Add the spec-required 100/1000-event batching tests and cluster-failover
tests that were missing from the existing C.1 suite:
- AahClientManagedAlarmEventWriterTests: add Large_batch_all_ack_returns_all_true
(batchSize 100 + 1000) and Large_batch_alternating_outcomes_are_positionally_correct
(batchSize 100 + 1000) to satisfy the "1 / 100 / 1000 events" spec requirement;
add Backend_retry_then_succeed_simulates_cluster_failover to cover the
RetryPlease-then-Ack sequence at the IPC layer (unit-level stand-in for the
rig-gated live cluster-failover path).
- SdkAlarmHistorianWriteBackendTests (new file): unit tests that pin the
placeholder backend's RetryPlease-for-every-slot contract (preserves queued
events while D.1 is unresolved); plus two Skip("rig-required") integration
tests covering the live SDK single-event roundtrip and cluster failover via
HistorianClusterEndpointPicker — remove the Skip in PR D.1.
Feasibility note: aahClientManaged.dll IS present in lib/ and referenced in
the csproj; the SDK call site is isolated behind IAlarmHistorianWriteBackend
in SdkAlarmHistorianWriteBackend.WriteBatchAsync (single method, D.1 seam).
The full AahClientManagedAlarmEventWriter implementation was already complete.
Build: 0 errors, 0 warnings.
Tests: 64 passed, 2 skipped (rig-gated), 0 failed.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
246 lines
11 KiB
C#
246 lines
11 KiB
C#
using System;
|
|
using System.Collections.Generic;
|
|
using System.Linq;
|
|
using System.Threading;
|
|
using System.Threading.Tasks;
|
|
using Shouldly;
|
|
using Xunit;
|
|
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Backend;
|
|
using ZB.MOM.WW.OtOpcUa.Driver.Historian.Wonderware.Ipc;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Driver.Galaxy.Host.Tests
|
|
{
|
|
/// <summary>
|
|
/// PR C.1 — pins the trinary outcome → IPC bool[] mapping that the sidecar uses
|
|
/// on the WriteAlarmEvents reply. Per-event outcomes:
|
|
/// Ack → true, RetryPlease → false, PermanentFail → false.
|
|
/// The sender's B.4 widens the IPC bool back into the trinary outcome at the
|
|
/// IPC boundary using structured diagnostics; the wire intentionally collapses
|
|
/// to "ok / not-ok".
|
|
/// </summary>
|
|
[Trait("Category", "Unit")]
|
|
public sealed class AahClientManagedAlarmEventWriterTests
|
|
{
|
|
[Fact]
|
|
public async Task Empty_batch_returns_empty_array_without_invoking_backend()
|
|
{
|
|
var backend = new RecordingBackend(_ => throw new InvalidOperationException("must not invoke for empty input"));
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var result = await writer.WriteAsync(Array.Empty<AlarmHistorianEventDto>(), CancellationToken.None);
|
|
|
|
result.ShouldBeEmpty();
|
|
backend.Calls.ShouldBe(0);
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Single_ack_outcome_maps_to_true()
|
|
{
|
|
var backend = new RecordingBackend(events => events.Select(_ => AlarmHistorianWriteOutcome.Ack).ToArray());
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var result = await writer.WriteAsync(new[] { Event("E1") }, CancellationToken.None);
|
|
|
|
result.ShouldBe(new[] { true });
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Mixed_batch_preserves_per_slot_ordering()
|
|
{
|
|
// Ack / Retry / Permanent / Ack — the sender uses positional matching against
|
|
// its queue, so every slot must hit the exact bool corresponding to its input.
|
|
var backend = new RecordingBackend(_ => new[]
|
|
{
|
|
AlarmHistorianWriteOutcome.Ack,
|
|
AlarmHistorianWriteOutcome.RetryPlease,
|
|
AlarmHistorianWriteOutcome.PermanentFail,
|
|
AlarmHistorianWriteOutcome.Ack,
|
|
});
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var result = await writer.WriteAsync(
|
|
new[] { Event("E1"), Event("E2"), Event("E3"), Event("E4") },
|
|
CancellationToken.None);
|
|
|
|
result.ShouldBe(new[] { true, false, false, true });
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Backend_exception_marks_whole_batch_RetryPlease()
|
|
{
|
|
var backend = new RecordingBackend(_ => throw new InvalidOperationException("cluster unreachable"));
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var result = await writer.WriteAsync(
|
|
new[] { Event("E1"), Event("E2"), Event("E3") },
|
|
CancellationToken.None);
|
|
|
|
// Whole batch must end up as "not ok" (RetryPlease at the trinary layer) —
|
|
// dropping a transiently-failed batch corrupts the sender's queue.
|
|
result.ShouldBe(new[] { false, false, false });
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Cancellation_propagates_from_backend()
|
|
{
|
|
var backend = new RecordingBackend(_ => throw new OperationCanceledException());
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var ex = await Should.ThrowAsync<OperationCanceledException>(() =>
|
|
writer.WriteAsync(new[] { Event("E1") }, CancellationToken.None));
|
|
ex.ShouldNotBeNull();
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Backend_returning_wrong_count_degrades_to_RetryPlease()
|
|
{
|
|
// Backend returns more outcomes than inputs — defensive degrade rather than
|
|
// letting a backend bug desync the sender's queue accounting.
|
|
var backend = new RecordingBackend(_ => new[]
|
|
{
|
|
AlarmHistorianWriteOutcome.Ack,
|
|
AlarmHistorianWriteOutcome.Ack,
|
|
});
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var result = await writer.WriteAsync(new[] { Event("E1") }, CancellationToken.None);
|
|
|
|
result.ShouldBe(new[] { false });
|
|
}
|
|
|
|
[Theory]
|
|
[InlineData(100)]
|
|
[InlineData(1000)]
|
|
public async Task Large_batch_all_ack_returns_all_true(int batchSize)
|
|
{
|
|
// Spec: "1 / 100 / 1000 events through a fake aahClientManaged writer;
|
|
// assert per-row outcome list parallel to input order."
|
|
var backend = new RecordingBackend(events => events.Select(_ => AlarmHistorianWriteOutcome.Ack).ToArray());
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var batch = Enumerable.Range(0, batchSize)
|
|
.Select(i => Event($"E{i}"))
|
|
.ToArray();
|
|
|
|
var result = await writer.WriteAsync(batch, CancellationToken.None);
|
|
|
|
result.Length.ShouldBe(batchSize);
|
|
result.ShouldAllBe(ok => ok);
|
|
backend.Calls.ShouldBe(1);
|
|
}
|
|
|
|
[Theory]
|
|
[InlineData(100)]
|
|
[InlineData(1000)]
|
|
public async Task Large_batch_alternating_outcomes_are_positionally_correct(int batchSize)
|
|
{
|
|
// Verifies that per-row outcome ordering is preserved for large batches;
|
|
// a backend that returns the outcomes in a different allocation order would
|
|
// fail this test if the writer incorrectly indexing outcomes.
|
|
var backend = new RecordingBackend(events =>
|
|
events.Select((_, i) => i % 2 == 0
|
|
? AlarmHistorianWriteOutcome.Ack
|
|
: AlarmHistorianWriteOutcome.RetryPlease).ToArray());
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
|
|
var batch = Enumerable.Range(0, batchSize).Select(i => Event($"E{i}")).ToArray();
|
|
var result = await writer.WriteAsync(batch, CancellationToken.None);
|
|
|
|
result.Length.ShouldBe(batchSize);
|
|
for (var i = 0; i < result.Length; i++)
|
|
{
|
|
var expected = i % 2 == 0;
|
|
result[i].ShouldBe(expected, $"slot {i}: expected {expected}");
|
|
}
|
|
}
|
|
|
|
[Fact]
|
|
public async Task Backend_retry_then_succeed_simulates_cluster_failover()
|
|
{
|
|
// Spec: "Cluster failover: primary node returns BadCommunicationError;
|
|
// picker rotates to secondary; assert eventual success."
|
|
//
|
|
// The real cluster-failover path is internal to SdkAlarmHistorianWriteBackend
|
|
// (which is rig-gated) and is exercised at the HistorianClusterEndpointPicker
|
|
// level in HistorianClusterEndpointPickerTests. Here we test the
|
|
// AahClientManagedAlarmEventWriter's handling of a backend that returns
|
|
// RetryPlease on the first call (primary-node failure) and Ack on the
|
|
// second call (secondary-node success), confirming the IPC layer correctly
|
|
// propagates the trinary outcome across two separate drain ticks.
|
|
var callCount = 0;
|
|
var backend = new RecordingBackend(events =>
|
|
{
|
|
callCount++;
|
|
if (callCount == 1)
|
|
{
|
|
// First call: simulate communication error (isCommunicationError=true)
|
|
// which produces RetryPlease — equivalent to primary node failing.
|
|
return events.Select(_ => AlarmHistorianWriteOutcome.RetryPlease).ToArray();
|
|
}
|
|
// Second call (after cluster picker has rotated to secondary): Ack.
|
|
return events.Select(_ => AlarmHistorianWriteOutcome.Ack).ToArray();
|
|
});
|
|
var writer = new AahClientManagedAlarmEventWriter(backend);
|
|
var batch = new[] { Event("E1"), Event("E2") };
|
|
|
|
// First drain tick: primary "fails" → all RetryPlease (false at IPC layer).
|
|
var firstResult = await writer.WriteAsync(batch, CancellationToken.None);
|
|
firstResult.ShouldBe(new[] { false, false });
|
|
|
|
// Second drain tick: secondary succeeds → all Ack (true at IPC layer).
|
|
var secondResult = await writer.WriteAsync(batch, CancellationToken.None);
|
|
secondResult.ShouldBe(new[] { true, true });
|
|
|
|
backend.Calls.ShouldBe(2);
|
|
}
|
|
|
|
[Theory]
|
|
// hresult 0 + clean → Ack
|
|
[InlineData(0, false, false, AlarmHistorianWriteOutcome.Ack)]
|
|
// hresult 0 but malformed → PermanentFail (malformed wins)
|
|
[InlineData(0, false, true, AlarmHistorianWriteOutcome.PermanentFail)]
|
|
// non-zero hresult + comm error → RetryPlease
|
|
[InlineData(unchecked((int)0x80131500), true, false, AlarmHistorianWriteOutcome.RetryPlease)]
|
|
// non-zero hresult, no comm flag, no malformed → conservative RetryPlease
|
|
[InlineData(unchecked((int)0x80131500), false, false, AlarmHistorianWriteOutcome.RetryPlease)]
|
|
// any malformed input → PermanentFail regardless of hresult
|
|
[InlineData(unchecked((int)0x80131500), true, true, AlarmHistorianWriteOutcome.PermanentFail)]
|
|
public void MapOutcome_table(int hresult, bool isCommunicationError, bool isMalformedInput, AlarmHistorianWriteOutcome expected)
|
|
{
|
|
AahClientManagedAlarmEventWriter
|
|
.MapOutcome(hresult, isCommunicationError, isMalformedInput)
|
|
.ShouldBe(expected);
|
|
}
|
|
|
|
private static AlarmHistorianEventDto Event(string id) => new AlarmHistorianEventDto
|
|
{
|
|
EventId = id,
|
|
SourceName = "Tank01",
|
|
ConditionId = "Tank01.Level.HiHi",
|
|
AlarmType = "AnalogLimitAlarm.HiHi",
|
|
Message = "Tank 01 high-high level",
|
|
Severity = 750,
|
|
EventTimeUtcTicks = DateTime.UtcNow.Ticks,
|
|
AckComment = null,
|
|
};
|
|
|
|
private sealed class RecordingBackend : IAlarmHistorianWriteBackend
|
|
{
|
|
private readonly Func<AlarmHistorianEventDto[], AlarmHistorianWriteOutcome[]> _produce;
|
|
public int Calls { get; private set; }
|
|
|
|
public RecordingBackend(Func<AlarmHistorianEventDto[], AlarmHistorianWriteOutcome[]> produce)
|
|
{
|
|
_produce = produce;
|
|
}
|
|
|
|
public Task<AlarmHistorianWriteOutcome[]> WriteBatchAsync(
|
|
AlarmHistorianEventDto[] events, CancellationToken cancellationToken)
|
|
{
|
|
Calls++;
|
|
return Task.FromResult(_produce(events));
|
|
}
|
|
}
|
|
}
|
|
}
|