fix(dcl): treat OPC UA BadResourceUnavailable as transient Bad; Bad+null keeps last-known value (ScadaBridge#112)
OtOpcUa's out-of-process script runner publishes 0x80040000 with a null value. - OpcUaDataConnection: logs entry/recovery once per tag, names the symbolic status in read errors; never a disconnect (not in the reconnect status set). - InstanceActor: a Bad update with no value is a quality-only transition (keep value, quality Bad, stream publish, no script/alarm/waiter re-eval), matching the connection-drop rule. Bad with a value is unchanged. Claude-Session: https://claude.ai/code/session_01GT67AEHd2Acv1YPwGfXEoV
This commit is contained in:
Joseph Doherty
@@ -1,3 +1,4 @@
|
||||
using System.Collections.Concurrent;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Protocol;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Serialization;
|
||||
@@ -41,6 +42,14 @@ public class OpcUaDataConnection
|
||||
private StaleTagMonitor? _staleMonitor;
|
||||
private string? _heartbeatSubscriptionId;
|
||||
|
||||
/// <summary>
|
||||
/// Tags whose latest notification is <c>BadResourceUnavailable</c> (ScadaBridge#112), so the
|
||||
/// distinct "source temporarily unable to compute" log line fires once per entry and once per
|
||||
/// recovery rather than per notification. Written from the SDK publish threads, hence
|
||||
/// concurrent (DCL-019). Bounded by the subscribed tag set; cleared on (re)connect.
|
||||
/// </summary>
|
||||
private readonly ConcurrentDictionary<string, byte> _resourceUnavailableTags = new();
|
||||
|
||||
/// <summary>
|
||||
/// Initializes a new instance of <see cref="OpcUaDataConnection"/>.
|
||||
/// </summary>
|
||||
@@ -99,6 +108,7 @@ public class OpcUaDataConnection
|
||||
MaxMonitoredItemsPerSubscription: config.MaxMonitoredItemsPerSubscription);
|
||||
|
||||
_status = ConnectionHealth.Connecting;
|
||||
_resourceUnavailableTags.Clear();
|
||||
|
||||
// Reconnect reuses this adapter instance (DataConnectionActor re-calls
|
||||
// ConnectAsync on auto-reconnect): detach + dispose the previous client so
|
||||
@@ -191,6 +201,7 @@ public class OpcUaDataConnection
|
||||
(nodeId, value, timestamp, statusCode) =>
|
||||
{
|
||||
var quality = MapStatusCode(statusCode);
|
||||
TrackResourceUnavailable(tagPath, statusCode);
|
||||
callback(tagPath, new TagValue(value, quality, new DateTimeOffset(timestamp, TimeSpan.Zero)));
|
||||
},
|
||||
cancellationToken);
|
||||
@@ -209,6 +220,7 @@ public class OpcUaDataConnection
|
||||
(nodeId, value, timestamp, statusCode) =>
|
||||
{
|
||||
var quality = MapStatusCode(statusCode);
|
||||
TrackResourceUnavailable(nodeId, statusCode);
|
||||
callback(nodeId, new TagValue(value, quality, new DateTimeOffset(timestamp, TimeSpan.Zero)));
|
||||
},
|
||||
cancellationToken);
|
||||
@@ -267,7 +279,7 @@ public class OpcUaDataConnection
|
||||
var quality = MapStatusCode(statusCode);
|
||||
|
||||
if (quality == QualityCode.Bad)
|
||||
return new ReadResult(false, null, $"OPC UA read returned bad status: 0x{statusCode:X8}");
|
||||
return new ReadResult(false, null, DescribeBadRead(statusCode));
|
||||
|
||||
return new ReadResult(true, new TagValue(value, quality, new DateTimeOffset(timestamp, TimeSpan.Zero)), null);
|
||||
}
|
||||
@@ -306,7 +318,7 @@ public class OpcUaDataConnection
|
||||
|
||||
var quality = MapStatusCode(outcome.StatusCode);
|
||||
results[outcome.NodeId] = quality == QualityCode.Bad
|
||||
? new ReadResult(false, null, $"OPC UA read returned bad status: 0x{outcome.StatusCode:X8}")
|
||||
? new ReadResult(false, null, DescribeBadRead(outcome.StatusCode))
|
||||
: new ReadResult(true,
|
||||
new TagValue(outcome.Value, quality, new DateTimeOffset(outcome.SourceTimestamp, TimeSpan.Zero)),
|
||||
null);
|
||||
@@ -461,6 +473,60 @@ public class OpcUaDataConnection
|
||||
Disconnected?.Invoke();
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// OPC UA <c>BadResourceUnavailable</c> — the code part (high 16 bits) of
|
||||
/// <see cref="Opc.Ua.StatusCodes.BadResourceUnavailable"/>. OtOpcUa's out-of-process script
|
||||
/// runner publishes it on script-computed nodes when the script worker died under the
|
||||
/// evaluation or no worker is ready (ScadaBridge#112, lmxopcua#780). It is a per-node,
|
||||
/// transient "cannot compute this value right now": a plain Bad quality on the tag — never a
|
||||
/// connection fault, so it must not reach <c>RaiseDisconnected</c> or the connection-level
|
||||
/// status set the DataConnectionActor reconnects on.
|
||||
/// </summary>
|
||||
internal const uint BadResourceUnavailableCode = Opc.Ua.StatusCodes.BadResourceUnavailable;
|
||||
|
||||
/// <summary>True when <paramref name="statusCode"/>'s code part is BadResourceUnavailable
|
||||
/// (the low 16 bits are info bits and do not change the meaning).</summary>
|
||||
internal static bool IsResourceUnavailable(uint statusCode) =>
|
||||
(statusCode & 0xFFFF0000u) == BadResourceUnavailableCode;
|
||||
|
||||
/// <summary>Read-failure text naming the symbolic status, e.g.
|
||||
/// <c>0x80040000 BadResourceUnavailable</c>, so a script/diagnostic reader can tell a
|
||||
/// transient source-side condition from a configuration or security error.</summary>
|
||||
internal static string DescribeBadRead(uint statusCode)
|
||||
{
|
||||
var name = Opc.Ua.StatusCodes.LookupSymbolicId(statusCode & 0xFFFF0000u);
|
||||
var text = string.IsNullOrEmpty(name)
|
||||
? $"OPC UA read returned bad status: 0x{statusCode:X8}"
|
||||
: $"OPC UA read returned bad status: 0x{statusCode:X8} {name}";
|
||||
return IsResourceUnavailable(statusCode)
|
||||
? text + " (source node temporarily unable to compute the value)"
|
||||
: text;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Logs the entry into / recovery from <c>BadResourceUnavailable</c> once per transition per
|
||||
/// tag. Hot path: a tag that is not and was not unavailable costs one status compare and an
|
||||
/// empty-dictionary check.
|
||||
/// </summary>
|
||||
private void TrackResourceUnavailable(string tagPath, uint statusCode)
|
||||
{
|
||||
if (IsResourceUnavailable(statusCode))
|
||||
{
|
||||
if (_resourceUnavailableTags.TryAdd(tagPath, 0))
|
||||
_logger.LogInformation(
|
||||
"OPC UA source {Endpoint} reports BadResourceUnavailable (0x{Status:X8}) for {TagPath} — "
|
||||
+ "the source node is temporarily unable to compute this value; tag quality is Bad, "
|
||||
+ "last-known value kept, connection unaffected",
|
||||
_endpointUrl, statusCode, tagPath);
|
||||
}
|
||||
else if (!_resourceUnavailableTags.IsEmpty && _resourceUnavailableTags.TryRemove(tagPath, out _))
|
||||
{
|
||||
_logger.LogInformation(
|
||||
"OPC UA source {Endpoint} recovered {TagPath} from BadResourceUnavailable (now 0x{Status:X8})",
|
||||
_endpointUrl, tagPath, statusCode);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Maps OPC UA StatusCode to QualityCode.
|
||||
/// StatusCode 0 = Good, high bit set = Bad, otherwise Uncertain.
|
||||
|
||||
@@ -1223,6 +1223,23 @@ public class InstanceActor : ReceiveActor
|
||||
traced = true;
|
||||
}
|
||||
|
||||
// Bad quality WITHOUT a value (ScadaBridge#112) is a quality-only transition: the
|
||||
// source is saying "I cannot give you a value right now", not "the value is now
|
||||
// null". OPC UA servers commonly omit the value on a Bad status — OtOpcUa always
|
||||
// does, e.g. BadResourceUnavailable (0x80040000) from its out-of-process script
|
||||
// runner — and the DCL's own tag-resolution failure pushes Bad+null too. Treat it
|
||||
// exactly like a connection drop (HandleConnectionQualityChanged, DCL design
|
||||
// "Connection drop detection"): keep the last-known value, flip quality to Bad,
|
||||
// publish to the stream, and do NOT re-notify scripts/alarms or evaluate waiters —
|
||||
// nulling the stored value would fire value-change scripts with a null and make a
|
||||
// computed alarm re-evaluate on a value that never existed. A Bad update that DOES
|
||||
// carry a value still takes the normal path below.
|
||||
if (update.Quality == QualityCode.Bad && update.Value is null)
|
||||
{
|
||||
ApplyQualityOnlyBad(attrName, update.TagPath, update.Timestamp, traceSource, traced);
|
||||
continue;
|
||||
}
|
||||
|
||||
// A List-typed attribute coerces the incoming OPC UA array
|
||||
// (a CLR array/IEnumerable from the SDK) into a typed List<T>. On an
|
||||
// element-type mismatch we set the attribute's quality to Bad, log a
|
||||
@@ -1271,6 +1288,22 @@ public class InstanceActor : ReceiveActor
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Marks a data-sourced attribute Bad while keeping its last-known value (ScadaBridge#112):
|
||||
/// quality + timestamp move, the stored value does not, and only the site stream / debug
|
||||
/// view is told — mirroring <see cref="HandleConnectionQualityChanged"/>.
|
||||
/// </summary>
|
||||
private void ApplyQualityOnlyBad(
|
||||
string attrName, string tagPath, DateTimeOffset timestamp, Guid? traceSource, bool traced)
|
||||
{
|
||||
_attributeQualities[attrName] = "Bad";
|
||||
_attributeTimestamps[attrName] = timestamp;
|
||||
_attributes.TryGetValue(attrName, out var currentValue);
|
||||
_streamManager?.PublishAttributeValueChanged(new AttributeValueChanged(
|
||||
_instanceUniqueName, tagPath, attrName, currentValue, "Bad", timestamp,
|
||||
SourceExecutionId: traceSource, Trace: traced, SourceExecutionInferred: traced));
|
||||
}
|
||||
|
||||
/// <summary>Parses a <see cref="ResolvedAttribute.DataType"/> string, defaulting to
|
||||
/// <see cref="DataType.String"/> on an unrecognized value (never throws).</summary>
|
||||
private static DataType ParseDataType(string dataType) =>
|
||||
|
||||
Reference in New Issue
Block a user