feat(deploy): batch instance staleness over one flatten session

DeploymentService.GetInstanceStalenessAsync shares a FlattenSession across
the batch, reads only the (InstanceId, RevisionHash) projection and pays the
snapshot read + I-1 List normalisation only for a mismatch, so the fleet
aggregate agrees exactly with the per-instance Topology badge. The I-1 logic
is extracted from GetDeploymentComparisonAsync unchanged.

Claude-Session: https://claude.ai/code/session_01Y5ef34iUUMjmwnMpL9xgmB
This commit is contained in:
Joseph Doherty
2026-09-14 13:40:19 -04:00
parent dd202e5dde
commit dc60ba1212
2 changed files with 425 additions and 34 deletions
@@ -0,0 +1,273 @@
using System.Text.Json;
using Microsoft.Extensions.Logging.Abstractions;
using Microsoft.Extensions.Options;
using NSubstitute;
using ZB.MOM.WW.ScadaBridge.Commons.Entities.Deployment;
using ZB.MOM.WW.ScadaBridge.Commons.Entities.Sites;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Repositories;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Services;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Transport;
using ZB.MOM.WW.ScadaBridge.Commons.Types;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Flattening;
using ZB.MOM.WW.ScadaBridge.Commons.Types.Templates;
using ZB.MOM.WW.ScadaBridge.Communication;
using ZB.MOM.WW.ScadaBridge.TemplateEngine.Flattening;
using ZB.MOM.WW.ScadaBridge.TemplateEngine.Validation;
namespace ZB.MOM.WW.ScadaBridge.DeploymentManager.Tests;
/// <summary>
/// Coverage for <see cref="DeploymentService.GetInstanceStalenessAsync"/> — the
/// fleet-wide batch behind the pending-updates aggregate.
///
/// <para>
/// The three properties under test are the ones that make the batch both cheap
/// and exactly consistent with the per-instance Topology badge: ONE shared
/// <see cref="FlattenSession"/> for the whole batch, a hash-projection read for
/// everyone, and the fat snapshot read + I-1 List normalisation paid ONLY when
/// the projected hash already disagrees.
/// </para>
/// </summary>
public class DeploymentServiceStalenessTests
{
private readonly IDeploymentManagerRepository _repo = Substitute.For<IDeploymentManagerRepository>();
private readonly IFlatteningPipeline _pipeline = Substitute.For<IFlatteningPipeline>();
private readonly RevisionHashService _hasher = new();
private readonly DeploymentService _service;
/// <summary>The single session every flatten in a batch must share.</summary>
private readonly FlattenSession _session = new(new TemplateGraphWatermark());
/// <summary>
/// Builds the service over substituted repository and pipeline seams; every
/// other dependency is the real concrete collaborator (as elsewhere in this
/// suite) because the staleness path only exercises hashing.
/// </summary>
public DeploymentServiceStalenessTests()
{
_pipeline.CreateSession().Returns(_session);
var siteRepo = Substitute.For<ISiteRepository>();
siteRepo.GetSiteByIdAsync(Arg.Any<int>(), Arg.Any<CancellationToken>())
.Returns(callInfo =>
{
var id = callInfo.ArgAt<int>(0);
return new Site($"Test Site {id}", $"site-{id}") { Id = id };
});
_service = new DeploymentService(
_repo,
siteRepo,
_pipeline,
new CommunicationService(
Options.Create(new CommunicationOptions()),
NullLogger<CommunicationService>.Instance),
new OperationLockManager(),
Substitute.For<IAuditService>(),
new DiffService(),
_hasher,
new DeploymentStatusNotifier(NullLogger<DeploymentStatusNotifier>.Instance),
Substitute.For<IStaleInstanceProbe>(),
Options.Create(new DeploymentManagerOptions
{
OperationLockTimeout = TimeSpan.FromSeconds(5)
}),
Options.Create(new CommunicationOptions()),
NullLogger<DeploymentService>.Instance);
}
/// <summary>Builds a one-attribute flattened config with the given scalar value.</summary>
private static FlattenedConfiguration ScalarConfig(string value) => new()
{
InstanceUniqueName = "TestInst",
Attributes = [new ResolvedAttribute { CanonicalName = "Setpoint", Value = value, DataType = "Int32" }]
};
/// <summary>Stubs a successful flatten of <paramref name="instanceId"/>.</summary>
private void ArrangeFlatten(int instanceId, FlattenedConfiguration config, string hash) =>
_pipeline.FlattenAndValidateAsync(
instanceId, Arg.Any<CancellationToken>(), Arg.Any<bool>(), Arg.Any<FlattenSession?>())
.Returns(Result<FlatteningPipelineResult>.Success(
new FlatteningPipelineResult(config, hash, ValidationResult.Success())));
/// <summary>Stubs the fat snapshot read for <paramref name="instanceId"/>.</summary>
private void ArrangeSnapshot(int instanceId, FlattenedConfiguration config, string frozenHash) =>
_repo.GetDeployedSnapshotByInstanceIdAsync(instanceId, Arg.Any<CancellationToken>())
.Returns(new DeployedConfigSnapshot("dep1", frozenHash, JsonSerializer.Serialize(config))
{
InstanceId = instanceId,
DeployedAt = DateTimeOffset.UtcNow
});
/// <summary>Stubs the (InstanceId, RevisionHash) projection read.</summary>
private void ArrangeDeployedHashes(params (int InstanceId, string Hash)[] rows) =>
_repo.GetDeployedRevisionHashesAsync(Arg.Any<CancellationToken>())
.Returns(rows.ToDictionary(r => r.InstanceId, r => r.Hash));
[Fact]
public async Task GetInstanceStalenessAsync_SharesOneSessionAcrossTheBatch()
{
var config = ScalarConfig("5");
var hash = _hasher.ComputeHash(config);
ArrangeDeployedHashes((1, hash), (2, hash), (3, hash));
ArrangeFlatten(1, config, hash);
ArrangeFlatten(2, config, hash);
ArrangeFlatten(3, config, hash);
var result = await _service.GetInstanceStalenessAsync([1, 2, 3]);
Assert.Equal(3, result.Count);
// One session created, and the SAME instance handed to every flatten —
// that is what makes a template chain shared by N instances walked once.
_pipeline.Received(1).CreateSession();
await _pipeline.Received(1).FlattenAndValidateAsync(1, Arg.Any<CancellationToken>(), false, _session);
await _pipeline.Received(1).FlattenAndValidateAsync(2, Arg.Any<CancellationToken>(), false, _session);
await _pipeline.Received(1).FlattenAndValidateAsync(3, Arg.Any<CancellationToken>(), false, _session);
}
[Fact]
public async Task GetInstanceStalenessAsync_HashMatches_NotStaleAndNoSnapshotRead()
{
var config = ScalarConfig("5");
var hash = _hasher.ComputeHash(config);
ArrangeDeployedHashes((1, hash));
ArrangeFlatten(1, config, hash);
var result = await _service.GetInstanceStalenessAsync([1]);
Assert.False(result[1]);
// The whole point of the projection read: an up-to-date fleet never
// deserialises a single ConfigurationJson.
await _repo.DidNotReceive().GetDeployedSnapshotByInstanceIdAsync(1, Arg.Any<CancellationToken>());
}
[Fact]
public async Task GetInstanceStalenessAsync_OldFormListSnapshot_NormalisesToNotStale()
{
// I-1 parity with the Topology badge: a List attribute deployed in the OLD
// quoted form froze a hash that differs from the native re-flatten's, so
// the projection read reports a mismatch. Re-reading the snapshot and
// recomputing over the normalised config collapses old form → native, and
// the instance is correctly NOT stale.
var oldFormConfig = new FlattenedConfiguration
{
InstanceUniqueName = "ListInst",
Attributes =
[
new ResolvedAttribute
{
CanonicalName = "Thresholds",
DataType = "List",
ElementDataType = "Int32",
Value = "[\"10\",\"20\",\"30\"]" // OLD quoted form
}
]
};
var nativeConfig = oldFormConfig with
{
Attributes = [oldFormConfig.Attributes[0] with { Value = "[10,20,30]" }]
};
var frozenOldFormHash = _hasher.ComputeHash(oldFormConfig);
var nativeHash = _hasher.ComputeHash(nativeConfig);
// Sanity: without the normalisation this instance WOULD read as stale.
Assert.NotEqual(frozenOldFormHash, nativeHash);
ArrangeDeployedHashes((50, frozenOldFormHash));
ArrangeSnapshot(50, oldFormConfig, frozenOldFormHash);
ArrangeFlatten(50, nativeConfig, nativeHash);
var result = await _service.GetInstanceStalenessAsync([50]);
Assert.False(result[50]);
await _repo.Received(1).GetDeployedSnapshotByInstanceIdAsync(50, Arg.Any<CancellationToken>());
}
[Fact]
public async Task GetInstanceStalenessAsync_GenuineMismatch_IsStale()
{
var deployedConfig = ScalarConfig("5");
var deployedHash = _hasher.ComputeHash(deployedConfig);
var currentConfig = ScalarConfig("9");
var currentHash = _hasher.ComputeHash(currentConfig);
ArrangeDeployedHashes((1, deployedHash));
ArrangeSnapshot(1, deployedConfig, deployedHash);
ArrangeFlatten(1, currentConfig, currentHash);
var result = await _service.GetInstanceStalenessAsync([1]);
Assert.True(result[1]);
}
[Fact]
public async Task GetInstanceStalenessAsync_FlattenFails_ReportsUnknown()
{
ArrangeDeployedHashes((1, "sha256:deployed"));
_pipeline.FlattenAndValidateAsync(
1, Arg.Any<CancellationToken>(), Arg.Any<bool>(), Arg.Any<FlattenSession?>())
.Returns(Result<FlatteningPipelineResult>.Failure("template missing"));
var result = await _service.GetInstanceStalenessAsync([1]);
// null = could not evaluate. Never counted as stale.
Assert.True(result.ContainsKey(1));
Assert.Null(result[1]);
}
[Fact]
public async Task GetInstanceStalenessAsync_InstanceWithoutSnapshot_IsOmitted()
{
var config = ScalarConfig("5");
var hash = _hasher.ComputeHash(config);
ArrangeDeployedHashes((1, hash));
ArrangeFlatten(1, config, hash);
var result = await _service.GetInstanceStalenessAsync([1, 2]);
Assert.True(result.ContainsKey(1));
// Instance 2 has never been deployed — not stale, not unknown, absent.
Assert.False(result.ContainsKey(2));
await _pipeline.DidNotReceive().FlattenAndValidateAsync(
2, Arg.Any<CancellationToken>(), Arg.Any<bool>(), Arg.Any<FlattenSession?>());
}
[Fact]
public async Task GetInstanceStalenessAsync_SnapshotVanishedBetweenReads_IsOmitted()
{
// Undeployed between the projection read and the mismatch's snapshot read:
// there is nothing left to be stale against, so report nothing at all.
ArrangeDeployedHashes((1, "sha256:deployed"));
_repo.GetDeployedSnapshotByInstanceIdAsync(1, Arg.Any<CancellationToken>())
.Returns((DeployedConfigSnapshot?)null);
ArrangeFlatten(1, ScalarConfig("5"), "sha256:current");
var result = await _service.GetInstanceStalenessAsync([1]);
Assert.False(result.ContainsKey(1));
}
[Fact]
public async Task GetInstanceStalenessAsync_DuplicateIds_FlattenedOnce()
{
var config = ScalarConfig("5");
var hash = _hasher.ComputeHash(config);
ArrangeDeployedHashes((1, hash));
ArrangeFlatten(1, config, hash);
var result = await _service.GetInstanceStalenessAsync([1, 1, 1]);
Assert.Single(result);
await _pipeline.Received(1).FlattenAndValidateAsync(
1, Arg.Any<CancellationToken>(), Arg.Any<bool>(), Arg.Any<FlattenSession?>());
}
[Fact]
public async Task GetInstanceStalenessAsync_EmptyInput_ReturnsEmptyWithoutReads()
{
var result = await _service.GetInstanceStalenessAsync([]);
Assert.Empty(result);
await _repo.DidNotReceive().GetDeployedRevisionHashesAsync(Arg.Any<CancellationToken>());
}
}