Merge lane K: clients, CLI, AB transport (#747)

Claude-Session: https://claude.ai/code/session_01Ub9hGmYLQvn9XETzw7CMsT
This commit is contained in:
Joseph Doherty
2026-10-22 17:38:08 -04:00
53 changed files with 2339 additions and 510 deletions
@@ -47,7 +47,7 @@ public class HistoryReadCommand : CommandBase
/// <summary>
/// Gets the optional aggregate name used when the operator wants processed history instead of raw samples.
/// </summary>
[CommandOption("aggregate", Description = "Aggregate function: Average, Minimum, Maximum, Count, Start, End, StandardDeviation, TimeAverage, TimeAverage2, Total, Total2, Interpolative")]
[CommandOption("aggregate", Description = "Aggregate function: Average, Minimum, Maximum, Count, Start, End, TimeAverage, TimeAverage2, Total, Total2, Interpolative, Range, Delta, MinimumActualTime, MaximumActualTime, PercentGood, PercentBad")]
public string? Aggregate { get; init; }
/// <summary>
@@ -199,24 +199,33 @@ public class HistoryReadCommand : CommandBase
}
}
private static readonly string SupportedAggregates = string.Join(", ", Enum.GetNames<AggregateType>());
private static AggregateType ParseAggregateType(string name)
{
return name.Trim().ToLowerInvariant() switch
var trimmed = name.Trim();
var alias = trimmed.ToLowerInvariant() switch
{
"average" or "avg" => AggregateType.Average,
"minimum" or "min" => AggregateType.Minimum,
"maximum" or "max" => AggregateType.Maximum,
"count" => AggregateType.Count,
"start" or "first" => AggregateType.Start,
"end" or "last" => AggregateType.End,
"standarddeviation" or "stddev" or "stdev" => AggregateType.StandardDeviation,
"timeaverage" or "timeavg" => AggregateType.TimeAverage,
"timeaverage2" or "timeavg2" => AggregateType.TimeAverage2,
"total" => AggregateType.Total,
"total2" => AggregateType.Total2,
"interpolative" or "interp" => AggregateType.Interpolative,
_ => throw new ArgumentException(
$"Unknown aggregate: '{name}'. Supported: Average, Minimum, Maximum, Count, Start, End, StandardDeviation, TimeAverage, TimeAverage2, Total, Total2, Interpolative")
"avg" => AggregateType.Average,
"min" => AggregateType.Minimum,
"max" => AggregateType.Maximum,
"first" => AggregateType.Start,
"last" => AggregateType.End,
"timeavg" => AggregateType.TimeAverage,
"timeavg2" => AggregateType.TimeAverage2,
"interp" => AggregateType.Interpolative,
"mintime" => AggregateType.MinimumActualTime,
"maxtime" => AggregateType.MaximumActualTime,
_ => (AggregateType?)null
};
if (alias is { } a) return a;
// Every enum name (the served set; a parity test pins it), case-insensitive. Numeric strings are refused:
// Enum.TryParse would accept "6" or "99" as an undefined value.
if (!int.TryParse(trimmed, out _) &&
Enum.TryParse<AggregateType>(trimmed, ignoreCase: true, out var parsed) && Enum.IsDefined(parsed))
return parsed;
throw new ArgumentException($"Unknown aggregate: '{name}'. Supported: {SupportedAggregates}");
}
}
@@ -115,22 +115,6 @@ internal sealed class DefaultSessionAdapter : ISessionAdapter
return (nextCp, nextRefs ?? []);
}
/// <inheritdoc />
public async Task<bool> HasChildrenAsync(NodeId nodeId, CancellationToken ct)
{
var (_, _, references) = await _session.BrowseAsync(
null,
null,
nodeId,
1u,
BrowseDirection.Forward,
ReferenceTypeIds.HierarchicalReferences,
true,
0u);
return references != null && references.Count > 0;
}
/// <inheritdoc />
public async Task<Models.HistoryUpdateOutcome> HistoryUpdateAsync(HistoryUpdateDetails details, CancellationToken ct)
{
@@ -164,46 +148,16 @@ internal sealed class DefaultSessionAdapter : ISessionAdapter
ReturnBounds = false
};
var nodesToRead = new HistoryReadValueIdCollection
{
new HistoryReadValueId { NodeId = nodeId }
};
var allValues = new List<DataValue>();
byte[]? continuationPoint = null;
do
{
if (continuationPoint != null)
nodesToRead[0].ContinuationPoint = continuationPoint;
// Use the async overload so this method is genuinely asynchronous,
// honors the cancellation token, and does not block the caller's thread
// (which would block the UI dispatcher for client.ui consumers).
var response = await _session.HistoryReadAsync(
null,
new ExtensionObject(details),
TimestampsToReturn.Source,
continuationPoint != null,
nodesToRead,
ct).ConfigureAwait(false);
var results = response.Results;
if (results == null || results.Count == 0)
break;
var result = results[0];
// A refused read (BadHistoryOperationUnsupported, BadUserAccessDenied, ...) must surface; only
// BadNoData is an empty result. Swallowing it printed "0 values returned" for a refusal.
HistoryReadStatus.ThrowIfRefused(result.StatusCode, nodeId);
if (result.HistoryData is ExtensionObject ext && ext.Body is HistoryData historyData)
allValues.AddRange(historyData.DataValues);
continuationPoint = result.ContinuationPoint;
} while (continuationPoint != null && continuationPoint.Length > 0 && allValues.Count < maxValues);
return allValues;
// Continuation pages are READ, never released, until the server finishes or the cap is reached; a read stopped
// by the cap releases the server's cursor (HistoryReadPaging). This path used to pass
// `releaseContinuationPoints: continuationPoint != null`, which RELEASED the second page instead of reading it,
// silently truncating every raw read to its first server page.
return await HistoryReadPaging.ReadAllAsync(
(cp, release, token) => ReadHistoryPageAsync(details, nodeId, cp, release, TimestampsToReturn.Source, token),
result => result.HistoryData is ExtensionObject { Body: HistoryData historyData }
? historyData.DataValues
: [],
maxValues, nodeId, ct).ConfigureAwait(false);
}
/// <inheritdoc />
@@ -219,59 +173,41 @@ internal sealed class DefaultSessionAdapter : ISessionAdapter
ReturnBounds = false
};
return await HistoryReadPaging.ReadAllAsync(
(cp, release, token) => ReadHistoryPageAsync(details, nodeId, cp, release, TimestampsToReturn.Both, token),
ToModifiedEntries, maxValues, nodeId, ct).ConfigureAwait(false);
}
private static IEnumerable<Models.HistoryModifiedEntry> ToModifiedEntries(HistoryReadResult result)
{
if (result.HistoryData is not ExtensionObject { Body: HistoryModifiedData modified }) yield break;
for (var i = 0; i < modified.DataValues.Count; i++)
{
var info = i < modified.ModificationInfos.Count ? modified.ModificationInfos[i] : null;
yield return new Models.HistoryModifiedEntry(
modified.DataValues[i],
info?.ModificationTime ?? DateTime.MinValue,
info?.UpdateType ?? default,
info?.UserName);
}
}
/// <summary>Issues one single-node HistoryRead (or a release of its continuation point).</summary>
private async Task<HistoryReadResult?> ReadHistoryPageAsync(
ReadRawModifiedDetails details, NodeId nodeId, byte[]? continuationPoint, bool release,
TimestampsToReturn timestamps, CancellationToken ct)
{
var nodesToRead = new HistoryReadValueIdCollection
{
new HistoryReadValueId { NodeId = nodeId }
new HistoryReadValueId { NodeId = nodeId, ContinuationPoint = continuationPoint }
};
var all = new List<Models.HistoryModifiedEntry>();
byte[]? continuationPoint = null;
// The async overload honours the token and does not block the caller's thread (the UI dispatcher for
// client.ui consumers).
var response = await _session.HistoryReadAsync(
null, new ExtensionObject(details), timestamps, release, nodesToRead, ct).ConfigureAwait(false);
do
{
if (continuationPoint != null)
nodesToRead[0].ContinuationPoint = continuationPoint;
var response = await _session.HistoryReadAsync(
null,
new ExtensionObject(details),
TimestampsToReturn.Both,
false,
nodesToRead,
ct).ConfigureAwait(false);
var results = response.Results;
if (results == null || results.Count == 0)
break;
var result = results[0];
HistoryReadStatus.ThrowIfRefused(result.StatusCode, nodeId);
if (result.HistoryData is ExtensionObject ext && ext.Body is HistoryModifiedData modified)
{
for (var i = 0; i < modified.DataValues.Count; i++)
{
var info = i < modified.ModificationInfos.Count ? modified.ModificationInfos[i] : null;
all.Add(new Models.HistoryModifiedEntry(
modified.DataValues[i],
info?.ModificationTime ?? DateTime.MinValue,
info?.UpdateType ?? default,
info?.UserName));
}
}
continuationPoint = result.ContinuationPoint;
} while (continuationPoint != null && continuationPoint.Length > 0 && all.Count < maxValues);
// A read stopped by the client's own cap leaves a server cursor behind; release it.
if (continuationPoint is { Length: > 0 })
{
nodesToRead[0].ContinuationPoint = continuationPoint;
await _session.HistoryReadAsync(null, new ExtensionObject(details), TimestampsToReturn.Both, true,
nodesToRead, ct).ConfigureAwait(false);
}
return all;
return response.Results is { Count: > 0 } results ? results[0] : null;
}
/// <inheritdoc />
@@ -327,9 +263,22 @@ internal sealed class DefaultSessionAdapter : ISessionAdapter
};
_session.AddSubscription(subscription);
await subscription.CreateAsync(ct);
try
{
await subscription.CreateAsync(ct);
}
catch
{
// A subscription the server never created must not linger in Session.Subscriptions either.
try { await _session.RemoveSubscriptionAsync(subscription, CancellationToken.None); }
catch (Exception ex) { Logger.Warning(ex, "Error removing a subscription that failed to create"); }
throw;
}
return new DefaultSubscriptionAdapter(subscription);
// Deleting the adapter also removes the subscription from the SDK session, so a re-targeted alarm/data
// subscription does not accumulate dead Subscription objects in Session.Subscriptions.
return new DefaultSubscriptionAdapter(subscription,
async (s, token) => await _session.RemoveSubscriptionAsync(s, token).ConfigureAwait(false));
}
/// <inheritdoc />
@@ -12,14 +12,23 @@ internal sealed class DefaultSubscriptionAdapter : ISubscriptionAdapter
private static readonly ILogger Logger = Log.ForContext<DefaultSubscriptionAdapter>();
private readonly Dictionary<uint, MonitoredItem> _monitoredItems = new();
private readonly Subscription _subscription;
private readonly Func<Subscription, CancellationToken, Task>? _detach;
private int _detached;
/// <summary>
/// Wraps a live OPC UA subscription so client code can manage monitored items through a testable abstraction.
/// </summary>
/// <param name="subscription">The underlying OPC UA subscription that owns monitored items for this client workflow.</param>
public DefaultSubscriptionAdapter(Subscription subscription)
/// <param name="detach">
/// Removes the subscription from its owning SDK <c>Session</c> once it is deleted. Without it a deleted
/// subscription stays in <c>Session.Subscriptions</c> until the session is disposed, so a UI that re-targets
/// alarms repeatedly accumulates dead subscriptions the SDK still iterates (transfer / recreate on reconnect).
/// </param>
public DefaultSubscriptionAdapter(Subscription subscription,
Func<Subscription, CancellationToken, Task>? detach = null)
{
_subscription = subscription;
_detach = detach;
}
/// <inheritdoc />
@@ -113,17 +122,39 @@ internal sealed class DefaultSubscriptionAdapter : ISubscriptionAdapter
Logger.Warning(ex, "Error deleting subscription");
}
// Detach whether or not the server-side delete succeeded: the adapter is finished with it either way.
await DetachAsync(ct);
_monitoredItems.Clear();
}
private async Task DetachAsync(CancellationToken ct)
{
if (_detach == null || Interlocked.Exchange(ref _detached, 1) != 0) return;
try
{
await _detach(_subscription, ct);
}
catch (Exception ex)
{
Logger.Warning(ex, "Error removing subscription from its session");
}
}
/// <summary>
/// Releases the wrapped OPC UA subscription and clears tracked monitored items held by the adapter.
/// </summary>
public void Dispose()
{
// One bounded bridge (5 s) for delete + detach, so a dispose never blocks longer than before (review m6).
// DetachAsync swallows its own failures; a failed delete must not skip the detach.
try
{
DisposeBridge.Run(ct => _subscription.DeleteAsync(true, ct));
DisposeBridge.Run(async ct =>
{
try { await _subscription.DeleteAsync(true, ct); }
catch (Exception ex) { Logger.Warning(ex, "Error deleting subscription"); }
await DetachAsync(ct);
});
}
catch
{
@@ -90,14 +90,6 @@ internal interface ISessionAdapter : IDisposable
Task<(byte[]? ContinuationPoint, ReferenceDescriptionCollection References)> BrowseNextAsync(
byte[] continuationPoint, CancellationToken ct = default);
/// <summary>
/// Checks whether a node has any forward hierarchical child references.
/// </summary>
/// <param name="nodeId">The node to inspect for child objects or variables.</param>
/// <param name="ct">The cancellation token that aborts the child lookup.</param>
/// <returns><c>true</c> when the node has at least one forward hierarchical child reference; otherwise <c>false</c>.</returns>
Task<bool> HasChildrenAsync(NodeId nodeId, CancellationToken ct = default);
/// <summary>
/// Reads raw historical data.
/// </summary>
@@ -23,12 +23,17 @@ public static class AggregateTypeMapper
AggregateType.Count => ObjectIds.AggregateFunction_Count,
AggregateType.Start => ObjectIds.AggregateFunction_Start,
AggregateType.End => ObjectIds.AggregateFunction_End,
AggregateType.StandardDeviation => ObjectIds.AggregateFunction_StandardDeviationPopulation,
AggregateType.TimeAverage => ObjectIds.AggregateFunction_TimeAverage,
AggregateType.TimeAverage2 => ObjectIds.AggregateFunction_TimeAverage2,
AggregateType.Total => ObjectIds.AggregateFunction_Total,
AggregateType.Total2 => ObjectIds.AggregateFunction_Total2,
AggregateType.Interpolative => ObjectIds.AggregateFunction_Interpolative,
AggregateType.Range => ObjectIds.AggregateFunction_Range,
AggregateType.Delta => ObjectIds.AggregateFunction_Delta,
AggregateType.MinimumActualTime => ObjectIds.AggregateFunction_MinimumActualTime,
AggregateType.MaximumActualTime => ObjectIds.AggregateFunction_MaximumActualTime,
AggregateType.PercentGood => ObjectIds.AggregateFunction_PercentGood,
AggregateType.PercentBad => ObjectIds.AggregateFunction_PercentBad,
_ => throw new ArgumentOutOfRangeException(nameof(aggregate), aggregate, "Unknown AggregateType value.")
};
}
@@ -0,0 +1,96 @@
using Opc.Ua;
using Serilog;
namespace ZB.MOM.WW.OtOpcUa.Client.Shared.Helpers;
/// <summary>
/// The client-side HistoryRead paging loop shared by the raw and modified reads. Continuation pages are
/// READ (<c>releaseContinuationPoints = false</c>) while the caller still wants values; a read stopped by the
/// caller's own cap while the server still holds a cursor releases that cursor so it does not occupy one of the
/// session's continuation-point slots until eviction.
/// </summary>
internal static class HistoryReadPaging
{
private static readonly ILogger Logger = Log.ForContext(typeof(HistoryReadPaging));
/// <summary>Reads (or, with <paramref name="releaseContinuationPoints"/>, releases) one page.</summary>
/// <param name="continuationPoint">The cursor to resume, or <see langword="null"/> for the first page.</param>
/// <param name="releaseContinuationPoints"><see langword="true"/> to release the cursor instead of reading.</param>
/// <param name="ct">The caller's cancellation token.</param>
/// <returns>The per-node result, or <see langword="null"/> when the response carried none.</returns>
public delegate Task<HistoryReadResult?> PageReader(
byte[]? continuationPoint, bool releaseContinuationPoints, CancellationToken ct);
/// <summary>The bound on a best-effort release that does not ride the caller's (possibly cancelled) token.</summary>
internal static readonly TimeSpan ReleaseTimeout = TimeSpan.FromSeconds(5);
/// <summary>Reads pages until the server finishes or the caller's cap is reached.</summary>
/// <typeparam name="T">The element type extracted from each page.</typeparam>
/// <param name="readPage">Issues one HistoryRead for the single node.</param>
/// <param name="extract">Extracts the page's elements from a result.</param>
/// <param name="maxValues">The caller's cap; must be positive. The result is trimmed to it.</param>
/// <param name="nodeId">The node being read, for refusal messages.</param>
/// <param name="ct">The caller's cancellation token.</param>
/// <returns>At most <paramref name="maxValues"/> elements.</returns>
/// <exception cref="ArgumentOutOfRangeException"><paramref name="maxValues"/> is not positive: an uncapped client
/// read would materialise a tag's whole window (the client side of review 08 1.1).</exception>
/// <exception cref="ServiceResultException">A page was refused (see <see cref="HistoryReadStatus"/>).</exception>
/// <exception cref="OperationCanceledException"><paramref name="ct"/> was cancelled mid-read; the outstanding
/// cursor is released (best effort) first.</exception>
public static async Task<List<T>> ReadAllAsync<T>(
PageReader readPage, Func<HistoryReadResult, IEnumerable<T>> extract, int maxValues, NodeId nodeId,
CancellationToken ct)
{
ArgumentOutOfRangeException.ThrowIfNegativeOrZero(maxValues);
var all = new List<T>();
byte[]? continuationPoint = null;
try
{
while (true)
{
var result = await readPage(continuationPoint, false, ct).ConfigureAwait(false);
if (result == null) return Trim(all, maxValues);
HistoryReadStatus.ThrowIfRefused(result.StatusCode, nodeId);
all.AddRange(extract(result));
continuationPoint = result.ContinuationPoint;
if (continuationPoint is not { Length: > 0 }) return Trim(all, maxValues);
if (all.Count >= maxValues) break;
}
}
catch (OperationCanceledException)
{
// Cancelled between pages (or during page N+1) with a cursor outstanding: release it rather than leave it
// occupying one of the session's continuation-point slots, then surface the cancellation.
if (continuationPoint is { Length: > 0 }) await ReleaseAsync(readPage, continuationPoint, nodeId);
throw;
}
// Stopped by the client's own cap: the server still holds a cursor for this session. Release it — on its own
// bounded token, so a cancellation racing the release cannot lose the values already in hand.
await ReleaseAsync(readPage, continuationPoint, nodeId);
return Trim(all, maxValues);
}
private static List<T> Trim<T>(List<T> all, int maxValues)
{
if (all.Count > maxValues) all.RemoveRange(maxValues, all.Count - maxValues);
return all;
}
private static async Task ReleaseAsync(PageReader readPage, byte[] continuationPoint, NodeId nodeId)
{
try
{
using var cts = new CancellationTokenSource(ReleaseTimeout);
await readPage(continuationPoint, true, cts.Token).ConfigureAwait(false);
}
catch (Exception ex)
{
Logger.Warning(ex, "Releasing the HistoryRead continuation point for {NodeId} failed", nodeId);
}
}
}
@@ -1,43 +1,64 @@
namespace ZB.MOM.WW.OtOpcUa.Client.Shared.Models;
/// <summary>
/// Aggregate functions for processed history reads.
/// Aggregate functions for processed history reads — exactly the seventeen the server's SQL historian backends
/// serve (<c>AggregateFamilies.Served</c>; a parity test pins it). The Gateway backend serves a subset and refuses
/// the rest with <c>BadAggregateNotSupported</c>.
/// </summary>
/// <remarks>
/// Values are explicit so the pre-existing members keep their numbers. 6 (the former <c>StandardDeviation</c>,
/// which no backend serves) is retired; do not reuse it.
/// </remarks>
public enum AggregateType
{
/// <summary>Average of values in the interval.</summary>
Average,
Average = 0,
/// <summary>Minimum value in the interval.</summary>
Minimum,
Minimum = 1,
/// <summary>Maximum value in the interval.</summary>
Maximum,
Maximum = 2,
/// <summary>Count of values in the interval.</summary>
Count,
Count = 3,
/// <summary>First value in the interval.</summary>
Start,
Start = 4,
/// <summary>Last value in the interval.</summary>
End,
/// <summary>Population standard deviation of values in the interval.</summary>
StandardDeviation,
End = 5,
/// <summary>Time-weighted average, interpolated bounds (Part 13 TimeAverage).</summary>
TimeAverage,
TimeAverage = 7,
/// <summary>Time-weighted average, stepped bounds (Part 13 TimeAverage2).</summary>
TimeAverage2,
TimeAverage2 = 8,
/// <summary>Time-weighted integral over the interval (Part 13 Total).</summary>
Total,
Total = 9,
/// <summary>Time-weighted integral, stepped bounds (Part 13 Total2).</summary>
Total2,
Total2 = 10,
/// <summary>Interpolated value at the interval start (Part 13 Interpolative).</summary>
Interpolative
}
Interpolative = 11,
/// <summary>Maximum minus minimum in the interval (Part 13 Range).</summary>
Range = 12,
/// <summary>Last minus first value in the interval (Part 13 Delta).</summary>
Delta = 13,
/// <summary>Minimum value with its own timestamp (Part 13 MinimumActualTime).</summary>
MinimumActualTime = 14,
/// <summary>Maximum value with its own timestamp (Part 13 MaximumActualTime).</summary>
MaximumActualTime = 15,
/// <summary>Percentage of the interval with Good data (Part 13 PercentGood).</summary>
PercentGood = 16,
/// <summary>Percentage of the interval with Bad data (Part 13 PercentBad).</summary>
PercentBad = 17
}
@@ -34,7 +34,9 @@ public sealed class BrowseResult
public string NodeClass { get; }
/// <summary>
/// Whether the node has child references.
/// Whether the node MAY have child references: <see langword="true"/> for every Object, confirmed lazily when the
/// caller browses it (an expanded empty folder simply yields no children). Variables and Methods report
/// <see langword="false"/>.
/// </summary>
public bool HasChildren { get; }
}
@@ -15,16 +15,17 @@ public sealed class OpcUaClientService : IOpcUaClientService
{
private static readonly ILogger Logger = Log.ForContext<OpcUaClientService>();
// Guards all access to the subscription-bookkeeping state below
// (_activeDataSubscriptions and _activeAlarmSubscription). The dictionary
// and tuple are mutated from the caller thread, the keep-alive failover
// path, and DisconnectAsync, so every read/write must be inside this lock.
// Guards all access to the subscription state below (_activeDataSubscriptions, _activeAlarmSubscription,
// _dataSubscription, _alarmSubscription). They are touched from the caller thread, the keep-alive failover path
// and DisconnectAsync, so every read/write is inside this lock — including failover's null-outs.
private readonly object _subscriptionLock = new();
// Serialises SubscribeAlarmsAsync / UnsubscribeAlarmsAsync so concurrent callers
// cannot both pass the _alarmSubscription == null check and create duplicate event
// subscriptions. Capacity 1 = at most one waiter; async-friendly (no thread-block).
private readonly SemaphoreSlim _alarmSubscribeSemaphore = new(1, 1);
// Serialises every subscription operation that awaits I/O (Subscribe/Unsubscribe, SubscribeAlarms/
// UnsubscribeAlarms) AND the failover's teardown + reconnect + replay. A subscribe is therefore either
// wholly before a failover (recorded, then replayed onto the new session) or wholly after it (on the new
// session) — never half on the dying session. Async-friendly (no thread block). Deliberately never disposed:
// async-only waits hold no kernel handle, and a failover still running at Dispose releases it afterwards.
private readonly SemaphoreSlim _subscriptionGate = new(1, 1);
// Track active data subscriptions for replay after failover
private readonly Dictionary<string, (NodeId NodeId, int IntervalMs, uint Handle)> _activeDataSubscriptions = new();
@@ -34,6 +35,15 @@ public sealed class OpcUaClientService : IOpcUaClientService
// run at a time. 0 = idle, 1 = failover in progress (Interlocked-managed).
private int _failoverInProgress;
// The connection epoch (review I1): ConnectAsync and DisconnectAsync each start a new one (under
// _subscriptionLock). A failover runs under the epoch it started in and abandons itself — disposing any session it
// opened, making no state transition — the moment the epoch moves, so a user Disconnect + Connect during a
// failover is never undone by it. A keep-alive from a previous connection's session cannot start one either.
private long _connectionEpoch;
/// <summary>The most recent keep-alive-triggered failover task (test seam: lets a test await it).</summary>
internal Task? LastFailover { get; private set; }
private readonly IApplicationConfigurationFactory _configFactory;
private readonly IEndpointDiscovery _endpointDiscovery;
@@ -99,6 +109,15 @@ public sealed class OpcUaClientService : IOpcUaClientService
ThrowIfDisposed();
settings.Validate();
// Overwriting a live (or reconnecting) session would leak it and orphan its subscriptions and keep-alive
// handler. The caller must disconnect first.
if (_state != ConnectionState.Disconnected || _session != null)
throw new InvalidOperationException(
$"Already {_state.ToString().ToLowerInvariant()}; call DisconnectAsync before connecting again.");
long epoch;
lock (_subscriptionLock) epoch = ++_connectionEpoch;
_settings = settings;
_allEndpointUrls = FailoverUrlParser.Parse(settings.EndpointUrl, settings.FailoverUrls);
_currentEndpointIndex = 0;
@@ -108,11 +127,11 @@ public sealed class OpcUaClientService : IOpcUaClientService
try
{
var session = await ConnectToEndpointAsync(settings, _allEndpointUrls[0], ct);
_session = session;
lock (_subscriptionLock) _session = session;
session.RegisterKeepAliveHandler(isGood =>
{
if (!isGood) _ = HandleKeepAliveFailureAsync();
if (!isGood) OnKeepAliveFailed(epoch);
});
CurrentConnectionInfo = BuildConnectionInfo(session);
@@ -133,6 +152,9 @@ public sealed class OpcUaClientService : IOpcUaClientService
if (_state == ConnectionState.Disconnected)
return;
// A new epoch first: a failover still connecting abandons itself instead of resurrecting the connection.
lock (_subscriptionLock) _connectionEpoch++;
var endpointUrl = _session?.EndpointUrl ?? _settings?.EndpointUrl ?? string.Empty;
// Snapshot the subscription adapter references under the lock so a concurrent
@@ -224,18 +246,15 @@ public sealed class OpcUaClientService : IOpcUaClientService
while (references.Count > 0)
{
// Child detection is lazy: an Object MAY have children and is confirmed when the caller expands or
// recurses into it. Probing each Object child with its own Browse made one level of N folders cost N + 1
// round trips, and a recursive subscribe over a 50k-node tree ~50k extra Browse calls.
foreach (var reference in references)
{
var childNodeId = ExpandedNodeId.ToNodeId(reference.NodeId, _session.NamespaceUris);
var hasChildren = reference.NodeClass == NodeClass.Object &&
await _session.HasChildrenAsync(childNodeId, ct);
results.Add(new BrowseResult(
reference.NodeId.ToString(),
reference.DisplayName?.Text ?? string.Empty,
reference.NodeClass.ToString(),
hasChildren));
}
reference.NodeClass == NodeClass.Object));
if (continuationPoint is not { Length: > 0 } pending) break;
(continuationPoint, references) = await _session.BrowseNextAsync(pending, ct);
@@ -251,20 +270,39 @@ public sealed class OpcUaClientService : IOpcUaClientService
ThrowIfNotConnected();
var nodeIdStr = nodeId.ToString();
lock (_subscriptionLock)
await _subscriptionGate.WaitAsync(ct);
try
{
if (_activeDataSubscriptions.ContainsKey(nodeIdStr))
return; // Already subscribed
// A failover may have run (and failed) while this call waited for the gate.
ThrowIfNotConnected();
ISubscriptionAdapter? subscription;
ISessionAdapter session;
lock (_subscriptionLock)
{
if (_activeDataSubscriptions.ContainsKey(nodeIdStr))
return; // Already subscribed
subscription = _dataSubscription;
session = _session!;
}
if (subscription == null)
{
subscription = await session.CreateSubscriptionAsync(intervalMs, ct);
lock (_subscriptionLock) _dataSubscription = subscription;
}
var handle = await subscription.AddDataChangeMonitoredItemAsync(
nodeId, intervalMs, OnDataChangeNotification, ct);
lock (_subscriptionLock)
{
_activeDataSubscriptions[nodeIdStr] = (nodeId, intervalMs, handle);
}
}
if (_dataSubscription == null) _dataSubscription = await _session!.CreateSubscriptionAsync(intervalMs, ct);
var handle = await _dataSubscription.AddDataChangeMonitoredItemAsync(
nodeId, intervalMs, OnDataChangeNotification, ct);
lock (_subscriptionLock)
finally
{
_activeDataSubscriptions[nodeIdStr] = (nodeId, intervalMs, handle);
_subscriptionGate.Release();
}
Logger.Debug("Subscribed to data changes on {NodeId}", nodeId);
@@ -276,18 +314,35 @@ public sealed class OpcUaClientService : IOpcUaClientService
ThrowIfDisposed();
var nodeIdStr = nodeId.ToString();
(NodeId NodeId, int IntervalMs, uint Handle) sub;
lock (_subscriptionLock)
await _subscriptionGate.WaitAsync(ct);
try
{
if (!_activeDataSubscriptions.TryGetValue(nodeIdStr, out sub))
return; // Not subscribed, safe to ignore
(NodeId NodeId, int IntervalMs, uint Handle) sub;
ISubscriptionAdapter? subscription;
lock (_subscriptionLock)
{
if (!_activeDataSubscriptions.TryGetValue(nodeIdStr, out sub))
return; // Not subscribed, safe to ignore
subscription = _dataSubscription;
}
try
{
if (subscription != null) await subscription.RemoveMonitoredItemAsync(sub.Handle, ct);
}
finally
{
// The caller asked to stop: drop the bookkeeping even when the server-side remove failed (a session
// that died under us), or a later failover would replay the item onto the new session (review m5).
lock (_subscriptionLock)
{
_activeDataSubscriptions.Remove(nodeIdStr);
}
}
}
if (_dataSubscription != null) await _dataSubscription.RemoveMonitoredItemAsync(sub.Handle, ct);
lock (_subscriptionLock)
finally
{
_activeDataSubscriptions.Remove(nodeIdStr);
_subscriptionGate.Release();
}
Logger.Debug("Unsubscribed from data changes on {NodeId}", nodeId);
@@ -303,17 +358,25 @@ public sealed class OpcUaClientService : IOpcUaClientService
// Serialise check-and-create under the semaphore: concurrent
// callers cannot both pass the null-check and create duplicate alarm subscriptions.
// The semaphore is async-friendly; the subscription I/O runs inside the critical section.
await _alarmSubscribeSemaphore.WaitAsync(ct);
await _subscriptionGate.WaitAsync(ct);
try
{
if (_alarmSubscription != null)
return; // Already subscribed to alarms
ThrowIfNotConnected();
ISessionAdapter session;
lock (_subscriptionLock)
{
if (_alarmSubscription != null)
return; // Already subscribed to alarms
session = _session!;
}
var monitorNode = sourceNodeId ?? ObjectIds.Server;
_alarmSubscription = await _session!.CreateSubscriptionAsync(intervalMs, ct);
var subscription = await session.CreateSubscriptionAsync(intervalMs, ct);
lock (_subscriptionLock) _alarmSubscription = subscription;
var filter = CreateAlarmEventFilter();
await _alarmSubscription.AddEventMonitoredItemAsync(
await subscription.AddEventMonitoredItemAsync(
monitorNode, intervalMs, filter, OnAlarmEventNotification, ct);
lock (_subscriptionLock)
@@ -325,7 +388,7 @@ public sealed class OpcUaClientService : IOpcUaClientService
}
finally
{
_alarmSubscribeSemaphore.Release();
_subscriptionGate.Release();
}
}
@@ -334,15 +397,27 @@ public sealed class OpcUaClientService : IOpcUaClientService
{
ThrowIfDisposed();
if (_alarmSubscription == null)
return;
await _alarmSubscription.DeleteAsync(ct);
_alarmSubscription = null;
lock (_subscriptionLock)
await _subscriptionGate.WaitAsync(ct);
try
{
_activeAlarmSubscription = null;
ISubscriptionAdapter? subscription;
lock (_subscriptionLock)
{
subscription = _alarmSubscription;
if (subscription == null) return;
}
await subscription.DeleteAsync(ct);
lock (_subscriptionLock)
{
_alarmSubscription = null;
_activeAlarmSubscription = null;
}
}
finally
{
_subscriptionGate.Release();
}
Logger.Debug("Unsubscribed from alarm events");
@@ -354,10 +429,12 @@ public sealed class OpcUaClientService : IOpcUaClientService
ThrowIfDisposed();
ThrowIfNotConnected();
if (_alarmSubscription == null)
ISubscriptionAdapter? subscription;
lock (_subscriptionLock) subscription = _alarmSubscription;
if (subscription == null)
throw new InvalidOperationException("No alarm subscription is active.");
await _alarmSubscription.ConditionRefreshAsync(ct);
await subscription.ConditionRefreshAsync(ct);
Logger.Debug("Condition refresh requested");
}
@@ -640,13 +717,16 @@ public sealed class OpcUaClientService : IOpcUaClientService
/// </summary>
public void Dispose()
{
if (_disposed) return;
_disposed = true;
lock (_subscriptionLock)
{
if (_disposed) return;
_disposed = true;
_connectionEpoch++; // a failover still running abandons itself
}
_dataSubscription?.Dispose();
_alarmSubscription?.Dispose();
_session?.Dispose();
_alarmSubscribeSemaphore.Dispose();
lock (_subscriptionLock)
{
@@ -688,19 +768,27 @@ public sealed class OpcUaClientService : IOpcUaClientService
ct);
}
private async Task HandleKeepAliveFailureAsync()
/// <summary>A bad keep-alive from the session of connection <paramref name="epoch"/>.</summary>
private void OnKeepAliveFailed(long epoch)
{
// Serialize failover: the OPC UA stack raises KeepAlive repeatedly
// while a session is down, so multiple bad keep-alives can fire before
// the first failover loop finishes. CompareExchange atomically claims
// the failover slot; a re-entrant call sees 1 and returns immediately,
// guaranteeing exactly one failover loop runs at a time.
// A late keep-alive from a previous connection's session is not about the current one.
if (!IsCurrentEpoch(epoch)) return;
// Serialize failover: the OPC UA stack raises KeepAlive repeatedly while a session is down, so several bad
// keep-alives can fire before the first failover loop finishes. CompareExchange claims the failover slot; a
// re-entrant call sees 1 and returns, so exactly one loop runs — and only the winner sets the test seam
// (review m8: a re-entrant call used to overwrite it with an already-completed no-op).
if (Interlocked.CompareExchange(ref _failoverInProgress, 1, 0) != 0)
return;
LastFailover = HandleKeepAliveFailureAsync(epoch);
}
private async Task HandleKeepAliveFailureAsync(long epoch)
{
try
{
await RunFailoverAsync();
await RunFailoverAsync(epoch);
}
finally
{
@@ -708,74 +796,136 @@ public sealed class OpcUaClientService : IOpcUaClientService
}
}
private async Task RunFailoverAsync()
private bool IsCurrentEpoch(long epoch)
{
lock (_subscriptionLock) return _connectionEpoch == epoch && !_disposed;
}
/// <summary>
/// A state transition made only while <paramref name="epoch"/> is still current (checked and applied under
/// <see cref="_subscriptionLock"/>, the event raised outside it).
/// </summary>
/// <returns><see langword="false"/> when the epoch has moved on (the caller must abandon).</returns>
private bool TransitionStateIfCurrent(long epoch, ConnectionState newState, string endpointUrl)
{
ConnectionState oldState;
lock (_subscriptionLock)
{
if (_connectionEpoch != epoch || _disposed) return false;
oldState = _state;
if (oldState == newState) return true;
_state = newState;
}
ConnectionStateChanged?.Invoke(this, new ConnectionStateChangedEventArgs(oldState, newState, endpointUrl));
return true;
}
private async Task RunFailoverAsync(long epoch)
{
if (_state == ConnectionState.Reconnecting || _state == ConnectionState.Disconnected)
return;
var oldEndpoint = _session?.EndpointUrl ?? string.Empty;
TransitionState(ConnectionState.Reconnecting, oldEndpoint);
var oldSession = _session;
var oldEndpoint = oldSession?.EndpointUrl ?? string.Empty;
if (!TransitionStateIfCurrent(epoch, ConnectionState.Reconnecting, oldEndpoint)) return;
Logger.Warning("Session lost on {EndpointUrl}. Attempting failover...", oldEndpoint);
// Close old session
if (_session != null)
// Dispose the dead session BEFORE taking the gate: an in-flight subscribe holding the gate is blocked on
// that session, and disposing it is what makes the call fail fast and release the gate.
if (oldSession != null)
{
try
{
_session.Dispose();
oldSession.Dispose();
}
catch
{
}
_session = null;
}
_dataSubscription = null;
_alarmSubscription = null;
if (_settings == null || _allEndpointUrls == null)
// The rest runs under the subscription gate (and its null-outs under _subscriptionLock): no subscribe can
// interleave with the teardown, the reconnect or the replay.
await _subscriptionGate.WaitAsync();
try
{
TransitionState(ConnectionState.Disconnected, oldEndpoint);
return;
}
// Try each endpoint
for (var attempt = 0; attempt < _allEndpointUrls.Length; attempt++)
{
_currentEndpointIndex = (_currentEndpointIndex + 1) % _allEndpointUrls.Length;
var url = _allEndpointUrls[_currentEndpointIndex];
try
// The user's settings / endpoint list as of THIS epoch: a Connect during the failover replaces the fields.
ConnectionSettings? settings;
string[]? endpoints;
lock (_subscriptionLock)
{
Logger.Information("Failover attempt to {EndpointUrl}", url);
var session = await ConnectToEndpointAsync(_settings, url, CancellationToken.None);
_session = session;
if (_connectionEpoch != epoch || _disposed) return; // the user disconnected / reconnected meanwhile
if (ReferenceEquals(_session, oldSession)) _session = null;
_dataSubscription = null;
_alarmSubscription = null;
settings = _settings;
endpoints = _allEndpointUrls;
}
session.RegisterKeepAliveHandler(isGood =>
{
if (!isGood) _ = HandleKeepAliveFailureAsync();
});
CurrentConnectionInfo = BuildConnectionInfo(session);
TransitionState(ConnectionState.Connected, url);
Logger.Information("Failover succeeded to {EndpointUrl}", url);
// Replay subscriptions
await ReplaySubscriptionsAsync();
if (settings == null || endpoints == null)
{
TransitionStateIfCurrent(epoch, ConnectionState.Disconnected, oldEndpoint);
return;
}
catch (Exception ex)
{
Logger.Warning(ex, "Failover to {EndpointUrl} failed", url);
}
}
Logger.Error("All failover endpoints unreachable");
TransitionState(ConnectionState.Disconnected, oldEndpoint);
// Try each endpoint
for (var attempt = 0; attempt < endpoints.Length; attempt++)
{
if (!IsCurrentEpoch(epoch)) return; // stop trying once the user has moved on (m5)
_currentEndpointIndex = (_currentEndpointIndex + 1) % endpoints.Length;
var url = endpoints[_currentEndpointIndex];
try
{
Logger.Information("Failover attempt to {EndpointUrl}", url);
var session = await ConnectToEndpointAsync(settings, url, CancellationToken.None);
// A Disconnect / Connect / Dispose that ran while this attempt was connecting wins: never
// resurrect the old connection or overwrite the user's new session. Checked and installed
// atomically against the epoch.
bool installed;
lock (_subscriptionLock)
{
installed = _connectionEpoch == epoch && !_disposed;
if (installed) _session = session;
}
if (!installed)
{
session.Dispose();
return;
}
session.RegisterKeepAliveHandler(isGood =>
{
if (!isGood) OnKeepAliveFailed(epoch);
});
CurrentConnectionInfo = BuildConnectionInfo(session);
if (!TransitionStateIfCurrent(epoch, ConnectionState.Connected, url)) return;
Logger.Information("Failover succeeded to {EndpointUrl}", url);
// Replay subscriptions
await ReplaySubscriptionsAsync(session);
return;
}
catch (Exception ex)
{
Logger.Warning(ex, "Failover to {EndpointUrl} failed", url);
}
}
if (TransitionStateIfCurrent(epoch, ConnectionState.Disconnected, oldEndpoint))
Logger.Error("All failover endpoints unreachable");
}
finally
{
_subscriptionGate.Release();
}
}
private async Task ReplaySubscriptionsAsync()
/// <summary>Re-creates the recorded subscriptions on <paramref name="session"/>. Runs under the subscription gate.</summary>
private async Task ReplaySubscriptionsAsync(ISessionAdapter session)
{
// Snapshot the bookkeeping state under the lock, then clear it so the
// replayed handles can be recorded fresh as each monitored item is
@@ -791,13 +941,17 @@ public sealed class OpcUaClientService : IOpcUaClientService
}
// Replay data subscriptions
ISubscriptionAdapter? dataSubscription = null;
foreach (var (nodeIdStr, (nodeId, intervalMs, _)) in subscriptions)
try
{
if (_dataSubscription == null)
_dataSubscription = await _session!.CreateSubscriptionAsync(intervalMs, CancellationToken.None);
if (dataSubscription == null)
{
dataSubscription = await session.CreateSubscriptionAsync(intervalMs, CancellationToken.None);
lock (_subscriptionLock) _dataSubscription = dataSubscription;
}
var handle = await _dataSubscription.AddDataChangeMonitoredItemAsync(
var handle = await dataSubscription.AddDataChangeMonitoredItemAsync(
nodeId, intervalMs, OnDataChangeNotification, CancellationToken.None);
lock (_subscriptionLock)
@@ -817,9 +971,10 @@ public sealed class OpcUaClientService : IOpcUaClientService
try
{
var monitorNode = sourceNodeId ?? ObjectIds.Server;
_alarmSubscription = await _session!.CreateSubscriptionAsync(intervalMs, CancellationToken.None);
var replayedAlarms = await session.CreateSubscriptionAsync(intervalMs, CancellationToken.None);
lock (_subscriptionLock) _alarmSubscription = replayedAlarms;
var filter = CreateAlarmEventFilter();
await _alarmSubscription.AddEventMonitoredItemAsync(
await replayedAlarms.AddEventMonitoredItemAsync(
monitorNode, intervalMs, filter, OnAlarmEventNotification, CancellationToken.None);
lock (_subscriptionLock)
@@ -937,9 +1092,13 @@ public sealed class OpcUaClientService : IOpcUaClientService
private void TransitionState(ConnectionState newState, string endpointUrl)
{
var oldState = _state;
if (oldState == newState) return;
_state = newState;
ConnectionState oldState;
lock (_subscriptionLock)
{
oldState = _state;
if (oldState == newState) return;
_state = newState;
}
ConnectionStateChanged?.Invoke(this, new ConnectionStateChangedEventArgs(oldState, newState, endpointUrl));
}
@@ -43,23 +43,9 @@ public partial class HistoryViewModel : ObservableObject
_dispatcher = dispatcher;
}
/// <summary>Available aggregate types (null means "Raw").</summary>
/// <summary>Available aggregate types (null means "Raw"): every client aggregate, which is the served set.</summary>
public IReadOnlyList<AggregateType?> AggregateTypes { get; } =
[
null,
AggregateType.Average,
AggregateType.Minimum,
AggregateType.Maximum,
AggregateType.Count,
AggregateType.Start,
AggregateType.End,
AggregateType.StandardDeviation,
AggregateType.TimeAverage,
AggregateType.TimeAverage2,
AggregateType.Total,
AggregateType.Total2,
AggregateType.Interpolative
];
[null, .. Enum.GetValues<AggregateType>().Select(a => (AggregateType?)a)];
/// <summary>Gets a value indicating whether an aggregate read is selected.</summary>
public bool IsAggregateRead => SelectedAggregateType != null;
@@ -1,4 +1,5 @@
using System.Collections.ObjectModel;
using System.Collections.Specialized;
using CommunityToolkit.Mvvm.ComponentModel;
using CommunityToolkit.Mvvm.Input;
using Opc.Ua;
@@ -19,6 +20,11 @@ public partial class SubscriptionsViewModel : ObservableObject
private readonly IUiDispatcher _dispatcher;
private readonly IOpcUaClientService _service;
// NodeId -> its rows, kept in step with ActiveSubscriptions by OnActiveSubscriptionsChanged, so a notification is
// one lookup instead of a scan of every row on the UI thread (2 000 items at 1 Hz was 4M string compares/s).
// Touched only on the UI thread, like the collection itself.
private readonly Dictionary<string, List<SubscriptionItemViewModel>> _rowsByNodeId = new(StringComparer.Ordinal);
/// <summary>
/// Last user-visible status message — set when a subscribe/unsubscribe operation fails so the
/// shell can surface the diagnostic instead of silently dropping the error. Cleared on success.
@@ -49,9 +55,13 @@ public partial class SubscriptionsViewModel : ObservableObject
{
_service = service;
_dispatcher = dispatcher;
ActiveSubscriptions.CollectionChanged += OnActiveSubscriptionsChanged;
_service.DataChanged += OnDataChanged;
}
/// <summary>The number of distinct NodeIds in the notification index (test seam).</summary>
internal int IndexedNodeCount => _rowsByNodeId.Count;
/// <summary>Currently active subscriptions.</summary>
public ObservableCollection<SubscriptionItemViewModel> ActiveSubscriptions { get; } = [];
@@ -62,16 +72,42 @@ public partial class SubscriptionsViewModel : ObservableObject
{
_dispatcher.Post(() =>
{
foreach (var item in ActiveSubscriptions)
if (item.NodeId == e.NodeId)
{
item.Value = Helpers.ValueFormatter.Format(e.Value.Value);
item.Status = Helpers.StatusCodeFormatter.Format(e.Value.StatusCode);
item.Timestamp = e.Value.SourceTimestamp.ToString("O");
}
if (!_rowsByNodeId.TryGetValue(e.NodeId, out var rows)) return;
foreach (var item in rows)
{
item.Value = Helpers.ValueFormatter.Format(e.Value.Value);
item.Status = Helpers.StatusCodeFormatter.Format(e.Value.StatusCode);
item.Timestamp = e.Value.SourceTimestamp.ToString("O");
}
});
}
private void OnActiveSubscriptionsChanged(object? sender, NotifyCollectionChangedEventArgs e)
{
if (e.Action == NotifyCollectionChangedAction.Reset)
{
_rowsByNodeId.Clear();
foreach (var item in ActiveSubscriptions) Index(item);
return;
}
if (e.OldItems != null)
foreach (SubscriptionItemViewModel item in e.OldItems)
if (_rowsByNodeId.TryGetValue(item.NodeId, out var rows) && rows.Remove(item) && rows.Count == 0)
_rowsByNodeId.Remove(item.NodeId);
if (e.NewItems != null)
foreach (SubscriptionItemViewModel item in e.NewItems)
Index(item);
}
private void Index(SubscriptionItemViewModel item)
{
if (!_rowsByNodeId.TryGetValue(item.NodeId, out var rows))
_rowsByNodeId[item.NodeId] = rows = [];
rows.Add(item);
}
private bool CanAddSubscription()
{
return IsConnected && !string.IsNullOrWhiteSpace(NewNodeIdText);
@@ -149,7 +185,7 @@ public partial class SubscriptionsViewModel : ObservableObject
if (!IsConnected || string.IsNullOrWhiteSpace(nodeIdStr)) return;
// Skip if already subscribed
if (ActiveSubscriptions.Any(s => s.NodeId == nodeIdStr)) return;
if (_rowsByNodeId.ContainsKey(nodeIdStr)) return;
try
{
@@ -44,17 +44,21 @@ public sealed class ProbeCommand : AbCipCommandBase
await using var driver = new AbCipDriver(options, DriverInstanceId);
try
{
await driver.InitializeAsync("{}", ct);
var snapshot = await driver.ReadAsync(["__probe"], ct);
var health = driver.GetHealth();
// Ctrl-C prints "Cancelled." instead of an OperationCanceledException stack trace (review 07 U7).
await RunCancellableAsync(console, ct, async () =>
{
await driver.InitializeAsync("{}", ct);
var snapshot = await driver.ReadAsync(["__probe"], ct);
var health = driver.GetHealth();
await console.Output.WriteLineAsync($"Gateway: {Gateway}");
await console.Output.WriteLineAsync($"Family: {Family}");
await console.Output.WriteLineAsync($"Health: {health.State}");
if (health.LastError is { } err)
await console.Output.WriteLineAsync($"Last error: {err}");
await console.Output.WriteLineAsync();
await console.Output.WriteLineAsync(SnapshotFormatter.Format(TagPath, snapshot[0]));
await console.Output.WriteLineAsync($"Gateway: {Gateway}");
await console.Output.WriteLineAsync($"Family: {Family}");
await console.Output.WriteLineAsync($"Health: {health.State}");
if (health.LastError is { } err)
await console.Output.WriteLineAsync($"Last error: {err}");
await console.Output.WriteLineAsync();
await console.Output.WriteLineAsync(SnapshotFormatter.Format(TagPath, snapshot[0]));
});
}
finally
{
@@ -45,9 +45,13 @@ public sealed class ReadCommand : AbCipCommandBase
await using var driver = new AbCipDriver(options, DriverInstanceId);
try
{
await driver.InitializeAsync("{}", ct);
var snapshot = await driver.ReadAsync([tagName], ct);
await console.Output.WriteLineAsync(SnapshotFormatter.Format(TagPath, snapshot[0]));
// Ctrl-C prints "Cancelled." instead of an OperationCanceledException stack trace (review 07 U7).
await RunCancellableAsync(console, ct, async () =>
{
await driver.InitializeAsync("{}", ct);
var snapshot = await driver.ReadAsync([tagName], ct);
await console.Output.WriteLineAsync(SnapshotFormatter.Format(TagPath, snapshot[0]));
});
}
finally
{
@@ -50,23 +50,22 @@ public sealed class SubscribeCommand : AbCipCommandBase
await using var driver = new AbCipDriver(options, DriverInstanceId);
ISubscriptionHandle? handle = null;
// The poll engine raises OnDataChange on a background thread: serialise its lines against each other and
// against this thread's own, and never let a failed console write fault the poll loop (review 07 U7).
var writeLock = new object();
try
{
await driver.InitializeAsync("{}", ct);
await console.Output.WriteLineAsync(
$"Subscribed to {TagPath} @ {IntervalMs}ms. Ctrl+C to stop.");
driver.OnDataChange += (_, e) =>
{
var line = $"[{DateTime.UtcNow:HH:mm:ss.fff}] " +
$"{e.FullReference} = {SnapshotFormatter.FormatValue(e.Snapshot.Value)} " +
$"({SnapshotFormatter.FormatStatus(e.Snapshot.StatusCode)})";
console.Output.WriteLine(line);
};
driver.OnDataChange += CreateChangeLineWriter(console.Output, writeLock);
handle = await driver.SubscribeAsync([tagName], TimeSpan.FromMilliseconds(IntervalMs), ct);
lock (writeLock)
{
console.Output.WriteLine($"Subscribed to {TagPath} @ {IntervalMs}ms. Ctrl+C to stop.");
}
try
{
await Task.Delay(System.Threading.Timeout.InfiniteTimeSpan, ct);
@@ -76,6 +75,10 @@ public sealed class SubscribeCommand : AbCipCommandBase
// Expected on Ctrl+C.
}
}
catch (OperationCanceledException) when (ct.IsCancellationRequested)
{
// Ctrl+C while still connecting/subscribing: a clean exit, not a stack trace (review 07 U7).
}
finally
{
if (handle is not null)
@@ -57,9 +57,13 @@ public sealed class WriteCommand : AbCipCommandBase
await using var driver = new AbCipDriver(options, DriverInstanceId);
try
{
await driver.InitializeAsync("{}", ct);
var results = await driver.WriteAsync([new WriteRequest(tagName, parsed)], ct);
await console.Output.WriteLineAsync(SnapshotFormatter.FormatWrite(TagPath, results[0]));
// Ctrl-C prints "Cancelled." instead of an OperationCanceledException stack trace (review 07 U7).
await RunCancellableAsync(console, ct, async () =>
{
await driver.InitializeAsync("{}", ct);
var results = await driver.WriteAsync([new WriteRequest(tagName, parsed)], ct);
await console.Output.WriteLineAsync(SnapshotFormatter.FormatWrite(TagPath, results[0]));
});
}
finally
{
@@ -32,27 +32,6 @@ public abstract class AbLegacyCommandBase : DriverCommandBase
"LogixPccc unverified).")]
public AbLegacyCliTransport Transport { get; init; } = AbLegacyCliTransport.Default;
/// <summary>
/// Runs a one-shot command's driver work so a Ctrl-C (cancellation of <paramref name="ct"/>) prints
/// <c>Cancelled.</c> instead of an unhandled <see cref="OperationCanceledException"/> stack trace (review 07 U7).
/// Any other exception — and an OCE the operator did not ask for — still propagates.
/// </summary>
/// <param name="console">The CLI console.</param>
/// <param name="ct">The console's Ctrl-C token.</param>
/// <param name="body">The command body.</param>
/// <returns>A task that completes when the body has finished or was cancelled.</returns>
internal static async ValueTask RunCancellableAsync(CliFx.Infrastructure.IConsole console, CancellationToken ct, Func<Task> body)
{
try
{
await body();
}
catch (OperationCanceledException) when (ct.IsCancellationRequested)
{
await console.Error.WriteLineAsync("Cancelled.");
}
}
/// <summary>Gets the per-operation timeout in milliseconds.</summary>
[CommandOption("timeout-ms", Description = "Per-operation timeout in ms (default 5000).")]
public int TimeoutMs { get; init; } = 5000;
@@ -79,5 +79,61 @@ public abstract class DriverCommandBase : ICommand
/// </summary>
protected static void FlushLogging() => Log.CloseAndFlush();
/// <summary>
/// Runs a one-shot command's driver work so a Ctrl-C (cancellation of <paramref name="ct"/>) prints
/// <c>Cancelled.</c> instead of an unhandled <see cref="OperationCanceledException"/> stack trace (review 07 U7).
/// Any other exception — and an OCE the operator did not ask for — still propagates.
/// </summary>
/// <param name="console">The CLI console.</param>
/// <param name="ct">The console's Ctrl-C token.</param>
/// <param name="body">The command body.</param>
/// <returns>A task that completes when the body has finished or was cancelled.</returns>
public static async ValueTask RunCancellableAsync(IConsole console, CancellationToken ct, Func<Task> body)
{
try
{
await body();
}
catch (OperationCanceledException) when (ct.IsCancellationRequested)
{
await console.Error.WriteLineAsync("Cancelled.");
}
}
/// <summary>
/// Builds the <c>OnDataChange</c> handler a <c>subscribe</c> command attaches: one
/// <c>[HH:mm:ss.fff] ref = value (status)</c> line per change. Writes are serialised on
/// <paramref name="writeLock"/> (the poll engine raises from a background thread, concurrently with the
/// command thread's own lines), and a failing console write (closed pipe, redirected stream error) is logged
/// and swallowed so it cannot fault the driver's poll loop (review 07 U7).
/// </summary>
/// <param name="output">The console output writer.</param>
/// <param name="writeLock">The lock every console write of the command takes.</param>
/// <returns>The event handler.</returns>
public static EventHandler<ZB.MOM.WW.OtOpcUa.Core.Abstractions.DataChangeEventArgs> CreateChangeLineWriter(
TextWriter output, object writeLock)
{
ArgumentNullException.ThrowIfNull(output);
ArgumentNullException.ThrowIfNull(writeLock);
return (_, e) =>
{
try
{
var line = $"[{DateTime.UtcNow:HH:mm:ss.fff}] " +
$"{e.FullReference} = {SnapshotFormatter.FormatValue(e.Snapshot.Value)} " +
$"({SnapshotFormatter.FormatStatus(e.Snapshot.StatusCode)})";
lock (writeLock)
{
output.WriteLine(line);
}
}
catch (Exception ex)
{
Log.Logger.Warning(ex, "subscribe: console write failed for {Tag}; continuing the poll loop.",
e.FullReference);
}
};
}
private bool _loggingConfigured;
}
@@ -101,7 +101,11 @@ public static class SnapshotFormatter
return sb.ToString().TrimEnd();
}
/// <summary>Formats a value for console output, handling null, bool, string, and formattable types.</summary>
/// <summary>
/// Formats a value for console output, handling null, bool, string, formattable and array/list types. An
/// array renders its elements (<c>[1, 2, 3]</c>, each formatted as a scalar) rather than its CLR type name
/// (<c>System.Int32[]</c>).
/// </summary>
/// <param name="value">The value to format.</param>
/// <returns>A formatted string representation of the value.</returns>
public static string FormatValue(object? value) => value switch
@@ -110,9 +114,23 @@ public static class SnapshotFormatter
bool b => b ? "true" : "false",
string s => $"\"{s}\"",
IFormattable f => f.ToString(null, CultureInfo.InvariantCulture),
System.Collections.IEnumerable items => FormatSequence(items),
_ => value.ToString() ?? "<null>",
};
private static string FormatSequence(System.Collections.IEnumerable items)
{
var sb = new System.Text.StringBuilder("[");
var first = true;
foreach (var item in items)
{
if (!first) sb.Append(", ");
sb.Append(FormatValue(item));
first = false;
}
return sb.Append(']').ToString();
}
/// <summary>Formats an OPC UA status code as a hexadecimal string with named severity classification.</summary>
/// <param name="statusCode">The OPC UA status code to format.</param>
/// <returns>A formatted status string like "0x00000000 (Good)" or "0x80050000 (BadCommunicationError)".</returns>
@@ -0,0 +1,12 @@
namespace ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport;
/// <summary>
/// An <see cref="AbTransportException"/> whose status came OFF THE WIRE: the device (or the bridge's Execute PCCC
/// object) replied with a non-zero CIP envelope status or PCCC STS. It lets a driver tell a refusal the device
/// ANSWERED from the same <see cref="AbStatus"/> raised locally before anything was sent — most importantly
/// <see cref="AbStatus.Unsupported"/>, which a native runtime also throws for operations it refuses pre-wire
/// (review lane K I2).
/// </summary>
/// <param name="status">The status mapped from the reply.</param>
/// <param name="message">The exception message.</param>
public sealed class AbDeviceReplyException(AbStatus status, string message) : AbTransportException(status, message);
@@ -1,39 +1,81 @@
namespace ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport;
/// <summary>
/// Maps wire statuses (CIP general/extended, PCCC STS/EXT STS) to the transport-neutral <see cref="AbStatus"/> the
/// drivers classify. The class an <see cref="AbStatus"/> lands in is load-bearing for driver health (#527/#737/#738):
/// an ANSWERED refusal (NotFound / NotAllowed / OutOfBounds / TooLarge / TooSmall / TypeMismatch /
/// DeviceStateConflict, and for AbCip Unsupported) proves the device replied; <see cref="AbStatus.BadConnection"/>
/// is the no-reply comms class; <see cref="AbStatus.BadReply"/> / <see cref="AbStatus.Partial"/> are a reply that
/// cannot be classified. Every code not named below is deliberately <see cref="AbStatus.BadReply"/>.
/// </summary>
public static class AbStatusCodes
{
/// <summary>Maps a CIP general status (and optional extended status words) to an <see cref="AbStatus"/>.</summary>
/// <param name="general">The CIP general status byte.</param>
/// <param name="extended">The extended status words, if any.</param>
/// <returns>The mapped status.</returns>
/// <remarks>
/// 0x01 (connection failure, incl. a routing hop's unconnected-send timeout) and 0x07 (connection lost) stay
/// <see cref="AbStatus.BadReply"/> on purpose: a bridge reports a dead END device that way, so they are neither an
/// answer nor proof of no reply (AbLegacy #738 "opaque"). A Forward Open refused with one of the request-level
/// codes (0x1C / 0x20 / 0xFF-0x2104) stays a connection failure — see
/// <c>ConnectionManagerServices.ParseForwardOpenReply</c>.
/// </remarks>
public static AbStatus FromCip(byte general, ReadOnlySpan<ushort> extended) => general switch
{
0x00 or 0x0B => AbStatus.Ok,
0x04 or 0x05 or 0x16 => AbStatus.NotFound,
0x06 => AbStatus.Partial,
0x08 => AbStatus.Unsupported,
0x0A => AbStatus.OutOfBounds,
0x0C or 0x10 => AbStatus.DeviceStateConflict,
0x0E or 0x0F => AbStatus.NotAllowed,
0x13 => AbStatus.TooSmall,
0x15 => AbStatus.TooLarge,
0xFF when extended.Length > 0 && extended[0] == 0x2105 => AbStatus.OutOfBounds,
0xFF when extended.Length > 0 && extended[0] == 0x2107 => AbStatus.TypeMismatch,
0x00 or 0x0B => AbStatus.Ok, // success / already in requested mode
0x04 or 0x05 or 0x16 => AbStatus.NotFound, // path segment error / path unknown / object does not exist
0x06 => AbStatus.Partial, // partial transfer (fragmented read continues)
0x08 => AbStatus.Unsupported, // service not supported
0x0A => AbStatus.OutOfBounds, // attribute list error
0x0C or 0x10 => AbStatus.DeviceStateConflict, // object state conflict / device state conflict
0x0E or 0x0F => AbStatus.NotAllowed, // attribute not settable / privilege violation
0x13 => AbStatus.TooSmall, // not enough data
0x15 => AbStatus.TooLarge, // too much data
// Lane K F1 (#737): the controller answered and refused this one request — not a garbled reply, so not a
// comms fault that degrades the driver and evicts the runtime.
0x1C => AbStatus.Unsupported, // missing attribute list entry data
0x20 => AbStatus.Unsupported, // invalid parameter
0xFF when extended.Length > 0 && extended[0] == 0x2104 => AbStatus.OutOfBounds, // offset beyond end of tag
0xFF when extended.Length > 0 && extended[0] == 0x2105 => AbStatus.OutOfBounds, // beyond end of the object
0xFF when extended.Length > 0 && extended[0] == 0x2107 => AbStatus.TypeMismatch, // data type mismatch
_ => AbStatus.BadReply,
};
/// <summary>
/// True for the CIP statuses Lane K F1 moved from <see cref="AbStatus.BadReply"/> to a request-level refusal.
/// A Forward Open refused with one of them is still a connection failure.
/// </summary>
/// <param name="general">The CIP general status byte.</param>
/// <param name="extended">The extended status words, if any.</param>
/// <returns><see langword="true"/> for 0x1C, 0x20 and 0xFF/0x2104.</returns>
internal static bool IsRequestLevelRefusal(byte general, ReadOnlySpan<ushort> extended) =>
general is 0x1C or 0x20 || (general == 0xFF && extended.Length > 0 && extended[0] == 0x2104);
/// <summary>Maps a PCCC status byte (and optional extended status) to an <see cref="AbStatus"/>.</summary>
/// <param name="sts">The PCCC STS byte.</param>
/// <param name="extSts">The extended status byte, when present.</param>
/// <returns>The mapped status.</returns>
/// <remarks>
/// Per the DF1/PCCC STS table (1770-6.5.16). Lane K F3 (AbLegacy F8, review 07 r0 I4): 0x20, 0x30 and 0x90 are
/// reported by the HOST or a BRIDGE (a DHRIO, a 1761-NET-ENI) when the END device cannot be reached, so they are
/// the no-reply comms class. Mapping them to an answered refusal made a dead DH+/DH-485 node behind a bridge count
/// as reachable forever — no fail-fast backoff, no comms-loss watchdog.
/// </remarks>
public static AbStatus FromPccc(byte sts, byte? extSts) => sts switch
{
0x00 => AbStatus.Ok,
0x10 => AbStatus.Unsupported,
0x20 => AbStatus.NotFound,
0x30 => AbStatus.NotAllowed,
0x40 or 0x50 => AbStatus.DeviceStateConflict,
0xF0 when extSts is 0x06 or 0x07 => AbStatus.NotFound,
_ => AbStatus.BadReply,
0x10 => AbStatus.Unsupported, // illegal command or format
0x20 => AbStatus.BadConnection, // host has a problem and will not communicate
0x30 => AbStatus.BadConnection, // remote node host missing, disconnected or shut down
0x40 => AbStatus.DeviceStateConflict, // host could not complete: hardware fault
0x50 => AbStatus.NotFound, // addressing problem or memory protect rungs
0x60 => AbStatus.NotAllowed, // function not allowed due to command protection
0x70 => AbStatus.DeviceStateConflict, // processor is in Program mode
0x90 => AbStatus.BadConnection, // remote node cannot buffer command
0xB0 => AbStatus.DeviceStateConflict, // remote node problem due to download
0xF0 when extSts is 0x06 => AbStatus.NotFound, // EXT: address does not point to something usable
0xF0 when extSts is 0x07 => AbStatus.OutOfBounds, // EXT: file is wrong size
_ => AbStatus.BadReply, // 0x80, 0xA0, 0xC0, other EXT STS: unclassified
};
}
@@ -85,8 +85,15 @@ public static class ConnectionManagerServices
public static ForwardOpenReply ParseForwardOpenReply(CipReply reply)
{
if (reply.GeneralStatus != 0)
throw new ForwardOpenRefusedException(reply.Status == AbStatus.BadReply ? AbStatus.BadConnection : reply.Status,
reply.GeneralStatus, reply.ExtendedStatus);
{
// An unclassified refusal, or one of the request-level codes AbStatusCodes maps to a per-request refusal
// for TAG services (0x1C / 0x20 / 0xFF-0x2104), is a connection failure here: no tag can be served.
var status = reply.Status == AbStatus.BadReply
|| AbStatusCodes.IsRequestLevelRefusal(reply.GeneralStatus, reply.ExtendedStatus)
? AbStatus.BadConnection
: reply.Status;
throw new ForwardOpenRefusedException(status, reply.GeneralStatus, reply.ExtendedStatus);
}
var r = new CipReader(reply.Data.Span);
var ot = r.U32(); var to = r.U32(); r.U16(); r.U16(); r.U32();
return new ForwardOpenReply(ot, to, r.U32(), r.U32());
@@ -47,6 +47,10 @@ public sealed class EncapsulationClient : IAsyncDisposable
private readonly SemaphoreSlim _gate = new(1, 1);
private long _ctx;
private ushort _seq; // connected sequence count; only touched under _gate
// R07:L5: the 24-byte header of the frame being read. Frames are read only by RunExchangeAsync, which holds _gate
// for the whole exchange, so one buffer per session serves every read (it used to be a fresh array per reply).
private readonly byte[] _head = new byte[EncapsulationHeader.Size];
private volatile bool _faulted;
private int _disposed;
@@ -282,11 +286,12 @@ public sealed class EncapsulationClient : IAsyncDisposable
private async Task<byte[]> ReadFrameAsync(CancellationToken ct)
{
var head = new byte[EncapsulationHeader.Size];
await _stream.ReadExactlyAsync(head, ct).ConfigureAwait(false);
var len = head[2] | (head[3] << 8);
// Only called under _gate (RunExchangeAsync), so the shared header buffer is never read concurrently. The frame
// itself is allocated exactly: the matched reply's CIP payload is returned as a slice of it and outlives the call.
await _stream.ReadExactlyAsync(_head, ct).ConfigureAwait(false);
var len = _head[2] | (_head[3] << 8);
var frame = new byte[EncapsulationHeader.Size + len];
head.CopyTo(frame, 0);
_head.CopyTo(frame, 0);
await _stream.ReadExactlyAsync(frame.AsMemory(EncapsulationHeader.Size), ct).ConfigureAwait(false);
return frame;
}
@@ -1,3 +1,4 @@
using System.Buffers;
using ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport.Cip;
namespace ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport.Logix;
@@ -52,34 +53,61 @@ public sealed class LogixTagClient(RequestScheduler scheduler, ICipChannel chann
var reply = await _scheduler.SendAsync(LogixServices.ReadTagFragmented(path, elements, 0), ct,
expectedReplyBytes: ExpectedReadReplyBytes(elements, elementBytes, 0)).ConfigureAwait(false);
var (type, handle, first) = LogixServices.ParseReadReply(reply); // throws on any status but 0x00/0x06
var data = new List<byte>(first.Length);
data.AddRange(first.Span);
var lastChunk = first.Length;
while (reply.GeneralStatus == StatusPartial)
// R07:L5: the common single-reply read is one copy of the reply data (it used to go through a List<byte> and a
// second ToArray); a fragmented read reassembles in a pooled buffer and copies out once at the end.
if (reply.GeneralStatus != StatusPartial) return (type, handle, first.ToArray());
var data = ArrayPool<byte>.Shared.Rent(Math.Max(first.Length * 4, 1024));
var count = 0;
try
{
if (lastChunk == 0)
throw new AbTransportException(AbStatus.BadReply, "Partial read reply carried no data; the fragment loop cannot progress.");
reply = await _scheduler.SendAsync(
LogixServices.ReadTagFragmented(path, elements, (uint)data.Count), ct,
expectedReplyBytes: ExpectedReadReplyBytes(elements, elementBytes, data.Count)).ConfigureAwait(false);
var (fragmentType, fragmentHandle, chunk) = LogixServices.ParseReadReply(reply);
if (fragmentType != type)
throw new AbTransportException(AbStatus.BadReply,
$"Read fragment type 0x{fragmentType:X4} differs from the first reply's 0x{type:X4}.");
// A mid-read change of the structure handle means the tag's type changed under us (a
// download / online edit); stitching the halves would yield a value of neither type.
if (fragmentHandle != handle)
throw new AbTransportException(AbStatus.BadReply,
$"Read fragment structure handle {FormatHandle(fragmentHandle)} differs from the first reply's {FormatHandle(handle)}; the tag changed mid-read.");
data.AddRange(chunk.Span);
lastChunk = chunk.Length;
if (data.Count > MaxReadBytes)
throw new AbTransportException(AbStatus.TooLarge,
$"Fragmented read exceeded {MaxReadBytes} bytes; the controller kept answering Partial.");
}
Append(ref data, ref count, first.Span);
var lastChunk = first.Length;
return (type, handle, data.ToArray());
while (reply.GeneralStatus == StatusPartial)
{
if (lastChunk == 0)
throw new AbTransportException(AbStatus.BadReply, "Partial read reply carried no data; the fragment loop cannot progress.");
reply = await _scheduler.SendAsync(
LogixServices.ReadTagFragmented(path, elements, (uint)count), ct,
expectedReplyBytes: ExpectedReadReplyBytes(elements, elementBytes, count)).ConfigureAwait(false);
var (fragmentType, fragmentHandle, chunk) = LogixServices.ParseReadReply(reply);
if (fragmentType != type)
throw new AbTransportException(AbStatus.BadReply,
$"Read fragment type 0x{fragmentType:X4} differs from the first reply's 0x{type:X4}.");
// A mid-read change of the structure handle means the tag's type changed under us (a
// download / online edit); stitching the halves would yield a value of neither type.
if (fragmentHandle != handle)
throw new AbTransportException(AbStatus.BadReply,
$"Read fragment structure handle {FormatHandle(fragmentHandle)} differs from the first reply's {FormatHandle(handle)}; the tag changed mid-read.");
Append(ref data, ref count, chunk.Span);
lastChunk = chunk.Length;
if (count > MaxReadBytes)
throw new AbTransportException(AbStatus.TooLarge,
$"Fragmented read exceeded {MaxReadBytes} bytes; the controller kept answering Partial.");
}
return (type, handle, data.AsSpan(0, count).ToArray());
}
finally
{
ArrayPool<byte>.Shared.Return(data);
}
}
/// <summary>Appends <paramref name="chunk"/> to a pooled buffer, growing it (rent bigger, copy, return) as needed.</summary>
private static void Append(ref byte[] buffer, ref int count, ReadOnlySpan<byte> chunk)
{
if (count + chunk.Length > buffer.Length)
{
var bigger = ArrayPool<byte>.Shared.Rent(Math.Max(buffer.Length * 2, count + chunk.Length));
buffer.AsSpan(0, count).CopyTo(bigger);
ArrayPool<byte>.Shared.Return(buffer);
buffer = bigger;
}
chunk.CopyTo(buffer.AsSpan(count));
count += chunk.Length;
}
private static string FormatHandle(ushort? handle) => handle is { } h ? $"0x{h:X4}" : "(none)";
@@ -113,7 +113,7 @@ public static class PcccServices
public static ReadOnlyMemory<byte> ParseReply(CipReply reply, ushort expectedTns, byte[]? expectedRequestorId = null)
{
if (reply.GeneralStatus != 0)
throw new AbTransportException(reply.Status, $"Execute PCCC CIP status 0x{reply.GeneralStatus:X2}.");
throw new AbDeviceReplyException(reply.Status, $"Execute PCCC CIP status 0x{reply.GeneralStatus:X2}.");
var r = new CipReader(reply.Data.Span);
var idLen = r.U8();
if (idLen < 1) throw new AbTransportException(AbStatus.BadReply, "Empty requestor id in PCCC reply.");
@@ -131,7 +131,7 @@ public static class PcccServices
throw new AbTransportException(AbStatus.BadReply, $"PCCC TNS {tns} != {expectedTns}.");
byte? ext = sts == 0xF0 ? r.U8() : null;
if (sts != 0)
throw new AbTransportException(AbStatusCodes.FromPccc(sts, ext),
throw new AbDeviceReplyException(AbStatusCodes.FromPccc(sts, ext),
$"PCCC STS 0x{sts:X2}{(ext is { } e ? $" EXT 0x{e:X2}" : "")}.");
return reply.Data[r.Position..];
}
@@ -1,17 +1,38 @@
using System.Buffers;
using System.Buffers.Binary;
namespace ZB.MOM.WW.OtOpcUa.Driver.Ab.Transport.Wire;
/// <summary>Growable little-endian writer for CIP / EIP frames.</summary>
/// <remarks>
/// R07:L5: the working buffer is rented from <see cref="ArrayPool{T}.Shared"/> (a 256-byte array per request used
/// to be allocated and thrown away) and handed back by <see cref="ToArray"/>, which therefore COMPLETES the writer:
/// the result is the caller's own array, a second <see cref="ToArray"/> returns another copy of it, and any further
/// write throws <see cref="InvalidOperationException"/> (the buffer belongs to the pool again). A writer abandoned
/// before <see cref="ToArray"/> (a builder that threw) simply leaves its buffer to the GC.
/// </remarks>
public sealed class CipWriter
{
private byte[] _buf = new byte[256];
private const int InitialCapacity = 256;
private byte[]? _buf = ArrayPool<byte>.Shared.Rent(InitialCapacity);
private byte[]? _result;
/// <summary>Gets the number of bytes written so far.</summary>
public int Length { get; private set; }
private byte[] Buffer => _buf ?? throw new InvalidOperationException(
"This CipWriter was completed by ToArray(); its buffer has been returned to the pool.");
private Span<byte> Take(int n)
{
if (Length + n > _buf.Length) Array.Resize(ref _buf, Math.Max(_buf.Length * 2, Length + n));
var s = _buf.AsSpan(Length, n);
var buf = Buffer;
if (Length + n > buf.Length)
{
var bigger = ArrayPool<byte>.Shared.Rent(Math.Max(buf.Length * 2, Length + n));
buf.AsSpan(0, Length).CopyTo(bigger);
ArrayPool<byte>.Shared.Return(buf);
_buf = buf = bigger;
}
var s = buf.AsSpan(Length, n);
Length += n;
return s;
}
@@ -45,14 +66,27 @@ public sealed class CipWriter
/// <param name="v">The replacement value.</param>
/// <exception cref="ArgumentOutOfRangeException">The two bytes at <paramref name="offset"/> are not already
/// written (an offset in the spare buffer capacity would otherwise be patched silently and lost).</exception>
/// <exception cref="InvalidOperationException">The writer was completed by <see cref="ToArray"/>.</exception>
public void PatchU16(int offset, ushort v)
{
var buf = Buffer;
if (offset < 0 || offset > Length - 2)
throw new ArgumentOutOfRangeException(nameof(offset), offset, $"Cannot patch 2 bytes at {offset}: only {Length} bytes written.");
BinaryPrimitives.WriteUInt16LittleEndian(_buf.AsSpan(offset, 2), v);
BinaryPrimitives.WriteUInt16LittleEndian(buf.AsSpan(offset, 2), v);
}
/// <summary>Copies the written bytes to a new array.</summary>
/// <returns>The bytes written so far.</returns>
public byte[] ToArray() => _buf.AsSpan(0, Length).ToArray();
/// <summary>
/// Copies the written bytes to a new array and returns the working buffer to the pool, completing the writer
/// (see the remarks on <see cref="CipWriter"/>).
/// </summary>
/// <returns>The bytes written, in an array the caller owns.</returns>
public byte[] ToArray()
{
if (_result is { } done) return (byte[])done.Clone();
var buf = Buffer;
_result = buf.AsSpan(0, Length).ToArray();
_buf = null;
ArrayPool<byte>.Shared.Return(buf);
return _result;
}
}
@@ -13,10 +13,10 @@ namespace ZB.MOM.WW.OtOpcUa.Driver.AbCip;
/// never writes <c>Degraded</c>, never opens the device-wide connect backoff, and warns once per tag. Everything
/// else (timeout, bad connection, a reply that failed to parse, partial, abort, …) is a comms fault.
/// <para>
/// The native transport currently folds CIP general statuses 0x1C, 0x20 and 0xFF/0x2104 into
/// <see cref="AbStatus.BadReply"/> (<c>AbStatusCodes.FromCip</c>, owned by <c>Driver.Ab.Transport</c>), which
/// this classification cannot tell from a garbled reply; until the transport maps them explicitly they stay
/// comms faults.
/// The native transport maps CIP general statuses 0x1C (missing attribute list entry) and 0x20 (invalid
/// parameter) to <see cref="AbStatus.Unsupported"/> and 0xFF/0x2104 (offset beyond end) to
/// <see cref="AbStatus.OutOfBounds"/> (<c>AbStatusCodes.FromCip</c>, Lane K F1), so they classify here as
/// device refusals. A Forward Open refused with one of them stays a connection failure.
/// </para>
/// </remarks>
internal static class AbCipRefusals
@@ -789,9 +789,9 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
results[item.Index] = new DataValueSnapshot(null, AbLegacyStatusMapper.BadNotSupported, null, now);
return (OpVerdict.Neutral, null);
}
catch (AbTransportException ex) when (IsDeviceRefusal(ex.Status))
catch (AbTransportException ex) when (IsAnsweredRefusal(ex))
{
// The native runtime raises a device's refusal (e.g. STS 0x20 "file not found") as an exception.
// The native runtime raises a device's refusal (e.g. STS 0x50 "addressing problem") as an exception.
WarnRefusalOnce(device, def, "read", ex.Message, AbLegacyStatusMapper.MapStatus(ex.Status));
results[item.Index] = new DataValueSnapshot(null, AbLegacyStatusMapper.MapStatus(ex.Status), null, now);
return (OpVerdict.Answered, null);
@@ -838,10 +838,10 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
/// reachability (backoff reset, <c>LastSuccessfulRead</c>, Healthy).
/// </summary>
/// <remarks>
/// ⚠️ Inherits the native transport's PCCC STS table (<c>AbStatusCodes.FromPccc</c>, Lane K): it maps STS 0x30
/// ("remote node missing" — a dead DH+/DH-485 node behind a bridge) and 0x20 to <c>NotAllowed</c>/<c>NotFound</c>,
/// so on the NATIVE transport such a dead node still reads as answered. Follow-up F8 (review 07 r0 I4); this
/// classification needs no change once it lands.
/// Inherits the native transport's PCCC STS table (<c>AbStatusCodes.FromPccc</c>). Since Lane K F3 (F8, review
/// 07 r0 I4) STS 0x20 / 0x30 / 0x90 — the host or a bridge reporting an unreachable END device — map to
/// <see cref="AbStatus.BadConnection"/> (no reply), so a dead DH+/DH-485 node behind a bridge is a comms fault,
/// not an answer (<c>NativePcccBridgeStatusHealthTests</c>).
/// </remarks>
/// <param name="status">The transport status.</param>
/// <returns><see langword="true"/> for a device refusal.</returns>
@@ -1035,7 +1035,7 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
results[i] = new WriteResult(AbLegacyStatusMapper.BadCommunicationError);
outcome.FaultMessage ??= tex.Message;
}
catch (AbTransportException ex) when (IsDeviceRefusal(ex.Status))
catch (AbTransportException ex) when (IsAnsweredRefusal(ex))
{
device.RecordAnswered();
outcome.AnyAnswered = true;
@@ -1210,7 +1210,7 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
try { probeRuntime?.Dispose(); } catch { }
probeRuntime = null;
state.ProbeInitialized = false;
if (ex is AbTransportException ate && IsDeviceRefusal(ate.Status)) state.RecordAnswered();
if (IsAnsweredRefusal(ex)) state.RecordAnswered();
else if (ex is not AbTransportException { Status: var st } || IsNoReply(st)) state.RecordCommsFault(Clock());
}
@@ -1478,7 +1478,7 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
{
return (null, AbLegacyStatusMapper.BadNotSupported, false, false);
}
catch (AbTransportException ex) when (IsDeviceRefusal(ex.Status))
catch (AbTransportException ex) when (IsAnsweredRefusal(ex))
{
// The device answered: the index file/element does not exist. Per-tag, not a comms fault.
return (null, AbLegacyStatusMapper.MapStatus(ex.Status), false, false);
@@ -1617,10 +1617,26 @@ public sealed partial class AbLegacyDriver : IDriver, IReadable, IWritable, ITag
/// all PLC-5 writes), and libplctag's ErrorUnsupported maps to it too. It says nothing about the
/// device's reachability, so it must not evict the handle or degrade driver health.
/// </summary>
/// <remarks>
/// An Unsupported that came OFF THE WIRE (<see cref="AbDeviceReplyException"/>: CIP 0x08 / 0x1C / 0x20 on the
/// Execute PCCC envelope, PCCC STS 0x10) is NOT local — the device answered — and is classified by
/// <see cref="IsAnsweredRefusal"/> instead (review lane K I2).
/// </remarks>
/// <param name="ex">The exception to classify.</param>
/// <returns><see langword="true"/> if the exception is a local refusal that never reached the wire.</returns>
internal static bool IsLocalRefusal(Exception ex) =>
ex is AbTransportException { Status: AbStatus.Unsupported };
ex is AbTransportException { Status: AbStatus.Unsupported } and not AbDeviceReplyException;
/// <summary>
/// True for an exception proving the device ANSWERED and refused this operation: a device-refusal status
/// (<see cref="IsDeviceRefusal"/>), or an <see cref="AbStatus.Unsupported"/> that came off the wire
/// (<see cref="AbDeviceReplyException"/>). Per-tag Bad, keeps the handle, advances <c>LastSuccessfulRead</c>.
/// </summary>
/// <param name="ex">The exception to classify.</param>
/// <returns><see langword="true"/> for an answered refusal.</returns>
internal static bool IsAnsweredRefusal(Exception ex) =>
ex is AbTransportException ate
&& (IsDeviceRefusal(ate.Status) || ate is AbDeviceReplyException { Status: AbStatus.Unsupported });
/// <summary>
/// Initializes a freshly created runtime. A NATIVE runtime whose init (one read) is refused locally is
@@ -1,3 +1,4 @@
using System.Buffers;
namespace ZB.MOM.WW.OtOpcUa.Driver.Modbus;
/// <summary>
@@ -55,12 +56,33 @@ public static class ModbusRtuFraming
/// <returns>A new array: <c>[unitId, ...pdu, crcLo, crcHi]</c>.</returns>
public static byte[] BuildAdu(byte unitId, ReadOnlySpan<byte> pdu)
{
var frame = new byte[1 + pdu.Length];
frame[0] = unitId;
pdu.CopyTo(frame.AsSpan(1));
return ModbusCrc.Append(frame);
var frame = new byte[AduLength(pdu.Length)];
WriteAdu(unitId, pdu, frame);
return frame;
}
/// <summary>The length of the RTU ADU for a PDU of <paramref name="pduLength"/> bytes (unit id + PDU + CRC).</summary>
/// <param name="pduLength">The bare PDU length.</param>
/// <returns>The ADU length.</returns>
internal static int AduLength(int pduLength) => 1 + pduLength + 2;
/// <summary>Writes the RTU ADU into <paramref name="destination"/> (exactly <see cref="AduLength"/> bytes).</summary>
/// <param name="unitId">The RTU slave/unit address.</param>
/// <param name="pdu">The bare PDU.</param>
/// <param name="destination">The ADU buffer, exactly <see cref="AduLength"/>(<paramref name="pdu"/>.Length) long.</param>
internal static void WriteAdu(byte unitId, ReadOnlySpan<byte> pdu, Span<byte> destination)
{
destination[0] = unitId;
pdu.CopyTo(destination[1..]);
var body = destination[..(1 + pdu.Length)];
var crc = ModbusCrc.Compute(body);
destination[1 + pdu.Length] = (byte)(crc & 0xFF); // CRC low byte first
destination[2 + pdu.Length] = (byte)(crc >> 8);
}
/// <summary>The largest RTU response frame: addr + fc + byteCount + 255 data bytes + CRC.</summary>
private const int MaxResponseFrame = 3 + 255 + 2;
/// <summary>
/// Reads a single RTU response frame from <paramref name="stream"/> and returns its bare PDU
/// (<c>[fc, ...data]</c>), with the leading unit-id and trailing CRC stripped.
@@ -82,58 +104,56 @@ public static class ModbusRtuFraming
public static async Task<byte[]> ReadResponsePduAsync(
Stream stream, byte expectedUnit, CancellationToken ct)
{
// Header: addr(1) + fc(1). The function code selects how many more bytes to read.
var header = new byte[2];
await ReadExactlyAsync(stream, header, ct).ConfigureAwait(false);
var fc = header[1];
// R07:L5: the whole frame is read into ONE pooled buffer and validated in place; only the returned PDU is
// allocated (it used to be five arrays: header, byteCount, rest, the reassembled frame and the PDU).
var frame = ArrayPool<byte>.Shared.Rent(MaxResponseFrame);
try
{
// Header: addr(1) + fc(1). The function code selects how many more bytes to read.
await ReadExactlyAsync(stream, frame.AsMemory(0, 2), ct).ConfigureAwait(false);
var fc = frame[1];
int trailing; // bytes after addr+fc, up to and including the 2 CRC bytes.
if ((fc & 0x80) != 0)
{
// Exception frame: excCode(1) + CRC(2).
trailing = 1 + 2;
}
else if (fc is 0x01 or 0x02 or 0x03 or 0x04 or 0x17)
{
// Read response (and FC23 Read/Write Multiple, whose reply is a read): byteCount(1) then
// byteCount data bytes + CRC(2).
var bc = new byte[1];
await ReadExactlyAsync(stream, bc, ct).ConfigureAwait(false);
var byteCount = bc[0];
var rest = new byte[byteCount + 2];
await ReadExactlyAsync(stream, rest, ct).ConfigureAwait(false);
return ValidateAndStrip(expectedUnit, header, bc, rest);
}
else
{
// Fixed 4-byte echo: correct for the write FCs this driver emits (05/06/0F/10). FC23 is
// variable-length and handled above; any NEW variable-length response FC must be added there
// or it is mis-sized here and surfaces as a desync.
trailing = 4 + 2;
}
int length; // the whole frame, addr through CRC
var already = 2; // bytes of the frame read so far
if ((fc & 0x80) != 0)
{
// Exception frame: excCode(1) + CRC(2).
length = 2 + 1 + 2;
}
else if (fc is 0x01 or 0x02 or 0x03 or 0x04 or 0x17)
{
// Read response (and FC23 Read/Write Multiple, whose reply is a read): byteCount(1) then
// byteCount data bytes + CRC(2).
await ReadExactlyAsync(stream, frame.AsMemory(2, 1), ct).ConfigureAwait(false);
length = 3 + frame[2] + 2;
already = 3;
}
else
{
// Fixed 4-byte echo: correct for the write FCs this driver emits (05/06/0F/10). FC23 is
// variable-length and handled above; any NEW variable-length response FC must be added there
// or it is mis-sized here and surfaces as a desync.
length = 2 + 4 + 2;
}
var tail = new byte[trailing];
await ReadExactlyAsync(stream, tail, ct).ConfigureAwait(false);
return ValidateAndStrip(expectedUnit, header, ReadOnlySpan<byte>.Empty, tail);
await ReadExactlyAsync(stream, frame.AsMemory(already, length - already), ct).ConfigureAwait(false);
return ValidateAndStrip(expectedUnit, frame.AsSpan(0, length));
}
finally
{
ArrayPool<byte>.Shared.Return(frame);
}
}
/// <summary>
/// Assembles the full frame from its pieces, validates the trailing CRC over everything
/// except the CRC bytes, then validates the response address against
/// <paramref name="expectedUnit"/> and strips <c>addr</c> + <c>CRC</c> to return the bare PDU.
/// Validates the trailing CRC over everything except the CRC bytes, then validates the response address
/// against <paramref name="expectedUnit"/> and strips <c>addr</c> + <c>CRC</c> to return the bare PDU.
/// A CRC-valid exception PDU throws <see cref="ModbusException"/>.
/// </summary>
private static byte[] ValidateAndStrip(
byte expectedUnit, ReadOnlySpan<byte> header, ReadOnlySpan<byte> middle, ReadOnlySpan<byte> tail)
private static byte[] ValidateAndStrip(byte expectedUnit, ReadOnlySpan<byte> frame)
{
// Reassemble the whole frame: header(addr,fc) + middle(optional byteCount) + tail.
var frame = new byte[header.Length + middle.Length + tail.Length];
header.CopyTo(frame);
middle.CopyTo(frame.AsSpan(header.Length));
tail.CopyTo(frame.AsSpan(header.Length + middle.Length));
// CRC covers everything except the trailing 2 CRC bytes.
var body = frame.AsSpan(0, frame.Length - 2);
var body = frame[..^2];
var expected = ModbusCrc.Compute(body);
var actual = (ushort)(frame[^2] | (frame[^1] << 8));
if (actual != expected)
@@ -172,12 +192,12 @@ public static class ModbusRtuFraming
/// <see cref="ModbusTransportDesyncException"/> so a length-less RTU frame that arrives
/// short is classified as a desync rather than a bare <see cref="EndOfStreamException"/>.
/// </summary>
private static async Task ReadExactlyAsync(Stream stream, byte[] buf, CancellationToken ct)
private static async Task ReadExactlyAsync(Stream stream, Memory<byte> buf, CancellationToken ct)
{
var read = 0;
while (read < buf.Length)
{
var n = await stream.ReadAsync(buf.AsMemory(read), ct).ConfigureAwait(false);
var n = await stream.ReadAsync(buf[read..], ct).ConfigureAwait(false);
if (n == 0)
throw new ModbusTransportDesyncException(
ModbusTransportDesyncException.DesyncReason.TruncatedFrame,
@@ -1,3 +1,4 @@
using System.Buffers;
using System.Net.Sockets;
namespace ZB.MOM.WW.OtOpcUa.Driver.Modbus;
@@ -150,14 +151,17 @@ public sealed class ModbusRtuOverTcpTransport : IModbusTransport
var stream = CurrentStream;
if (stream is null) throw new InvalidOperationException("Transport not connected");
// RTU ADU: [unitId] + PDU + CRC — no MBAP header, no TxId.
var adu = ModbusRtuFraming.BuildAdu(unitId, pdu);
// RTU ADU: [unitId] + PDU + CRC — no MBAP header, no TxId. Built in a pooled buffer (R07:L5); the same bytes
// ModbusRtuFraming.BuildAdu produces (pinned by a test).
var aduLength = ModbusRtuFraming.AduLength(pdu.Length);
var adu = ArrayPool<byte>.Shared.Rent(aduLength);
ModbusRtuFraming.WriteAdu(unitId, pdu, adu.AsSpan(0, aduLength));
using var cts = CancellationTokenSource.CreateLinkedTokenSource(ct);
cts.CancelAfter(_timeout);
try
{
await stream.WriteAsync(adu.AsMemory(), cts.Token).ConfigureAwait(false);
await stream.WriteAsync(adu.AsMemory(0, aduLength), cts.Token).ConfigureAwait(false);
await stream.FlushAsync(cts.Token).ConfigureAwait(false);
// Framing owns the length-less RTU deframe + CRC + unit-address validation. A CRC-valid
@@ -181,6 +185,11 @@ public sealed class ModbusRtuOverTcpTransport : IModbusTransport
ModbusTransportDesyncException.DesyncReason.Timeout,
$"Modbus per-op response timeout after {_timeout.TotalMilliseconds:0}ms");
}
finally
{
// The write has completed, or was cancelled and the stream torn down, so nothing still reads it.
ArrayPool<byte>.Shared.Return(adu);
}
}
/// <summary>Asynchronously disposes the transport and underlying socket resources.</summary>
@@ -1,3 +1,4 @@
using System.Buffers;
using System.Net.Sockets;
namespace ZB.MOM.WW.OtOpcUa.Driver.Modbus;
@@ -59,6 +60,10 @@ public sealed class ModbusTcpTransport : IModbusTransport
/// <summary>The socket lifecycle this transport composes (test seam for its clock).</summary>
internal ModbusSocketLifecycle Lifecycle => _life;
// R07:L5: the 7-byte MBAP header of the reply being read. SendOnceAsync runs only under _gate (single-flight), so
// one buffer per transport serves every transaction (it used to be a fresh array per reply).
private readonly byte[] _header = new byte[7];
/// <inheritdoc />
public Task ConnectAsync(CancellationToken ct) => _life.ConnectAsync(ct);
@@ -139,11 +144,16 @@ public sealed class ModbusTcpTransport : IModbusTransport
if (stream is null) throw new InvalidOperationException("Transport not connected");
var txId = ++_nextTx;
// MBAP: [TxId(2)][Proto=0(2)][Length(2)][UnitId(1)] + PDU
var adu = new byte[7 + pdu.Length];
// MBAP: [TxId(2)][Proto=0(2)][Length(2)][UnitId(1)] + PDU. Built in a pooled buffer (R07:L5): the request
// never escapes, and the write has completed (or been cancelled and the socket torn down) before the finally
// hands it back. Only the reply PDU, which the caller keeps, is allocated.
// (One async method on purpose: a second awaited helper costs a state-machine box per call, which ate the saving.)
var aduLength = 7 + pdu.Length;
var adu = ArrayPool<byte>.Shared.Rent(aduLength);
adu[0] = (byte)(txId >> 8);
adu[1] = (byte)(txId & 0xFF);
// protocol id already zero
adu[2] = 0; // protocol id
adu[3] = 0;
var len = (ushort)(1 + pdu.Length); // unit id + pdu
adu[4] = (byte)(len >> 8);
adu[5] = (byte)(len & 0xFF);
@@ -154,10 +164,10 @@ public sealed class ModbusTcpTransport : IModbusTransport
cts.CancelAfter(_timeout);
try
{
await stream.WriteAsync(adu.AsMemory(), cts.Token).ConfigureAwait(false);
await stream.WriteAsync(adu.AsMemory(0, aduLength), cts.Token).ConfigureAwait(false);
await stream.FlushAsync(cts.Token).ConfigureAwait(false);
var header = new byte[7];
var header = _header;
await ReadExactlyAsync(stream, header, cts.Token).ConfigureAwait(false);
var respTxId = (ushort)((header[0] << 8) | header[1]);
if (respTxId != txId)
@@ -211,6 +221,11 @@ public sealed class ModbusTcpTransport : IModbusTransport
ModbusTransportDesyncException.DesyncReason.Timeout,
$"Modbus per-op response timeout after {_timeout.TotalMilliseconds:0}ms");
}
finally
{
// The write has completed, or was cancelled and the socket torn down, so nothing still reads it.
ArrayPool<byte>.Shared.Return(adu);
}
}
private static async Task ReadExactlyAsync(Stream s, byte[] buf, CancellationToken ct)