232bff5df7
1. Wiped-node back-fill (live gate check 4). Fixed upstream in ZB.MOM.WW.LocalDb 0.1.2 and pinned here. The gate's diagnosis was slightly off: the oplog cap was not the gate. Snapshot detection measured the peer's gap against the oldest surviving oplog row and read an empty oplog as "no gap possible" — and an empty oplog is the steady state of a converged pair, since ack-pruning deletes everything the peer confirmed. The healthy state was the one state that could not heal a wiped peer. Now measured against last_acked_seq when the oplog is empty. Pinned at this level too, not just the library's: the pair harness grows a WipePassiveAsync (a NEW database — a rebuilt node comes back with a new node id and a zero watermark), and the new scenario asserts the emptied oplog as its precondition before wiping, then requires the deployment artifact to come back byte-identical with no new deploy. Verified RED against the pinned 0.1.1 (times out waiting for back-fill) and green on 0.1.2. 2. Oplog growth on default-OFF nodes (live gate check 8), fixed at the source: StoreAsync now skips entirely when the pointer already names this deployment/revision, the SHA matches the bytes, and the expected chunk count is present. Re-caching an artifact the node already holds — every restart's boot-from-cache, every RestoreApplied — writes nothing and mints no oplog rows, where before it cost a delete plus an insert per chunk plus a pointer update, all identical to what was already there. Identity is over the bytes and the chunks are counted, both deliberately: a re-composed artifact can carry the same ids with different bytes, and a pointer can name a deployment whose chunks are missing, where skipping would make an unreadable cache permanent. Both guards verified RED against a naive pointer-only skip. The gate's stated bound was also wrong and is corrected in the doc: growth was never headed for the 1M row cap. AddZbLocalDbReplication is registered unconditionally, so MaintenanceBackgroundService runs on default-OFF nodes and the 7-day MaxOplogAge cap prunes. Runtime.Tests 412/0/31, Host.IntegrationTests LocalDb 45/45. Pre-existing and unrelated: AbCip_Green_AgainstSim (needs the AB CIP docker fixture, red on a clean master too) and a flaky Roslyn race test (green 2/2 in isolation). Claude-Session: https://claude.ai/code/session_01GASWkNEi68FSCtvr6rLoEW
367 lines
15 KiB
C#
367 lines
15 KiB
C#
using System.Net;
|
|
using Microsoft.AspNetCore.Builder;
|
|
using Microsoft.AspNetCore.Hosting;
|
|
using Microsoft.AspNetCore.Hosting.Server;
|
|
using Microsoft.AspNetCore.Hosting.Server.Features;
|
|
using Microsoft.AspNetCore.Server.Kestrel.Core;
|
|
using Microsoft.Extensions.Configuration;
|
|
using Microsoft.Extensions.DependencyInjection;
|
|
using Microsoft.Extensions.Hosting;
|
|
using Microsoft.Extensions.Logging.Abstractions;
|
|
using Xunit;
|
|
using ZB.MOM.WW.LocalDb;
|
|
using ZB.MOM.WW.LocalDb.Replication;
|
|
using ZB.MOM.WW.OtOpcUa.Host.Configuration;
|
|
using ZB.MOM.WW.OtOpcUa.Runtime.DeploymentCache;
|
|
|
|
namespace ZB.MOM.WW.OtOpcUa.Host.IntegrationTests.LocalDb;
|
|
|
|
/// <summary>
|
|
/// Serializes the two-node convergence tests against one another: each stands up a real Kestrel
|
|
/// h2c listener plus two SQLite files, and running them concurrently under CI contention is a
|
|
/// flakiness risk. The rest of the assembly parallelizes normally.
|
|
/// </summary>
|
|
[CollectionDefinition("LocalDbPairConvergence")]
|
|
public sealed class LocalDbPairConvergenceCollection;
|
|
|
|
/// <summary>
|
|
/// Two driver-role OtOpcUa nodes replicating the deployment-artifact cache over a REAL loopback
|
|
/// gRPC transport (Kestrel h2c on 127.0.0.1), through the REAL fail-closed
|
|
/// <see cref="LocalDbSyncAuthInterceptor"/>. Node A is the initiator (it dials the peer); node B
|
|
/// is passive (it hosts <c>MapZbLocalDbSync</c>).
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// <para>
|
|
/// Both databases are initialised through the production <see cref="LocalDbSetup.OnReady"/> —
|
|
/// a hand-written schema here would prove only that the test agrees with itself. The tables,
|
|
/// their primary keys, and the DDL→<c>RegisterReplicated</c> ordering under test are the ones
|
|
/// the host actually runs.
|
|
/// </para>
|
|
/// <para>
|
|
/// The two <see cref="ILocalDb"/> instances are owned by the harness and registered into the
|
|
/// hosts as pre-constructed singletons. MS.DI does not dispose instances it did not create,
|
|
/// so tearing a host down (the transport-loss scenario) leaves the databases intact and
|
|
/// writable — which is exactly what lets node A accumulate writes while B is down.
|
|
/// </para>
|
|
/// <para>
|
|
/// A real loopback socket (not an in-memory TestServer) is deliberate: killing the passive
|
|
/// host disposes the server and closes the socket, faulting the initiator's active stream
|
|
/// promptly. An in-memory TestServer does not model a connection drop and leaves the client
|
|
/// hanging.
|
|
/// </para>
|
|
/// <para>
|
|
/// The API keys are per-node so the wrong-key scenario can hand A and B different keys and
|
|
/// assert non-convergence — with a matching-key positive control proving the same harness
|
|
/// does converge when the keys agree (an absence assertion without a positive control passed
|
|
/// vacuously in ScadaBridge).
|
|
/// </para>
|
|
/// <para>Offline: no docker, no external services.</para>
|
|
/// </remarks>
|
|
public sealed class LocalDbPairHarness : IAsyncDisposable
|
|
{
|
|
/// <summary>The key both nodes share unless a test overrides one of them.</summary>
|
|
public const string DefaultApiKey = "otopcua-localdb-pair-convergence-key";
|
|
|
|
/// <summary>How long a scenario waits for the pair to agree (or to stay diverged) before deciding.</summary>
|
|
public static readonly TimeSpan ConvergeTimeout = TimeSpan.FromSeconds(30);
|
|
|
|
private readonly string _apiKeyA;
|
|
private readonly string _apiKeyB;
|
|
|
|
private readonly string _pathA = Path.Combine(Path.GetTempPath(), $"otopcua-pairA-{Guid.NewGuid():N}.db");
|
|
|
|
// Not readonly: WipePassiveAsync replaces node B's database wholesale, which is what a rebuilt
|
|
// node with a lost volume actually is — a new file, and with it a new node id.
|
|
private string _pathB = Path.Combine(Path.GetTempPath(), $"otopcua-pairB-{Guid.NewGuid():N}.db");
|
|
|
|
private readonly ServiceProvider _dbProviderA;
|
|
private ServiceProvider _dbProviderB;
|
|
|
|
private IHost? _serverHost; // node B — passive
|
|
private IHost? _initiatorHost; // node A — dials the peer
|
|
|
|
static LocalDbPairHarness() =>
|
|
// Grpc.Net.Client dials the loopback server over HTTP/2 cleartext (h2c).
|
|
AppContext.SetSwitch("System.Net.Http.SocketsHttpHandler.Http2UnencryptedSupport", true);
|
|
|
|
/// <param name="apiKeyA">Node A's replication key. Defaults to <see cref="DefaultApiKey"/>.</param>
|
|
/// <param name="apiKeyB">Node B's replication key. Defaults to <see cref="DefaultApiKey"/>.</param>
|
|
public LocalDbPairHarness(string? apiKeyA = null, string? apiKeyB = null)
|
|
{
|
|
_apiKeyA = apiKeyA ?? DefaultApiKey;
|
|
_apiKeyB = apiKeyB ?? DefaultApiKey;
|
|
|
|
_dbProviderA = BuildDatabaseProvider(_pathA);
|
|
_dbProviderB = BuildDatabaseProvider(_pathB);
|
|
}
|
|
|
|
/// <summary>Node A — the initiator, which dials the peer.</summary>
|
|
public ILocalDb A => _dbProviderA.GetRequiredService<ILocalDb>();
|
|
|
|
/// <summary>Node B — the passive node, which listens.</summary>
|
|
public ILocalDb B => _dbProviderB.GetRequiredService<ILocalDb>();
|
|
|
|
/// <summary>The production artifact cache over node A's database.</summary>
|
|
public IDeploymentArtifactCache CacheA =>
|
|
new LocalDbDeploymentArtifactCache(A, NullLogger<LocalDbDeploymentArtifactCache>.Instance);
|
|
|
|
/// <summary>The production artifact cache over node B's database.</summary>
|
|
public IDeploymentArtifactCache CacheB =>
|
|
new LocalDbDeploymentArtifactCache(B, NullLogger<LocalDbDeploymentArtifactCache>.Instance);
|
|
|
|
// ---- lifecycle --------------------------------------------------------------------------
|
|
|
|
/// <summary>Forces both databases to construct (running OnReady) then brings the pair online.</summary>
|
|
public async Task StartAsync()
|
|
{
|
|
_ = A;
|
|
_ = B;
|
|
|
|
await StartPassiveAsync();
|
|
await StartInitiatorAsync();
|
|
}
|
|
|
|
/// <summary>Takes node B's listener down, leaving its database intact and writable.</summary>
|
|
public async Task StopPassiveAsync()
|
|
{
|
|
await StopHostAsync(_serverHost);
|
|
_serverHost = null;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Destroys node B's database and replaces it with an empty one, leaving the pairing config
|
|
/// untouched — the rebuilt-node case: a lost volume, a re-imaged host, a fresh container.
|
|
/// </summary>
|
|
/// <remarks>
|
|
/// A new file, not a truncated one, because that is what the real thing is: the node id lives
|
|
/// in the database, so a rebuilt node comes back with a new identity and a zero watermark. The
|
|
/// caller follows with <see cref="RestartPairAsync"/> to bring the wiped node back online.
|
|
/// </remarks>
|
|
public async Task WipePassiveAsync()
|
|
{
|
|
await StopPassiveAsync();
|
|
await _dbProviderB.DisposeAsync();
|
|
|
|
// Pooled connections outlive the provider; without this the delete silently no-ops on
|
|
// Windows and the "wiped" node would still hold its rows.
|
|
Microsoft.Data.Sqlite.SqliteConnection.ClearAllPools();
|
|
DeleteDatabaseFiles(_pathB);
|
|
|
|
_pathB = Path.Combine(Path.GetTempPath(), $"otopcua-pairB-{Guid.NewGuid():N}.db");
|
|
_dbProviderB = BuildDatabaseProvider(_pathB);
|
|
_ = B;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Brings node B back on a NEW loopback port and re-dials from A. The initiator re-reads the
|
|
/// peer address on each reconnect, so this is a genuine rejoin over the same databases.
|
|
/// </summary>
|
|
public async Task RestartPairAsync()
|
|
{
|
|
await StartPassiveAsync();
|
|
await StopHostAsync(_initiatorHost);
|
|
_initiatorHost = null;
|
|
await StartInitiatorAsync();
|
|
}
|
|
|
|
// ---- convergence helpers ----------------------------------------------------------------
|
|
|
|
/// <summary>Polls <paramref name="condition"/> until true or the deadline passes; fails otherwise.</summary>
|
|
public static async Task WaitUntilAsync(Func<Task<bool>> condition, string because)
|
|
{
|
|
var deadline = DateTime.UtcNow + ConvergeTimeout;
|
|
while (DateTime.UtcNow < deadline)
|
|
{
|
|
if (await condition())
|
|
return;
|
|
await Task.Delay(50);
|
|
}
|
|
|
|
Assert.Fail($"Timed out after {ConvergeTimeout.TotalSeconds:0}s waiting for: {because}");
|
|
}
|
|
|
|
/// <summary>Waits out a bounded window and returns whether <paramref name="condition"/> ever held.</summary>
|
|
/// <remarks>
|
|
/// For the negative half of the wrong-key scenario: it must NOT converge. A short, fixed
|
|
/// window keeps the test quick while still giving a matching-key control ample time to
|
|
/// converge (the control uses <see cref="WaitUntilAsync"/> with the full timeout).
|
|
/// </remarks>
|
|
public static async Task<bool> HeldWithinAsync(Func<Task<bool>> condition, TimeSpan window)
|
|
{
|
|
var deadline = DateTime.UtcNow + window;
|
|
while (DateTime.UtcNow < deadline)
|
|
{
|
|
if (await condition())
|
|
return true;
|
|
await Task.Delay(50);
|
|
}
|
|
|
|
return false;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Dumps the <c>__localdb_row_version</c> rows for one table, ordered by pk, as
|
|
/// <c>pk_json|hlc|node_id|is_tombstone</c>. Equal dumps on both nodes prove B holds A's
|
|
/// origin-stamped row (same HLC + node id), not a locally re-derived one.
|
|
/// </summary>
|
|
public static async Task<string> DumpRowVersionAsync(ILocalDb db, string table)
|
|
{
|
|
var rows = await db.QueryAsync(
|
|
"""
|
|
SELECT pk_json, hlc, node_id, is_tombstone
|
|
FROM __localdb_row_version
|
|
WHERE table_name = @Table
|
|
ORDER BY pk_json
|
|
""",
|
|
static r => $"{r.GetString(0)}|{r.GetInt64(1)}|{r.GetString(2)}|{r.GetInt64(3)}",
|
|
new { Table = table });
|
|
return string.Join("\n", rows);
|
|
}
|
|
|
|
/// <summary>Counts <c>deployment_artifacts</c> chunk rows for one deployment on a node.</summary>
|
|
public static async Task<long> ChunkCountAsync(ILocalDb db, string deploymentId)
|
|
{
|
|
var rows = await db.QueryAsync(
|
|
"SELECT COUNT(*) FROM deployment_artifacts WHERE deployment_id = @DeploymentId",
|
|
static r => r.GetInt64(0),
|
|
new { DeploymentId = deploymentId });
|
|
return rows[0];
|
|
}
|
|
|
|
/// <summary>
|
|
/// Counts oplog rows on a node. Zero means every local change has been acked by the peer and
|
|
/// pruned — the steady state of a converged pair, and the state from which a wiped peer can
|
|
/// only be healed by a snapshot.
|
|
/// </summary>
|
|
public static async Task<long> OplogDepthAsync(ILocalDb db)
|
|
{
|
|
var rows = await db.QueryAsync("SELECT COUNT(*) FROM __localdb_oplog", static r => r.GetInt64(0));
|
|
return rows[0];
|
|
}
|
|
|
|
/// <summary>Counts tombstone rows in <c>__localdb_row_version</c> for one table on a node.</summary>
|
|
public static async Task<long> TombstoneCountAsync(ILocalDb db, string table)
|
|
{
|
|
var rows = await db.QueryAsync(
|
|
"""
|
|
SELECT COUNT(*) FROM __localdb_row_version
|
|
WHERE table_name = @Table AND is_tombstone = 1
|
|
""",
|
|
static r => r.GetInt64(0),
|
|
new { Table = table });
|
|
return rows[0];
|
|
}
|
|
|
|
// ---- fixture internals ------------------------------------------------------------------
|
|
|
|
/// <summary>
|
|
/// A provider owning one deployment-cache database, initialised through the host's own
|
|
/// <see cref="LocalDbSetup.OnReady"/> — same schema, same registration order.
|
|
/// </summary>
|
|
private static ServiceProvider BuildDatabaseProvider(string path)
|
|
{
|
|
var config = new ConfigurationBuilder()
|
|
.AddInMemoryCollection(new Dictionary<string, string?> { ["LocalDb:Path"] = path })
|
|
.Build();
|
|
|
|
return new ServiceCollection()
|
|
.AddZbLocalDb(config, LocalDbSetup.OnReady)
|
|
.BuildServiceProvider();
|
|
}
|
|
|
|
private IConfiguration ReplicationConfig(string apiKey, string? peerAddress)
|
|
{
|
|
var values = new Dictionary<string, string?>
|
|
{
|
|
// Tight flush + bounded reconnect backoff so convergence is observable well inside the
|
|
// poll deadline. The 60 s production default would let the doubling backoff overrun it
|
|
// after a peer outage.
|
|
["LocalDb:Replication:FlushInterval"] = "00:00:00.050",
|
|
["LocalDb:Replication:ReconnectBackoffMax"] = "00:00:02",
|
|
["LocalDb:Replication:ApiKey"] = apiKey,
|
|
};
|
|
|
|
if (peerAddress is not null)
|
|
values["LocalDb:Replication:PeerAddress"] = peerAddress;
|
|
|
|
return new ConfigurationBuilder().AddInMemoryCollection(values).Build();
|
|
}
|
|
|
|
/// <summary>Starts node B, the passive listener, behind the real auth interceptor.</summary>
|
|
private async Task StartPassiveAsync()
|
|
{
|
|
var config = ReplicationConfig(_apiKeyB, peerAddress: null);
|
|
|
|
_serverHost = await new HostBuilder()
|
|
.ConfigureWebHost(web =>
|
|
{
|
|
web.UseKestrel(o =>
|
|
o.Listen(IPAddress.Loopback, 0, listen => listen.Protocols = HttpProtocols.Http2));
|
|
web.ConfigureServices(services =>
|
|
{
|
|
services.AddLogging();
|
|
services.AddRouting();
|
|
// The REAL interceptor, not a stand-in. If it rejected legitimate peer traffic,
|
|
// every matching-key scenario would fail — which is the point.
|
|
services.AddGrpc(o => o.Interceptors.Add<LocalDbSyncAuthInterceptor>());
|
|
services.AddSingleton(B);
|
|
services.AddZbLocalDbReplication(config);
|
|
})
|
|
.Configure(app =>
|
|
{
|
|
app.UseRouting();
|
|
app.UseEndpoints(e => e.MapZbLocalDbSync());
|
|
});
|
|
})
|
|
.StartAsync();
|
|
}
|
|
|
|
/// <summary>Starts node A, which dials the passive node.</summary>
|
|
private async Task StartInitiatorAsync()
|
|
{
|
|
var config = ReplicationConfig(_apiKeyA, PassiveAddress());
|
|
|
|
_initiatorHost = await new HostBuilder()
|
|
.ConfigureServices(services =>
|
|
{
|
|
services.AddLogging();
|
|
services.AddSingleton(A);
|
|
services.AddZbLocalDbReplication(config);
|
|
})
|
|
.StartAsync();
|
|
}
|
|
|
|
private string PassiveAddress()
|
|
=> _serverHost!.Services.GetRequiredService<IServer>()
|
|
.Features.Get<IServerAddressesFeature>()!.Addresses.Single();
|
|
|
|
private static async Task StopHostAsync(IHost? host)
|
|
{
|
|
if (host is null)
|
|
return;
|
|
try { await host.StopAsync(TimeSpan.FromSeconds(5)); } catch { /* teardown */ }
|
|
host.Dispose();
|
|
}
|
|
|
|
public async ValueTask DisposeAsync()
|
|
{
|
|
await StopHostAsync(_initiatorHost);
|
|
await StopHostAsync(_serverHost);
|
|
await _dbProviderA.DisposeAsync();
|
|
await _dbProviderB.DisposeAsync();
|
|
|
|
Microsoft.Data.Sqlite.SqliteConnection.ClearAllPools();
|
|
DeleteDatabaseFiles(_pathA);
|
|
DeleteDatabaseFiles(_pathB);
|
|
}
|
|
|
|
/// <summary>Deletes a SQLite database and its WAL/shm sidecars, best effort.</summary>
|
|
private static void DeleteDatabaseFiles(string path)
|
|
{
|
|
foreach (var suffix in new[] { "", "-wal", "-shm" })
|
|
{
|
|
try { File.Delete(path + suffix); } catch { /* best effort */ }
|
|
}
|
|
}
|
|
}
|