feat(auditlog): combined telemetry dual-write transaction (#23 M3)

This commit is contained in:
Joseph Doherty
2026-05-20 14:33:14 -04:00
parent 2b54290c7f
commit 0a97fff906
6 changed files with 777 additions and 0 deletions

View File

@@ -0,0 +1,391 @@
using Akka.Actor;
using Akka.TestKit.Xunit2;
using Microsoft.EntityFrameworkCore;
using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Logging.Abstractions;
using ScadaLink.AuditLog.Central;
using ScadaLink.Commons.Entities.Audit;
using ScadaLink.Commons.Interfaces.Repositories;
using ScadaLink.Commons.Messages.Audit;
using ScadaLink.Commons.Types;
using ScadaLink.Commons.Types.Audit;
using ScadaLink.Commons.Types.Enums;
using ScadaLink.ConfigurationDatabase;
using ScadaLink.ConfigurationDatabase.Repositories;
using ScadaLink.ConfigurationDatabase.Tests.Migrations;
namespace ScadaLink.AuditLog.Tests.Central;
/// <summary>
/// Bundle D D2 tests for <see cref="AuditLogIngestActor"/>'s M3 combined-
/// telemetry dual-write transaction. Uses the same <see cref="MsSqlMigrationFixture"/>
/// as the M1 + M2 repository tests so the actor exercises real
/// <see cref="AuditLogRepository.InsertIfNotExistsAsync"/> +
/// <see cref="SiteCallAuditRepository.UpsertAsync"/> against a per-test MSSQL
/// database. The transaction commits or rolls back inside one
/// <see cref="DbContext.Database"/>.
/// </summary>
public class AuditLogIngestActorCombinedTelemetryTests : TestKit, IClassFixture<MsSqlMigrationFixture>
{
private readonly MsSqlMigrationFixture _fixture;
public AuditLogIngestActorCombinedTelemetryTests(MsSqlMigrationFixture fixture)
{
_fixture = fixture;
}
private ScadaLinkDbContext CreateReadContext()
{
var options = new DbContextOptionsBuilder<ScadaLinkDbContext>()
.UseSqlServer(_fixture.ConnectionString)
.Options;
return new ScadaLinkDbContext(options);
}
private static string NewSiteId() =>
"test-bundle-d2-cached-" + Guid.NewGuid().ToString("N").Substring(0, 8);
private static (AuditEvent audit, SiteCall siteCall) NewEntry(
string siteId,
TrackedOperationId? trackedOperationId = null,
Guid? eventId = null,
string status = "Submitted",
AuditStatus auditStatus = AuditStatus.Submitted)
{
var trackedId = trackedOperationId ?? TrackedOperationId.New();
var now = new DateTime(2026, 5, 20, 10, 0, 0, DateTimeKind.Utc);
var audit = new AuditEvent
{
EventId = eventId ?? Guid.NewGuid(),
OccurredAtUtc = now,
Channel = AuditChannel.ApiOutbound,
Kind = AuditKind.CachedSubmit,
Status = auditStatus,
SourceSiteId = siteId,
CorrelationId = trackedId.Value,
};
var siteCall = new SiteCall
{
TrackedOperationId = trackedId,
Channel = "ApiOutbound",
Target = "ERP.GetOrder",
SourceSite = siteId,
Status = status,
RetryCount = 0,
CreatedAtUtc = now,
UpdatedAtUtc = now,
IngestedAtUtc = now, // overwritten by the actor
};
return (audit, siteCall);
}
/// <summary>
/// Builds a minimal DI container around the per-test MSSQL fixture's
/// connection string — DbContext + the two repositories the dual-write
/// handler resolves. Mirrors AddConfigurationDatabase without the
/// DataProtection wiring (we never write secret columns in these tests).
/// </summary>
private IServiceProvider BuildServiceProvider(
Func<ScadaLinkDbContext, ISiteCallAuditRepository>? siteCallRepoFactory = null)
{
var services = new ServiceCollection();
services.AddDbContext<ScadaLinkDbContext>(opts =>
opts.UseSqlServer(_fixture.ConnectionString)
.ConfigureWarnings(w => w.Ignore(
Microsoft.EntityFrameworkCore.Diagnostics.RelationalEventId.PendingModelChangesWarning)));
services.AddScoped<IAuditLogRepository>(sp =>
new AuditLogRepository(sp.GetRequiredService<ScadaLinkDbContext>()));
if (siteCallRepoFactory is null)
{
services.AddScoped<ISiteCallAuditRepository>(sp =>
new SiteCallAuditRepository(sp.GetRequiredService<ScadaLinkDbContext>()));
}
else
{
services.AddScoped(sp =>
siteCallRepoFactory(sp.GetRequiredService<ScadaLinkDbContext>()));
}
return services.BuildServiceProvider();
}
private IActorRef CreateActor(IServiceProvider serviceProvider) =>
Sys.ActorOf(Props.Create(() => new AuditLogIngestActor(
serviceProvider,
NullLogger<AuditLogIngestActor>.Instance)));
[SkippableFact]
public async Task Receive_OneCachedPacket_WritesAuditRow_AND_SiteCallRow_AcksId()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var (audit, siteCall) = NewEntry(siteId);
var sp = BuildServiceProvider();
var actor = CreateActor(sp);
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(audit, siteCall) }),
TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
Assert.Single(reply.AcceptedEventIds);
Assert.Equal(audit.EventId, reply.AcceptedEventIds[0]);
// Verify rows landed in both tables.
await using var read = CreateReadContext();
var auditRow = await read.Set<AuditEvent>().SingleOrDefaultAsync(e => e.EventId == audit.EventId);
Assert.NotNull(auditRow);
Assert.NotNull(auditRow!.IngestedAtUtc);
var siteCallRow = await read.Set<SiteCall>()
.SingleOrDefaultAsync(s => s.TrackedOperationId == siteCall.TrackedOperationId);
Assert.NotNull(siteCallRow);
Assert.Equal(siteCall.Status, siteCallRow!.Status);
}
[SkippableFact]
public async Task Receive_DuplicateEventId_SameStatus_NoOp_RowCountUnchanged_AcksId()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var trackedId = TrackedOperationId.New();
var eventId = Guid.NewGuid();
var (audit, siteCall) = NewEntry(siteId, trackedId, eventId);
var sp = BuildServiceProvider();
var actor = CreateActor(sp);
// First write
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(audit, siteCall) }),
TestActor);
ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
// Second write — same EventId and TrackedOperationId, same status. Both
// the audit insert (idempotent) and the SiteCalls upsert (monotonic
// same-rank → no-op) should silently do nothing while still acking.
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(audit, siteCall) }),
TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
Assert.Single(reply.AcceptedEventIds);
Assert.Equal(eventId, reply.AcceptedEventIds[0]);
await using var read = CreateReadContext();
var auditCount = await read.Set<AuditEvent>().CountAsync(e => e.EventId == eventId);
Assert.Equal(1, auditCount);
var siteCallCount = await read.Set<SiteCall>()
.CountAsync(s => s.TrackedOperationId == trackedId);
Assert.Equal(1, siteCallCount);
}
[SkippableFact]
public async Task Receive_DuplicateEventId_AdvancedSiteCallStatus_UpdatesSiteCall()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var trackedId = TrackedOperationId.New();
var sp = BuildServiceProvider();
var actor = CreateActor(sp);
// 1st packet — Submitted (audit EventId #1, SiteCalls Status=Submitted).
var (auditSubmit, siteCallSubmit) = NewEntry(
siteId, trackedId, status: "Submitted", auditStatus: AuditStatus.Submitted);
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(auditSubmit, siteCallSubmit) }),
TestActor);
ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
// 2nd packet — Attempted with retry count 1 (audit EventId #2,
// SiteCalls Status=Attempted — monotonic upsert wins). Same
// TrackedOperationId throughout.
var (auditAttempt, siteCallAttempt) = NewEntry(
siteId, trackedId, status: "Attempted", auditStatus: AuditStatus.Attempted);
var advanced = siteCallAttempt with { RetryCount = 1, UpdatedAtUtc = siteCallAttempt.UpdatedAtUtc.AddMinutes(1) };
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(auditAttempt, advanced) }),
TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
Assert.Single(reply.AcceptedEventIds);
Assert.Equal(auditAttempt.EventId, reply.AcceptedEventIds[0]);
// Both audit rows exist.
await using var read = CreateReadContext();
var auditRows = await read.Set<AuditEvent>()
.Where(e => e.SourceSiteId == siteId)
.ToListAsync();
Assert.Equal(2, auditRows.Count);
// SiteCalls row advanced to Attempted with retry count 1.
var siteCallRow = await read.Set<SiteCall>()
.SingleAsync(s => s.TrackedOperationId == trackedId);
Assert.Equal("Attempted", siteCallRow.Status);
Assert.Equal(1, siteCallRow.RetryCount);
}
[SkippableFact]
public async Task Receive_AuditInsertSucceeds_SiteCallThrows_BothRolledBack_NoOrphanRow()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var (audit, siteCall) = NewEntry(siteId);
// Wrap the SiteCalls repo so UpsertAsync always throws — the dual-write
// transaction must roll back the AuditLog INSERT done in the same
// transaction, leaving no orphan row.
var sp = BuildServiceProvider(
ctx => new ThrowingSiteCallRepo(new SiteCallAuditRepository(ctx)));
var actor = CreateActor(sp);
actor.Tell(
new IngestCachedTelemetryCommand(new[] { new CachedTelemetryEntry(audit, siteCall) }),
TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
Assert.Empty(reply.AcceptedEventIds);
await using var read = CreateReadContext();
var auditRow = await read.Set<AuditEvent>().SingleOrDefaultAsync(e => e.EventId == audit.EventId);
Assert.Null(auditRow);
var siteCallRow = await read.Set<SiteCall>()
.SingleOrDefaultAsync(s => s.TrackedOperationId == siteCall.TrackedOperationId);
Assert.Null(siteCallRow);
}
[SkippableFact]
public async Task Receive_FiveCachedPackets_AllPersistedSeparately_AllAcked()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var entries = Enumerable.Range(0, 5).Select(_ =>
{
var (audit, siteCall) = NewEntry(siteId);
return new CachedTelemetryEntry(audit, siteCall);
}).ToList();
var sp = BuildServiceProvider();
var actor = CreateActor(sp);
actor.Tell(new IngestCachedTelemetryCommand(entries), TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
Assert.Equal(5, reply.AcceptedEventIds.Count);
Assert.True(entries.Select(e => e.Audit.EventId).ToHashSet()
.SetEquals(reply.AcceptedEventIds.ToHashSet()));
await using var read = CreateReadContext();
var auditCount = await read.Set<AuditEvent>().CountAsync(e => e.SourceSiteId == siteId);
Assert.Equal(5, auditCount);
var siteCallCount = await read.Set<SiteCall>().CountAsync(s => s.SourceSite == siteId);
Assert.Equal(5, siteCallCount);
}
[SkippableFact]
public async Task Receive_OnePacketSucceeds_NextPacketThrows_FirstStillCommitted_BatchContinues()
{
Skip.IfNot(_fixture.Available, _fixture.SkipReason);
var siteId = NewSiteId();
var (audit1, siteCall1) = NewEntry(siteId);
var (audit2, siteCall2) = NewEntry(siteId);
var (audit3, siteCall3) = NewEntry(siteId);
var poisonTrackedId = siteCall2.TrackedOperationId;
// Throw only for the middle entry's TrackedOperationId — entries on
// either side must commit their own transactions independently.
var sp = BuildServiceProvider(
ctx => new PoisonOnIdSiteCallRepo(new SiteCallAuditRepository(ctx), poisonTrackedId));
var actor = CreateActor(sp);
actor.Tell(
new IngestCachedTelemetryCommand(new[]
{
new CachedTelemetryEntry(audit1, siteCall1),
new CachedTelemetryEntry(audit2, siteCall2),
new CachedTelemetryEntry(audit3, siteCall3),
}),
TestActor);
var reply = ExpectMsg<IngestCachedTelemetryReply>(TimeSpan.FromSeconds(15));
// Two entries committed; poison entry rolled back.
Assert.Equal(2, reply.AcceptedEventIds.Count);
Assert.Contains(audit1.EventId, reply.AcceptedEventIds);
Assert.Contains(audit3.EventId, reply.AcceptedEventIds);
Assert.DoesNotContain(audit2.EventId, reply.AcceptedEventIds);
await using var read = CreateReadContext();
var auditRows = await read.Set<AuditEvent>().Where(e => e.SourceSiteId == siteId).ToListAsync();
Assert.Equal(2, auditRows.Count);
Assert.DoesNotContain(auditRows, r => r.EventId == audit2.EventId);
var siteCallRows = await read.Set<SiteCall>().Where(s => s.SourceSite == siteId).ToListAsync();
Assert.Equal(2, siteCallRows.Count);
Assert.DoesNotContain(siteCallRows, r => r.TrackedOperationId == poisonTrackedId);
}
/// <summary>
/// Test double — throws unconditionally from <see cref="UpsertAsync"/> so
/// the dual-write transaction is forced to roll back. Lets the AuditLog
/// row insert succeed in-transaction; the rollback must remove it.
/// </summary>
private sealed class ThrowingSiteCallRepo : ISiteCallAuditRepository
{
private readonly ISiteCallAuditRepository _inner;
public ThrowingSiteCallRepo(ISiteCallAuditRepository inner) { _inner = inner; }
public Task UpsertAsync(SiteCall siteCall, CancellationToken ct = default) =>
throw new InvalidOperationException("simulated SiteCalls upsert failure");
public Task<SiteCall?> GetAsync(TrackedOperationId id, CancellationToken ct = default) =>
_inner.GetAsync(id, ct);
public Task<IReadOnlyList<SiteCall>> QueryAsync(
SiteCallQueryFilter filter, SiteCallPaging paging, CancellationToken ct = default) =>
_inner.QueryAsync(filter, paging, ct);
public Task<int> PurgeTerminalAsync(DateTime olderThanUtc, CancellationToken ct = default) =>
_inner.PurgeTerminalAsync(olderThanUtc, ct);
}
/// <summary>
/// Test double — throws only when the supplied poison TrackedOperationId
/// is the one being upserted. Demonstrates per-entry transaction isolation:
/// one entry's failed transaction must not abort the batch's other entries.
/// </summary>
private sealed class PoisonOnIdSiteCallRepo : ISiteCallAuditRepository
{
private readonly ISiteCallAuditRepository _inner;
private readonly TrackedOperationId _poisonId;
public PoisonOnIdSiteCallRepo(ISiteCallAuditRepository inner, TrackedOperationId poisonId)
{
_inner = inner;
_poisonId = poisonId;
}
public Task UpsertAsync(SiteCall siteCall, CancellationToken ct = default)
{
if (siteCall.TrackedOperationId == _poisonId)
{
throw new InvalidOperationException("simulated SiteCalls upsert failure for poison id");
}
return _inner.UpsertAsync(siteCall, ct);
}
public Task<SiteCall?> GetAsync(TrackedOperationId id, CancellationToken ct = default) =>
_inner.GetAsync(id, ct);
public Task<IReadOnlyList<SiteCall>> QueryAsync(
SiteCallQueryFilter filter, SiteCallPaging paging, CancellationToken ct = default) =>
_inner.QueryAsync(filter, paging, ct);
public Task<int> PurgeTerminalAsync(DateTime olderThanUtc, CancellationToken ct = default) =>
_inner.PurgeTerminalAsync(olderThanUtc, ct);
}
}

View File

@@ -0,0 +1,121 @@
using Akka.Actor;
using Akka.TestKit.Xunit2;
using Google.Protobuf.WellKnownTypes;
using Grpc.Core;
using Microsoft.Extensions.Logging.Abstractions;
using NSubstitute;
using ScadaLink.Commons.Messages.Audit;
using ScadaLink.Communication.Grpc;
namespace ScadaLink.Communication.Tests;
/// <summary>
/// Bundle D D2 tests for <see cref="SiteStreamGrpcServer.IngestCachedTelemetry"/>.
/// Verifies the DTO→entity→actor→ack round-trip through the gRPC handler. A
/// tiny <c>EchoCachedIngestActor</c> stands in for the central
/// <c>AuditLogIngestActor</c>, replying with the EventIds it received so the
/// test asserts the wiring without depending on MSSQL.
/// </summary>
public class SiteStreamIngestCachedTelemetryTests : TestKit
{
private readonly ISiteStreamSubscriber _subscriber = Substitute.For<ISiteStreamSubscriber>();
private SiteStreamGrpcServer CreateServer() =>
new(_subscriber, NullLogger<SiteStreamGrpcServer>.Instance);
private static ServerCallContext NewContext(CancellationToken ct = default)
{
var context = Substitute.For<ServerCallContext>();
context.CancellationToken.Returns(ct);
return context;
}
private static CachedTelemetryPacket NewPacket(Guid? eventId = null, Guid? trackedId = null)
{
var now = Timestamp.FromDateTime(
DateTime.SpecifyKind(new DateTime(2026, 5, 20, 10, 0, 0), DateTimeKind.Utc));
return new CachedTelemetryPacket
{
AuditEvent = new AuditEventDto
{
EventId = (eventId ?? Guid.NewGuid()).ToString(),
OccurredAtUtc = now,
Channel = "ApiOutbound",
Kind = "CachedSubmit",
Status = "Submitted",
SourceSiteId = "site-1",
CorrelationId = (trackedId ?? Guid.NewGuid()).ToString(),
},
Operational = new SiteCallOperationalDto
{
TrackedOperationId = (trackedId ?? Guid.NewGuid()).ToString(),
Channel = "ApiOutbound",
Target = "ERP.GetOrder",
SourceSite = "site-1",
Status = "Submitted",
RetryCount = 0,
CreatedAtUtc = now,
UpdatedAtUtc = now,
},
};
}
[Fact]
public async Task IngestCachedTelemetry_RoutesToActor_ReturnsReply()
{
// Arrange — stub actor that echoes every received EventId back.
var stubActor = Sys.ActorOf(Props.Create(() => new EchoCachedIngestActor()));
var server = CreateServer();
server.SetAuditIngestActor(stubActor);
var packets = Enumerable.Range(0, 3)
.Select(_ => NewPacket())
.ToList();
var batch = new CachedTelemetryBatch();
batch.Packets.AddRange(packets);
// Act
var ack = await server.IngestCachedTelemetry(batch, NewContext());
// Assert — every packet's EventId appears in the ack, demonstrating
// end-to-end routing through the actor.
Assert.Equal(3, ack.AcceptedEventIds.Count);
var expectedIds = packets.Select(p => p.AuditEvent.EventId).ToHashSet();
Assert.True(expectedIds.SetEquals(ack.AcceptedEventIds.ToHashSet()));
}
[Fact]
public async Task IngestCachedTelemetry_NoActorWired_ReturnsEmptyAck()
{
var server = CreateServer();
// Intentionally do NOT call SetAuditIngestActor — simulates host
// startup race window.
var batch = new CachedTelemetryBatch();
batch.Packets.Add(NewPacket());
var ack = await server.IngestCachedTelemetry(batch, NewContext());
Assert.Empty(ack.AcceptedEventIds);
}
/// <summary>
/// Tiny ReceiveActor that echoes every EventId in an incoming
/// <see cref="IngestCachedTelemetryCommand"/> back as an
/// <see cref="IngestCachedTelemetryReply"/>. Stands in for the central
/// AuditLogIngestActor so this test never touches MSSQL.
/// </summary>
private sealed class EchoCachedIngestActor : ReceiveActor
{
public EchoCachedIngestActor()
{
Receive<IngestCachedTelemetryCommand>(cmd =>
{
var ids = cmd.Entries.Select(e => e.Audit.EventId).ToList();
Sender.Tell(new IngestCachedTelemetryReply(ids));
});
}
}
}