Joseph Doherty
099bc1b6e0
The F2 live gate failed (10 value regressions over 4 blips): IsLateReplay disarmed a ref on its first in-order notification, which arrives ~1 s after recovery, while the SDK's late replay lands 4-6 s later. Equal source times also passed, so a replay equal to the recovery read got through. While the window is open each ref now carries a high-water mark (seeded at arming, raised by the recovery read, advanced by every accepted notification); a notification at or below it is dropped (equal included — OPC UA moves the source timestamp on every value/status change). Null source time passes without moving the mark. Window expiry still disarms entirely, so an upstream clock step-back is never frozen outside the window. Arm/expiry serialised by a lock so an expiry racing a re-arm cannot wipe fresh seeds.
47 lines
2.6 KiB
C#
47 lines
2.6 KiB
C#
using ZB.MOM.WW.OtOpcUa.Commons.Observability;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Driver.OpcUaClient;
|
|
|
|
/// <summary>
|
|
/// Publishes an OPC UA Client driver instance's session/publish events (#276) on the shared
|
|
/// <c>otopcua.driver.opcuaclient.events</c> OTel counter, tagged with <c>driver_instance</c> and
|
|
/// <c>event</c>. The counter is thread-safe, so the SDK's notification / keep-alive threads record
|
|
/// directly with no locking here.
|
|
/// </summary>
|
|
internal sealed class OpcUaClientDiagnostics
|
|
{
|
|
/// <summary>A NotificationMessage arrived (one per Publish response that carried data).</summary>
|
|
public const string PublishResponse = "publish_response";
|
|
/// <summary>Items carried by notification messages.</summary>
|
|
public const string Notification = "notification";
|
|
/// <summary>One monitored-item data change was delivered.</summary>
|
|
public const string DataChange = "data_change";
|
|
/// <summary>A delivered data change carried a Bad status.</summary>
|
|
public const string BadStatusValue = "bad_status_value";
|
|
/// <summary>A Publish failed (missing publish requests, subscription errors).</summary>
|
|
public const string PublishError = "publish_error";
|
|
/// <summary>A keep-alive came back Bad.</summary>
|
|
public const string KeepAliveMiss = "keepalive_miss";
|
|
/// <summary>A keep-alive came back Good after a bad one on the same session (an in-place recovery, #670).</summary>
|
|
public const string KeepAliveRecovered = "keepalive_recovered";
|
|
/// <summary>A late replayed notification (source time at or below the ref's high-water mark) was dropped inside the post-recovery replay window (#670 F2).</summary>
|
|
public const string StaleNotificationDropped = "stale_notification_dropped";
|
|
|
|
private readonly string _driverInstanceId;
|
|
|
|
/// <summary>Creates the recorder for one driver instance.</summary>
|
|
/// <param name="driverInstanceId">Value of the <c>driver_instance</c> tag.</param>
|
|
public OpcUaClientDiagnostics(string driverInstanceId) => _driverInstanceId = driverInstanceId;
|
|
|
|
/// <summary>Add <paramref name="count"/> to the counter for <paramref name="evt"/>.</summary>
|
|
/// <param name="evt">One of the event constants.</param>
|
|
/// <param name="count">Amount to add (default 1).</param>
|
|
public void Record(string evt, long count = 1)
|
|
{
|
|
if (count <= 0) return;
|
|
OtOpcUaTelemetry.OpcUaClientEvents.Add(count,
|
|
new KeyValuePair<string, object?>(OtOpcUaTelemetry.PollOverrunDriverInstanceTag, _driverInstanceId),
|
|
new KeyValuePair<string, object?>("event", evt));
|
|
}
|
|
}
|