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 +1,457 @@
|
||||
using Akka.Actor;
|
||||
using Akka.Cluster;
|
||||
using Akka.Cluster.Tools.Client;
|
||||
using Akka.Event;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Artifacts;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Audit;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.DebugView;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Deployment;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.InboundApi;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Integration;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Lifecycle;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Notification;
|
||||
using ZB.MOM.WW.ScadaBridge.Commons.Messages.RemoteQuery;
|
||||
|
||||
namespace ZB.MOM.WW.ScadaBridge.Communication.Actors;
|
||||
|
||||
/// <summary>
|
||||
/// Site-side actor that receives messages from central via ClusterClient and routes
|
||||
/// them to the appropriate local actors. Also sends heartbeats and health reports
|
||||
/// to central via the registered ClusterClient.
|
||||
///
|
||||
/// WP-4: Routes all 8 message patterns to local handlers.
|
||||
/// </summary>
|
||||
public class SiteCommunicationActor : ReceiveActor, IWithTimers
|
||||
{
|
||||
private readonly ILoggingAdapter _log = Context.GetLogger();
|
||||
private readonly string _siteId;
|
||||
private readonly CommunicationOptions _options;
|
||||
|
||||
/// <summary>
|
||||
/// Communication-018: predicate that returns <c>true</c> when this node is
|
||||
/// the active member of the local site cluster (used to stamp
|
||||
/// <see cref="HeartbeatMessage.IsActive"/>). Production builds default to
|
||||
/// the Akka <see cref="Cluster"/> leader check; tests inject a stub so they
|
||||
/// do not need a real cluster.
|
||||
/// </summary>
|
||||
private readonly Func<bool> _isActiveCheck;
|
||||
|
||||
/// <summary>
|
||||
/// Reference to the local Deployment Manager singleton proxy.
|
||||
/// </summary>
|
||||
private readonly IActorRef _deploymentManagerProxy;
|
||||
|
||||
/// <summary>
|
||||
/// ClusterClient reference for sending messages to the central cluster.
|
||||
/// Set via RegisterCentralClient message.
|
||||
/// </summary>
|
||||
private IActorRef? _centralClient;
|
||||
|
||||
/// <summary>
|
||||
/// Local actor references for routing specific message patterns.
|
||||
/// Populated via registration messages.
|
||||
/// </summary>
|
||||
private IActorRef? _eventLogHandler;
|
||||
private IActorRef? _parkedMessageHandler;
|
||||
private IActorRef? _integrationHandler;
|
||||
private IActorRef? _artifactHandler;
|
||||
|
||||
/// <summary>Akka timer scheduler injected by the framework via <see cref="IWithTimers"/>.</summary>
|
||||
public ITimerScheduler Timers { get; set; } = null!;
|
||||
|
||||
/// <summary>Initializes the actor, wires all message pattern handlers, and schedules the periodic heartbeat.</summary>
|
||||
/// <param name="siteId">The site identifier included in outbound messages.</param>
|
||||
/// <param name="options">Communication options including heartbeat interval and transport settings.</param>
|
||||
/// <param name="deploymentManagerProxy">Local reference to the Deployment Manager singleton proxy.</param>
|
||||
/// <param name="isActiveCheck">
|
||||
/// Communication-018: optional override returning <c>true</c> when this node
|
||||
/// is the active member of the site cluster. <c>null</c> uses the real
|
||||
/// Akka <see cref="Cluster"/> leader check (the default for production
|
||||
/// wiring); tests pass a stub so they do not need to load Akka.Cluster
|
||||
/// into the <c>TestKit</c> ActorSystem.
|
||||
/// </param>
|
||||
public SiteCommunicationActor(
|
||||
string siteId,
|
||||
CommunicationOptions options,
|
||||
IActorRef deploymentManagerProxy,
|
||||
Func<bool>? isActiveCheck = null)
|
||||
{
|
||||
_siteId = siteId;
|
||||
_options = options;
|
||||
_deploymentManagerProxy = deploymentManagerProxy;
|
||||
_isActiveCheck = isActiveCheck ?? DefaultIsActiveCheck;
|
||||
|
||||
// Registration
|
||||
Receive<RegisterCentralClient>(msg =>
|
||||
{
|
||||
_centralClient = msg.Client;
|
||||
_log.Info("Registered central ClusterClient");
|
||||
});
|
||||
Receive<RegisterLocalHandler>(HandleRegisterLocalHandler);
|
||||
|
||||
// Pattern 1: Instance Deployment — forward to Deployment Manager
|
||||
Receive<DeployInstanceCommand>(msg =>
|
||||
{
|
||||
_log.Debug("Routing DeployInstanceCommand for {0} to DeploymentManager", msg.InstanceUniqueName);
|
||||
_deploymentManagerProxy.Forward(msg);
|
||||
});
|
||||
|
||||
// Pattern 2: Lifecycle — forward to Deployment Manager
|
||||
Receive<DisableInstanceCommand>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
Receive<EnableInstanceCommand>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
Receive<DeleteInstanceCommand>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
|
||||
// DeploymentManager-006: query-the-site-before-redeploy — forward to
|
||||
// the Deployment Manager, which owns the deployed-config store and
|
||||
// answers with the instance's currently-applied deployment identity.
|
||||
Receive<DeploymentStateQueryRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
|
||||
// Pattern 3: Artifact Deployment — forward to artifact handler if registered
|
||||
Receive<DeployArtifactsCommand>(msg =>
|
||||
{
|
||||
if (_artifactHandler != null)
|
||||
_artifactHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
_log.Warning("No artifact handler registered, replying with failure");
|
||||
Sender.Tell(new ArtifactDeploymentResponse(
|
||||
msg.DeploymentId, _siteId, false, "Artifact handler not available", DateTimeOffset.UtcNow));
|
||||
}
|
||||
});
|
||||
|
||||
// Pattern 4: Integration Routing — forward to integration handler
|
||||
Receive<IntegrationCallRequest>(msg =>
|
||||
{
|
||||
if (_integrationHandler != null)
|
||||
_integrationHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new IntegrationCallResponse(
|
||||
msg.CorrelationId, _siteId, false, null, "Integration handler not available", DateTimeOffset.UtcNow));
|
||||
}
|
||||
});
|
||||
|
||||
// Pattern 5: Debug View — forward to Deployment Manager (which routes to Instance Actor)
|
||||
Receive<SubscribeDebugViewRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
Receive<UnsubscribeDebugViewRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
|
||||
// Pattern 6a: Debug Snapshot (one-shot) — forward to Deployment Manager
|
||||
Receive<DebugSnapshotRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
|
||||
// Inbound API Route.To() — forward to Deployment Manager for instance routing
|
||||
Receive<RouteToCallRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
Receive<RouteToGetAttributesRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
Receive<RouteToSetAttributesRequest>(msg => _deploymentManagerProxy.Forward(msg));
|
||||
|
||||
// Pattern 7: Remote Queries
|
||||
Receive<EventLogQueryRequest>(msg =>
|
||||
{
|
||||
if (_eventLogHandler != null)
|
||||
_eventLogHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new EventLogQueryResponse(
|
||||
msg.CorrelationId, _siteId, [], null, false, false,
|
||||
"Event log handler not available", DateTimeOffset.UtcNow));
|
||||
}
|
||||
});
|
||||
|
||||
Receive<ParkedMessageQueryRequest>(msg =>
|
||||
{
|
||||
if (_parkedMessageHandler != null)
|
||||
_parkedMessageHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new ParkedMessageQueryResponse(
|
||||
msg.CorrelationId, _siteId, [], 0, msg.PageNumber, msg.PageSize, false,
|
||||
"Parked message handler not available", DateTimeOffset.UtcNow));
|
||||
}
|
||||
});
|
||||
|
||||
Receive<ParkedMessageRetryRequest>(msg =>
|
||||
{
|
||||
if (_parkedMessageHandler != null)
|
||||
_parkedMessageHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new ParkedMessageRetryResponse(
|
||||
msg.CorrelationId, false, "Parked message handler not available"));
|
||||
}
|
||||
});
|
||||
|
||||
Receive<ParkedMessageDiscardRequest>(msg =>
|
||||
{
|
||||
if (_parkedMessageHandler != null)
|
||||
_parkedMessageHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new ParkedMessageDiscardResponse(
|
||||
msg.CorrelationId, false, "Parked message handler not available"));
|
||||
}
|
||||
});
|
||||
|
||||
// Task 5 (#22): central→site Retry/Discard relay for parked cached
|
||||
// operations. SiteCallAuditActor relays these over the command/control
|
||||
// channel; the parked-message handler executes them against the local
|
||||
// S&F buffer and replies a ParkedOperationActionAck that routes back to
|
||||
// the relaying SiteCallAuditActor's Ask.
|
||||
Receive<RetryParkedOperation>(msg =>
|
||||
{
|
||||
if (_parkedMessageHandler != null)
|
||||
_parkedMessageHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new ParkedOperationActionAck(
|
||||
msg.CorrelationId, Applied: false, "Parked message handler not available"));
|
||||
}
|
||||
});
|
||||
|
||||
Receive<DiscardParkedOperation>(msg =>
|
||||
{
|
||||
if (_parkedMessageHandler != null)
|
||||
_parkedMessageHandler.Forward(msg);
|
||||
else
|
||||
{
|
||||
Sender.Tell(new ParkedOperationActionAck(
|
||||
msg.CorrelationId, Applied: false, "Parked message handler not available"));
|
||||
}
|
||||
});
|
||||
|
||||
// Notification Outbox: forward a buffered notification submitted by the site
|
||||
// Store-and-Forward Engine to the central cluster. The original Sender (the
|
||||
// S&F forwarder's Ask) is forwarded as the ClusterClient.Send sender so the
|
||||
// NotificationSubmitAck routes straight back to the waiting Ask, not here.
|
||||
Receive<NotificationSubmit>(msg =>
|
||||
{
|
||||
if (_centralClient == null)
|
||||
{
|
||||
// No ClusterClient registered yet (e.g. central contact points not
|
||||
// configured, or registration not yet completed). A non-accepted ack
|
||||
// makes the S&F forwarder treat this as transient and retry later.
|
||||
_log.Warning(
|
||||
"Cannot forward NotificationSubmit {0} — no central ClusterClient registered",
|
||||
msg.NotificationId);
|
||||
Sender.Tell(new NotificationSubmitAck(
|
||||
msg.NotificationId, Accepted: false, Error: "Central ClusterClient not registered"));
|
||||
return;
|
||||
}
|
||||
|
||||
_log.Debug("Forwarding NotificationSubmit {0} to central", msg.NotificationId);
|
||||
_centralClient.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", msg), Sender);
|
||||
});
|
||||
|
||||
// Notification Outbox: forward a Notify.Status query to the central cluster.
|
||||
// The original Sender (the Notify helper's Ask) is forwarded as the
|
||||
// ClusterClient.Send sender so the NotificationStatusResponse routes straight
|
||||
// back to the waiting Ask, not here.
|
||||
Receive<NotificationStatusQuery>(msg =>
|
||||
{
|
||||
if (_centralClient == null)
|
||||
{
|
||||
// No ClusterClient registered yet. Reply Found: false so Notify.Status
|
||||
// falls back to the site S&F buffer to decide Forwarding vs Unknown.
|
||||
_log.Warning(
|
||||
"Cannot forward NotificationStatusQuery {0} — no central ClusterClient registered",
|
||||
msg.NotificationId);
|
||||
Sender.Tell(new NotificationStatusResponse(
|
||||
msg.CorrelationId, Found: false, Status: "Unknown",
|
||||
RetryCount: 0, LastError: null, DeliveredAt: null));
|
||||
return;
|
||||
}
|
||||
|
||||
_log.Debug("Forwarding NotificationStatusQuery {0} to central", msg.NotificationId);
|
||||
_centralClient.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", msg), Sender);
|
||||
});
|
||||
|
||||
// Audit Log (#23): forward a batch of site-local audit events to the
|
||||
// central cluster. The site SiteAuditTelemetryActor drains its SQLite
|
||||
// Pending queue through the ClusterClientSiteAuditClient, which Asks
|
||||
// this actor; the original Sender (that Ask) is passed as the
|
||||
// ClusterClient.Send sender so the IngestAuditEventsReply routes
|
||||
// straight back to the waiting Ask, not here. Mirrors NotificationSubmit.
|
||||
Receive<IngestAuditEventsCommand>(msg =>
|
||||
{
|
||||
if (_centralClient == null)
|
||||
{
|
||||
// No ClusterClient registered yet (e.g. central contact points
|
||||
// not configured, or registration not yet completed). Faulting
|
||||
// the Ask makes the SiteAuditTelemetryActor drain loop treat
|
||||
// this as transient and keep the rows Pending for the next tick.
|
||||
_log.Warning(
|
||||
"Cannot forward IngestAuditEventsCommand ({0} events) — no central ClusterClient registered",
|
||||
msg.Events.Count);
|
||||
Sender.Tell(new Status.Failure(
|
||||
new InvalidOperationException("Central ClusterClient not registered")));
|
||||
return;
|
||||
}
|
||||
|
||||
_log.Debug("Forwarding IngestAuditEventsCommand ({0} events) to central", msg.Events.Count);
|
||||
_centralClient.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", msg), Sender);
|
||||
});
|
||||
|
||||
// Audit Log (#23) M3: forward a batch of combined cached-call telemetry
|
||||
// packets to the central cluster. Same forward + reply-routing pattern
|
||||
// as IngestAuditEventsCommand; central replies with an
|
||||
// IngestCachedTelemetryReply.
|
||||
Receive<IngestCachedTelemetryCommand>(msg =>
|
||||
{
|
||||
if (_centralClient == null)
|
||||
{
|
||||
_log.Warning(
|
||||
"Cannot forward IngestCachedTelemetryCommand ({0} entries) — no central ClusterClient registered",
|
||||
msg.Entries.Count);
|
||||
Sender.Tell(new Status.Failure(
|
||||
new InvalidOperationException("Central ClusterClient not registered")));
|
||||
return;
|
||||
}
|
||||
|
||||
_log.Debug("Forwarding IngestCachedTelemetryCommand ({0} entries) to central", msg.Entries.Count);
|
||||
_centralClient.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", msg), Sender);
|
||||
});
|
||||
|
||||
// Internal: send heartbeat tick
|
||||
Receive<SendHeartbeat>(_ => SendHeartbeatToCentral());
|
||||
|
||||
// Internal: forward health report to central
|
||||
Receive<SiteHealthReport>(msg =>
|
||||
{
|
||||
_centralClient?.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", msg), Self);
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
protected override SupervisorStrategy SupervisorStrategy()
|
||||
{
|
||||
return new OneForOneStrategy(
|
||||
maxNrOfRetries: -1,
|
||||
withinTimeRange: Timeout.InfiniteTimeSpan,
|
||||
decider: Decider.From(ex =>
|
||||
{
|
||||
_log.Warning(ex, "Child actor of SiteCommunicationActor faulted, resuming (state preserved)");
|
||||
return Directive.Resume;
|
||||
}));
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
protected override void PreStart()
|
||||
{
|
||||
_log.Info("SiteCommunicationActor started for site {0}", _siteId);
|
||||
|
||||
// Schedule periodic heartbeat to central
|
||||
Timers.StartPeriodicTimer(
|
||||
"heartbeat",
|
||||
new SendHeartbeat(),
|
||||
TimeSpan.FromSeconds(1), // initial delay
|
||||
_options.TransportHeartbeatInterval);
|
||||
}
|
||||
|
||||
private void HandleRegisterLocalHandler(RegisterLocalHandler msg)
|
||||
{
|
||||
switch (msg.HandlerType)
|
||||
{
|
||||
case LocalHandlerType.EventLog:
|
||||
_eventLogHandler = msg.Handler;
|
||||
break;
|
||||
case LocalHandlerType.ParkedMessages:
|
||||
_parkedMessageHandler = msg.Handler;
|
||||
break;
|
||||
case LocalHandlerType.Integration:
|
||||
_integrationHandler = msg.Handler;
|
||||
break;
|
||||
case LocalHandlerType.Artifacts:
|
||||
_artifactHandler = msg.Handler;
|
||||
break;
|
||||
}
|
||||
|
||||
_log.Info("Registered local handler for {0}", msg.HandlerType);
|
||||
}
|
||||
|
||||
private void SendHeartbeatToCentral()
|
||||
{
|
||||
if (_centralClient == null)
|
||||
return;
|
||||
|
||||
var hostname = Environment.MachineName;
|
||||
|
||||
// Communication-018: stamp HeartbeatMessage.IsActive with this node's
|
||||
// true active/standby role rather than hard-coding `true`. The field is
|
||||
// part of the wire contract (additive-only-evolution) so a future
|
||||
// central health dashboard can distinguish "active node down, standby
|
||||
// up" from "site fully offline" without a new message type.
|
||||
bool isActive;
|
||||
try
|
||||
{
|
||||
isActive = _isActiveCheck();
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
// Defensive: never let a cluster-state read failure abort the
|
||||
// heartbeat itself (heartbeats are health signal — their absence is
|
||||
// already meaningful). Fall back to the safest non-claiming value:
|
||||
// standby. Logged at Debug because this path normally only fires
|
||||
// during ActorSystem warm-up.
|
||||
_log.Debug(ex,
|
||||
"Active-node check threw while sending heartbeat for site {0}; reporting IsActive=false",
|
||||
_siteId);
|
||||
isActive = false;
|
||||
}
|
||||
|
||||
var heartbeat = new HeartbeatMessage(
|
||||
_siteId,
|
||||
hostname,
|
||||
IsActive: isActive,
|
||||
DateTimeOffset.UtcNow);
|
||||
|
||||
_centralClient.Tell(
|
||||
new ClusterClient.Send("/user/central-communication", heartbeat), Self);
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Communication-018: default active-node check used when no override is
|
||||
/// supplied. Mirrors <c>ActiveNodeGate</c> in the Host (and
|
||||
/// <c>ActiveNodeHealthCheck</c>): the node is the active member of the
|
||||
/// site cluster when it is the current cluster leader AND its own
|
||||
/// <see cref="MemberStatus"/> is <see cref="MemberStatus.Up"/>. Any other
|
||||
/// state (still joining, leaving, no leader yet) reports standby —
|
||||
/// safe-by-default, matching the standby case.
|
||||
/// </summary>
|
||||
private bool DefaultIsActiveCheck()
|
||||
{
|
||||
var cluster = Cluster.Get(Context.System);
|
||||
var self = cluster.SelfMember;
|
||||
if (self.Status != MemberStatus.Up)
|
||||
return false;
|
||||
|
||||
var leader = cluster.State.Leader;
|
||||
return leader != null && leader == self.Address;
|
||||
}
|
||||
|
||||
// ── Internal messages ──
|
||||
|
||||
internal record SendHeartbeat;
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Command to register a ClusterClient for communicating with the central cluster.
|
||||
/// </summary>
|
||||
public record RegisterCentralClient(IActorRef Client);
|
||||
|
||||
/// <summary>
|
||||
/// Command to register a local actor as a handler for a specific message pattern.
|
||||
/// </summary>
|
||||
public record RegisterLocalHandler(LocalHandlerType HandlerType, IActorRef Handler);
|
||||
|
||||
public enum LocalHandlerType
|
||||
{
|
||||
EventLog,
|
||||
ParkedMessages,
|
||||
Integration,
|
||||
Artifacts
|
||||
}
|
||||
Reference in New Issue
Block a user