
/// carries <c>family = UNSPECIFIED</c> — means silently ignoring a documented MUST if
/// resume is ever switched on. Enabling resume is a larger change than it looks: the
/// sequence is only meaningful within one gateway session, and our reconnect path
/// recreates the session, so a remembered sequence replayed against a fresh session
/// would set the server's live watermark above every event it is about to send.
/// </remarks>
private void HandleStreamAttached(ZB.MOM.WW.MxGateway.Contracts.Proto.StreamAttached attached)
{
StreamAttachedAcks.Add(1, _clientTag);
if (!_attachAckExpected)
{
// An unrequested ack (capability read raced a session swap, or a gateway that sends it anyway)
// is harmless — still a control signal, still never dispatched.
_logger.LogDebug("Galaxy event stream sent a stream-attached acknowledgement that was not expected — ignoring it.");
}
else
{
_logger.LogDebug(
"Galaxy event stream attached on the gateway (live after worker_sequence {LiveAfter}).",
attached.LiveAfterSequence);
}
Volatile.Write(ref _attachAckReceived, true);
_streamAttached.TrySetResult();
}
private void HandleReplayGap(ReplayGap gap)
{
ReplayGapsObserved.Add(1, _clientTag);
_logger.LogWarning(
"Galaxy event stream reported a replay gap: events after worker_sequence {RequestedAfter} " +
"up to {OldestAvailable} were evicted from the gateway's replay ring and cannot be " +
"recovered. Forcing a re-snapshot of every active subscription.",
gap.RequestedAfterSequence, gap.OldestAvailableSequence);
if (_onReplayGap is null) return;
try { _onReplayGap(gap); }
catch (Exception ex)
{
_logger.LogWarning(ex,
"Galaxy EventPump replay-gap callback threw — the re-snapshot may not have run.");
}
}
private async Task DispatchLoopAsync(CancellationToken ct)
{
try
{
await foreach (var ev in _channel.Reader.ReadAllAsync(ct).ConfigureAwait(false))
{
if (ReferenceEquals(ev, WakeSentinel))
{
DispatchReadyEvents();
continue;
}
Dispatch(ev);
EventsDispatched.Add(1, _clientTag);
}
}
catch (Exception) when (ct.IsCancellationRequested)
{
// Clean shutdown.
}
catch (Exception ex)
{
// The read loop is still draining the stream into a channel nobody reads: the pump is
// as dead as after a transport fault, but used to raise nothing — health stayed
// Healthy and the comms-loss watchdog never tripped (a clean termination evading the
// watchdog). Report it as a stream fault so the supervisor recreates the pump.
_logger.LogWarning(ex,
"Galaxy EventPump dispatch loop ended with an exception — notifying reconnect supervisor so the pump is recreated.");
NotifyStreamFault(ex);
}
}
private void Dispatch(MxEvent ev)
{
switch (ev.Family)
{
case MxEventFamily.OnDataChange:
DispatchDataChange(ev);
break;
default:
// OnAlarmTransition is no longer carried on the per-session event stream
// — alarms come from the gateway's session-less StreamAlarms feed
// (GatewayGalaxyAlarmFeed). OnWriteComplete / OperationComplete /
// OnBufferedDataChange are filtered out: write callers get their reply
// via the InvokeAsync round-trip, not via the event stream. Still replay any
// promoted early events: a wake lost to a full channel relies on the next item.
DispatchReadyEvents();
return;
}
}
private void DispatchDataChange(MxEvent ev)
{
var outcome = _registry.ResolveOrPark(ev, _session, out var subscribers, out var replayFirst);
// Replay promoted early events (#859) BEFORE fanning this event out. A registration writes
// the reverse map and promotes its parked events in ONE critical section under the
// registry's park gate, and ResolveOrPark resolves — and takes the ready queue — under that
// same gate whenever anything is held. So if this event resolved, every older parked event
// for its handle is in replayFirst, and replaying it first preserves per-handle order.
ReplayEarly(replayFirst);
switch (outcome)
{
case EarlyEventOutcome.Resolved:
break;
case EarlyEventOutcome.Parked:
// The handle's SubscribeBulk reply has not been registered yet — MXAccess's initial
// value can overtake it. Replayed when the registration lands.
EarlyEventsParked.Add(1, _clientTag);
return;
case EarlyEventOutcome.Overflow:
EarlyEventsOverflowed.Add(1, _clientTag);
return;
default:
return; // stale event after unsubscribe (no subscribe in flight) — drop quietly
}
FanOut(ev, subscribers);
}
/// <summary>
/// Dispatch every early event a registration promoted (#859). Runs only on the dispatch
/// thread, so it is serialised with live dispatch. A promoted event whose subscription was
/// removed again before the replay resolves to nobody and is dropped like any stale event.
/// </summary>
private void DispatchReadyEvents() => ReplayEarly(_registry.TakeReadyEvents(_session));
private void ReplayEarly(IReadOnlyList<MxEvent> ready)
{
if (ready.Count == 0) return;
foreach (var early in ready)
{
var subscribers = _registry.ResolveSubscribers(early.ItemHandle);
if (subscribers.Count == 0) continue;
EarlyEventsReplayed.Add(1, _clientTag);
FanOut(early, subscribers);
}
}
private void FanOut(MxEvent ev, IReadOnlyList<(long SubscriptionId, string FullReference)> subscribers)
{
var snapshot = ToSnapshot(ev);
foreach (var (subscriptionId, fullReference) in subscribers)
{
var handle = _handleFactory(subscriptionId);
try
{
OnDataChange?.Invoke(this, new DataChangeEventArgs(handle, fullReference, snapshot));
}
catch (Exception ex)
{
_logger.LogWarning(ex,
"Galaxy OnDataChange handler threw for {FullRef} subscription {SubscriptionId} — continuing fan-out.",
fullReference, subscriptionId);
}
}
}
private DataValueSnapshot ToSnapshot(MxEvent ev)
{
if (!MxValueDecoder.TryDecode(ev.Value, out var value))
{
// A value we cannot represent is published as Bad, NOT as a null carrying the
// event's own (typically Good) quality. A good null is indistinguishable from a
// real null reading, so a client would treat a value it never received as a
// genuine one — the failure would be invisible on the wire and survive only in a
// log nobody is reading. BadTypeMismatch says what actually happened: the payload
// arrived, and this driver has no CLR type to carry it in.
ValuesUndecodable.Add(1, _clientTag);
WarnUndecodableOnce(ev);
return new DataValueSnapshot(
Value: null,
StatusCode: StatusCodeMap.BadTypeMismatch,
SourceTimestampUtc: ev.SourceTimestamp is { } undecodableTs ? undecodableTs.ToDateTime() : null,
ServerTimestampUtc: DateTime.UtcNow);
}
// A failure status row wins (it names why the read failed); otherwise the item's OPC DA quality grades
// the value. The gateway fills Statuses on every data change, so keying on "any statuses present" meant
// Quality was never read and an off-scan / Bad / Uncertain attribute with an OK status row was
// published Good (#866 review). Every gateway path (live OnDataChange, value-cache replay, session
// snapshot) carries Quality.
var statusCode = ev.Statuses.Count > 0 && !ev.Statuses[0].IsSuccess()
? StatusCodeMap.FromMxStatus(ev.Statuses[0], _logger)
: StatusCodeMap.FromQualityByte((byte)(ev.Quality & 0xFF), _logger);
DateTime? sourceTimestamp = ev.SourceTimestamp is { } ts ? ts.ToDateTime() : null;
return new DataValueSnapshot(
Value: value,
StatusCode: statusCode,
SourceTimestampUtc: sourceTimestamp,
ServerTimestampUtc: DateTime.UtcNow);
}
/// <summary>Disposes the event pump and cancels all running tasks.</summary>
/// <returns>A value task representing the asynchronous disposal operation.</returns>
public async ValueTask DisposeAsync()
{
if (_disposed) return;
_disposed = true;
_registry.ParkedEventsReady -= WakeForReadyEvents;
_cts.Cancel();
_channel.Writer.TryComplete();
if (_loop is not null)
{
try { await _loop.ConfigureAwait(false); } catch { /* shutdown */ }
}
if (_dispatchLoop is not null)
{
try { await _dispatchLoop.ConfigureAwait(false); } catch { /* shutdown */ }
}
_cts.Dispose();
}
}