Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.Host.Tests/Grpc/TelemetryStreamGrpcServiceTests.cs
T

358 lines
16 KiB
C#

using Grpc.Core;
using Microsoft.Extensions.Logging.Abstractions;
using Shouldly;
using Xunit;
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Alerts;
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Drivers;
using ZB.MOM.WW.OtOpcUa.Commons.Messages.Logging;
using ZB.MOM.WW.OtOpcUa.Commons.Protos.Telemetry.V1;
using ZB.MOM.WW.OtOpcUa.Host.Grpc;
using ZB.MOM.WW.OtOpcUa.Runtime.Telemetry;
namespace ZB.MOM.WW.OtOpcUa.Host.Tests.Grpc;
/// <summary>
/// Verifies the node-side telemetry streaming service (per-cluster mesh Phase 5): the hub is
/// fanned to a connected caller as <see cref="TelemetryEvent"/> envelopes, every domain field is
/// transcribed onto its proto field, DateTime→Timestamp mapping is Kind-defensive, a cancelled
/// context ends the stream cleanly, and the process-wide concurrency cap sheds excess dials with
/// <see cref="StatusCode.ResourceExhausted"/>.
/// </summary>
public sealed class TelemetryStreamGrpcServiceTests
{
private static TelemetryStreamGrpcService NewService(ITelemetryLocalHub hub) =>
new(hub, NullLogger<TelemetryStreamGrpcService>.Instance);
private static ServerCallContext Ctx(CancellationToken token) => new FakeServerCallContext(token);
private static async Task WaitUntilAsync(Func<bool> condition, string because)
{
var deadline = DateTime.UtcNow.AddSeconds(5);
while (DateTime.UtcNow < deadline)
{
if (condition())
return;
await Task.Delay(15);
}
throw new TimeoutException($"Timed out waiting: {because}");
}
[Fact]
public async Task Streams_one_of_each_kind_with_fields_transcribed()
{
var hub = new TelemetryLocalHub();
var service = NewService(hub);
var writer = new CapturingStreamWriter();
using var cts = new CancellationTokenSource();
var request = new TelemetryStreamRequest { CorrelationId = "corr-1" };
var publishedHealth = new DateTime(2026, 7, 23, 10, 0, 0, DateTimeKind.Utc);
var health = new DriverHealthChanged(
"cluster-a", "drv-1", "Healthy", LastSuccessfulReadUtc: null, LastError: null,
ErrorCount5Min: 3, PublishedUtc: publishedHealth);
var resilience = new DriverResilienceStatusChanged(
"drv-1", "host-x", BreakerOpen: true, ConsecutiveFailures: 4, CurrentInFlight: 2,
LastBreakerOpenUtc: null, LastSampledUtc: DateTime.UtcNow, PublishedUtc: DateTime.UtcNow);
// Snapshot-style items are cached, so emitting them BEFORE the service attaches guarantees they
// are replayed to the fresh subscription — a deterministic "the pump is draining" signal.
hub.Emit(new TelemetryItem.Health(health));
hub.Emit(new TelemetryItem.Resilience(resilience));
var pump = service.Subscribe(request, writer, Ctx(cts.Token));
await WaitUntilAsync(() => writer.Count >= 2, "cached snapshots to be replayed");
// Append-style items are live-only: emit them once the subscription is proven attached.
var alarm = new AlarmTransitionEvent(
"raw/dev/Speed", "Area/Line/Equip", "HighSpeed", "Activated", 700, "over limit", "operator1",
new DateTime(2026, 7, 23, 11, 0, 0, DateTimeKind.Utc), "LimitAlarm",
Comment: "manual ack", HistorizeToAveva: true,
ReferencingEquipmentPaths: ["Area/Line/EquipA", "Area/Line/EquipB"]);
var script = new ScriptLogEntry(
"script-9", "Warning", "threshold near", new DateTime(2026, 7, 23, 12, 0, 0, DateTimeKind.Utc),
VirtualTagId: "vt-1", AlarmId: null, EquipmentId: "equip-1");
hub.Emit(new TelemetryItem.Alarm(alarm));
hub.Emit(new TelemetryItem.Script(script));
await WaitUntilAsync(() => writer.Count >= 4, "all four telemetry events to be streamed");
cts.Cancel();
await pump; // cancellation must be swallowed — Subscribe returns cleanly.
var events = writer.Snapshot();
events.ShouldAllBe(e => e.CorrelationId == "corr-1");
var healthEvt = events.Single(e => e.EventCase == TelemetryEvent.EventOneofCase.DriverHealth);
healthEvt.DriverHealth.ClusterId.ShouldBe("cluster-a");
healthEvt.DriverHealth.State.ShouldBe("Healthy");
healthEvt.DriverHealth.ErrorCount5Min.ShouldBe(3);
healthEvt.DriverHealth.PublishedUtc.ToDateTime().ShouldBe(publishedHealth);
healthEvt.DriverHealth.LastSuccessfulReadUtc.ShouldBeNull(); // nullable DateTime absent
healthEvt.DriverHealth.HasLastError.ShouldBeFalse(); // nullable string absent
var resilienceEvt = events.Single(e => e.EventCase == TelemetryEvent.EventOneofCase.DriverResilience);
resilienceEvt.DriverResilience.DriverInstanceId.ShouldBe("drv-1");
resilienceEvt.DriverResilience.BreakerOpen.ShouldBeTrue();
resilienceEvt.DriverResilience.LastBreakerOpenUtc.ShouldBeNull();
var alarmEvt = events.Single(e => e.EventCase == TelemetryEvent.EventOneofCase.AlarmTransition);
alarmEvt.AlarmTransition.AlarmId.ShouldBe("raw/dev/Speed");
alarmEvt.AlarmTransition.TransitionKind.ShouldBe("Activated");
alarmEvt.AlarmTransition.Severity.ShouldBe(700);
alarmEvt.AlarmTransition.Comment.ShouldBe("manual ack");
alarmEvt.AlarmTransition.HistorizeToAveva.ShouldBeTrue();
alarmEvt.AlarmTransition.ReferencingEquipmentPaths.ShouldBe(["Area/Line/EquipA", "Area/Line/EquipB"]);
var scriptEvt = events.Single(e => e.EventCase == TelemetryEvent.EventOneofCase.ScriptLog);
scriptEvt.ScriptLog.ScriptId.ShouldBe("script-9");
scriptEvt.ScriptLog.Level.ShouldBe("Warning");
scriptEvt.ScriptLog.VirtualTagId.ShouldBe("vt-1");
scriptEvt.ScriptLog.HasAlarmId.ShouldBeFalse(); // nullable string absent
scriptEvt.ScriptLog.EquipmentId.ShouldBe("equip-1");
}
[Fact]
public async Task Cancelled_context_ends_stream_cleanly()
{
var hub = new TelemetryLocalHub();
var service = NewService(hub);
var writer = new CapturingStreamWriter();
using var cts = new CancellationTokenSource();
var request = new TelemetryStreamRequest { CorrelationId = "corr-cancel" };
var pump = service.Subscribe(request, writer, Ctx(cts.Token));
cts.Cancel();
await Should.NotThrowAsync(() => pump); // client disconnect is normal, not an error.
}
[Theory]
[InlineData("")]
[InlineData(" ")]
public async Task Empty_correlation_id_is_invalid_argument(string correlationId)
{
var service = NewService(new TelemetryLocalHub());
using var cts = new CancellationTokenSource();
var ex = await Should.ThrowAsync<RpcException>(() => service.Subscribe(
new TelemetryStreamRequest { CorrelationId = correlationId },
new CapturingStreamWriter(), Ctx(cts.Token)));
ex.StatusCode.ShouldBe(StatusCode.InvalidArgument);
}
[Fact]
public async Task Over_long_correlation_id_is_invalid_argument()
{
var service = NewService(new TelemetryLocalHub());
using var cts = new CancellationTokenSource();
var ex = await Should.ThrowAsync<RpcException>(() => service.Subscribe(
new TelemetryStreamRequest { CorrelationId = new string('x', 257) },
new CapturingStreamWriter(), Ctx(cts.Token)));
ex.StatusCode.ShouldBe(StatusCode.InvalidArgument);
}
[Fact]
public async Task Concurrency_cap_sheds_the_over_the_limit_dial()
{
// Serial assembly (see AssemblyInfo) => the static active-stream counter starts at 0 here.
var hub = new TelemetryLocalHub();
var service = NewService(hub);
using var cts = new CancellationTokenSource();
// Open exactly the cap. Each stream blocks in the pump (hub emits nothing and is never completed),
// so all 100 stay open, holding the counter at 100.
var open = new List<Task>();
for (var i = 0; i < 100; i++)
open.Add(service.Subscribe(
new TelemetryStreamRequest { CorrelationId = $"cap-{i}" },
new CapturingStreamWriter(), Ctx(cts.Token)));
// The 101st dial must be rejected.
var ex = await Should.ThrowAsync<RpcException>(() => service.Subscribe(
new TelemetryStreamRequest { CorrelationId = "cap-overflow" },
new CapturingStreamWriter(), Ctx(cts.Token)));
ex.StatusCode.ShouldBe(StatusCode.ResourceExhausted);
// Drain the 100 open streams; the counter returns to 0 for the next test.
cts.Cancel();
await Task.WhenAll(open);
// With the counter back at 0, a fresh single dial is accepted (proves no leak / no double-count).
using var cts2 = new CancellationTokenSource();
var writer = new CapturingStreamWriter();
var pump = service.Subscribe(
new TelemetryStreamRequest { CorrelationId = "cap-after" }, writer, Ctx(cts2.Token));
cts2.Cancel();
await Should.NotThrowAsync(() => pump);
}
[Fact]
public void ToProto_health_with_unspecified_kind_datetime_does_not_throw_and_roundtrips()
{
// Producers use UtcNow, but a Kind=Unspecified value must never crash the stream. The mapper
// assumes an Unspecified value is already-UTC, so the instant round-trips on any machine.
var wall = new DateTime(2026, 7, 23, 13, 30, 0, DateTimeKind.Unspecified);
var expectedUtc = DateTime.SpecifyKind(wall, DateTimeKind.Utc);
var health = new DriverHealthChanged(
"cluster-a", "drv-1", "Healthy", LastSuccessfulReadUtc: wall, LastError: null,
ErrorCount5Min: 0, PublishedUtc: wall);
TelemetryEvent evt = null!;
Should.NotThrow(() => evt = TelemetryProtoMapNode.ToProto(new TelemetryItem.Health(health), "c"));
evt.DriverHealth.PublishedUtc.ToDateTime().ShouldBe(expectedUtc);
evt.DriverHealth.LastSuccessfulReadUtc.ToDateTime().ShouldBe(expectedUtc);
}
[Fact]
public async Task Client_disconnect_mid_stream_ends_cleanly_without_leaking_a_slot()
{
// A broken pipe surfaces as IOException out of WriteAsync. It must be swallowed as a routine
// disconnect (not escape), and the finally must still decrement the counter. Looping well past
// the cap proves no leak: a single leaked slot per pass would trip ResourceExhausted by pass 101.
var hub = new TelemetryLocalHub();
var service = NewService(hub);
// Cached snapshot ⇒ every fresh subscription is deterministically handed one item to write.
hub.Emit(new TelemetryItem.Health(new DriverHealthChanged(
"cluster-a", "drv-1", "Healthy", null, null, 0, DateTime.UtcNow)));
for (var i = 0; i < 150; i++)
{
using var cts = new CancellationTokenSource();
var pump = service.Subscribe(
new TelemetryStreamRequest { CorrelationId = $"disc-{i}" },
new ThrowingStreamWriter(new IOException("connection reset")),
Ctx(cts.Token));
// No exception escapes Subscribe, and no ResourceExhausted ever fires (proves the slot is freed).
await Should.NotThrowAsync(() => pump);
}
// Counter is back at its prior value: a normal stream still opens and pumps.
using var okCts = new CancellationTokenSource();
var writer = new CapturingStreamWriter();
var okPump = service.Subscribe(
new TelemetryStreamRequest { CorrelationId = "disc-after" }, writer, Ctx(okCts.Token));
await WaitUntilAsync(() => writer.Count >= 1, "the cached snapshot to stream after the disconnect loop");
okCts.Cancel();
await okPump;
}
[Fact]
public void ToProto_null_required_string_does_not_throw_and_maps_to_empty()
{
// Required proto string setters throw on null; the domain records carry no runtime guard.
var alarm = new AlarmTransitionEvent(
AlarmId: null!, EquipmentPath: null!, AlarmName: null!, TransitionKind: null!,
Severity: 100, Message: null!, User: null!, TimestampUtc: DateTime.UtcNow,
AlarmTypeName: null!, Comment: null, HistorizeToAveva: null, ReferencingEquipmentPaths: null);
AlarmTransition msg = null!;
Should.NotThrow(() => msg = TelemetryProtoMapNode.ToProto(new TelemetryItem.Alarm(alarm), "c").AlarmTransition);
msg.AlarmId.ShouldBe("");
msg.EquipmentPath.ShouldBe("");
msg.AlarmName.ShouldBe("");
msg.TransitionKind.ShouldBe("");
msg.Message.ShouldBe("");
msg.User.ShouldBe("");
msg.AlarmTypeName.ShouldBe("");
}
[Fact]
public void ToProto_alarm_omits_absent_nullables()
{
var alarm = new AlarmTransitionEvent(
"id", "Area/Line/Equip", "Name", "Cleared", 100, "msg", "system",
DateTime.UtcNow, Comment: null, HistorizeToAveva: null, ReferencingEquipmentPaths: null);
var msg = TelemetryProtoMapNode.ToProto(new TelemetryItem.Alarm(alarm), "c").AlarmTransition;
msg.HasComment.ShouldBeFalse();
msg.HasHistorizeToAveva.ShouldBeFalse();
msg.ReferencingEquipmentPaths.ShouldBeEmpty();
}
/// <summary>Minimal <see cref="ServerCallContext"/> exposing a caller-controlled cancellation token.</summary>
private sealed class FakeServerCallContext(CancellationToken token) : ServerCallContext
{
protected override string MethodCore => "/telemetry.v1.TelemetryStreamService/Subscribe";
protected override string HostCore => "localhost";
protected override string PeerCore => "ipv4:127.0.0.1:0";
protected override DateTime DeadlineCore => DateTime.MaxValue;
protected override Metadata RequestHeadersCore => [];
protected override CancellationToken CancellationTokenCore => token;
protected override Metadata ResponseTrailersCore { get; } = [];
protected override Status StatusCore { get; set; }
protected override WriteOptions? WriteOptionsCore { get; set; }
protected override AuthContext AuthContextCore => new(null, new Dictionary<string, List<AuthProperty>>());
protected override ContextPropagationToken CreatePropagationTokenCore(ContextPropagationOptions? options) =>
throw new NotSupportedException();
protected override Task WriteResponseHeadersAsyncCore(Metadata responseHeaders) => Task.CompletedTask;
}
/// <summary>
/// Captures every streamed <see cref="TelemetryEvent"/>. Implements the cancellable
/// <c>WriteAsync</c> overload explicitly — otherwise the interface's default method throws
/// <see cref="NotSupportedException"/> for the pump's cancellable lifetime token.
/// </summary>
private sealed class CapturingStreamWriter : IServerStreamWriter<TelemetryEvent>
{
private readonly List<TelemetryEvent> _items = [];
private readonly Lock _gate = new();
public WriteOptions? WriteOptions { get; set; }
public int Count
{
get
{
lock (_gate)
return _items.Count;
}
}
public Task WriteAsync(TelemetryEvent message)
{
lock (_gate)
_items.Add(message);
return Task.CompletedTask;
}
public Task WriteAsync(TelemetryEvent message, CancellationToken cancellationToken)
{
cancellationToken.ThrowIfCancellationRequested();
return WriteAsync(message);
}
public List<TelemetryEvent> Snapshot()
{
lock (_gate)
return [.. _items];
}
}
/// <summary>A stream writer that always throws the given exception — models a broken client pipe.</summary>
private sealed class ThrowingStreamWriter(Exception toThrow) : IServerStreamWriter<TelemetryEvent>
{
public WriteOptions? WriteOptions { get; set; }
public Task WriteAsync(TelemetryEvent message) => throw toThrow;
public Task WriteAsync(TelemetryEvent message, CancellationToken cancellationToken)
{
cancellationToken.ThrowIfCancellationRequested();
return WriteAsync(message);
}
}
}