feat(comm): batch site→central stream events over gRPC (R2)

Every AttributeValueChanged/AlarmStateChanged rode its own gRPC message on SiteStreamService; at target scale that is ~37.5k messages/s/site of pure framing overhead. Coalesce them, additively, with no new RPC. Wire (sitestream.proto, regenerated via docker/regen-proto.sh sitestream): InstanceStreamRequest.batching_supported = 3 SiteStreamRequest.batching_supported = 2 SiteStreamEvent.batch = 4 (new oneof case) SiteStreamEventBatch { repeated SiteStreamEvent events = 1 } The proto3 default of batching_supported IS the negotiation, and it is load-bearing: a batch frame reaches a pre-R2 central as EventOneofCase.None, whose ConvertToDomainEvent returns null — the whole batch would vanish with no error anywhere. An old central cannot set the flag so it never receives one; an old site ignores the unknown request field and keeps sending per-event frames, which the new client's ForEachEvent handles as the single-event case. Both skew directions are covered by tests that go through a real proto serialize/parse round-trip. Server: SiteStreamEventBatcher, a per-subscriber pump replacing the handler's await-foreach/WriteAsync loop and byte-identical to it at a cap of 1. It never delays a lone event — it drains the already-queued backlog for free and lingers only once a backlog is proven — emits a single-event buffer as a plain frame, preserves order and per-event Timestamps exactly, and flushes what is buffered when the send channel's writer completes. It sits DOWNSTREAM of StreamRelayActor's bounded DropOldest channel, so it changes framing only and does not move the burst ceiling (deferred register row 31, which lives in the shared publish stage upstream of the BroadcastHub). Client: sets the flag on both subscriptions and unpacks in order into the existing per-event pipeline, so SiteAlarmAggregatorActor, DebugStreamBridgeActor, consumer-keepalive/orphan logic, reconnect-on-graceful-completion, generation fencing, the (siteId, endpoint) factory key and IsLive semantics are untouched. Options (validated): GrpcStreamBatchMaxEvents 100 (1 disables), GrpcStreamBatchWindow 25 ms — validated strictly under 250 ms, the load test's end-to-end P99 threshold. Measured worst case (trickle-with-backlog, window-bound rather than cap-bound): P50 13.8 ms, P99 25.4 ms, max 25.8 ms; cap-bound case sent 600 queued events in 6 frames. Telemetry: histogram scadabridge.site.stream.batch_size tagged by stream kind, recorded only on negotiated streams (per-event otherwise). It rides ScadaBridgeTelemetry.MeterName, already in the ObservedMeters allowlist. Docs: Component-Communication.md gains an Event Batching section; CLAUDE.md's gRPC streaming bullet records the wire shape and the negotiation rationale.
2026-08-15 03:39:59 -04:00
parent 2b74851f96
commit 9b5cb3dd9d
16 changed files with 2150 additions and 131 deletions
@@ -90,6 +90,73 @@ public class CommunicationOptionsValidatorTests
        Assert.Contains("GrpcMaxConcurrentStreams", result.FailureMessage);
    }

+    // ── R2: site→central stream event batching ──────────────────────────────────
+
+    [Fact]
+    public void DefaultStreamBatchOptions_AreValid()
+    {
+        var options = new CommunicationOptions();
+        Assert.Equal(100, options.GrpcStreamBatchMaxEvents);
+        Assert.Equal(TimeSpan.FromMilliseconds(25), options.GrpcStreamBatchWindow);
+        Assert.True(Validate(options).Succeeded);
+    }
+
+    [Fact]
+    public void StreamBatchMaxEventsOfOne_IsValid_AndMeansBatchingDisabled()
+    {
+        var result = Validate(new CommunicationOptions { GrpcStreamBatchMaxEvents = 1 });
+        Assert.True(result.Succeeded, result.FailureMessage);
+    }
+
+    [Fact]
+    public void NonPositiveStreamBatchMaxEvents_IsRejected()
+    {
+        var result = Validate(new CommunicationOptions { GrpcStreamBatchMaxEvents = 0 });
+        Assert.True(result.Failed);
+        Assert.Contains("GrpcStreamBatchMaxEvents", result.FailureMessage);
+    }
+
+    [Fact]
+    public void ZeroStreamBatchWindow_IsValid()
+    {
+        // Zero = "pack only what is already queued, never wait" — a legitimate posture for
+        // a latency-critical deployment that still wants the framing saving.
+        var result = Validate(new CommunicationOptions { GrpcStreamBatchWindow = TimeSpan.Zero });
+        Assert.True(result.Succeeded, result.FailureMessage);
+    }
+
+    [Fact]
+    public void NegativeStreamBatchWindow_IsRejected()
+    {
+        var result = Validate(new CommunicationOptions
+        {
+            GrpcStreamBatchWindow = TimeSpan.FromMilliseconds(-1)
+        });
+        Assert.True(result.Failed);
+        Assert.Contains("GrpcStreamBatchWindow", result.FailureMessage);
+    }
+
+    [Fact]
+    public void StreamBatchWindowAtOrAboveTheLatencyBudget_IsRejected()
+    {
+        // The coalescing window is the only latency batching adds and the target-scale
+        // load test holds end-to-end stream latency to a 250 ms P99 — a window that could
+        // spend the whole budget must not boot.
+        foreach (var window in new[] { TimeSpan.FromMilliseconds(250), TimeSpan.FromSeconds(1) })
+        {
+            var result = Validate(new CommunicationOptions { GrpcStreamBatchWindow = window });
+            Assert.True(result.Failed, $"{window} was accepted");
+            Assert.Contains("GrpcStreamBatchWindow", result.FailureMessage);
+        }
+
+        // Just inside the ceiling is accepted — the bound is exclusive, not a round-down.
+        Assert.True(Validate(new CommunicationOptions
+        {
+            GrpcStreamBatchWindow = CommunicationOptionsValidator.StreamBatchWindowCeiling
+                - TimeSpan.FromMilliseconds(1)
+        }).Succeeded);
+    }
+
    // ── Aggregated live alarm cache options (plan #10, Task 6) ───────────────────

    [Fact]