ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.PerformanceTests/Streaming/SiteStreamThroughputTests.cs

using System.Diagnostics;
using Akka.Actor;
using Microsoft.Extensions.Logging.Abstractions;
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Streaming;
using ZB.MOM.WW.ScadaBridge.SiteRuntime;
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Streaming;

namespace ZB.MOM.WW.ScadaBridge.PerformanceTests.Streaming;

/// <summary>
/// Throughput measurement for the site-wide attribute/alarm stream
/// (<see cref="SiteStreamManager"/>: <c>Source.ActorRef</c> → <c>BroadcastHub</c>
/// with per-subscriber buffering, <c>DropHead</c> overflow). Design envelope: this
/// stream carries every attribute value change on a site; it must comfortably
/// sustain tens of thousands of events/sec. Thresholds are deliberately
/// conservative (CI-machine safe) — this test exists to catch order-of-magnitude
/// regressions, not to benchmark.
/// </summary>
/// <remarks>
/// <para>
/// This is the first of the two highest-value real measurements arch-review 08 §2.3
/// called for. It follows the existing <c>HotPathLatencyTests</c> style:
/// <see cref="Stopwatch"/>-based, <c>[Trait("Category", "Performance")]</c>,
/// conservative thresholds so CI stays green on slow machines.
/// </para>
/// <para>
/// It spins up a real (non-clustered) <see cref="ActorSystem"/> rather than using
/// Akka.TestKit — the PerformanceTests project references SiteRuntime (which brings
/// in Akka + Akka.Streams transitively) but not Akka.TestKit.Xunit2, so no csproj
/// change is required.
/// </para>
/// </remarks>
public class SiteStreamThroughputTests
{
    private sealed class CountingActor : ReceiveActor
    {
        public static long Received;

        /// <summary>Initializes the actor and registers the handlers that count received attribute value changes.</summary>
        public CountingActor()
        {
            // The manager Tells the raw ISiteStreamEvent record (AttributeValueChanged)
            // straight to the subscriber — no wrapper — so we match on the record.
            Receive<AttributeValueChanged>(_ => Interlocked.Increment(ref Received));
            ReceiveAny(_ => { });
        }
    }

    /// <summary>Verifies that the site stream sustains at least 10,000 events per second to a single subscriber.</summary>
    /// <returns>A task that represents the asynchronous operation.</returns>
    [Trait("Category", "Performance")]
    [Fact]
    public async Task SiteStream_SustainsAtLeast10kEventsPerSecond_ToOneSubscriber()
    {
        const int eventCount = 100_000;
        CountingActor.Received = 0;

        var system = ActorSystem.Create("SiteStreamThroughputTests");
        try
        {
            // Buffer sized to the whole burst so DropHead should not fire.
            var manager = new SiteStreamManager(
                new SiteRuntimeOptions { StreamBufferSize = eventCount },
                NullLogger<SiteStreamManager>.Instance);
            manager.Initialize(system);

            var counter = system.ActorOf(Props.Create<CountingActor>());
            manager.Subscribe("PerfInstance", counter);

            var sw = Stopwatch.StartNew();
            for (var i = 0; i < eventCount; i++)
            {
                manager.PublishAttributeValueChanged(new AttributeValueChanged(
                    "PerfInstance", "Attr", "Attr", i, "Good", DateTimeOffset.UtcNow));
            }

            // Drain: wait until the counter goes quiet (no growth across a 200ms window).
            long last = -1;
            var deadline = DateTime.UtcNow.AddSeconds(30);
            while (DateTime.UtcNow < deadline)
            {
                var now = Interlocked.Read(ref CountingActor.Received);
                if (now == last && now > 0) break;
                last = now;
                await Task.Delay(200);
            }
            sw.Stop();

            var received = Interlocked.Read(ref CountingActor.Received);
            var eventsPerSecond = received / sw.Elapsed.TotalSeconds;

            // DropHead means under extreme pressure some events may drop; with the
            // buffer sized to the burst, deliver ratio should be ~1.0.
            Assert.True(received >= eventCount * 0.9,
                $"Expected >=90% delivery, got {received}/{eventCount}");
            Assert.True(eventsPerSecond >= 10_000,
                $"Expected >=10k events/s sustained, got {eventsPerSecond:F0}/s over {sw.Elapsed.TotalSeconds:F1}s " +
                $"(delivered {received}/{eventCount})");
        }
        finally
        {
            await system.Terminate();
        }
    }
}