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
206 lines
8.5 KiB
C#
206 lines
8.5 KiB
C#
using System.Text.Json;
|
|
using Microsoft.Extensions.Logging.Abstractions;
|
|
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Deployment;
|
|
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-7 (Phase 8): Recovery drill test scaffolds.
|
|
/// Mid-deploy failover, communication drops, and site restart with persisted configs.
|
|
/// </summary>
|
|
public class RecoveryDrillTests
|
|
{
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public void MidDeployFailover_SiteStateQuery_ThenRedeploy()
|
|
{
|
|
// Scenario: Deployment in progress, central node fails over.
|
|
// New central node queries site for current deployment state, then re-issues deploy.
|
|
|
|
// Step 1: Deployment started
|
|
var initialStatus = new DeploymentStatusResponse(
|
|
"dep-1", "pump-station-1", DeploymentStatus.InProgress,
|
|
null, DateTimeOffset.UtcNow);
|
|
|
|
Assert.Equal(DeploymentStatus.InProgress, initialStatus.Status);
|
|
|
|
// Step 2: Central failover — new node queries site state
|
|
// Site reports current status (InProgress or whatever it actually is)
|
|
var queriedStatus = new DeploymentStatusResponse(
|
|
"dep-1", "pump-station-1", DeploymentStatus.InProgress,
|
|
null, DateTimeOffset.UtcNow.AddSeconds(5));
|
|
|
|
Assert.Equal(DeploymentStatus.InProgress, queriedStatus.Status);
|
|
|
|
// Step 3: Central re-deploys with same deployment ID + revision hash
|
|
// Idempotent: same deploymentId + revisionHash = no-op if already applied
|
|
var redeployCommand = new DeployInstanceCommand(
|
|
"dep-1", "pump-station-1", "abc123",
|
|
"""{"attributes":[],"scripts":[],"alarms":[]}""",
|
|
"admin", DateTimeOffset.UtcNow.AddSeconds(10));
|
|
|
|
Assert.Equal("dep-1", redeployCommand.DeploymentId);
|
|
Assert.Equal("abc123", redeployCommand.RevisionHash);
|
|
|
|
// Step 4: Site applies (idempotent — revision hash matches)
|
|
var completedStatus = new DeploymentStatusResponse(
|
|
"dep-1", "pump-station-1", DeploymentStatus.Success,
|
|
null, DateTimeOffset.UtcNow.AddSeconds(15));
|
|
|
|
Assert.Equal(DeploymentStatus.Success, completedStatus.Status);
|
|
}
|
|
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public async Task CommunicationDrop_DuringArtifactDeployment_BuffersForRetry()
|
|
{
|
|
// Scenario: Communication drops while deploying system-wide artifacts.
|
|
// The deployment command is buffered by S&F and retried when connection restores.
|
|
var dbPath = Path.Combine(Path.GetTempPath(), $"sf_commdrop_{Guid.NewGuid():N}.db");
|
|
|
|
// The store takes an ILocalDb (LocalDb has no in-memory mode), so the buffer
|
|
// lives in a real temp file for the duration of the drill.
|
|
TestLocalDb? localDb = null;
|
|
|
|
try
|
|
{
|
|
localDb = TestLocalDb.Create(dbPath);
|
|
var storage = new StoreAndForwardStorage(localDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await storage.InitializeAsync();
|
|
|
|
var options = new StoreAndForwardOptions
|
|
{
|
|
DefaultRetryInterval = TimeSpan.FromSeconds(5),
|
|
DefaultMaxRetries = 100,
|
|
};
|
|
var service = new StoreAndForwardService(storage, options, NullLogger<StoreAndForwardService>.Instance);
|
|
await service.StartAsync();
|
|
|
|
// Register a handler that simulates communication failure
|
|
var callCount = 0;
|
|
service.RegisterDeliveryHandler(StoreAndForwardCategory.ExternalSystem,
|
|
_ =>
|
|
{
|
|
callCount++;
|
|
throw new InvalidOperationException("Connection to site lost");
|
|
});
|
|
|
|
// Attempt delivery — should fail and buffer
|
|
var result = await service.EnqueueAsync(
|
|
StoreAndForwardCategory.ExternalSystem,
|
|
"site-01/artifacts",
|
|
"""{"deploymentId":"dep-1","artifacts":["shared-script-v2"]}""");
|
|
|
|
Assert.True(result.Accepted);
|
|
Assert.True(result.WasBuffered);
|
|
Assert.Equal(1, callCount);
|
|
|
|
// Verify the message is in the buffer
|
|
var depths = await service.GetBufferDepthAsync();
|
|
Assert.True(depths.ContainsKey(StoreAndForwardCategory.ExternalSystem));
|
|
Assert.Equal(1, depths[StoreAndForwardCategory.ExternalSystem]);
|
|
|
|
await service.StopAsync();
|
|
}
|
|
finally
|
|
{
|
|
// Dispose before deleting — the master connection anchors the WAL sidecars.
|
|
localDb?.Dispose();
|
|
TestLocalDb.DeleteFiles(dbPath);
|
|
}
|
|
}
|
|
|
|
[Trait("Category", "Integration")]
|
|
[Fact]
|
|
public async Task SiteRestart_WithPersistedConfigs_RebuildFromSQLite()
|
|
{
|
|
// Scenario: Site restarts. Deployed instance configs are persisted in SQLite.
|
|
// On startup, the Deployment Manager Actor reads configs from SQLite and
|
|
// recreates Instance Actors.
|
|
var dbPath = Path.Combine(Path.GetTempPath(), $"sf_restart_{Guid.NewGuid():N}.db");
|
|
|
|
// The restarted "process" opens its own local database over the SAME file — that
|
|
// is what this drill verifies survives.
|
|
TestLocalDb? preRestartDb = null;
|
|
TestLocalDb? restartedDb = null;
|
|
|
|
try
|
|
{
|
|
// Pre-restart: S&F messages in buffer
|
|
preRestartDb = TestLocalDb.Create(dbPath);
|
|
var storage = new StoreAndForwardStorage(preRestartDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await storage.InitializeAsync();
|
|
|
|
for (var i = 0; i < 3; i++)
|
|
{
|
|
await storage.EnqueueAsync(new StoreAndForwardMessage
|
|
{
|
|
Id = $"msg-{i}",
|
|
Category = StoreAndForwardCategory.ExternalSystem,
|
|
Target = "api-endpoint",
|
|
PayloadJson = $$"""{"instanceName":"machine-{{i}}","value":42}""",
|
|
MaxRetries = 50,
|
|
RetryIntervalMs = 30000,
|
|
CreatedAt = DateTimeOffset.UtcNow,
|
|
Status = StoreAndForwardMessageStatus.Pending,
|
|
OriginInstanceName = $"machine-{i}"
|
|
});
|
|
}
|
|
|
|
// Post-restart: new storage instance reads same DB
|
|
restartedDb = TestLocalDb.Create(dbPath);
|
|
var restartedStorage = new StoreAndForwardStorage(restartedDb.Db, NullLogger<StoreAndForwardStorage>.Instance);
|
|
await restartedStorage.InitializeAsync();
|
|
|
|
var pending = await restartedStorage.GetMessagesForRetryAsync();
|
|
Assert.Equal(3, pending.Count);
|
|
|
|
// Verify each message retains its origin instance
|
|
Assert.Contains(pending, m => m.OriginInstanceName == "machine-0");
|
|
Assert.Contains(pending, m => m.OriginInstanceName == "machine-1");
|
|
Assert.Contains(pending, m => m.OriginInstanceName == "machine-2");
|
|
}
|
|
finally
|
|
{
|
|
// Dispose before deleting — the master connections anchor the WAL sidecars.
|
|
restartedDb?.Dispose();
|
|
preRestartDb?.Dispose();
|
|
TestLocalDb.DeleteFiles(dbPath);
|
|
}
|
|
}
|
|
|
|
[Fact]
|
|
public void DeploymentIdempotency_SameRevisionHash_NoOp()
|
|
{
|
|
// Verify the deployment model supports idempotency via revision hash.
|
|
// Two deploy commands with the same deploymentId + revisionHash should
|
|
// produce the same result (site can detect the duplicate and skip).
|
|
var cmd1 = new DeployInstanceCommand(
|
|
"dep-1", "pump-1", "rev-abc123",
|
|
"""{"attributes":[]}""", "admin", DateTimeOffset.UtcNow);
|
|
|
|
var cmd2 = new DeployInstanceCommand(
|
|
"dep-1", "pump-1", "rev-abc123",
|
|
"""{"attributes":[]}""", "admin", DateTimeOffset.UtcNow.AddSeconds(30));
|
|
|
|
Assert.Equal(cmd1.DeploymentId, cmd2.DeploymentId);
|
|
Assert.Equal(cmd1.RevisionHash, cmd2.RevisionHash);
|
|
Assert.Equal(cmd1.InstanceUniqueName, cmd2.InstanceUniqueName);
|
|
}
|
|
|
|
[Fact]
|
|
public void FlattenedConfigSnapshot_ContainsRevisionHash()
|
|
{
|
|
// The FlattenedConfigurationSnapshot includes a revision hash for staleness detection.
|
|
var snapshot = new FlattenedConfigurationSnapshot(
|
|
"inst-1", "rev-abc123",
|
|
"""{"attributes":[],"scripts":[],"alarms":[]}""",
|
|
DateTimeOffset.UtcNow);
|
|
|
|
Assert.Equal("rev-abc123", snapshot.RevisionHash);
|
|
}
|
|
}
|