feat(opcuaserver): bounded per-node parallel HistoryRead within a batch (03/S3)

src/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer/OtOpcUaNodeManager.cs

@@ -1816,6 +1816,7 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
         IDictionary<NodeId, NodeState> cache)
     {
         var session = context.OperationContext?.Session;
+        var work = new List<Func<Task>>(nodesToProcess.Count);
         foreach (var handle in nodesToProcess)
         {
             if (details.IsReadModified)
@@ -1825,12 +1826,13 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
                 continue;
             }
 
-            // Interim: still bridged sequentially per node (bounded fan-out lands in a later slice).
-            ServeRawPagedAsync(
+            work.Add(() => ServeRawPagedAsync(
                 handle, session, nodesToRead, results, errors,
                 details.StartTime, details.EndTime, details.NumValuesPerNode,
-                CancellationToken.None).GetAwaiter().GetResult();
+                CancellationToken.None));
         }
+
+        RunBounded(work, HistoryReadBatchParallelism);
     }
 
     /// <inheritdoc />
@@ -1846,6 +1848,7 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
     {
         // OPC UA ProcessingInterval is a Duration in milliseconds — convert once per batch.
         var interval = TimeSpan.FromMilliseconds(details.ProcessingInterval);
+        var work = new List<Func<Task>>(nodesToProcess.Count);
         foreach (var handle in nodesToProcess)
         {
             // AggregateType is a per-node parallel collection (same length as nodesToRead, enforced by
@@ -1863,15 +1866,17 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
             // and the single-shot backend returns every bucket in one read, so there is no "full page ⇒
             // maybe more" signal to page on. Returning the complete aggregate result with a null CP is
             // spec-conformant (OPC UA Part 11 lets a server return all available data in one response).
-            // Interim: still bridged sequentially per node (bounded fan-out lands in a later slice).
-            ServeNodeAsync(handle, results, errors, (source, tagname, token) => source.ReadProcessedAsync(
+            var agg = aggregate.Value;
+            work.Add(() => ServeNodeAsync(handle, results, errors, (source, tagname, token) => source.ReadProcessedAsync(
                 tagname,
                 details.StartTime,
                 details.EndTime,
                 interval,
-                aggregate.Value,
-                token), CancellationToken.None).GetAwaiter().GetResult();
+                agg,
+                token), CancellationToken.None));
         }
+
+        RunBounded(work, HistoryReadBatchParallelism);
     }
 
     /// <inheritdoc />
@@ -1887,14 +1892,16 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
     {
         // Snapshot the requested timestamps once — the same list is read for every node.
         var timestamps = details.ReqTimes?.ToList() ?? new List<DateTime>();
+        var work = new List<Func<Task>>(nodesToProcess.Count);
         foreach (var handle in nodesToProcess)
         {
-            // Interim: still bridged sequentially per node (bounded fan-out lands in a later slice).
-            ServeNodeAsync(handle, results, errors, (source, tagname, token) => source.ReadAtTimeAsync(
+            work.Add(() => ServeNodeAsync(handle, results, errors, (source, tagname, token) => source.ReadAtTimeAsync(
                 tagname,
                 timestamps,
-                token), CancellationToken.None).GetAwaiter().GetResult();
+                token), CancellationToken.None));
         }
+
+        RunBounded(work, HistoryReadBatchParallelism);
     }
 
     /// <inheritdoc />
@@ -1911,6 +1918,7 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
         // Snapshot the select clauses once — the same filter projects every node's events.
         var selectClauses = details.Filter?.SelectClauses ?? new SimpleAttributeOperandCollection();
 
+        var work = new List<Func<Task>>(nodesToProcess.Count);
         foreach (var handle in nodesToProcess)
         {
             var idString = handle.NodeId.Identifier?.ToString();
@@ -1924,10 +1932,11 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
                 continue;
             }
 
-            // Interim: still bridged sequentially per node (bounded fan-out lands in a later slice).
-            ServeEventsAsync(handle, sourceName, details, selectClauses, results, errors, CancellationToken.None)
-                .GetAwaiter().GetResult();
+            var sn = sourceName;
+            work.Add(() => ServeEventsAsync(handle, sn, details, selectClauses, results, errors, CancellationToken.None));
         }
+
+        RunBounded(work, HistoryReadBatchParallelism);
     }
 
     /// <summary>
@@ -2099,6 +2108,52 @@ public sealed class OtOpcUaNodeManager : CustomNodeManager2
     /// <param name="errors">The service-level errors list to fill at <c>handle.Index</c>.</param>
     /// <param name="read">Invokes the resolved data-source read with the resolved tagname; only called
     /// once the tagname is confirmed present.</param>
+    /// <summary>
+    ///     Run a batch of per-node HistoryRead work items with BOUNDED parallelism (arch-review 03/S3),
+    ///     block-bridged ONCE at the arm boundary. <b>Contract:</b> every work item must be fully
+    ///     self-contained — it fills its own results/errors slot and NEVER throws (all per-node handlers
+    ///     catch every exception, including cancellation, and surface a Bad status for that node only). That
+    ///     invariant is what makes the single <c>GetAwaiter().GetResult()</c> safe: <see cref="Task.WhenAll(Task[])"/>
+    ///     can never fault, so it cannot throw out of the synchronous SDK override. A degree ≤ 1 (or a
+    ///     single item) runs sequentially — no semaphore, no extra tasks.
+    /// </summary>
+    /// <param name="work">The per-node work items (index-disjoint writes into the shared results/errors).</param>
+    /// <param name="degree">Max concurrent work items (<see cref="HistoryReadBatchParallelism"/>).</param>
+    private static void RunBounded(IReadOnlyList<Func<Task>> work, int degree)
+    {
+        if (work.Count == 0) return;
+        if (degree <= 1 || work.Count == 1)
+        {
+            foreach (var item in work)
+                item().GetAwaiter().GetResult();
+            return;
+        }
+
+        using var gate = new SemaphoreSlim(degree);
+        var tasks = new Task[work.Count];
+        for (var i = 0; i < work.Count; i++)
+            tasks[i] = RunGatedAsync(gate, work[i]);
+
+        // Safe: every body is self-contained + never throws, so WhenAll never faults (see contract above).
+        Task.WhenAll(tasks).GetAwaiter().GetResult();
+    }
+
+    /// <summary>Awaits one work item under a semaphore permit, releasing it when the item completes.</summary>
+    /// <param name="gate">The concurrency-limiting semaphore.</param>
+    /// <param name="work">The per-node work item.</param>
+    private static async Task RunGatedAsync(SemaphoreSlim gate, Func<Task> work)
+    {
+        await gate.WaitAsync().ConfigureAwait(false);
+        try
+        {
+            await work().ConfigureAwait(false);
+        }
+        finally
+        {
+            gate.Release();
+        }
+    }
+
     private async Task ServeNodeAsync(
         NodeHandle handle,
         IList<SdkHistoryReadResult> results,