Files
lmxopcua/tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests/TcpStallProxy.cs
T
Joseph Doherty fccffd0a0f feat(opcuaclient): #676 follow-ups — endpoint rewrite, stall wire test, fast definitive-loss recovery
- Endpoint rewrite: the driver now connects to the configured host AND port (scheme
  match, advertised path kept) instead of the server-advertised URL — fixes NAT/port-map
  upstreams and lets an in-test proxy carry the session (SDK SelectEndpoint rule).
- TcpStallProxy + OpcUaClientDriverStallWireTests: the in-place blip (#670) is now
  wire-tested on loopback — one Bad, frozen read stamp, same session, identical value
  republished Good, a post-recovery change arrives, no source-time regression after
  the SDK's late backlog flush.
- Defect found by that test, fixed: a change published right after a stall rode a
  Publish response the SDK timed out and never republished, leaving the node Good on
  the pre-change value indefinitely. New trailing reconcile read (Timeout +
  KeepAliveInterval after recovery) publishes any Good value newer than the last
  accepted one, through the replay guard's mark.
- IDriverConnectionLossSource (Core.Abstractions): opt-in definitive-loss signal.
  DriverInstanceActor attaches in PreStart / detaches in PostStop and turns a raise
  into a disconnect only while Connected. OpcUaClient raises once per session on
  keep-alive BadSessionIdInvalid/BadSessionClosed/BadSessionNotActivated/
  BadServerHalted (measured: the SDK never re-opens a halted channel) or a dropped
  subscription; ambiguous codes stay with the #527 watchdog.
- Replay guard: one Information summary per recovery when the window closes
  ("dropped N late notifications across M refs"), with a timer so quiet
  subscriptions log it too.
- ReconnectPeriod deleted (options, AdminUI form, docs, tests); stored configs that
  carry reconnectPeriod still parse in the factory, probe and browser.
- Docs: OpcUaClient.md, DriverLifecycle.md, driver-specs.md, CLAUDE.md.
2026-10-11 11:35:52 -04:00

127 lines
4.6 KiB
C#

using System.Net;
using System.Net.Sockets;
namespace ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests;
/// <summary>
/// Gitea #676 — an in-test TCP forwarder that can STALL a connection without closing it: the shape of a
/// <c>docker pause</c>, a hung switch port or a congested WAN link, where the socket stays open and simply stops
/// carrying bytes. Each accepted connection gets a fresh upstream connection and two copy pumps; every pump awaits a
/// shared gate before each write, so <see cref="Pause"/> holds all traffic in both directions (bytes already read
/// are held, the rest back up in the kernel buffers) and <see cref="Resume"/> lets it all through in order. Nothing
/// is ever closed by a pause — the outage is invisible at the TCP level, exactly as in production.
/// </summary>
internal sealed class TcpStallProxy : IAsyncDisposable
{
private readonly TcpListener _listener = new(IPAddress.Loopback, 0);
private readonly int _targetPort;
private readonly CancellationTokenSource _cts = new();
private readonly List<TcpClient> _sockets = [];
private readonly Lock _lock = new();
private TaskCompletionSource _gate = Open();
private Task _acceptLoop = Task.CompletedTask;
private TcpStallProxy(int targetPort) => _targetPort = targetPort;
/// <summary>The loopback port clients connect to.</summary>
public int Port => ((IPEndPoint)_listener.LocalEndpoint).Port;
/// <summary>Number of client connections accepted so far — a new one means the client re-connected.</summary>
public int AcceptedConnections { get; private set; }
/// <summary>Starts forwarding <c>127.0.0.1:{Port}</c> to <c>127.0.0.1:{targetPort}</c>.</summary>
public static TcpStallProxy Start(int targetPort)
{
var proxy = new TcpStallProxy(targetPort);
proxy._listener.Start();
proxy._acceptLoop = proxy.AcceptLoopAsync();
return proxy;
}
/// <summary>Rewrites the port of an <c>opc.tcp</c> URL to this proxy's.</summary>
public string Through(string endpointUrl) => new UriBuilder(endpointUrl) { Port = Port }.Uri.ToString();
/// <summary>Stops all traffic in both directions; sockets stay open.</summary>
public void Pause()
{
lock (_lock)
if (_gate.Task.IsCompleted) _gate = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
}
/// <summary>Releases everything held since <see cref="Pause"/>, in order.</summary>
public void Resume()
{
lock (_lock) _gate.TrySetResult();
}
private static TaskCompletionSource Open()
{
var tcs = new TaskCompletionSource(TaskCreationOptions.RunContinuationsAsynchronously);
tcs.SetResult();
return tcs;
}
private Task CurrentGate()
{
lock (_lock) return _gate.Task;
}
private async Task AcceptLoopAsync()
{
while (!_cts.IsCancellationRequested)
{
TcpClient client;
try { client = await _listener.AcceptTcpClientAsync(_cts.Token); }
catch { return; }
var upstream = new TcpClient();
try { await upstream.ConnectAsync(IPAddress.Loopback, _targetPort, _cts.Token); }
catch
{
client.Dispose();
upstream.Dispose();
continue;
}
lock (_lock)
{
AcceptedConnections++;
_sockets.Add(client);
_sockets.Add(upstream);
}
_ = PumpAsync(client.GetStream(), upstream.GetStream());
_ = PumpAsync(upstream.GetStream(), client.GetStream());
}
}
private async Task PumpAsync(NetworkStream from, NetworkStream to)
{
var buffer = new byte[64 * 1024];
try
{
while (true)
{
var n = await from.ReadAsync(buffer, _cts.Token);
if (n == 0) break;
await CurrentGate().WaitAsync(_cts.Token);
await to.WriteAsync(buffer.AsMemory(0, n), _cts.Token);
}
}
catch { /* either side gone or the proxy disposed */ }
// Half-close propagation is not needed: a real close (server stopped) tears the pair down on the next read.
try { to.Socket.Shutdown(SocketShutdown.Send); } catch { }
}
public async ValueTask DisposeAsync()
{
Resume();
await _cts.CancelAsync();
_listener.Stop();
try { await _acceptLoop; } catch { }
lock (_lock)
{
foreach (var s in _sockets) s.Dispose();
_sockets.Clear();
}
_cts.Dispose();
}
}