Files
ScadaBridge/tests/ZB.MOM.WW.ScadaBridge.Host.Tests/CoordinatedShutdownTests.cs
T
Joseph Doherty e9c412e528 fix(host): unhandled boot exception now kills the process instead of wedging the container (#34)
Root cause: dotnet runs as container PID 1 and Linux ignores default-action
signals sent to PID 1, so the runtime's unhandled-exception path (banner,
then abort() -> SIGABRT) could never terminate the process — it printed the
trace and spun the main thread at 100% CPU with the container `running`,
so `restart: unless-stopped` never fired. Reproduced deterministically:
same StartupValidator throw exits 134 under an init process and wedges
without one.

Two layers, each covering the other's gap:
- Program.cs registers an AppDomain.UnhandledException handler before the
  first statement that can throw: prints the trace, best-effort flushes
  Serilog, Environment.Exit(134) — exit() is a syscall PID 1 CAN perform,
  134 preserves the 128+SIGABRT crash code, and it covers every thread,
  not just the boot window. It cannot fire under WebApplicationFactory
  (the test host catches entry-point exceptions), so the designed
  boot-refusal exceptions still propagate to tests unchanged.
- docker-compose: init: true on all 8 nodes for the crash paths that
  bypass the managed event (Environment.FailFast, runtime-internal aborts).

The CoordinatedShutdown no-Environment.Exit guard gains a precise carve-out
(exactly one call, only inside the handler); Environment.Exit still fires
the CLR shutdown hook Akka binds via run-by-clr-shutdown-hook = on, so the
crash path skips nothing abort() kept. New pin test keeps the handler ahead
of the configuration build.

Live-verified on the rig image: crash now yields Exited (134) +
RestartCount climbing under `unless-stopped`, trace intact, with and
without init; full 8-node rig redeployed healthy with docker-init as PID 1.

Closes #34.

Claude-Session: https://claude.ai/code/session_014WNM4vjoVksyyBraTXSZE1
2026-08-08 05:23:26 -04:00

139 lines
6.0 KiB
C#

using System.Reflection;
namespace ZB.MOM.WW.ScadaBridge.Host.Tests;
/// <summary>
/// WP-16: Tests for CoordinatedShutdown configuration.
/// Verifies no Environment.Exit calls exist in source and HOCON config is correct.
/// </summary>
public class CoordinatedShutdownTests
{
[Fact]
public void HostSource_DoesNotContainEnvironmentExit()
{
var hostProjectDir = FindHostProjectDirectory();
Assert.NotNull(hostProjectDir);
var sourceFiles = Directory.GetFiles(hostProjectDir, "*.cs", SearchOption.AllDirectories);
Assert.NotEmpty(sourceFiles);
foreach (var file in sourceFiles)
{
var content = File.ReadAllText(file);
// Sole permitted call site: Program.cs's AppDomain.UnhandledException handler
// (ScadaBridge#34). That is the crash path — the alternative there was never a
// CoordinatedShutdown but the runtime's abort(), which cannot terminate PID 1
// and wedged the container; Environment.Exit still fires the CLR shutdown hook
// Akka binds via run-by-clr-shutdown-hook = on, so it skips nothing abort kept.
// Everywhere else the original rule stands: no code path may bypass
// CoordinatedShutdown by exiting directly.
if (Path.GetFileName(file) == "Program.cs")
{
var occurrences = CountOccurrences(content, "Environment.Exit(");
Assert.Equal(1, occurrences);
var handlerAt = content.IndexOf(
"AppDomain.CurrentDomain.UnhandledException +=", StringComparison.Ordinal);
Assert.True(handlerAt >= 0, "Program.cs must register the UnhandledException handler");
var handlerEnd = content.IndexOf("};", handlerAt, StringComparison.Ordinal);
var exitAt = content.IndexOf("Environment.Exit(", StringComparison.Ordinal);
Assert.True(exitAt > handlerAt && exitAt < handlerEnd,
"Environment.Exit in Program.cs is only permitted inside the UnhandledException handler");
continue;
}
Assert.DoesNotContain("Environment.Exit", content,
StringComparison.Ordinal);
}
}
[Fact]
public void AkkaHostedService_HoconConfig_IncludesCoordinatedShutdownSettings()
{
// Read the AkkaHostedService source to verify HOCON configuration
var hostProjectDir = FindHostProjectDirectory();
Assert.NotNull(hostProjectDir);
var akkaServiceFile = Path.Combine(hostProjectDir, "Actors", "AkkaHostedService.cs");
Assert.True(File.Exists(akkaServiceFile), $"AkkaHostedService.cs not found at {akkaServiceFile}");
var content = File.ReadAllText(akkaServiceFile);
// Verify critical HOCON settings are present
Assert.Contains("run-by-clr-shutdown-hook = on", content);
Assert.Contains("run-coordinated-shutdown-when-down = on", content);
}
[Fact]
public void AllCentralSingletons_RegisterThroughRegistrarWithDrain()
{
var hostProjectDir = FindHostProjectDirectory();
Assert.NotNull(hostProjectDir);
var content = File.ReadAllText(Path.Combine(hostProjectDir!, "Actors", "AkkaHostedService.cs"));
// Review 01 [Medium]: notification-outbox and audit-log-ingest were the
// only central singletons WITHOUT a cluster-leave drain task. All seven
// now go through SingletonRegistrar.Start, which always adds the
// PhaseClusterLeave GracefulStop drain.
Assert.Contains("SingletonRegistrar.Start(", content);
foreach (var name in new[] { "notification-outbox", "audit-log-ingest", "site-call-audit",
"audit-log-purge", "site-audit-reconciliation",
"kpi-history-recorder", "pending-deployment-purge" })
{
Assert.Contains($"\"{name}\"", content);
}
// No hand-rolled ClusterSingletonManager registrations remain anywhere:
// the two role-scoped SITE singletons now also go through the registrar
// (SingletonRegistrar.Start(..., role: siteRole)), so every singleton in
// the file is created through the registrar with a drain task.
Assert.Equal(0, CountOccurrences(content, "ClusterSingletonManager.Props("));
}
[Fact]
public void SiteSingletons_RegisterThroughRegistrarWithDrain()
{
var hostProjectDir = FindHostProjectDirectory();
Assert.NotNull(hostProjectDir);
var content = File.ReadAllText(Path.Combine(hostProjectDir!, "Actors", "AkkaHostedService.cs"));
// Round-2 N5: the two role-scoped SITE singletons previously stayed
// hand-rolled (bare PoisonPill, no PhaseClusterLeave drain). They now
// go through SingletonRegistrar.Start(..., role: siteRole), which
// always adds the GracefulStop drain — in-flight SQLite writes
// (static overrides, native_alarm_state) complete before handover.
Assert.Contains("\"deployment-manager\"", content);
Assert.Contains("\"event-log-handler\"", content);
Assert.Contains("role: siteRole", content);
Assert.Equal(0, CountOccurrences(content, "ClusterSingletonManager.Props("));
}
private static int CountOccurrences(string haystack, string needle)
{
int count = 0, i = 0;
while ((i = haystack.IndexOf(needle, i, StringComparison.Ordinal)) >= 0)
{
count++;
i += needle.Length;
}
return count;
}
private static string? FindHostProjectDirectory()
{
var assemblyDir = Path.GetDirectoryName(Assembly.GetExecutingAssembly().Location)!;
var dir = new DirectoryInfo(assemblyDir);
while (dir != null)
{
var hostPath = Path.Combine(dir.FullName, "src", "ZB.MOM.WW.ScadaBridge.Host");
if (Directory.Exists(hostPath))
return hostPath;
dir = dir.Parent;
}
return null;
}
}