feat(dashboard): in-process snapshot feed replaces the pages' loopback /hubs/snapshot hop
This commit is contained in:
Joseph Doherty
@@ -1,80 +1,96 @@
|
||||
using Microsoft.AspNetCore.Components;
|
||||
using Microsoft.AspNetCore.SignalR.Client;
|
||||
using ZB.MOM.WW.MxGateway.Server.Dashboard.Hubs;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Dashboard.Components;
|
||||
|
||||
/// <summary>
|
||||
/// Base class for Blazor dashboard pages that watch gateway metrics
|
||||
/// snapshots. The previous implementation polled
|
||||
/// <see cref="IDashboardSnapshotService.WatchSnapshotsAsync"/> directly; we
|
||||
/// now subscribe to <see cref="DashboardSnapshotHub"/> so updates are
|
||||
/// pushed and disconnects survive reconnects via SignalR's
|
||||
/// auto-reconnect.
|
||||
/// Base class for Blazor dashboard pages that watch gateway metrics snapshots.
|
||||
/// Pages subscribe to the in-process <see cref="IDashboardSnapshotFeed"/>, which
|
||||
/// multicasts a single <see cref="IDashboardSnapshotService.WatchSnapshotsAsync"/>
|
||||
/// enumeration to every circuit. An earlier implementation had each page open its
|
||||
/// own SignalR connection to <c>/hubs/snapshot</c> — a loopback WebSocket back into
|
||||
/// this same process, per page. The snapshot hub and its publisher remain for
|
||||
/// external (non-circuit) clients; server-rendered pages no longer use them.
|
||||
/// </summary>
|
||||
public abstract class DashboardPageBase : ComponentBase, IAsyncDisposable
|
||||
{
|
||||
private HubConnection? _hub;
|
||||
/// <summary>
|
||||
/// Upper bound on waiting for the watch loop while disposing. The loop marshals
|
||||
/// renders through the renderer's dispatcher and disposal can run on that same
|
||||
/// dispatcher, so the wait is bounded rather than unconditional.
|
||||
/// </summary>
|
||||
private static readonly TimeSpan WatchDrainTimeout = TimeSpan.FromSeconds(5);
|
||||
|
||||
/// <summary>Snapshot service used to seed the initial render before the hub connects.</summary>
|
||||
private readonly CancellationTokenSource _watchCancellation = new();
|
||||
private Task? _watchTask;
|
||||
|
||||
/// <summary>Snapshot service used to seed the initial render before the first feed update.</summary>
|
||||
[Inject]
|
||||
protected IDashboardSnapshotService SnapshotService { get; set; } = null!;
|
||||
|
||||
/// <summary>Factory that builds the SignalR connection (mints the hub bearer token).</summary>
|
||||
/// <summary>Shared in-process snapshot feed this page renders from.</summary>
|
||||
[Inject]
|
||||
protected DashboardHubConnectionFactory HubFactory { get; set; } = null!;
|
||||
protected IDashboardSnapshotFeed SnapshotFeed { get; set; } = null!;
|
||||
|
||||
/// <summary>
|
||||
/// The most recent gateway metric snapshot. Synchronously seeded from
|
||||
/// <see cref="IDashboardSnapshotService.GetSnapshot"/> for the very
|
||||
/// first render, then refreshed by hub push.
|
||||
/// <see cref="IDashboardSnapshotService.GetSnapshot"/> for the very first
|
||||
/// render, then refreshed from the feed.
|
||||
/// </summary>
|
||||
protected DashboardSnapshot? Snapshot { get; private set; }
|
||||
|
||||
/// <inheritdoc />
|
||||
protected override async Task OnInitializedAsync()
|
||||
protected override Task OnInitializedAsync()
|
||||
{
|
||||
Snapshot = SnapshotService.GetSnapshot();
|
||||
await ConnectHubAsync().ConfigureAwait(false);
|
||||
|
||||
// Deliberately not awaited: the watch loop runs for the lifetime of the page
|
||||
// and is cancelled and drained by DisposeAsync.
|
||||
_watchTask = WatchSnapshotsAsync(_watchCancellation.Token);
|
||||
return Task.CompletedTask;
|
||||
}
|
||||
|
||||
/// <summary>Disposes the SignalR hub connection created for this page, tolerating disposal-time errors.</summary>
|
||||
/// <summary>Cancels the snapshot subscription created for this page, tolerating disposal-time errors.</summary>
|
||||
/// <returns>A task that represents the asynchronous operation.</returns>
|
||||
public async ValueTask DisposeAsync()
|
||||
{
|
||||
if (_hub is not null)
|
||||
{
|
||||
try
|
||||
{
|
||||
await _hub.DisposeAsync().ConfigureAwait(false);
|
||||
}
|
||||
catch
|
||||
{
|
||||
// Disposal-time errors are best-effort.
|
||||
}
|
||||
}
|
||||
|
||||
GC.SuppressFinalize(this);
|
||||
}
|
||||
|
||||
private async Task ConnectHubAsync()
|
||||
{
|
||||
_hub = HubFactory.Create("/hubs/snapshot");
|
||||
_hub.On<DashboardSnapshot>(DashboardSnapshotHub.SnapshotMessage, async snapshot =>
|
||||
{
|
||||
Snapshot = snapshot;
|
||||
await InvokeAsync(StateHasChanged).ConfigureAwait(false);
|
||||
});
|
||||
|
||||
try
|
||||
{
|
||||
await _hub.StartAsync().ConfigureAwait(false);
|
||||
await _watchCancellation.CancelAsync().ConfigureAwait(false);
|
||||
|
||||
if (_watchTask is not null)
|
||||
{
|
||||
await _watchTask.WaitAsync(WatchDrainTimeout).ConfigureAwait(false);
|
||||
}
|
||||
}
|
||||
catch
|
||||
{
|
||||
// Hub is best-effort; the initial GetSnapshot() seed remains
|
||||
// valid and the snapshot service keeps populating its cache for
|
||||
// the next reconnect cycle.
|
||||
// Disposal-time errors (including a drain timeout) are best-effort.
|
||||
}
|
||||
|
||||
_watchCancellation.Dispose();
|
||||
GC.SuppressFinalize(this);
|
||||
}
|
||||
|
||||
private async Task WatchSnapshotsAsync(CancellationToken cancellationToken)
|
||||
{
|
||||
try
|
||||
{
|
||||
await foreach (DashboardSnapshot snapshot in SnapshotFeed
|
||||
.WatchAsync(cancellationToken)
|
||||
.ConfigureAwait(false))
|
||||
{
|
||||
Snapshot = snapshot;
|
||||
await InvokeAsync(StateHasChanged).ConfigureAwait(false);
|
||||
}
|
||||
}
|
||||
catch (OperationCanceledException)
|
||||
{
|
||||
// The page is going away.
|
||||
}
|
||||
catch
|
||||
{
|
||||
// The feed is best-effort: the last rendered snapshot stays on screen and
|
||||
// the snapshot service keeps serving GetSnapshot() for the next page load.
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -38,6 +38,7 @@ public static class DashboardServiceCollectionExtensions
|
||||
services.AddZbLdapAuth(configuration, "MxGateway:Ldap");
|
||||
|
||||
services.AddSingleton<IDashboardSnapshotService, DashboardSnapshotService>();
|
||||
services.AddSingleton<IDashboardSnapshotFeed, DashboardSnapshotFeed>();
|
||||
services.AddSingleton<IDashboardLiveDataService, DashboardLiveDataService>();
|
||||
services.AddSingleton<IDashboardAuthenticator, DashboardAuthenticator>();
|
||||
services.AddSingleton<IGroupRoleMapper<string>, DashboardGroupRoleMapper>();
|
||||
|
||||
@@ -0,0 +1,216 @@
|
||||
using System.Runtime.CompilerServices;
|
||||
using System.Threading.Channels;
|
||||
using Microsoft.Extensions.Logging;
|
||||
using Microsoft.Extensions.Logging.Abstractions;
|
||||
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Dashboard;
|
||||
|
||||
/// <summary>
|
||||
/// Fans one <see cref="IDashboardSnapshotService.WatchSnapshotsAsync"/> enumeration out to
|
||||
/// every dashboard circuit. The underlying watch is not multicast — each enumeration owns a
|
||||
/// timer and builds its own snapshot per tick — so subscribing per page would multiply the
|
||||
/// snapshot cost by the number of open pages.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// The pump is idle-gated: it starts when the subscriber count goes 0 → 1 and is cancelled
|
||||
/// and awaited when it goes 1 → 0, so an unwatched gateway runs no timer and builds no
|
||||
/// snapshots. Successive pumps are chained through <c>_pumpTask</c>, so a rapid
|
||||
/// unsubscribe/resubscribe restarts a fresh pump without ever running two enumerations at
|
||||
/// once.
|
||||
/// </remarks>
|
||||
public sealed class DashboardSnapshotFeed : IDashboardSnapshotFeed
|
||||
{
|
||||
private readonly IDashboardSnapshotService _snapshotService;
|
||||
private readonly ILogger<DashboardSnapshotFeed> _logger;
|
||||
private readonly object _gate = new();
|
||||
private readonly List<Channel<DashboardSnapshot>> _subscribers = [];
|
||||
|
||||
/// <summary>
|
||||
/// The most recent pump, completed while idle. A starting pump awaits its predecessor
|
||||
/// before enumerating, which is what guarantees a single live enumeration.
|
||||
/// </summary>
|
||||
private Task _pumpTask = Task.CompletedTask;
|
||||
|
||||
/// <summary>Cancellation for the live pump; null when no pump is running or one is being torn down.</summary>
|
||||
private CancellationTokenSource? _pumpCancellation;
|
||||
|
||||
/// <summary>Initializes a new instance of the <see cref="DashboardSnapshotFeed"/> class.</summary>
|
||||
/// <param name="snapshotService">Snapshot source to multicast.</param>
|
||||
/// <param name="logger">Optional logger for pump faults.</param>
|
||||
public DashboardSnapshotFeed(
|
||||
IDashboardSnapshotService snapshotService,
|
||||
ILogger<DashboardSnapshotFeed>? logger = null)
|
||||
{
|
||||
_snapshotService = snapshotService ?? throw new ArgumentNullException(nameof(snapshotService));
|
||||
_logger = logger ?? NullLogger<DashboardSnapshotFeed>.Instance;
|
||||
}
|
||||
|
||||
/// <inheritdoc />
|
||||
public async IAsyncEnumerable<DashboardSnapshot> WatchAsync(
|
||||
[EnumeratorCancellation] CancellationToken cancellationToken)
|
||||
{
|
||||
// Capacity 1 + DropOldest: a viewer only ever wants the latest snapshot, so a
|
||||
// circuit that renders slowly neither buffers without bound nor blocks the pump
|
||||
// (TryWrite always succeeds) — it just skips the snapshots it was too slow for.
|
||||
Channel<DashboardSnapshot> channel = Channel.CreateBounded<DashboardSnapshot>(
|
||||
new BoundedChannelOptions(1)
|
||||
{
|
||||
FullMode = BoundedChannelFullMode.DropOldest,
|
||||
SingleReader = true,
|
||||
SingleWriter = false,
|
||||
});
|
||||
|
||||
Subscribe(channel);
|
||||
try
|
||||
{
|
||||
await foreach (DashboardSnapshot snapshot in channel.Reader
|
||||
.ReadAllAsync(cancellationToken)
|
||||
.ConfigureAwait(false))
|
||||
{
|
||||
yield return snapshot;
|
||||
}
|
||||
}
|
||||
finally
|
||||
{
|
||||
// Untokened on purpose: teardown must run to completion even when this
|
||||
// subscriber is unwinding because its own token fired.
|
||||
await UnsubscribeAsync(channel).ConfigureAwait(false);
|
||||
}
|
||||
}
|
||||
|
||||
private void Subscribe(Channel<DashboardSnapshot> channel)
|
||||
{
|
||||
lock (_gate)
|
||||
{
|
||||
_subscribers.Add(channel);
|
||||
if (_subscribers.Count != 1)
|
||||
{
|
||||
return;
|
||||
}
|
||||
|
||||
CancellationTokenSource cancellation = new();
|
||||
Task previous = _pumpTask;
|
||||
_pumpCancellation = cancellation;
|
||||
|
||||
// Task.Run, not a direct call: an async iterator runs synchronously up to its
|
||||
// first suspension, and the first pull of the underlying watch can read the API
|
||||
// key table. That must not run on the subscribing circuit's thread, let alone
|
||||
// while this lock is held.
|
||||
_pumpTask = Task.Run(() => PumpAsync(previous, cancellation, cancellation.Token));
|
||||
}
|
||||
}
|
||||
|
||||
private async Task UnsubscribeAsync(Channel<DashboardSnapshot> channel)
|
||||
{
|
||||
CancellationTokenSource? cancellation;
|
||||
Task pump;
|
||||
lock (_gate)
|
||||
{
|
||||
if (!_subscribers.Remove(channel) || _subscribers.Count != 0)
|
||||
{
|
||||
// Either the pump already dropped this channel (it completed or faulted
|
||||
// and reset itself), or other viewers are still watching.
|
||||
return;
|
||||
}
|
||||
|
||||
cancellation = _pumpCancellation;
|
||||
_pumpCancellation = null;
|
||||
pump = _pumpTask;
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
cancellation?.Cancel();
|
||||
}
|
||||
catch (ObjectDisposedException)
|
||||
{
|
||||
// The pump reset itself and disposed its own cancellation source first.
|
||||
}
|
||||
|
||||
try
|
||||
{
|
||||
await pump.ConfigureAwait(false);
|
||||
}
|
||||
catch (Exception)
|
||||
{
|
||||
// A pump fault has already been reported to the subscribers it had; the
|
||||
// unsubscribing caller is only waiting for the enumeration to stop.
|
||||
}
|
||||
}
|
||||
|
||||
private async Task PumpAsync(Task previous, CancellationTokenSource cancellation, CancellationToken cancellationToken)
|
||||
{
|
||||
try
|
||||
{
|
||||
// Never overlap with the enumeration this pump replaces.
|
||||
await previous.ConfigureAwait(ConfigureAwaitOptions.SuppressThrowing);
|
||||
|
||||
await foreach (DashboardSnapshot snapshot in _snapshotService
|
||||
.WatchSnapshotsAsync(cancellationToken)
|
||||
.ConfigureAwait(false))
|
||||
{
|
||||
Broadcast(snapshot);
|
||||
}
|
||||
|
||||
// The source completed on its own; hand the completion to the subscribers
|
||||
// and re-arm so the next one starts a fresh enumeration.
|
||||
Reset(cancellation, error: null);
|
||||
}
|
||||
catch (OperationCanceledException) when (cancellationToken.IsCancellationRequested)
|
||||
{
|
||||
// Last subscriber left: the unsubscribing caller already detached the
|
||||
// channels and cleared the pump state.
|
||||
}
|
||||
catch (Exception error)
|
||||
{
|
||||
_logger.LogWarning(error, "Dashboard snapshot feed stopped; the next subscriber restarts it.");
|
||||
Reset(cancellation, error);
|
||||
}
|
||||
finally
|
||||
{
|
||||
cancellation.Dispose();
|
||||
}
|
||||
}
|
||||
|
||||
private void Broadcast(DashboardSnapshot snapshot)
|
||||
{
|
||||
lock (_gate)
|
||||
{
|
||||
foreach (Channel<DashboardSnapshot> subscriber in _subscribers)
|
||||
{
|
||||
// Bounded/DropOldest: always accepted unless the channel is completed.
|
||||
subscriber.Writer.TryWrite(snapshot);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// <summary>
|
||||
/// Detaches every subscriber and clears the pump state so the next subscriber starts a
|
||||
/// new enumeration. The detached subscribers observe <paramref name="error"/> (or a
|
||||
/// clean end of stream) from their own <c>WatchAsync</c>.
|
||||
/// </summary>
|
||||
/// <param name="cancellation">The calling pump's cancellation source, used as its ownership token.</param>
|
||||
/// <param name="error">Failure to surface, or null when the source completed cleanly.</param>
|
||||
private void Reset(CancellationTokenSource cancellation, Exception? error)
|
||||
{
|
||||
Channel<DashboardSnapshot>[] detached;
|
||||
lock (_gate)
|
||||
{
|
||||
if (!ReferenceEquals(_pumpCancellation, cancellation))
|
||||
{
|
||||
// A newer pump (or an in-flight teardown) owns the state now: its
|
||||
// subscribers must not be detached by this pump's exit.
|
||||
return;
|
||||
}
|
||||
|
||||
detached = _subscribers.ToArray();
|
||||
_subscribers.Clear();
|
||||
_pumpCancellation = null;
|
||||
}
|
||||
|
||||
foreach (Channel<DashboardSnapshot> subscriber in detached)
|
||||
{
|
||||
subscriber.Writer.TryComplete(error);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,26 @@
|
||||
namespace ZB.MOM.WW.MxGateway.Server.Dashboard;
|
||||
|
||||
/// <summary>
|
||||
/// In-process multicast over <see cref="IDashboardSnapshotService.WatchSnapshotsAsync"/>.
|
||||
/// One enumeration of the underlying watch is fanned out to every subscriber, so N
|
||||
/// dashboard circuits cost one snapshot build per tick instead of N — and while nobody
|
||||
/// subscribes, nothing runs at all.
|
||||
/// </summary>
|
||||
/// <remarks>
|
||||
/// There is no authentication or authorization gate here: the feed is reached only from
|
||||
/// Blazor dashboard components, whose endpoints already require
|
||||
/// <see cref="DashboardAuthenticationDefaults.ViewerPolicy"/>, so every caller is a circuit
|
||||
/// authorized as Viewer. Remote (non-circuit) consumers still go through
|
||||
/// <c>/hubs/snapshot</c>, which applies the hub authorization policy itself.
|
||||
/// </remarks>
|
||||
public interface IDashboardSnapshotFeed
|
||||
{
|
||||
/// <summary>
|
||||
/// Watches the shared snapshot stream. Each caller gets the snapshots produced while
|
||||
/// it is subscribed; a caller that reads slowly sees only the newest snapshot rather
|
||||
/// than a backlog, and never delays the other subscribers.
|
||||
/// </summary>
|
||||
/// <param name="cancellationToken">Token that ends this caller's subscription.</param>
|
||||
/// <returns>An asynchronous stream of dashboard snapshots.</returns>
|
||||
IAsyncEnumerable<DashboardSnapshot> WatchAsync(CancellationToken cancellationToken);
|
||||
}
|
||||
Reference in New Issue
Block a user