merge: startup reconcile starts the healed InstanceActor (register row 67) — EnsureInstanceStartedCommand to the DM singleton, idempotent, disable-wins, Warning site event on self-heal
This commit is contained in:
Joseph Doherty
@@ -0,0 +1,384 @@
|
||||
using System.Collections.Concurrent;
|
||||
using System.Text.Json;
|
||||
using Akka.Actor;
|
||||
using Akka.TestKit.Xunit2;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.DebugView;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Deployment;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Lifecycle;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Types.Flattening;
|
||||
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Actors;
|
||||
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Deployment;
|
||||
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Persistence;
|
||||
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Scripts;
|
||||
using ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.TestSupport;
|
||||
using ZB.MOM.WW.ScadaBridge.TestSupport;
|
||||
|
||||
namespace ZB.MOM.WW.ScadaBridge.SiteRuntime.Tests.Actors;
|
||||
|
||||
/// <summary>
|
||||
/// Regression tests for deferred register row 67 — <b>startup reconcile healed the FILE but not
|
||||
/// the RUNTIME</b>.
|
||||
///
|
||||
/// <para>
|
||||
/// Instance Actors are created from exactly two paths: the Deployment Manager's boot-time SQLite
|
||||
/// load, and an explicit deploy/enable command. <see cref="SiteReconciliationActor"/>'s
|
||||
/// node-STARTUP fetch runs AFTER that boot load has already read storage, so a config it healed
|
||||
/// into the file started nothing — the enabled, successfully-deployed instance stayed dead until
|
||||
/// the NEXT restart, whose load finally picked it up. Proven live on site-a 2026-08-15:
|
||||
/// "Reconcile: fetched + stored config" with no "InstanceActor started" after it, and a debug
|
||||
/// snapshot answering <c>instanceNotFound</c>.
|
||||
/// </para>
|
||||
///
|
||||
/// <para>
|
||||
/// The fix is an <see cref="EnsureInstanceStartedCommand"/> raised by the reconcile pass and
|
||||
/// handled by the Deployment Manager singleton. These tests pin both halves plus the seam
|
||||
/// between them.
|
||||
/// </para>
|
||||
/// </summary>
|
||||
public class ReconcileStartsInstanceTests : TestKit, IDisposable
|
||||
{
|
||||
private const string SiteIdentifier = "site-1";
|
||||
private const string NodeId = "node-a";
|
||||
|
||||
private readonly SiteStorageService _storage;
|
||||
private readonly ScriptCompilationService _compilationService;
|
||||
private readonly SharedScriptLibrary _sharedScriptLibrary;
|
||||
private readonly TestLocalDb _localDb;
|
||||
|
||||
public ReconcileStartsInstanceTests()
|
||||
{
|
||||
_localDb = TestLocalDb.CreateTemp("reconcile-start-test");
|
||||
_storage = new SiteStorageService(
|
||||
_localDb.Db, NullLogger<SiteStorageService>.Instance);
|
||||
_storage.InitializeAsync().GetAwaiter().GetResult();
|
||||
_compilationService = new ScriptCompilationService(
|
||||
NullLogger<ScriptCompilationService>.Instance);
|
||||
_sharedScriptLibrary = new SharedScriptLibrary(
|
||||
_compilationService, NullLogger<SharedScriptLibrary>.Instance);
|
||||
}
|
||||
|
||||
void IDisposable.Dispose()
|
||||
{
|
||||
// Shut the actors down BEFORE the ILocalDb they write through is disposed.
|
||||
Shutdown();
|
||||
var path = _localDb.Path;
|
||||
_localDb.Dispose();
|
||||
TestLocalDb.DeleteFiles(path);
|
||||
}
|
||||
|
||||
private IActorRef CreateDeploymentManager(IServiceProvider? serviceProvider = null) =>
|
||||
ActorOf(Props.Create(() => new DeploymentManagerActor(
|
||||
_storage,
|
||||
_compilationService,
|
||||
_sharedScriptLibrary,
|
||||
null,
|
||||
new SiteRuntimeOptions(),
|
||||
NullLogger<DeploymentManagerActor>.Instance,
|
||||
dclManager: null,
|
||||
healthCollector: null,
|
||||
serviceProvider: serviceProvider,
|
||||
loggerFactory: null,
|
||||
configFetcher: null)));
|
||||
|
||||
private IActorRef CreateReconciliationActor(
|
||||
IActorRef siteCommunicationActor,
|
||||
IDeploymentConfigFetcher fetcher,
|
||||
IActorRef? deploymentManager = null) =>
|
||||
ActorOf(Props.Create(() => new SiteReconciliationActor(
|
||||
_storage,
|
||||
fetcher,
|
||||
siteCommunicationActor,
|
||||
SiteIdentifier,
|
||||
NodeId,
|
||||
NullLogger<SiteReconciliationActor>.Instance,
|
||||
TimeSpan.FromMilliseconds(50), // initial delay — fast for tests
|
||||
TimeSpan.FromSeconds(5), // ask timeout
|
||||
deploymentManager)));
|
||||
|
||||
private static string MakeConfigJson(string instanceName)
|
||||
{
|
||||
var config = new FlattenedConfiguration
|
||||
{
|
||||
InstanceUniqueName = instanceName,
|
||||
Attributes =
|
||||
[
|
||||
new ResolvedAttribute { CanonicalName = "TestAttr", Value = "42", DataType = "Int32" }
|
||||
]
|
||||
};
|
||||
return JsonSerializer.Serialize(config);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Asks the Deployment Manager for a debug snapshot — the exact probe that answered
|
||||
/// <c>instanceNotFound</c> on the live rig. <c>InstanceNotFound == false</c> means an
|
||||
/// Instance Actor is running and routable.
|
||||
/// </summary>
|
||||
private async Task<bool> InstanceIsRunningAsync(IActorRef deploymentManager, string instanceName)
|
||||
{
|
||||
var snapshot = await deploymentManager.Ask<DebugViewSnapshot>(
|
||||
new SubscribeDebugViewRequest(instanceName, Guid.NewGuid().ToString()),
|
||||
TimeSpan.FromSeconds(5));
|
||||
return !snapshot.InstanceNotFound;
|
||||
}
|
||||
|
||||
// ── The reproduction ──
|
||||
|
||||
/// <summary>
|
||||
/// THE row-67 reproduction, end to end over one shared storage file: the node boots with no
|
||||
/// config for an enabled instance (so the Deployment Manager's startup load starts nothing),
|
||||
/// then the startup reconcile pass fetches and stores that config. The instance must be
|
||||
/// RUNNING afterwards — not merely present in SQLite waiting for a second restart.
|
||||
///
|
||||
/// <para>
|
||||
/// <b>Fails before the fix</b> at the final assert: the config row is stored, but the debug
|
||||
/// snapshot still answers <c>InstanceNotFound = true</c> because nothing ever created the
|
||||
/// Instance Actor.
|
||||
/// </para>
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task StartupReconcile_StoringConfigForEnabledInstance_StartsTheInstanceActor()
|
||||
{
|
||||
// Boot the Deployment Manager against EMPTY storage — this is the missing-config boot
|
||||
// (lost volume / first boot after a restore / rehomed data dir).
|
||||
var dm = CreateDeploymentManager();
|
||||
await Task.Delay(500);
|
||||
|
||||
// Baseline: the instance is genuinely not running.
|
||||
Assert.False(await InstanceIsRunningAsync(dm, "HealedPump"));
|
||||
|
||||
// Now the startup reconcile pass runs and central reports the instance as a gap.
|
||||
const string instanceName = "HealedPump";
|
||||
var configJson = MakeConfigJson(instanceName);
|
||||
var fetcher = new FakeConfigFetcher(_ => Task.FromResult(configJson));
|
||||
var commProbe = CreateTestProbe();
|
||||
|
||||
CreateReconciliationActor(commProbe, fetcher, dm);
|
||||
|
||||
commProbe.ExpectMsg<ReconcileSiteRequest>(TimeSpan.FromSeconds(5));
|
||||
commProbe.Reply(new ReconcileSiteResponse(
|
||||
[new ReconcileGapItem(instanceName, "dep-healed", "rev-healed", true, "tok-healed")],
|
||||
[],
|
||||
"http://central:9000"));
|
||||
|
||||
// The file heals...
|
||||
await AwaitAssertAsync(async () =>
|
||||
{
|
||||
var configs = await _storage.GetAllDeployedConfigsAsync();
|
||||
Assert.Contains(configs, c => c.InstanceUniqueName == instanceName);
|
||||
}, TimeSpan.FromSeconds(5));
|
||||
|
||||
// ...and so must the RUNTIME. This is the assertion that fails pre-fix.
|
||||
await AwaitAssertAsync(async () =>
|
||||
Assert.True(
|
||||
await InstanceIsRunningAsync(dm, instanceName),
|
||||
"Reconcile stored the config but the InstanceActor was never started "
|
||||
+ "— the instance would stay dead until the next restart (register row 67)"),
|
||||
TimeSpan.FromSeconds(10));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// The heal must not be silent: starting a reconcile-healed instance emits an operational
|
||||
/// <c>deployment</c> site event naming the instance, so an operator can see that a node
|
||||
/// booted without a config and self-repaired.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task ReconcileStartedInstance_EmitsASiteEvent()
|
||||
{
|
||||
var siteLog = new FakeSiteEventLogger();
|
||||
var dm = CreateDeploymentManager(new SingleServiceProvider(siteLog));
|
||||
await Task.Delay(500);
|
||||
|
||||
const string instanceName = "SurfacedPump";
|
||||
await _storage.StoreDeployedConfigAsync(
|
||||
instanceName, MakeConfigJson(instanceName), "dep-s", "rev-s", true);
|
||||
|
||||
dm.Tell(new EnsureInstanceStartedCommand(instanceName, "startup reconcile"));
|
||||
|
||||
await AwaitAssertAsync(() =>
|
||||
{
|
||||
Assert.Contains(siteLog.OfType("deployment"), r =>
|
||||
r.InstanceId == instanceName &&
|
||||
r.Source == "DeploymentManagerActor" &&
|
||||
r.Message.Contains("self-heal", StringComparison.OrdinalIgnoreCase));
|
||||
return Task.CompletedTask;
|
||||
}, TimeSpan.FromSeconds(10));
|
||||
}
|
||||
|
||||
// ── The reconcile half: which instances get a start request ──
|
||||
|
||||
/// <summary>
|
||||
/// An ENABLED instance healed by the pass produces an ensure-started request to the
|
||||
/// Deployment Manager proxy.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public void ReconcilePass_RequestsStart_ForHealedEnabledInstance()
|
||||
{
|
||||
var fetcher = new FakeConfigFetcher(_ => Task.FromResult("{\"instanceUniqueName\":\"B\"}"));
|
||||
var commProbe = CreateTestProbe();
|
||||
var dmProbe = CreateTestProbe();
|
||||
|
||||
CreateReconciliationActor(commProbe, fetcher, dmProbe);
|
||||
|
||||
commProbe.ExpectMsg<ReconcileSiteRequest>(TimeSpan.FromSeconds(5));
|
||||
commProbe.Reply(new ReconcileSiteResponse(
|
||||
[new ReconcileGapItem("B", "depB", "rev2", true, "tok-b")],
|
||||
[],
|
||||
"http://central:9000"));
|
||||
|
||||
var ensure = dmProbe.ExpectMsg<EnsureInstanceStartedCommand>(TimeSpan.FromSeconds(10));
|
||||
Assert.Equal("B", ensure.InstanceUniqueName);
|
||||
Assert.Contains("reconcile", ensure.Reason, StringComparison.OrdinalIgnoreCase);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// A DISABLED instance healed by the pass must NOT be started — a disabled instance
|
||||
/// legitimately has a config row and no running actor.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public void ReconcilePass_DoesNotRequestStart_ForHealedDisabledInstance()
|
||||
{
|
||||
var fetcher = new FakeConfigFetcher(_ => Task.FromResult("{\"instanceUniqueName\":\"D\"}"));
|
||||
var commProbe = CreateTestProbe();
|
||||
var dmProbe = CreateTestProbe();
|
||||
|
||||
CreateReconciliationActor(commProbe, fetcher, dmProbe);
|
||||
|
||||
commProbe.ExpectMsg<ReconcileSiteRequest>(TimeSpan.FromSeconds(5));
|
||||
commProbe.Reply(new ReconcileSiteResponse(
|
||||
[new ReconcileGapItem("D", "depD", "revD", false, "tok-d")],
|
||||
[],
|
||||
"http://central:9000"));
|
||||
|
||||
dmProbe.ExpectNoMsg(TimeSpan.FromSeconds(2));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// An item that failed to fetch was never stored, so it must not be started either.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public void ReconcilePass_DoesNotRequestStart_ForFailedFetch()
|
||||
{
|
||||
var fetcher = new FakeConfigFetcher(_ =>
|
||||
Task.FromException<string>(new DeploymentConfigFetchException("boom", isSuperseded: false)));
|
||||
var commProbe = CreateTestProbe();
|
||||
var dmProbe = CreateTestProbe();
|
||||
|
||||
CreateReconciliationActor(commProbe, fetcher, dmProbe);
|
||||
|
||||
commProbe.ExpectMsg<ReconcileSiteRequest>(TimeSpan.FromSeconds(5));
|
||||
commProbe.Reply(new ReconcileSiteResponse(
|
||||
[new ReconcileGapItem("Bad", "depBad", "revBad", true, "tok-bad")],
|
||||
[],
|
||||
"http://central:9000"));
|
||||
|
||||
dmProbe.ExpectNoMsg(TimeSpan.FromSeconds(2));
|
||||
}
|
||||
|
||||
// ── The Deployment Manager half: the ensure-started contract ──
|
||||
|
||||
/// <summary>
|
||||
/// The command is idempotent: both site nodes' reconcile actors legitimately raise it for
|
||||
/// the same instance, and a repeat must not disturb (or replace) the running actor.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task EnsureInstanceStarted_IsIdempotent_WhenAlreadyRunning()
|
||||
{
|
||||
var dm = CreateDeploymentManager();
|
||||
await Task.Delay(500);
|
||||
|
||||
const string instanceName = "IdempotentPump";
|
||||
dm.Tell(new DeployInstanceCommand(
|
||||
"dep-idem", instanceName, "sha256:abc",
|
||||
MakeConfigJson(instanceName), "admin", DateTimeOffset.UtcNow));
|
||||
ExpectMsg<DeploymentStatusResponse>(TimeSpan.FromSeconds(5));
|
||||
await Task.Delay(1000);
|
||||
|
||||
var before = await ResolveInstanceChildAsync(dm, instanceName);
|
||||
|
||||
// Two redundant ensure-started requests, as the two nodes would send.
|
||||
dm.Tell(new EnsureInstanceStartedCommand(instanceName, "startup reconcile"));
|
||||
dm.Tell(new EnsureInstanceStartedCommand(instanceName, "startup reconcile"));
|
||||
await Task.Delay(1000);
|
||||
|
||||
// Same actor ref — nothing was restarted or replaced, and it is still routable.
|
||||
var after = await ResolveInstanceChildAsync(dm, instanceName);
|
||||
Assert.Equal(before, after);
|
||||
Assert.True(await InstanceIsRunningAsync(dm, instanceName));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// The durable row is the authority on enabled/disabled state: a DISABLED instance stays
|
||||
/// stopped even if an ensure-started request arrives for it (e.g. a disable landed between
|
||||
/// the reconcile fetch and the start request).
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task EnsureInstanceStarted_DisabledInstance_StaysStopped()
|
||||
{
|
||||
var dm = CreateDeploymentManager();
|
||||
await Task.Delay(500);
|
||||
|
||||
const string instanceName = "DisabledPump";
|
||||
await _storage.StoreDeployedConfigAsync(
|
||||
instanceName, MakeConfigJson(instanceName), "dep-d", "rev-d", false);
|
||||
|
||||
dm.Tell(new EnsureInstanceStartedCommand(instanceName, "startup reconcile"));
|
||||
await Task.Delay(1500);
|
||||
|
||||
Assert.False(await InstanceIsRunningAsync(dm, instanceName));
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// An ensure-started request for an instance with no stored config on THIS node is a quiet
|
||||
/// no-op — the normal case on an unreplicated site whose peer node healed its own file.
|
||||
/// The Deployment Manager must not crash or invent an instance.
|
||||
/// </summary>
|
||||
[Fact]
|
||||
public async Task EnsureInstanceStarted_UnknownInstance_IsAQuietNoOp()
|
||||
{
|
||||
var dm = CreateDeploymentManager();
|
||||
await Task.Delay(500);
|
||||
|
||||
dm.Tell(new EnsureInstanceStartedCommand("NeverHeardOf", "startup reconcile"));
|
||||
await Task.Delay(1500);
|
||||
|
||||
Assert.False(await InstanceIsRunningAsync(dm, "NeverHeardOf"));
|
||||
|
||||
// The manager is still alive and serving other work.
|
||||
dm.Tell(new DeployInstanceCommand(
|
||||
"dep-after", "AfterPump", "sha256:abc",
|
||||
MakeConfigJson("AfterPump"), "admin", DateTimeOffset.UtcNow));
|
||||
Assert.Equal(
|
||||
DeploymentStatus.Success,
|
||||
ExpectMsg<DeploymentStatusResponse>(TimeSpan.FromSeconds(5)).Status);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Resolves the Instance Actor child of the Deployment Manager by path — the direct
|
||||
/// "the InstanceActor exists" check, complementing the debug-snapshot probe.
|
||||
/// </summary>
|
||||
private async Task<IActorRef> ResolveInstanceChildAsync(IActorRef deploymentManager, string instanceName) =>
|
||||
await Sys.ActorSelection(deploymentManager.Path / instanceName)
|
||||
.ResolveOne(TimeSpan.FromSeconds(5));
|
||||
|
||||
/// <summary>
|
||||
/// In-test fake <see cref="IDeploymentConfigFetcher"/>: runs a per-deploymentId behavior and
|
||||
/// records every call thread-safely (the fetch runs on a pool thread).
|
||||
/// </summary>
|
||||
private sealed class FakeConfigFetcher : IDeploymentConfigFetcher
|
||||
{
|
||||
private readonly Func<string, Task<string>> _behavior;
|
||||
public ConcurrentQueue<(string BaseUrl, string DeploymentId, string Token)> Calls { get; } = new();
|
||||
|
||||
public FakeConfigFetcher(Func<string, Task<string>> behavior) => _behavior = behavior;
|
||||
|
||||
public async Task<string> FetchAsync(
|
||||
string centralFetchBaseUrl, string deploymentId, string token, CancellationToken ct)
|
||||
{
|
||||
Calls.Enqueue((centralFetchBaseUrl, deploymentId, token));
|
||||
await Task.Yield();
|
||||
return await _behavior(deploymentId);
|
||||
}
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user