chore: organize solution into module folders (Core/Server/Drivers/Client/Tooling)

Group all 69 projects into category subfolders under src/ and tests/ so the
Rider Solution Explorer mirrors the module structure. Folders: Core, Server,
Drivers (with a nested Driver CLIs subfolder), Client, Tooling.

- Move every project folder on disk with git mv (history preserved as renames).
- Recompute relative paths in 57 .csproj files: cross-category ProjectReferences,
  the lib/ HintPath+None refs in Driver.Historian.Wonderware, and the external
  mxaccessgw refs in Driver.Galaxy and its test project.
- Rebuild ZB.MOM.WW.OtOpcUa.slnx with nested solution folders.
- Re-prefix project paths in functional scripts (e2e, compliance, smoke SQL,
  integration, install).

Build green (0 errors); unit tests pass. Docs left for a separate pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
Joseph Doherty
2026-05-17 01:55:28 -04:00
parent 69f02fed7f
commit a25593a9c6
1044 changed files with 365 additions and 343 deletions
@@ -0,0 +1,105 @@
using System;
using System.Threading;
using System.Threading.Tasks;
using Serilog;
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Ipc;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// IPC-side <see cref="IAlarmEventWriter"/> implementation that delegates to an
/// <see cref="IAlarmHistorianWriteBackend"/> (production: aahClientManaged-bound)
/// and maps the trinary <see cref="AlarmHistorianWriteOutcome"/> down to the
/// <c>bool[]</c> the IPC reply contract carries. Per-event outcomes:
/// <list type="bullet">
/// <item><description><see cref="AlarmHistorianWriteOutcome.Ack"/> → <c>true</c> (drop from sender's queue).</description></item>
/// <item><description><see cref="AlarmHistorianWriteOutcome.RetryPlease"/> → <c>false</c> (sender retries on next drain tick).</description></item>
/// <item><description><see cref="AlarmHistorianWriteOutcome.PermanentFail"/> → <c>false</c> (sender's B.4 widens the IPC bool back into the trinary outcome by inspecting structured diagnostics; this slot intentionally collapses to "not-ok" at the wire).</description></item>
/// </list>
/// </summary>
public sealed class AahClientManagedAlarmEventWriter : IAlarmEventWriter
{
private static readonly ILogger Log = Serilog.Log.ForContext<AahClientManagedAlarmEventWriter>();
private readonly IAlarmHistorianWriteBackend _backend;
public AahClientManagedAlarmEventWriter(IAlarmHistorianWriteBackend backend)
{
_backend = backend ?? throw new ArgumentNullException(nameof(backend));
}
public async Task<bool[]> WriteAsync(AlarmHistorianEventDto[] events, CancellationToken cancellationToken)
{
if (events is null || events.Length == 0)
{
return new bool[0];
}
AlarmHistorianWriteOutcome[] outcomes;
try
{
outcomes = await _backend.WriteBatchAsync(events, cancellationToken).ConfigureAwait(false);
}
catch (OperationCanceledException)
{
throw;
}
catch (Exception ex)
{
// Backend-level failure (cluster unreachable, transport error). Treat the
// whole batch as RetryPlease so the sender's queue holds the rows for
// the next drain tick — preferable to dropping them on a transient.
Log.Warning(ex,
"Alarm historian backend WriteBatchAsync threw — marking entire {Count}-event batch RetryPlease.",
events.Length);
var fallback = new bool[events.Length];
return fallback;
}
if (outcomes.Length != events.Length)
{
// Backend contract violation — defensive degrade so a bug in the backend
// doesn't desync the sender's queue accounting. Treat as RetryPlease.
Log.Warning(
"Alarm historian backend returned {ReturnedCount} outcomes for a batch of {InputCount} events; degrading to RetryPlease for the whole batch.",
outcomes.Length, events.Length);
return new bool[events.Length];
}
var perEventOk = new bool[outcomes.Length];
for (var i = 0; i < outcomes.Length; i++)
{
perEventOk[i] = outcomes[i] == AlarmHistorianWriteOutcome.Ack;
}
return perEventOk;
}
/// <summary>
/// Translate the outcome of a single SDK call (raw HRESULT + diagnostic) into the
/// trinary <see cref="AlarmHistorianWriteOutcome"/>. Exposed for the production
/// <see cref="SdkAlarmHistorianWriteBackend"/> to share the mapping with tests.
/// </summary>
public static AlarmHistorianWriteOutcome MapOutcome(int hresult, bool isCommunicationError, bool isMalformedInput)
{
// Order matters: malformed input is permanent regardless of HRESULT pattern;
// communication-class errors are transient regardless of which specific
// HRESULT bit fired.
if (isMalformedInput)
{
return AlarmHistorianWriteOutcome.PermanentFail;
}
if (hresult == 0)
{
return AlarmHistorianWriteOutcome.Ack;
}
if (isCommunicationError)
{
return AlarmHistorianWriteOutcome.RetryPlease;
}
// Default: unknown HRESULT failure — be conservative and let the sender retry.
// The sender's drain worker has its own dead-letter cap so a permanently-broken
// event won't loop forever.
return AlarmHistorianWriteOutcome.RetryPlease;
}
}
}
@@ -0,0 +1,19 @@
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Per-event outcome from <see cref="IAlarmHistorianWriteBackend.WriteBatchAsync"/>.
/// Sidecar-local twin of <c>Core.AlarmHistorian.HistorianWriteOutcome</c> (the
/// sidecar runs net48 and cannot reference the net10 Core project; the IPC
/// contract narrows this to <c>bool</c> per slot, so the lmxopcua-side consumer
/// widens that back into the trinary outcome at the IPC boundary in PR B.4).
/// </summary>
public enum AlarmHistorianWriteOutcome
{
/// <summary>Event accepted by the historian. Drop from the store-and-forward queue.</summary>
Ack,
/// <summary>Transient failure (server busy, disconnected, timeout). Leave queued; retry on next drain tick.</summary>
RetryPlease,
/// <summary>Permanent failure (malformed event, unrecoverable SDK error). Move to dead-letter on the lmxopcua side.</summary>
PermanentFail,
}
}
@@ -0,0 +1,129 @@
using System;
using System.Collections.Generic;
using System.Linq;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Thread-safe, pure-logic endpoint picker for the Wonderware Historian cluster. Tracks which
/// configured nodes are healthy, places failed nodes in a time-bounded cooldown, and hands
/// out an ordered list of eligible candidates for the data source to try in sequence.
/// </summary>
internal sealed class HistorianClusterEndpointPicker
{
private readonly Func<DateTime> _clock;
private readonly TimeSpan _cooldown;
private readonly object _lock = new object();
private readonly List<NodeEntry> _nodes;
public HistorianClusterEndpointPicker(HistorianConfiguration config)
: this(config, () => DateTime.UtcNow) { }
internal HistorianClusterEndpointPicker(HistorianConfiguration config, Func<DateTime> clock)
{
_clock = clock ?? throw new ArgumentNullException(nameof(clock));
_cooldown = TimeSpan.FromSeconds(Math.Max(0, config.FailureCooldownSeconds));
var names = (config.ServerNames != null && config.ServerNames.Count > 0)
? config.ServerNames
: new List<string> { config.ServerName };
_nodes = names
.Where(n => !string.IsNullOrWhiteSpace(n))
.Select(n => n.Trim())
.Distinct(StringComparer.OrdinalIgnoreCase)
.Select(n => new NodeEntry { Name = n })
.ToList();
}
public int NodeCount
{
get { lock (_lock) return _nodes.Count; }
}
public IReadOnlyList<string> GetHealthyNodes()
{
lock (_lock)
{
var now = _clock();
return _nodes.Where(n => IsHealthyAt(n, now)).Select(n => n.Name).ToList();
}
}
public int HealthyNodeCount
{
get
{
lock (_lock)
{
var now = _clock();
return _nodes.Count(n => IsHealthyAt(n, now));
}
}
}
public void MarkFailed(string node, string? error)
{
lock (_lock)
{
var entry = FindEntry(node);
if (entry == null) return;
var now = _clock();
entry.FailureCount++;
entry.LastError = error;
entry.LastFailureTime = now;
entry.CooldownUntil = _cooldown.TotalMilliseconds > 0 ? now + _cooldown : (DateTime?)null;
}
}
public void MarkHealthy(string node)
{
lock (_lock)
{
var entry = FindEntry(node);
if (entry == null) return;
entry.CooldownUntil = null;
}
}
public List<HistorianClusterNodeState> SnapshotNodeStates()
{
lock (_lock)
{
var now = _clock();
return _nodes.Select(n => new HistorianClusterNodeState
{
Name = n.Name,
IsHealthy = IsHealthyAt(n, now),
CooldownUntil = IsHealthyAt(n, now) ? null : n.CooldownUntil,
FailureCount = n.FailureCount,
LastError = n.LastError,
LastFailureTime = n.LastFailureTime
}).ToList();
}
}
private static bool IsHealthyAt(NodeEntry entry, DateTime now)
{
return entry.CooldownUntil == null || entry.CooldownUntil <= now;
}
private NodeEntry? FindEntry(string node)
{
for (var i = 0; i < _nodes.Count; i++)
if (string.Equals(_nodes[i].Name, node, StringComparison.OrdinalIgnoreCase))
return _nodes[i];
return null;
}
private sealed class NodeEntry
{
public string Name { get; set; } = "";
public DateTime? CooldownUntil { get; set; }
public int FailureCount { get; set; }
public string? LastError { get; set; }
public DateTime? LastFailureTime { get; set; }
}
}
}
@@ -0,0 +1,18 @@
using System;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Point-in-time state of a single historian cluster node. One entry per configured node
/// appears inside <see cref="HistorianHealthSnapshot"/>.
/// </summary>
public sealed class HistorianClusterNodeState
{
public string Name { get; set; } = "";
public bool IsHealthy { get; set; }
public DateTime? CooldownUntil { get; set; }
public int FailureCount { get; set; }
public string? LastError { get; set; }
public DateTime? LastFailureTime { get; set; }
}
}
@@ -0,0 +1,38 @@
using System.Collections.Generic;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Wonderware Historian SDK configuration. Populated from environment variables at Host
/// startup (see <c>Program.cs</c>) or from the Proxy's <c>DriverInstance.DriverConfig</c>
/// section passed during OpenSession. Kept OPC-UA-free — the Proxy side owns UA translation.
/// </summary>
public sealed class HistorianConfiguration
{
public bool Enabled { get; set; } = false;
/// <summary>Single-node fallback when <see cref="ServerNames"/> is empty.</summary>
public string ServerName { get; set; } = "localhost";
/// <summary>
/// Ordered cluster nodes. When non-empty, the data source tries each in order on connect,
/// falling through to the next on failure. A failed node is placed in cooldown for
/// <see cref="FailureCooldownSeconds"/> before being re-eligible.
/// </summary>
public List<string> ServerNames { get; set; } = new();
public int FailureCooldownSeconds { get; set; } = 60;
public bool IntegratedSecurity { get; set; } = true;
public string? UserName { get; set; }
public string? Password { get; set; }
public int Port { get; set; } = 32568;
public int CommandTimeoutSeconds { get; set; } = 30;
public int MaxValuesPerRead { get; set; } = 10000;
/// <summary>
/// Outer safety timeout applied to sync-over-async Historian operations. Must be
/// comfortably larger than <see cref="CommandTimeoutSeconds"/>.
/// </summary>
public int RequestTimeoutSeconds { get; set; } = 60;
}
}
@@ -0,0 +1,621 @@
using System;
using System.Collections.Generic;
using StringCollection = System.Collections.Specialized.StringCollection;
using System.Threading;
using System.Threading.Tasks;
using ArchestrA;
using Serilog;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Reads historical data from the Wonderware Historian via the aahClientManaged SDK.
/// OPC-UA-free — emits <see cref="HistorianSample"/>/<see cref="HistorianAggregateSample"/>
/// which the Proxy maps to OPC UA <c>DataValue</c> on its side of the IPC.
/// </summary>
public sealed class HistorianDataSource : IHistorianDataSource
{
private static readonly ILogger Log = Serilog.Log.ForContext<HistorianDataSource>();
private readonly HistorianConfiguration _config;
private readonly object _connectionLock = new object();
private readonly object _eventConnectionLock = new object();
private readonly IHistorianConnectionFactory _factory;
private HistorianAccess? _connection;
private HistorianAccess? _eventConnection;
private bool _disposed;
private readonly object _healthLock = new object();
private long _totalSuccesses;
private long _totalFailures;
private int _consecutiveFailures;
private DateTime? _lastSuccessTime;
private DateTime? _lastFailureTime;
private string? _lastError;
private string? _activeProcessNode;
private string? _activeEventNode;
private readonly HistorianClusterEndpointPicker _picker;
public HistorianDataSource(HistorianConfiguration config)
: this(config, new SdkHistorianConnectionFactory(), null) { }
internal HistorianDataSource(
HistorianConfiguration config,
IHistorianConnectionFactory factory,
HistorianClusterEndpointPicker? picker = null)
{
_config = config;
_factory = factory;
_picker = picker ?? new HistorianClusterEndpointPicker(config);
}
private (HistorianAccess Connection, string Node) ConnectToAnyHealthyNode(HistorianConnectionType type)
{
var candidates = _picker.GetHealthyNodes();
if (candidates.Count == 0)
{
var total = _picker.NodeCount;
throw new InvalidOperationException(
total == 0
? "No historian nodes configured"
: $"All {total} historian nodes are in cooldown — no healthy endpoints to connect to");
}
Exception? lastException = null;
foreach (var node in candidates)
{
var attemptConfig = CloneConfigWithServerName(node);
try
{
var conn = _factory.CreateAndConnect(attemptConfig, type);
_picker.MarkHealthy(node);
return (conn, node);
}
catch (Exception ex)
{
_picker.MarkFailed(node, ex.Message);
lastException = ex;
Log.Warning(ex, "Historian node {Node} failed during connect attempt; trying next candidate", node);
}
}
var inner = lastException?.Message ?? "(no detail)";
throw new InvalidOperationException(
$"All {candidates.Count} healthy historian candidate(s) failed during connect: {inner}",
lastException);
}
private HistorianConfiguration CloneConfigWithServerName(string serverName)
{
return new HistorianConfiguration
{
Enabled = _config.Enabled,
ServerName = serverName,
ServerNames = _config.ServerNames,
FailureCooldownSeconds = _config.FailureCooldownSeconds,
IntegratedSecurity = _config.IntegratedSecurity,
UserName = _config.UserName,
Password = _config.Password,
Port = _config.Port,
CommandTimeoutSeconds = _config.CommandTimeoutSeconds,
MaxValuesPerRead = _config.MaxValuesPerRead
};
}
public HistorianHealthSnapshot GetHealthSnapshot()
{
var nodeStates = _picker.SnapshotNodeStates();
var healthyCount = 0;
foreach (var n in nodeStates)
if (n.IsHealthy) healthyCount++;
lock (_healthLock)
{
return new HistorianHealthSnapshot
{
TotalQueries = _totalSuccesses + _totalFailures,
TotalSuccesses = _totalSuccesses,
TotalFailures = _totalFailures,
ConsecutiveFailures = _consecutiveFailures,
LastSuccessTime = _lastSuccessTime,
LastFailureTime = _lastFailureTime,
LastError = _lastError,
ProcessConnectionOpen = Volatile.Read(ref _connection) != null,
EventConnectionOpen = Volatile.Read(ref _eventConnection) != null,
ActiveProcessNode = _activeProcessNode,
ActiveEventNode = _activeEventNode,
NodeCount = nodeStates.Count,
HealthyNodeCount = healthyCount,
Nodes = nodeStates
};
}
}
private void RecordSuccess()
{
lock (_healthLock)
{
_totalSuccesses++;
_lastSuccessTime = DateTime.UtcNow;
_consecutiveFailures = 0;
_lastError = null;
}
}
private void RecordFailure(string error)
{
lock (_healthLock)
{
_totalFailures++;
_lastFailureTime = DateTime.UtcNow;
_consecutiveFailures++;
_lastError = error;
}
}
private void EnsureConnected()
{
if (_disposed)
throw new ObjectDisposedException(nameof(HistorianDataSource));
if (Volatile.Read(ref _connection) != null) return;
var (conn, winningNode) = ConnectToAnyHealthyNode(HistorianConnectionType.Process);
lock (_connectionLock)
{
if (_disposed)
{
conn.CloseConnection(out _);
conn.Dispose();
throw new ObjectDisposedException(nameof(HistorianDataSource));
}
if (_connection != null)
{
conn.CloseConnection(out _);
conn.Dispose();
return;
}
_connection = conn;
lock (_healthLock) _activeProcessNode = winningNode;
Log.Information("Historian SDK connection opened to {Server}:{Port}", winningNode, _config.Port);
}
}
private void HandleConnectionError(Exception? ex = null)
{
lock (_connectionLock)
{
if (_connection == null) return;
try
{
_connection.CloseConnection(out _);
_connection.Dispose();
}
catch (Exception disposeEx)
{
Log.Debug(disposeEx, "Error disposing Historian SDK connection during error recovery");
}
_connection = null;
string? failedNode;
lock (_healthLock)
{
failedNode = _activeProcessNode;
_activeProcessNode = null;
}
if (failedNode != null) _picker.MarkFailed(failedNode, ex?.Message ?? "mid-query failure");
Log.Warning(ex, "Historian SDK connection reset (node={Node})", failedNode ?? "(unknown)");
}
}
private void EnsureEventConnected()
{
if (_disposed)
throw new ObjectDisposedException(nameof(HistorianDataSource));
if (Volatile.Read(ref _eventConnection) != null) return;
var (conn, winningNode) = ConnectToAnyHealthyNode(HistorianConnectionType.Event);
lock (_eventConnectionLock)
{
if (_disposed)
{
conn.CloseConnection(out _);
conn.Dispose();
throw new ObjectDisposedException(nameof(HistorianDataSource));
}
if (_eventConnection != null)
{
conn.CloseConnection(out _);
conn.Dispose();
return;
}
_eventConnection = conn;
lock (_healthLock) _activeEventNode = winningNode;
Log.Information("Historian SDK event connection opened to {Server}:{Port}", winningNode, _config.Port);
}
}
private void HandleEventConnectionError(Exception? ex = null)
{
lock (_eventConnectionLock)
{
if (_eventConnection == null) return;
try
{
_eventConnection.CloseConnection(out _);
_eventConnection.Dispose();
}
catch (Exception disposeEx)
{
Log.Debug(disposeEx, "Error disposing Historian SDK event connection during error recovery");
}
_eventConnection = null;
string? failedNode;
lock (_healthLock)
{
failedNode = _activeEventNode;
_activeEventNode = null;
}
if (failedNode != null) _picker.MarkFailed(failedNode, ex?.Message ?? "mid-query failure");
Log.Warning(ex, "Historian SDK event connection reset (node={Node})", failedNode ?? "(unknown)");
}
}
public Task<List<HistorianSample>> ReadRawAsync(
string tagName, DateTime startTime, DateTime endTime, int maxValues,
CancellationToken ct = default)
{
var results = new List<HistorianSample>();
try
{
EnsureConnected();
using var query = _connection!.CreateHistoryQuery();
var args = new HistoryQueryArgs
{
TagNames = new StringCollection { tagName },
StartDateTime = startTime,
EndDateTime = endTime,
RetrievalMode = HistorianRetrievalMode.Full
};
if (maxValues > 0)
args.BatchSize = (uint)maxValues;
else if (_config.MaxValuesPerRead > 0)
args.BatchSize = (uint)_config.MaxValuesPerRead;
if (!query.StartQuery(args, out var error))
{
Log.Warning("Historian SDK raw query start failed for {Tag}: {Error}", tagName, error.ErrorCode);
RecordFailure($"raw StartQuery: {error.ErrorCode}");
HandleConnectionError();
return Task.FromResult(results);
}
var count = 0;
var limit = maxValues > 0 ? maxValues : _config.MaxValuesPerRead;
while (query.MoveNext(out error))
{
ct.ThrowIfCancellationRequested();
var result = query.QueryResult;
var timestamp = DateTime.SpecifyKind(result.StartDateTime, DateTimeKind.Utc);
object? value;
if (!string.IsNullOrEmpty(result.StringValue) && result.Value == 0)
value = result.StringValue;
else
value = result.Value;
results.Add(new HistorianSample
{
Value = value,
TimestampUtc = timestamp,
Quality = (byte)(result.OpcQuality & 0xFF),
});
count++;
if (limit > 0 && count >= limit) break;
}
query.EndQuery(out _);
RecordSuccess();
}
catch (OperationCanceledException) { throw; }
catch (ObjectDisposedException) { throw; }
catch (Exception ex)
{
Log.Warning(ex, "HistoryRead raw failed for {Tag}", tagName);
RecordFailure($"raw: {ex.Message}");
HandleConnectionError(ex);
}
Log.Debug("HistoryRead raw: {Tag} returned {Count} values ({Start} to {End})",
tagName, results.Count, startTime, endTime);
return Task.FromResult(results);
}
public Task<List<HistorianAggregateSample>> ReadAggregateAsync(
string tagName, DateTime startTime, DateTime endTime,
double intervalMs, string aggregateColumn,
CancellationToken ct = default)
{
var results = new List<HistorianAggregateSample>();
try
{
EnsureConnected();
using var query = _connection!.CreateAnalogSummaryQuery();
var args = new AnalogSummaryQueryArgs
{
TagNames = new StringCollection { tagName },
StartDateTime = startTime,
EndDateTime = endTime,
Resolution = (ulong)intervalMs
};
if (!query.StartQuery(args, out var error))
{
Log.Warning("Historian SDK aggregate query start failed for {Tag}: {Error}", tagName, error.ErrorCode);
RecordFailure($"aggregate StartQuery: {error.ErrorCode}");
HandleConnectionError();
return Task.FromResult(results);
}
while (query.MoveNext(out error))
{
ct.ThrowIfCancellationRequested();
var result = query.QueryResult;
var timestamp = DateTime.SpecifyKind(result.StartDateTime, DateTimeKind.Utc);
var value = ExtractAggregateValue(result, aggregateColumn);
results.Add(new HistorianAggregateSample
{
Value = value,
TimestampUtc = timestamp,
});
}
query.EndQuery(out _);
RecordSuccess();
}
catch (OperationCanceledException) { throw; }
catch (ObjectDisposedException) { throw; }
catch (Exception ex)
{
Log.Warning(ex, "HistoryRead aggregate failed for {Tag}", tagName);
RecordFailure($"aggregate: {ex.Message}");
HandleConnectionError(ex);
}
Log.Debug("HistoryRead aggregate ({Aggregate}): {Tag} returned {Count} values",
aggregateColumn, tagName, results.Count);
return Task.FromResult(results);
}
public Task<List<HistorianSample>> ReadAtTimeAsync(
string tagName, DateTime[] timestamps,
CancellationToken ct = default)
{
var results = new List<HistorianSample>();
if (timestamps == null || timestamps.Length == 0)
return Task.FromResult(results);
try
{
EnsureConnected();
foreach (var timestamp in timestamps)
{
ct.ThrowIfCancellationRequested();
using var query = _connection!.CreateHistoryQuery();
var args = new HistoryQueryArgs
{
TagNames = new StringCollection { tagName },
StartDateTime = timestamp,
EndDateTime = timestamp,
RetrievalMode = HistorianRetrievalMode.Interpolated,
BatchSize = 1
};
if (!query.StartQuery(args, out var error))
{
results.Add(new HistorianSample
{
Value = null,
TimestampUtc = DateTime.SpecifyKind(timestamp, DateTimeKind.Utc),
Quality = 0, // Bad
});
continue;
}
if (query.MoveNext(out error))
{
var result = query.QueryResult;
object? value;
if (!string.IsNullOrEmpty(result.StringValue) && result.Value == 0)
value = result.StringValue;
else
value = result.Value;
results.Add(new HistorianSample
{
Value = value,
TimestampUtc = DateTime.SpecifyKind(timestamp, DateTimeKind.Utc),
Quality = (byte)(result.OpcQuality & 0xFF),
});
}
else
{
results.Add(new HistorianSample
{
Value = null,
TimestampUtc = DateTime.SpecifyKind(timestamp, DateTimeKind.Utc),
Quality = 0,
});
}
query.EndQuery(out _);
}
RecordSuccess();
}
catch (OperationCanceledException) { throw; }
catch (ObjectDisposedException) { throw; }
catch (Exception ex)
{
Log.Warning(ex, "HistoryRead at-time failed for {Tag}", tagName);
RecordFailure($"at-time: {ex.Message}");
HandleConnectionError(ex);
}
Log.Debug("HistoryRead at-time: {Tag} returned {Count} values for {Timestamps} timestamps",
tagName, results.Count, timestamps.Length);
return Task.FromResult(results);
}
public Task<List<HistorianEventDto>> ReadEventsAsync(
string? sourceName, DateTime startTime, DateTime endTime, int maxEvents,
CancellationToken ct = default)
{
var results = new List<HistorianEventDto>();
try
{
EnsureEventConnected();
using var query = _eventConnection!.CreateEventQuery();
var args = new EventQueryArgs
{
StartDateTime = startTime,
EndDateTime = endTime,
EventCount = maxEvents > 0 ? (uint)maxEvents : (uint)_config.MaxValuesPerRead,
QueryType = HistorianEventQueryType.Events,
EventOrder = HistorianEventOrder.Ascending
};
if (!string.IsNullOrEmpty(sourceName))
{
query.AddEventFilter("Source", HistorianComparisionType.Equal, sourceName, out _);
}
if (!query.StartQuery(args, out var error))
{
Log.Warning("Historian SDK event query start failed: {Error}", error.ErrorCode);
RecordFailure($"events StartQuery: {error.ErrorCode}");
HandleEventConnectionError();
return Task.FromResult(results);
}
var count = 0;
while (query.MoveNext(out error))
{
ct.ThrowIfCancellationRequested();
results.Add(ToDto(query.QueryResult));
count++;
if (maxEvents > 0 && count >= maxEvents) break;
}
query.EndQuery(out _);
RecordSuccess();
}
catch (OperationCanceledException) { throw; }
catch (ObjectDisposedException) { throw; }
catch (Exception ex)
{
Log.Warning(ex, "HistoryRead events failed for source {Source}", sourceName ?? "(all)");
RecordFailure($"events: {ex.Message}");
HandleEventConnectionError(ex);
}
Log.Debug("HistoryRead events: source={Source} returned {Count} events ({Start} to {End})",
sourceName ?? "(all)", results.Count, startTime, endTime);
return Task.FromResult(results);
}
private static HistorianEventDto ToDto(HistorianEvent evt)
{
// The ArchestrA SDK marks these properties obsolete but still returns them; their
// successors aren't wired in the version we bind against. Using them is the documented
// v1 behavior — suppressed locally instead of project-wide so any non-event use of
// deprecated SDK surface still surfaces as an error.
#pragma warning disable CS0618
return new HistorianEventDto
{
Id = evt.Id,
Source = evt.Source,
EventTime = evt.EventTime,
ReceivedTime = evt.ReceivedTime,
DisplayText = evt.DisplayText,
Severity = (ushort)evt.Severity
};
#pragma warning restore CS0618
}
internal static double? ExtractAggregateValue(AnalogSummaryQueryResult result, string column)
{
switch (column)
{
case "Average": return result.Average;
case "Minimum": return result.Minimum;
case "Maximum": return result.Maximum;
case "ValueCount": return result.ValueCount;
case "First": return result.First;
case "Last": return result.Last;
case "StdDev": return result.StdDev;
default: return null;
}
}
public void Dispose()
{
if (_disposed) return;
_disposed = true;
try
{
_connection?.CloseConnection(out _);
_connection?.Dispose();
}
catch (Exception ex)
{
Log.Warning(ex, "Error closing Historian SDK connection");
}
try
{
_eventConnection?.CloseConnection(out _);
_eventConnection?.Dispose();
}
catch (Exception ex)
{
Log.Warning(ex, "Error closing Historian SDK event connection");
}
_connection = null;
_eventConnection = null;
}
}
}
@@ -0,0 +1,18 @@
using System;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// SDK-free representation of a Historian event record. Prevents ArchestrA types from
/// leaking beyond <c>HistorianDataSource</c>.
/// </summary>
public sealed class HistorianEventDto
{
public Guid Id { get; set; }
public string? Source { get; set; }
public DateTime EventTime { get; set; }
public DateTime ReceivedTime { get; set; }
public string? DisplayText { get; set; }
public ushort Severity { get; set; }
}
}
@@ -0,0 +1,27 @@
using System;
using System.Collections.Generic;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Point-in-time runtime health of the historian subsystem — consumed by the status dashboard
/// via an IPC health query (not wired in PR #5; deferred).
/// </summary>
public sealed class HistorianHealthSnapshot
{
public long TotalQueries { get; set; }
public long TotalSuccesses { get; set; }
public long TotalFailures { get; set; }
public int ConsecutiveFailures { get; set; }
public DateTime? LastSuccessTime { get; set; }
public DateTime? LastFailureTime { get; set; }
public string? LastError { get; set; }
public bool ProcessConnectionOpen { get; set; }
public bool EventConnectionOpen { get; set; }
public string? ActiveProcessNode { get; set; }
public string? ActiveEventNode { get; set; }
public int NodeCount { get; set; }
public int HealthyNodeCount { get; set; }
public List<HistorianClusterNodeState> Nodes { get; set; } = new();
}
}
@@ -0,0 +1,46 @@
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend;
/// <summary>
/// Maps a raw OPC DA quality byte (as returned by Wonderware Historian's <c>OpcQuality</c>)
/// to an OPC UA <c>StatusCode</c> uint. Preserves specific codes (BadNotConnected,
/// UncertainSubNormal, etc.) instead of collapsing to Good/Uncertain/Bad categories.
/// Mirrors v1 <c>QualityMapper.MapToOpcUaStatusCode</c> without pulling in OPC UA types —
/// the returned value is the 32-bit OPC UA <c>StatusCode</c> wire encoding that the Proxy
/// surfaces directly as <c>DataValueSnapshot.StatusCode</c>.
/// </summary>
public static class HistorianQualityMapper
{
/// <summary>
/// Map an 8-bit OPC DA quality byte to the corresponding OPC UA StatusCode. The byte
/// family bits decide the category (Good &gt;= 192, Uncertain 64-191, Bad 0-63); the
/// low-nibble subcode selects the specific code.
/// </summary>
public static uint Map(byte q) => q switch
{
// Good family (192+)
192 => 0x00000000u, // Good
216 => 0x00D80000u, // Good_LocalOverride
// Uncertain family (64-191)
64 => 0x40000000u, // Uncertain
68 => 0x40900000u, // Uncertain_LastUsableValue
80 => 0x40930000u, // Uncertain_SensorNotAccurate
84 => 0x40940000u, // Uncertain_EngineeringUnitsExceeded
88 => 0x40950000u, // Uncertain_SubNormal
// Bad family (0-63)
0 => 0x80000000u, // Bad
4 => 0x80890000u, // Bad_ConfigurationError
8 => 0x808A0000u, // Bad_NotConnected
12 => 0x808B0000u, // Bad_DeviceFailure
16 => 0x808C0000u, // Bad_SensorFailure
20 => 0x80050000u, // Bad_CommunicationError
24 => 0x808D0000u, // Bad_OutOfService
32 => 0x80320000u, // Bad_WaitingForInitialData
// Unknown code — fall back to the category so callers still get a sensible bucket.
_ when q >= 192 => 0x00000000u,
_ when q >= 64 => 0x40000000u,
_ => 0x80000000u,
};
}
@@ -0,0 +1,30 @@
using System;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// OPC-UA-free representation of a single historical data point. The Host returns these
/// across the IPC boundary as <c>GalaxyDataValue</c>; the Proxy maps quality and value to
/// OPC UA <c>DataValue</c>. Raw MX quality byte is preserved so the Proxy can use the same
/// quality mapper it already uses for live reads.
/// </summary>
public sealed class HistorianSample
{
public object? Value { get; set; }
/// <summary>Raw OPC DA quality byte from the historian SDK (low 8 bits of OpcQuality).</summary>
public byte Quality { get; set; }
public DateTime TimestampUtc { get; set; }
}
/// <summary>
/// Result of <see cref="IHistorianDataSource.ReadAggregateAsync"/>. When <see cref="Value"/> is
/// null the aggregate is unavailable for that bucket (Proxy maps to <c>BadNoData</c>).
/// </summary>
public sealed class HistorianAggregateSample
{
public double? Value { get; set; }
public DateTime TimestampUtc { get; set; }
}
}
@@ -0,0 +1,30 @@
using System.Threading;
using System.Threading.Tasks;
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Ipc;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// The actual aahClientManaged-bound writer. Extracted so unit tests can
/// substitute a fake without touching the SDK; the production
/// implementation lives in <see cref="SdkAlarmHistorianWriteBackend"/>.
/// </summary>
/// <remarks>
/// Implementations are responsible for connection management + cluster
/// failover. The wrapping <see cref="AahClientManagedAlarmEventWriter"/>
/// handles batch-level orchestration but delegates the per-event SDK call
/// here so the unit tests can drive every documented MxStatus outcome
/// without an installed AVEVA Historian.
/// </remarks>
public interface IAlarmHistorianWriteBackend
{
/// <summary>
/// Persist the supplied events to the historian. Returns one outcome per
/// input slot in the same order — must always return an array of the same
/// length as <paramref name="events"/>.
/// </summary>
Task<AlarmHistorianWriteOutcome[]> WriteBatchAsync(
AlarmHistorianEventDto[] events,
CancellationToken cancellationToken);
}
}
@@ -0,0 +1,73 @@
using System;
using System.Threading;
using ArchestrA;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Creates and opens Historian SDK connections. Extracted so tests can inject fakes that
/// control connection success, failure, and timeout behavior.
/// </summary>
internal interface IHistorianConnectionFactory
{
HistorianAccess CreateAndConnect(HistorianConfiguration config, HistorianConnectionType type);
}
/// <summary>Production implementation — opens real Historian SDK connections.</summary>
internal sealed class SdkHistorianConnectionFactory : IHistorianConnectionFactory
{
public HistorianAccess CreateAndConnect(HistorianConfiguration config, HistorianConnectionType type)
{
var conn = new HistorianAccess();
var args = new HistorianConnectionArgs
{
ServerName = config.ServerName,
TcpPort = (ushort)config.Port,
IntegratedSecurity = config.IntegratedSecurity,
UseArchestrAUser = config.IntegratedSecurity,
ConnectionType = type,
ReadOnly = true,
PacketTimeout = (uint)(config.CommandTimeoutSeconds * 1000)
};
if (!config.IntegratedSecurity)
{
args.UserName = config.UserName ?? string.Empty;
args.Password = config.Password ?? string.Empty;
}
if (!conn.OpenConnection(args, out var error))
{
conn.Dispose();
throw new InvalidOperationException(
$"Failed to open Historian SDK connection to {config.ServerName}:{config.Port}: {error.ErrorCode}");
}
var timeoutMs = config.CommandTimeoutSeconds * 1000;
var elapsed = 0;
while (elapsed < timeoutMs)
{
var status = new HistorianConnectionStatus();
conn.GetConnectionStatus(ref status);
if (status.ConnectedToServer)
return conn;
if (status.ErrorOccurred)
{
conn.Dispose();
throw new InvalidOperationException(
$"Historian SDK connection failed: {status.Error}");
}
Thread.Sleep(250);
elapsed += 250;
}
conn.Dispose();
throw new TimeoutException(
$"Historian SDK connection to {config.ServerName}:{config.Port} timed out after {config.CommandTimeoutSeconds}s");
}
}
}
@@ -0,0 +1,34 @@
using System;
using System.Collections.Generic;
using System.Threading;
using System.Threading.Tasks;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// OPC-UA-free surface for the Wonderware Historian subsystem inside Galaxy.Host.
/// Implementations read via the aahClient* SDK; the Proxy side maps returned samples
/// to OPC UA <c>DataValue</c>.
/// </summary>
public interface IHistorianDataSource : IDisposable
{
Task<List<HistorianSample>> ReadRawAsync(
string tagName, DateTime startTime, DateTime endTime, int maxValues,
CancellationToken ct = default);
Task<List<HistorianAggregateSample>> ReadAggregateAsync(
string tagName, DateTime startTime, DateTime endTime,
double intervalMs, string aggregateColumn,
CancellationToken ct = default);
Task<List<HistorianSample>> ReadAtTimeAsync(
string tagName, DateTime[] timestamps,
CancellationToken ct = default);
Task<List<HistorianEventDto>> ReadEventsAsync(
string? sourceName, DateTime startTime, DateTime endTime, int maxEvents,
CancellationToken ct = default);
HistorianHealthSnapshot GetHealthSnapshot();
}
}
@@ -0,0 +1,73 @@
using System;
using System.Threading;
using System.Threading.Tasks;
using Serilog;
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Ipc;
namespace ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend
{
/// <summary>
/// Production <see cref="IAlarmHistorianWriteBackend"/> backed by AVEVA Historian's
/// <c>aahClientManaged</c> alarm-event write API. The exact SDK entry point is
/// pinned during the live-rig smoke in PR D.1 — until that gate, this backend
/// reports <see cref="AlarmHistorianWriteOutcome.RetryPlease"/> for every
/// event with a structured diagnostic so the lmxopcua-side
/// <c>SqliteStoreAndForwardSink</c> retains the queued events rather than dropping
/// or hard-failing them.
/// </summary>
/// <remarks>
/// <para>
/// Cluster failover reuses <see cref="HistorianClusterEndpointPicker"/> via
/// the shared <see cref="HistorianDataSource"/> connection pool — there is
/// no second connection pool for writes. Wonderware Historian's alarm-event
/// write surface accepts the same <c>HistorianAccess</c> session a read
/// opens, so reusing the picker is parity-preserving with v1's
/// <c>GalaxyHistorianWriter</c>.
/// </para>
/// <para>
/// Once D.1 confirms the SDK entry point, this class swaps the placeholder
/// body for the real call sequence. The mapping from raw HRESULT /
/// <c>HistorianError</c> codes onto <see cref="AlarmHistorianWriteOutcome"/>
/// is already shared via <see cref="AahClientManagedAlarmEventWriter.MapOutcome"/>
/// so the smoke-pinned change stays minimal.
/// </para>
/// </remarks>
public sealed class SdkAlarmHistorianWriteBackend : IAlarmHistorianWriteBackend
{
private static readonly ILogger Log = Serilog.Log.ForContext<SdkAlarmHistorianWriteBackend>();
private readonly HistorianConfiguration _config;
public SdkAlarmHistorianWriteBackend(HistorianConfiguration config)
{
_config = config ?? throw new ArgumentNullException(nameof(config));
}
public Task<AlarmHistorianWriteOutcome[]> WriteBatchAsync(
AlarmHistorianEventDto[] events,
CancellationToken cancellationToken)
{
if (events is null || events.Length == 0)
{
return Task.FromResult(new AlarmHistorianWriteOutcome[0]);
}
// Placeholder: pin the SDK entry point in PR D.1 against a live AVEVA
// Historian. Until then the call returns RetryPlease for every slot so
// the lmxopcua-side sink keeps the events queued rather than dropping
// them — same effect as the current NullAlarmHistorianSink fallback,
// but visible through the structured diagnostic + per-event outcome.
Log.Warning(
"Alarm historian SDK write path not yet pinned — returning RetryPlease for {Count} event(s) from server {Server}. PR D.1 swaps this for the live aahClientManaged call.",
events.Length,
_config.ServerName);
var outcomes = new AlarmHistorianWriteOutcome[events.Length];
for (var i = 0; i < outcomes.Length; i++)
{
outcomes[i] = AlarmHistorianWriteOutcome.RetryPlease;
}
return Task.FromResult(outcomes);
}
}
}