fix(adminui): wire Test Connect probes + live panels on admin-only nodes
v2-ci / build (push) Failing after 36s
v2-ci / unit-tests (tests/Core/ZB.MOM.WW.OtOpcUa.Cluster.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Security.Tests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.Host.IntegrationTests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests) (push) Has been skipped
v2-ci / build (push) Failing after 36s
v2-ci / unit-tests (tests/Core/ZB.MOM.WW.OtOpcUa.Cluster.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.ControlPlane.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Runtime.Tests) (push) Has been skipped
v2-ci / unit-tests (tests/Server/ZB.MOM.WW.OtOpcUa.Security.Tests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.Host.IntegrationTests) (push) Has been skipped
v2-ci / integration (tests/Server/ZB.MOM.WW.OtOpcUa.OpcUaServer.IntegrationTests) (push) Has been skipped
Both bugs surfaced only on split-role deployments (the MAIN cluster's admin-only nodes), where the AdminUI runs without the driver role. - Test Connect returned "No probe registered" for every driver: the IDriverProbe set was registered only under the driver role, but the admin-operations singleton that consumes it is pinned to admin. Extract AddOtOpcUaDriverProbes() (idempotent via TryAddEnumerable) and call it in the hasAdmin path too. - Live driver-status/alerts/script-log panels showed "SignalR error: Connection refused": these Blazor Server components opened a HubConnection to their own hub via the browser's public URL, which server-side code can't reach behind Traefik (host :9200 -> container :9000). Read the in-process source directly instead -- DriverStatus via IDriverStatusSnapshotStore.SnapshotChanged, Alerts/ScriptLog via a new IInProcessBroadcaster<T>. Fleet status was unaffected (reads DB/ActorSystem). Adds unit tests for probe registration, the snapshot-store event, and the broadcaster.
This commit is contained in:
+38
-24
@@ -4,14 +4,14 @@
|
||||
DriverOperator-gated Reconnect/Restart buttons appear for authorised users. *@
|
||||
@implements IAsyncDisposable
|
||||
@using Microsoft.AspNetCore.Authorization
|
||||
@using Microsoft.AspNetCore.SignalR.Client
|
||||
@using ZB.MOM.WW.OtOpcUa.AdminUI.Hubs
|
||||
@using ZB.MOM.WW.OtOpcUa.Commons.Interfaces
|
||||
@using ZB.MOM.WW.OtOpcUa.Commons.Messages.Admin
|
||||
@using ZB.MOM.WW.OtOpcUa.Commons.Messages.Drivers
|
||||
@inject NavigationManager Nav
|
||||
@inject AuthenticationStateProvider AuthState
|
||||
@inject IAuthorizationService AuthorizationService
|
||||
@inject IAdminOperationsClient AdminOps
|
||||
@inject IDriverStatusSnapshotStore StatusStore
|
||||
|
||||
<section class="panel rise mt-3" style="animation-delay:.04s; @(_stale ? "opacity:0.5;" : "")">
|
||||
<div class="panel-head d-flex align-items-center gap-2">
|
||||
@@ -139,7 +139,6 @@
|
||||
[Parameter] public string ClusterId { get; set; } = "";
|
||||
[Parameter] public bool Enabled { get; set; } = true;
|
||||
|
||||
private HubConnection? _hub;
|
||||
private DriverHealthChanged? _snapshot;
|
||||
private DateTime _lastUpdateUtc = DateTime.MinValue;
|
||||
private bool _stale;
|
||||
@@ -180,30 +179,44 @@
|
||||
InvokeAsync(StateHasChanged);
|
||||
}, null, TimeSpan.FromSeconds(5), TimeSpan.FromSeconds(5));
|
||||
|
||||
_hub = new HubConnectionBuilder()
|
||||
.WithUrl(Nav.ToAbsoluteUri("/hubs/driverstatus"))
|
||||
.WithAutomaticReconnect()
|
||||
.Build();
|
||||
|
||||
_hub.On<DriverHealthChanged>("status", snap =>
|
||||
{
|
||||
_snapshot = snap;
|
||||
_lastUpdateUtc = DateTime.UtcNow;
|
||||
_stale = false;
|
||||
InvokeAsync(StateHasChanged);
|
||||
});
|
||||
|
||||
// Read live status straight from the in-process snapshot store rather than opening a
|
||||
// self-targeted SignalR connection. This component runs server-side (Blazor
|
||||
// InteractiveServer), so a HubConnection to the browser's public URL (e.g.
|
||||
// http://localhost:9200 behind Traefik) would dial that port from *inside* the container —
|
||||
// where only Kestrel's :9000 listens — and fail with "Connection refused". The store is fed
|
||||
// on every admin node by DriverStatusSignalRBridge (a per-node DistributedPubSub
|
||||
// subscriber), so the local singleton is always current regardless of which replica serves
|
||||
// this circuit.
|
||||
try
|
||||
{
|
||||
await _hub.StartAsync();
|
||||
_connecting = false;
|
||||
await _hub.InvokeAsync("JoinDriver", DriverInstanceId);
|
||||
StatusStore.SnapshotChanged += OnSnapshotChanged;
|
||||
if (StatusStore.TryGet(DriverInstanceId, out var snap))
|
||||
{
|
||||
_snapshot = snap;
|
||||
_lastUpdateUtc = DateTime.UtcNow;
|
||||
}
|
||||
}
|
||||
catch (Exception ex)
|
||||
{
|
||||
_connecting = false;
|
||||
_error = ex.Message;
|
||||
}
|
||||
finally
|
||||
{
|
||||
_connecting = false;
|
||||
}
|
||||
}
|
||||
|
||||
// Invoked by the snapshot store (on the bridge actor's thread) for every driver instance;
|
||||
// ignore snapshots for other instances and marshal onto the render sync context.
|
||||
private void OnSnapshotChanged(DriverHealthChanged snap)
|
||||
{
|
||||
if (!string.Equals(snap.DriverInstanceId, DriverInstanceId, StringComparison.Ordinal))
|
||||
return;
|
||||
|
||||
_snapshot = snap;
|
||||
_lastUpdateUtc = DateTime.UtcNow;
|
||||
_stale = false;
|
||||
InvokeAsync(StateHasChanged);
|
||||
}
|
||||
|
||||
private async Task ReconnectAsync()
|
||||
@@ -285,12 +298,13 @@
|
||||
|
||||
public async ValueTask DisposeAsync()
|
||||
{
|
||||
// Drain BOTH timers first so an in-flight callback can't invoke StateHasChanged on
|
||||
// a component whose hub has already been released. System.Threading.Timer's async
|
||||
// dispose awaits any in-flight callback (.NET 6+).
|
||||
// Unsubscribe first so the singleton store can't invoke a handler on a disposed component.
|
||||
StatusStore.SnapshotChanged -= OnSnapshotChanged;
|
||||
// Drain BOTH timers so an in-flight callback can't invoke StateHasChanged on a component
|
||||
// that's already gone. System.Threading.Timer's async dispose awaits any in-flight
|
||||
// callback (.NET 6+).
|
||||
if (_timer is not null) await _timer.DisposeAsync();
|
||||
if (_opResultClearTimer is not null) await _opResultClearTimer.DisposeAsync();
|
||||
if (_hub is not null) await _hub.DisposeAsync();
|
||||
}
|
||||
|
||||
// Map DriverState string → chip CSS class using the 4 defined theme variants.
|
||||
|
||||
Reference in New Issue
Block a user