f2efeb37b7
Tasks 5 and 6 of the Phase 2 plan, committed together because their test
fallout is entangled — several fixtures construct both stores.
StoreAndForwardStorage and SiteStorageService now take ILocalDb. Connections
come from ILocalDb.CreateConnection(), which hands out an already-open,
pragma-configured connection carrying the zb_hlc_next() UDF the capture triggers
call; a raw connection would lack the UDF and every write to a replicated table
would fail closed. Deleted with the connection strings: S&F's
EnsureDatabaseDirectoryExists and its per-open busy_timeout pragma, and the site
service's BusyTimeoutFloorSeconds normalization — LocalDb owns all of it now.
DI: AddSiteRuntime's string overload is gone (nothing left to supply), so the
Host calls the no-arg form. ScadaBridge:Database:SiteDbPath and
StoreAndForwardOptions.SqliteDbPath survive only as the migrator's source
locations in Tasks 8/9.
Two things the plan did not anticipate, both worth reading:
1. FOUND A REAL LATENT DEFECT, from Phase 1, now fixed. The plan assumed
directory creation simply moved to LocalDb along with file ownership. It did
not: the LocalDb library never creates the parent directory, and
SqliteLocalDb opens the file eagerly in its constructor — so a missing
directory is a hard boot failure ("SQLite Error 14: unable to open database
file"), not a degraded start. The default site config points at the RELATIVE
path ./data/site-localdb.db, so any site node without a pre-existing data/
directory fails to boot. The docker rig escapes only because its volume mount
happens to create /app/data — a coincidence that would have hidden this until
a bare-metal or fresh deployment. This has been latent since Phase 1 made
LocalDb:Path required; deleting S&F's EnsureDatabaseDirectoryExists here
would have widened it. Re-established the guarantee at the layer that now
owns the path (SiteLocalDbDirectory.Ensure, called before AddZbLocalDb) and
pinned it with SiteLocalDbDirectoryTests. Non-vacuity is not assumed: two
tests written against the wrong assumption failed with exactly this
SQLite Error 14 before the fix existed.
2. Test fallout was ~7x the plan's estimate. The plan named "fixtures" in one
project; the constructor change actually reaches 40 files across 7 test
projects, and most used Mode=Memory;Cache=Shared — which LocalDb has no
equivalent for, so every one had to move to a real temp file. Rather than
copy the Phase 1 TestLocalDb fixture into 7 projects, added a shared
tests/ZB.MOM.WW.ScadaBridge.TestSupport library (not a test project) so the
WAL-sidecar cleanup and the "real, not stubbed" rationale live in one place.
Retargeted rather than deleted, in both directions: the S&F WAL test now asserts
against the LocalDb-backed store (WAL genuinely is LocalDb's job), while the
directory-creation test moved to Host.Tests (that guarantee is NOT LocalDb's).
SiteStorageServiceTests.Initialize_EnablesWalJournalMode got the same treatment.
DeploymentManagerMediumFindingsTests induced a persistence failure via an
unopenable path, which no longer reaches the assertion since the fixture now
throws first; it induces the same failure shape via an uninitialized store.
Verified: full solution build 0 warnings; SiteRuntime 532, Host 318,
AuditLog 355, ExternalSystemGateway 142, HealthMonitoring 97,
StoreAndForward 153 — 1597 passed, 0 failed.
Claude-Session: https://claude.ai/code/session_01BL2Vu1ESDQ9SCN4gVKkdts
238 lines
9.3 KiB
C#
238 lines
9.3 KiB
C#
using System.Text.Json;
|
|
using Microsoft.Extensions.Logging.Abstractions;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Streaming;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Types.Enums;
|
|
using ZB.MOM.WW.ScadaBridge.StoreAndForward;
|
|
using ZB.MOM.WW.ScadaBridge.TestSupport;
|
|
|
|
namespace ZB.MOM.WW.ScadaBridge.IntegrationTests;
|
|
|
|
/// <summary>
|
|
/// WP-2 (Phase 8): Full-system failover testing — Site.
|
|
/// Verifies S&F buffer takeover, DCL reconnection structure, alarm re-evaluation,
|
|
/// and script trigger resumption after site failover.
|
|
/// </summary>
|
|
public class SiteFailoverTests
|
|
{
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public async Task StoreAndForward_BufferSurvivesRestart_MessagesRetained()
|
|
{
|
|
// Simulates site failover: messages buffered in SQLite survive process restart.
|
|
// The standby node picks up the same SQLite file and retries pending messages.
|
|
var dbPath = Path.Combine(Path.GetTempPath(), $"sf_failover_{Guid.NewGuid():N}.db");
|
|
|
|
// The store takes an ILocalDb; each "node" opens its own local database over the
|
|
// SAME file, which is how this test models the standby picking up the primary's
|
|
// buffer after failover.
|
|
TestLocalDb? primaryDb = null;
|
|
TestLocalDb? standbyDb = null;
|
|
|
|
try
|
|
{
|
|
// Phase 1: Buffer messages on "primary" node
|
|
primaryDb = TestLocalDb.Create(dbPath);
|
|
var storage = new StoreAndForwardStorage(primaryDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await storage.InitializeAsync();
|
|
|
|
var message = new StoreAndForwardMessage
|
|
{
|
|
Id = Guid.NewGuid().ToString("N"),
|
|
Category = StoreAndForwardCategory.ExternalSystem,
|
|
Target = "https://api.example.com/data",
|
|
PayloadJson = """{"temperature":42.5}""",
|
|
RetryCount = 2,
|
|
MaxRetries = 50,
|
|
RetryIntervalMs = 30000,
|
|
CreatedAt = DateTimeOffset.UtcNow,
|
|
Status = StoreAndForwardMessageStatus.Pending,
|
|
OriginInstanceName = "pump-station-1"
|
|
};
|
|
|
|
await storage.EnqueueAsync(message);
|
|
|
|
// Phase 2: "Standby" node opens the same database (simulating failover)
|
|
standbyDb = TestLocalDb.Create(dbPath);
|
|
var standbyStorage = new StoreAndForwardStorage(standbyDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await standbyStorage.InitializeAsync();
|
|
|
|
var pending = await standbyStorage.GetMessagesForRetryAsync();
|
|
Assert.Single(pending);
|
|
Assert.Equal(message.Id, pending[0].Id);
|
|
Assert.Equal("pump-station-1", pending[0].OriginInstanceName);
|
|
Assert.Equal(2, pending[0].RetryCount);
|
|
}
|
|
finally
|
|
{
|
|
// Dispose before deleting — the master connections anchor the WAL sidecars.
|
|
standbyDb?.Dispose();
|
|
primaryDb?.Dispose();
|
|
TestLocalDb.DeleteFiles(dbPath);
|
|
}
|
|
}
|
|
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public async Task StoreAndForward_ParkedMessages_SurviveFailover()
|
|
{
|
|
var dbPath = Path.Combine(Path.GetTempPath(), $"sf_parked_{Guid.NewGuid():N}.db");
|
|
|
|
TestLocalDb? primaryDb = null;
|
|
TestLocalDb? standbyDb = null;
|
|
|
|
try
|
|
{
|
|
primaryDb = TestLocalDb.Create(dbPath);
|
|
var storage = new StoreAndForwardStorage(primaryDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await storage.InitializeAsync();
|
|
|
|
var parkedMsg = new StoreAndForwardMessage
|
|
{
|
|
Id = Guid.NewGuid().ToString("N"),
|
|
Category = StoreAndForwardCategory.Notification,
|
|
Target = "alert-list",
|
|
PayloadJson = """{"subject":"Critical alarm"}""",
|
|
RetryCount = 50,
|
|
MaxRetries = 50,
|
|
RetryIntervalMs = 30000,
|
|
CreatedAt = DateTimeOffset.UtcNow.AddHours(-1),
|
|
LastAttemptAt = DateTimeOffset.UtcNow,
|
|
Status = StoreAndForwardMessageStatus.Parked,
|
|
LastError = "SMTP connection timeout",
|
|
OriginInstanceName = "compressor-1"
|
|
};
|
|
|
|
await storage.EnqueueAsync(parkedMsg);
|
|
|
|
// Standby opens same DB
|
|
standbyDb = TestLocalDb.Create(dbPath);
|
|
var standbyStorage = new StoreAndForwardStorage(standbyDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await standbyStorage.InitializeAsync();
|
|
|
|
var (parked, count) = await standbyStorage.GetParkedMessagesAsync();
|
|
Assert.Equal(1, count);
|
|
Assert.Equal("SMTP connection timeout", parked[0].LastError);
|
|
}
|
|
finally
|
|
{
|
|
// Dispose before deleting — the master connections anchor the WAL sidecars.
|
|
standbyDb?.Dispose();
|
|
primaryDb?.Dispose();
|
|
TestLocalDb.DeleteFiles(dbPath);
|
|
}
|
|
}
|
|
|
|
[Fact]
|
|
public void AlarmReEvaluation_IncomingValue_TriggersNewState()
|
|
{
|
|
// Structural verification: AlarmStateChanged carries all data needed for
|
|
// re-evaluation after failover. When DCL reconnects and pushes new values,
|
|
// the Alarm Actor evaluates from the incoming value (not stale state).
|
|
var alarmEvent = new AlarmStateChanged(
|
|
"pump-station-1",
|
|
"HighPressureAlarm",
|
|
AlarmState.Active,
|
|
1,
|
|
DateTimeOffset.UtcNow);
|
|
|
|
Assert.Equal(AlarmState.Active, alarmEvent.State);
|
|
Assert.Equal("pump-station-1", alarmEvent.InstanceUniqueName);
|
|
|
|
// After failover, a new value triggers re-evaluation
|
|
var clearedEvent = new AlarmStateChanged(
|
|
"pump-station-1",
|
|
"HighPressureAlarm",
|
|
AlarmState.Normal,
|
|
1,
|
|
DateTimeOffset.UtcNow.AddSeconds(5));
|
|
|
|
Assert.Equal(AlarmState.Normal, clearedEvent.State);
|
|
Assert.True(clearedEvent.Timestamp > alarmEvent.Timestamp);
|
|
}
|
|
|
|
[Fact]
|
|
public void ScriptTriggerResumption_ValueChangeTriggersScript()
|
|
{
|
|
// Structural verification: AttributeValueChanged messages from DCL after reconnection
|
|
// will be routed to Script Actors, which evaluate triggers based on incoming values.
|
|
// No stale trigger state needed — triggers fire on new values.
|
|
var valueChange = new AttributeValueChanged(
|
|
"pump-station-1",
|
|
"OPC:ns=2;s=Pressure",
|
|
"Pressure",
|
|
150.0,
|
|
"Good",
|
|
DateTimeOffset.UtcNow);
|
|
|
|
Assert.Equal("Pressure", valueChange.AttributeName);
|
|
Assert.Equal("OPC:ns=2;s=Pressure", valueChange.AttributePath);
|
|
Assert.Equal(150.0, valueChange.Value);
|
|
Assert.Equal("Good", valueChange.Quality);
|
|
}
|
|
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public async Task StoreAndForward_BufferDepth_ReportedAfterFailover()
|
|
{
|
|
var dbPath = Path.Combine(Path.GetTempPath(), $"sf_depth_{Guid.NewGuid():N}.db");
|
|
|
|
TestLocalDb? primaryDb = null;
|
|
TestLocalDb? standbyDb = null;
|
|
|
|
try
|
|
{
|
|
primaryDb = TestLocalDb.Create(dbPath);
|
|
var storage = new StoreAndForwardStorage(primaryDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await storage.InitializeAsync();
|
|
|
|
// Enqueue messages in different categories
|
|
for (var i = 0; i < 5; i++)
|
|
{
|
|
await storage.EnqueueAsync(new StoreAndForwardMessage
|
|
{
|
|
Id = Guid.NewGuid().ToString("N"),
|
|
Category = StoreAndForwardCategory.ExternalSystem,
|
|
Target = "api",
|
|
PayloadJson = "{}",
|
|
MaxRetries = 50,
|
|
RetryIntervalMs = 30000,
|
|
CreatedAt = DateTimeOffset.UtcNow,
|
|
Status = StoreAndForwardMessageStatus.Pending,
|
|
});
|
|
}
|
|
|
|
for (var i = 0; i < 3; i++)
|
|
{
|
|
await storage.EnqueueAsync(new StoreAndForwardMessage
|
|
{
|
|
Id = Guid.NewGuid().ToString("N"),
|
|
Category = StoreAndForwardCategory.Notification,
|
|
Target = "alerts",
|
|
PayloadJson = "{}",
|
|
MaxRetries = 50,
|
|
RetryIntervalMs = 30000,
|
|
CreatedAt = DateTimeOffset.UtcNow,
|
|
Status = StoreAndForwardMessageStatus.Pending,
|
|
});
|
|
}
|
|
|
|
// After failover, standby reads buffer depths
|
|
standbyDb = TestLocalDb.Create(dbPath);
|
|
var standbyStorage = new StoreAndForwardStorage(standbyDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await standbyStorage.InitializeAsync();
|
|
|
|
var depths = await standbyStorage.GetBufferDepthByCategoryAsync();
|
|
Assert.Equal(5, depths[StoreAndForwardCategory.ExternalSystem]);
|
|
Assert.Equal(3, depths[StoreAndForwardCategory.Notification]);
|
|
}
|
|
finally
|
|
{
|
|
// Dispose before deleting — the master connections anchor the WAL sidecars.
|
|
standbyDb?.Dispose();
|
|
primaryDb?.Dispose();
|
|
TestLocalDb.DeleteFiles(dbPath);
|
|
}
|
|
}
|
|
}
|