test+fix: eliminate Windows full-suite temp-file-lock flakiness

Full-host tests passed in isolation but failed 2-4/run under parallel execution on
Windows with 'the process cannot access the file ... because it is being used by
another process' (macOS never sees it — Unix deletes open files). Two shared-state
parallel collisions, discovered while verifying TST-08:

1. Self-signed cert generation. GatewayTlsBootstrapTests sets process-global
   Kestrel/TLS env vars that GatewayApplication.Build reads; a parallel host-building
   test inherits them mid-run and both generate a cert at the same path, racing on the
   fixed-name '<path>.tmp'. Fixes:
   - SelfSignedCertificateProvider: stage the PFX in a unique '<path>.<guid>.tmp' instead
     of a fixed name, so concurrent/interrupted writers never collide on the temp file
     (real robustness: two instances or a restart-during-write no longer clash). The
     final atomic Move (last-writer-wins) still yields an equivalent cert.
   - TestHostEnvironmentInitializer: default MxGateway__Tls__SelfSignedCertPath to a
     per-process temp path so the suite never writes the shared ProgramData default or
     fights the deployed service; first host-building test generates, the rest load it.
   - GatewayTlsBootstrapTests: [Collection] with DisableParallelization so its global
     env-var mutation cannot bleed into parallel tests (new GlobalEnvironmentCollection).

2. AuthStoreHealthCheckTests opened a real SQLite file; Microsoft.Data.Sqlite's
   connection pool keeps the .db handle open after 'await using', so the finally
   File.Delete threw. Reuse the existing TempDatabaseDirectory helper, which calls
   SqliteConnection.ClearAllPools() before deleting.

Server build clean; affected classes 17/17 on macOS. Windows full-suite verified separately.
This commit is contained in:
Joseph Doherty
2026-07-09 08:14:55 -04:00
parent 8c06635ee5
commit 11a716a07f
5 changed files with 63 additions and 10 deletions
@@ -163,7 +163,15 @@ public sealed class SelfSignedCertificateProvider
// temp file empty, harden its permissions, and only then write the PFX into
// the already-protected file. The temp path is in the same directory as the
// target so the Move is atomic and preserves the hardened DACL/mode.
string temp = path + ".tmp";
//
// The temp name carries a unique suffix rather than a fixed "<path>.tmp": two
// processes (or two parallel callers) generating to the same target must not
// collide on one temp file. On Windows a fixed name makes the second writer's
// File.Create/Move fail with "the process cannot access the file ... because it
// is being used by another process"; a unique name lets each generation stage
// independently, and the final atomic Move (last-writer-wins) still yields a
// valid, equivalent certificate at the shared path.
string temp = $"{path}.{Guid.NewGuid():N}.tmp";
using (File.Create(temp)) { }
HardenPermissions(temp);
@@ -1,6 +1,7 @@
using Microsoft.Extensions.Diagnostics.HealthChecks;
using ZB.MOM.WW.Auth.ApiKeys.Sqlite;
using ZB.MOM.WW.MxGateway.Server.Diagnostics;
using ZB.MOM.WW.MxGateway.Tests.Security.Authentication;
namespace ZB.MOM.WW.MxGateway.Tests.Diagnostics;
@@ -17,14 +18,14 @@ public sealed class AuthStoreHealthCheckTests
[Fact]
public async Task Healthy_WhenStoreReachable()
{
var path = Path.Combine(Path.GetTempPath(), $"authcheck-{Guid.NewGuid():N}.db");
try
{
var check = new AuthStoreHealthCheck(FactoryFor(path));
var result = await check.CheckHealthAsync(new HealthCheckContext());
Assert.Equal(HealthStatus.Healthy, result.Status);
}
finally { if (File.Exists(path)) File.Delete(path); }
// Open a real SQLite file via the health check. TempDatabaseDirectory clears the
// Microsoft.Data.Sqlite connection pool on dispose before deleting the file; without
// that the pool keeps the .db handle open and the delete throws "used by another
// process" on Windows (a latent full-suite flake — the file opens fine on macOS).
using TempDatabaseDirectory directory = TempDatabaseDirectory.Create("authcheck");
var check = new AuthStoreHealthCheck(FactoryFor(directory.DatabasePath()));
var result = await check.CheckHealthAsync(new HealthCheckContext());
Assert.Equal(HealthStatus.Healthy, result.Status);
}
/// <summary>The health check reports unhealthy when the database path cannot be opened.</summary>
@@ -9,6 +9,10 @@ using ZB.MOM.WW.MxGateway.Server;
namespace ZB.MOM.WW.MxGateway.Tests.Gateway;
// Sets process-global Kestrel/TLS environment variables that GatewayApplication.Build reads;
// serialized against all other collections so a parallel host-building test cannot inherit them
// mid-run and race on the generated-certificate file. See GlobalEnvironmentCollection.
[Collection(TestSupport.GlobalEnvironmentCollection.Name)]
public sealed class GatewayTlsBootstrapTests
{
/// <summary>
@@ -0,0 +1,18 @@
namespace ZB.MOM.WW.MxGateway.Tests.TestSupport;
/// <summary>
/// xUnit collection for tests that mutate <em>process-global</em> state (environment variables
/// read by <c>GatewayApplication.Build</c>, e.g. <c>Kestrel__Endpoints__…</c> and
/// <c>MxGateway__Tls__SelfSignedCertPath</c>). <c>DisableParallelization</c> keeps such a test from
/// running concurrently with any other collection: otherwise a parallel host-building test inherits
/// the mutated variables mid-run and the two race on the same generated-certificate file (on Windows,
/// "the process cannot access the file … because it is being used by another process"). Membership is
/// deliberately narrow — only add classes that set/clear real environment variables, not ones that
/// pass configuration through <c>Build([...])</c> command-line args.
/// </summary>
[CollectionDefinition(Name, DisableParallelization = true)]
public sealed class GlobalEnvironmentCollection
{
/// <summary>The collection name applied via <c>[Collection(GlobalEnvironmentCollection.Name)]</c>.</summary>
public const string Name = "GlobalEnvironmentMutation";
}
@@ -3,7 +3,8 @@ using System.Runtime.CompilerServices;
namespace ZB.MOM.WW.MxGateway.Tests.TestSupport;
/// <summary>
/// Defaults the host environment to Development for the whole test assembly.
/// Defaults the host environment to Development and isolates the test process's on-disk
/// gateway paths, for the whole test assembly.
/// </summary>
/// <remarks>
/// Many tests build the full gateway host through <c>GatewayApplication.Build</c> against the dev
@@ -15,6 +16,15 @@ namespace ZB.MOM.WW.MxGateway.Tests.TestSupport;
/// <c>GatewayOptionsValidator</c> with its <c>isProduction</c> constructor (no host environment) and
/// are unaffected; a test that needs Production can still pass <c>--environment=Production</c>, which
/// overrides this default.
/// <para>
/// The self-signed-cert path is also defaulted to a per-process temp file. Otherwise every
/// full-host test that triggers HTTPS-cert generation writes the shared
/// <c>CommonApplicationData/MxGateway/certs/gateway-selfsigned.pfx</c> default — parallel xUnit
/// test classes then collide on that path's temp file (Windows: "the process cannot access the
/// file ... because it is being used by another process"), and on a shared CI/dev box the suite
/// also fights the deployed gateway service for the same file. Pointing at a per-process path
/// isolates the suite: the first host-building test generates the cert, the rest load it.
/// </para>
/// </remarks>
internal static class TestHostEnvironmentInitializer
{
@@ -25,5 +35,17 @@ internal static class TestHostEnvironmentInitializer
{
Environment.SetEnvironmentVariable("ASPNETCORE_ENVIRONMENT", "Development");
}
if (string.IsNullOrEmpty(Environment.GetEnvironmentVariable("MxGateway__Tls__SelfSignedCertPath")))
{
// ProcessId keeps the path stable within this test process (so a valid cert
// generated by the first host-building test is reused by the rest) yet unique
// across processes (so concurrent test runs / the deployed service never share it).
string certPath = Path.Combine(
Path.GetTempPath(),
$"mxgw-tests-{Environment.ProcessId}",
"gateway-selfsigned.pfx");
Environment.SetEnvironmentVariable("MxGateway__Tls__SelfSignedCertPath", certPath);
}
}
}