refactor: rename ScadaLink → ZB.MOM.WW.ScadaBridge (code + projects + namespaces)
Solution + 23 src projects + 26 test projects renamed; folders, csproj, namespaces, and ScadaLinkDbContext/ScadaBridgeDbContext class updated. ActorSystem "scadalink" → "scadabridge", Akka seed-node URLs migrated. SQL roles/logins, LDAP domains, CLI command name, and CLI config dir (~/.scadalink → ~/.scadabridge) also renamed. Build green; 5 Host.Tests fail awaiting SQL login rename in next commit. Pre-existing StaleTagMonitor timing flakes unchanged. Rename script committed at tools/rename-to-scadabridge.sh.
This commit is contained in:
Joseph Doherty
@@ -0,0 +1,291 @@
|
||||
using Akka.Actor;
|
||||
using Akka.Event;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.DebugView;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Streaming;
|
||||
using ZB.MOM.WW.ScadaBridge.Communication.Grpc;
|
||||
|
||||
namespace ZB.MOM.WW.ScadaBridge.Communication.Actors;
|
||||
|
||||
/// <summary>
|
||||
/// Long-lived (one per active debug session) actor on the central side. Debug sessions
|
||||
/// are session-based and temporary — this actor holds no persisted state and does not
|
||||
/// derive from an Akka.Persistence base class; its state does not survive a restart.
|
||||
/// Sends SubscribeDebugViewRequest to the site via CentralCommunicationActor (with THIS actor
|
||||
/// as the Sender) to get the initial snapshot. After receiving the snapshot, opens a gRPC
|
||||
/// server-streaming subscription via SiteStreamGrpcClient for ongoing events.
|
||||
/// Stream events are marshalled back to the actor via Self.Tell for thread safety.
|
||||
/// </summary>
|
||||
public class DebugStreamBridgeActor : ReceiveActor, IWithTimers
|
||||
{
|
||||
private readonly ILoggingAdapter _log = Context.GetLogger();
|
||||
private readonly string _siteIdentifier;
|
||||
private readonly string _instanceUniqueName;
|
||||
private readonly string _correlationId;
|
||||
private readonly IActorRef _centralCommunicationActor;
|
||||
private readonly Action<object> _onEvent;
|
||||
private readonly Action _onTerminated;
|
||||
private readonly SiteStreamGrpcClientFactory _grpcFactory;
|
||||
private readonly string _grpcNodeAAddress;
|
||||
private readonly string _grpcNodeBAddress;
|
||||
|
||||
private const int MaxRetries = 3;
|
||||
private const string ReconnectTimerKey = "grpc-reconnect";
|
||||
private const string StabilityTimerKey = "grpc-stability";
|
||||
/// <summary>Delay between gRPC reconnection attempts.</summary>
|
||||
internal static TimeSpan ReconnectDelay { get; set; } = TimeSpan.FromSeconds(5);
|
||||
|
||||
/// <summary>
|
||||
/// How long a freshly-opened gRPC stream must stay up before its retry budget
|
||||
/// is considered "recovered" and <see cref="_retryCount"/> is reset to 0.
|
||||
/// Communication-008: the retry count must NOT be reset by individual events —
|
||||
/// a stream that connects, delivers one event, then fails repeatedly would
|
||||
/// otherwise reconnect forever and never trip <see cref="MaxRetries"/>. Resetting
|
||||
/// only after a stable interval bounds a flapping stream.
|
||||
/// </summary>
|
||||
internal static TimeSpan StabilityWindow { get; set; } = TimeSpan.FromSeconds(60);
|
||||
|
||||
private int _retryCount;
|
||||
private bool _useNodeA = true;
|
||||
private bool _stopped;
|
||||
private CancellationTokenSource? _grpcCts;
|
||||
|
||||
/// <summary>Timer scheduler for reconnect and stability window timers.</summary>
|
||||
public ITimerScheduler Timers { get; set; } = null!;
|
||||
|
||||
/// <summary>
|
||||
/// Initializes the debug stream bridge actor and registers message handlers.
|
||||
/// </summary>
|
||||
/// <param name="siteIdentifier">Site identifier for targeting ClusterClient messages and logging.</param>
|
||||
/// <param name="instanceUniqueName">Unique name of the instance whose debug stream is being bridged.</param>
|
||||
/// <param name="correlationId">Correlation id for the debug session.</param>
|
||||
/// <param name="centralCommunicationActor">Actor used to forward ClusterClient messages to the site.</param>
|
||||
/// <param name="onEvent">Callback invoked on each received debug event.</param>
|
||||
/// <param name="onTerminated">Callback invoked when the stream terminates.</param>
|
||||
/// <param name="grpcFactory">Factory for creating gRPC streaming clients.</param>
|
||||
/// <param name="grpcNodeAAddress">gRPC address of the site's node A.</param>
|
||||
/// <param name="grpcNodeBAddress">gRPC address of the site's node B.</param>
|
||||
public DebugStreamBridgeActor(
|
||||
string siteIdentifier,
|
||||
string instanceUniqueName,
|
||||
string correlationId,
|
||||
IActorRef centralCommunicationActor,
|
||||
Action<object> onEvent,
|
||||
Action onTerminated,
|
||||
SiteStreamGrpcClientFactory grpcFactory,
|
||||
string grpcNodeAAddress,
|
||||
string grpcNodeBAddress)
|
||||
{
|
||||
_siteIdentifier = siteIdentifier;
|
||||
_instanceUniqueName = instanceUniqueName;
|
||||
_correlationId = correlationId;
|
||||
_centralCommunicationActor = centralCommunicationActor;
|
||||
_onEvent = onEvent;
|
||||
_onTerminated = onTerminated;
|
||||
_grpcFactory = grpcFactory;
|
||||
_grpcNodeAAddress = grpcNodeAAddress;
|
||||
_grpcNodeBAddress = grpcNodeBAddress;
|
||||
|
||||
// Initial snapshot response from the site (via ClusterClient)
|
||||
Receive<DebugViewSnapshot>(snapshot =>
|
||||
{
|
||||
_log.Info("Received initial snapshot for {0} ({1} attrs, {2} alarms)",
|
||||
_instanceUniqueName, snapshot.AttributeValues.Count, snapshot.AlarmStates.Count);
|
||||
_onEvent(snapshot);
|
||||
OpenGrpcStream();
|
||||
});
|
||||
|
||||
// Domain events arriving via Self.Tell from gRPC callback.
|
||||
// Communication-008: receiving an event must NOT reset _retryCount — a
|
||||
// flapping stream that delivers a single event between failures would
|
||||
// otherwise never trip MaxRetries. The retry budget is recovered only by
|
||||
// GrpcStreamStable (a stream that has stayed up for StabilityWindow).
|
||||
Receive<AttributeValueChanged>(changed => _onEvent(changed));
|
||||
Receive<AlarmStateChanged>(changed => _onEvent(changed));
|
||||
|
||||
// Stream has been stably connected for StabilityWindow — recover the
|
||||
// retry budget so a future transient fault gets a fresh set of retries.
|
||||
Receive<GrpcStreamStable>(_ =>
|
||||
{
|
||||
if (_stopped) return;
|
||||
_retryCount = 0;
|
||||
_log.Debug("gRPC stream for {0} stable, retry count reset", _instanceUniqueName);
|
||||
});
|
||||
|
||||
// gRPC stream error — attempt reconnection
|
||||
Receive<GrpcStreamError>(msg =>
|
||||
{
|
||||
_log.Warning("gRPC stream error for {0}: {1}", _instanceUniqueName, msg.Exception.Message);
|
||||
HandleGrpcError();
|
||||
});
|
||||
|
||||
// Scheduled reconnection
|
||||
Receive<ReconnectGrpcStream>(_ => OpenGrpcStream());
|
||||
|
||||
// Consumer requests stop
|
||||
Receive<StopDebugStream>(_ =>
|
||||
{
|
||||
_log.Info("Stopping debug stream for {0}", _instanceUniqueName);
|
||||
CleanupGrpc();
|
||||
SendUnsubscribe();
|
||||
_stopped = true;
|
||||
Context.Stop(Self);
|
||||
});
|
||||
|
||||
// Site disconnected — CentralCommunicationActor notifies us
|
||||
Receive<DebugStreamTerminated>(msg =>
|
||||
{
|
||||
if (_stopped) return; // Idempotent — gRPC error may arrive simultaneously
|
||||
_log.Warning("Debug stream terminated for {0} (site {1} disconnected)", _instanceUniqueName, msg.SiteId);
|
||||
CleanupGrpc();
|
||||
_stopped = true;
|
||||
_onTerminated();
|
||||
Context.Stop(Self);
|
||||
});
|
||||
|
||||
// Orphan safety net — if nobody stops us within 5 minutes, self-terminate
|
||||
Context.SetReceiveTimeout(TimeSpan.FromMinutes(5));
|
||||
Receive<ReceiveTimeout>(_ =>
|
||||
{
|
||||
_log.Warning("Debug stream for {0} timed out (orphaned session), stopping", _instanceUniqueName);
|
||||
CleanupGrpc();
|
||||
SendUnsubscribe();
|
||||
_stopped = true;
|
||||
_onTerminated();
|
||||
Context.Stop(Self);
|
||||
});
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
protected override void PreStart()
|
||||
{
|
||||
_log.Info("Starting debug stream bridge for {0} on site {1}", _instanceUniqueName, _siteIdentifier);
|
||||
|
||||
// Send subscribe request via CentralCommunicationActor for the initial snapshot.
|
||||
var request = new SubscribeDebugViewRequest(_instanceUniqueName, _correlationId);
|
||||
var envelope = new SiteEnvelope(_siteIdentifier, request);
|
||||
_centralCommunicationActor.Tell(envelope, Self);
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
protected override void PostStop()
|
||||
{
|
||||
_grpcCts?.Cancel();
|
||||
_grpcCts?.Dispose();
|
||||
_grpcCts = null;
|
||||
base.PostStop();
|
||||
}
|
||||
|
||||
private void OpenGrpcStream()
|
||||
{
|
||||
if (_stopped) return;
|
||||
|
||||
var endpoint = _useNodeA ? _grpcNodeAAddress : _grpcNodeBAddress;
|
||||
_log.Info("Opening gRPC stream for {0} to {1}", _instanceUniqueName, endpoint);
|
||||
|
||||
_grpcCts?.Cancel();
|
||||
_grpcCts?.Dispose();
|
||||
_grpcCts = new CancellationTokenSource();
|
||||
|
||||
// Arm the stability timer: if the stream stays up for StabilityWindow the
|
||||
// retry budget is recovered (Communication-008). Cancelled by HandleGrpcError.
|
||||
Timers.StartSingleTimer(StabilityTimerKey, new GrpcStreamStable(), StabilityWindow);
|
||||
|
||||
var client = _grpcFactory.GetOrCreate(_siteIdentifier, endpoint);
|
||||
var self = Self;
|
||||
var ct = _grpcCts.Token;
|
||||
|
||||
// Launch as background task — onEvent and onError marshal back to actor via Tell
|
||||
Task.Run(async () =>
|
||||
{
|
||||
await client.SubscribeAsync(
|
||||
_correlationId,
|
||||
_instanceUniqueName,
|
||||
evt => self.Tell(evt),
|
||||
ex => self.Tell(new GrpcStreamError(ex)),
|
||||
ct);
|
||||
}, ct);
|
||||
}
|
||||
|
||||
private void HandleGrpcError()
|
||||
{
|
||||
if (_stopped) return;
|
||||
|
||||
// The stream failed before reaching the stability window — its retry
|
||||
// budget is NOT recovered (Communication-008).
|
||||
Timers.Cancel(StabilityTimerKey);
|
||||
|
||||
_retryCount++;
|
||||
|
||||
if (_retryCount > MaxRetries)
|
||||
{
|
||||
_log.Error("gRPC stream for {0} exceeded max retries ({1}), terminating", _instanceUniqueName, MaxRetries);
|
||||
CleanupGrpc();
|
||||
_stopped = true;
|
||||
_onTerminated();
|
||||
Context.Stop(Self);
|
||||
return;
|
||||
}
|
||||
|
||||
// Unsubscribe the failed stream on the *previous* endpoint before reconnecting.
|
||||
// This cancels the local subscription CTS and -- where the channel is still
|
||||
// alive -- propagates gRPC cancellation to the site so its SiteStreamGrpcServer
|
||||
// stops the StreamRelayActor for this correlation ID, rather than leaving a
|
||||
// zombie relay actor until TCP RST / keepalive eventually detects the loss.
|
||||
var previousEndpoint = _useNodeA ? _grpcNodeAAddress : _grpcNodeBAddress;
|
||||
var previousClient = _grpcFactory.GetOrCreate(_siteIdentifier, previousEndpoint);
|
||||
previousClient.Unsubscribe(_correlationId);
|
||||
|
||||
// Flip to the other node
|
||||
_useNodeA = !_useNodeA;
|
||||
|
||||
// First retry is immediate, subsequent retries use a short backoff
|
||||
if (_retryCount == 1)
|
||||
{
|
||||
Self.Tell(new ReconnectGrpcStream());
|
||||
}
|
||||
else
|
||||
{
|
||||
Timers.StartSingleTimer(ReconnectTimerKey, new ReconnectGrpcStream(), ReconnectDelay);
|
||||
}
|
||||
}
|
||||
|
||||
private void CleanupGrpc()
|
||||
{
|
||||
_grpcCts?.Cancel();
|
||||
_grpcCts?.Dispose();
|
||||
_grpcCts = null;
|
||||
|
||||
var client = _grpcFactory.GetOrCreate(_siteIdentifier,
|
||||
_useNodeA ? _grpcNodeAAddress : _grpcNodeBAddress);
|
||||
client.Unsubscribe(_correlationId);
|
||||
}
|
||||
|
||||
private void SendUnsubscribe()
|
||||
{
|
||||
var request = new UnsubscribeDebugViewRequest(_instanceUniqueName, _correlationId);
|
||||
var envelope = new SiteEnvelope(_siteIdentifier, request);
|
||||
_centralCommunicationActor.Tell(envelope, Self);
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Message sent to a DebugStreamBridgeActor to stop the debug stream session.
|
||||
/// </summary>
|
||||
public record StopDebugStream;
|
||||
|
||||
/// <summary>
|
||||
/// Internal message indicating a gRPC stream error occurred.
|
||||
/// </summary>
|
||||
internal record GrpcStreamError(Exception Exception);
|
||||
|
||||
/// <summary>
|
||||
/// Internal message to trigger gRPC stream reconnection.
|
||||
/// </summary>
|
||||
internal record ReconnectGrpcStream;
|
||||
|
||||
/// <summary>
|
||||
/// Internal message indicating the current gRPC stream has been connected long
|
||||
/// enough (<see cref="DebugStreamBridgeActor.StabilityWindow"/>) to be considered
|
||||
/// stable, so the reconnect retry budget can be recovered.
|
||||
/// </summary>
|
||||
internal record GrpcStreamStable;
|
||||
Reference in New Issue
Block a user