Joseph Doherty
a212283104
WP2.6 (arch-review remediation, cross-cutting misc): - SiteExternalSystemRepository: name/ID-indexed ExternalSystemDefinitionCache replaces the fetch-all + reverse-map scan on every by-ID/method lookup; loaded once per redeploy, invalidated by DeploymentManagerActor after HandleDeployArtifacts applies external-system changes. Static JsonSerializerOptions for method-list parsing. - Inbound API: short-TTL ApiMethodCache fronts the per-request ApiMethod repository fetch; invalidated by name via the existing ScriptArtifactChangeSubscriber/ IScriptArtifactChangeBus pipeline, self-healing via TTL for changes the bus doesn't cover (e.g. Management API edits). - StoreAndForward: the cached-call audit-observer queue — the one unbounded channel left in the system — is now bounded (ObserverQueueCapacity, default 10,000) with DropOldest overflow and a dropped-notification counter. - SiteStreamManager: alarm state changes now travel a dedicated publish source/broadcast hub, isolated from the (far higher-volume) attribute path, so an attribute storm can no longer evict a pending alarm transition; the alarm hand-off queue is bounded with a drop counter surfaced on the site health report (SiteStreamAlarmDropCount via the new SiteStreamAlarmDropReporter), and publishing is skipped entirely at zero subscribers on either path. - CLI ManagementHttpClient: explicit 30s HttpClient.Timeout on the shared construction (was the 100s framework default), overridable via SCADABRIDGE_HTTP_TIMEOUT_SECONDS. Deviation: the failback-probe heartbeat item is NOT included — its only viable surface (CentralChannelProvider.cs / heartbeat consumers) lives entirely in the Communication project, explicitly off-limits to this work package this phase. Tests: SiteRuntime.Tests (550), InboundAPI.Tests (278), StoreAndForward.Tests (133), CLI.Tests (390), HealthMonitoring.Tests (97) — all green after full solution build.
79 lines
3.3 KiB
C#
79 lines
3.3 KiB
C#
using Microsoft.Extensions.Hosting;
|
|
using Microsoft.Extensions.Logging;
|
|
using ZB.MOM.WW.ScadaBridge.HealthMonitoring;
|
|
|
|
namespace ZB.MOM.WW.ScadaBridge.SiteRuntime.Streaming;
|
|
|
|
/// <summary>
|
|
/// WP2.6d (arch-review misc — site stream alarm-vs-attribute shared buffer): site-side
|
|
/// hosted service that periodically reads <see cref="SiteStreamManager.AlarmPublishDroppedCount"/>
|
|
/// and pushes it into <see cref="ISiteHealthCollector.SetSiteStreamAlarmDropCount"/> so
|
|
/// the next <see cref="ISiteHealthCollector.CollectReport"/> carries a fresh snapshot on
|
|
/// the site health report. Mirrors <c>ScriptSchedulerStatsReporter</c>: immediate first
|
|
/// probe, fixed cadence, exceptions logged and swallowed so the loop survives every probe
|
|
/// failure.
|
|
/// </summary>
|
|
public sealed class SiteStreamAlarmDropReporter : BackgroundService
|
|
{
|
|
/// <summary>Default poll cadence (10 s) — coarse enough to amortise across health reports.</summary>
|
|
internal static readonly TimeSpan DefaultPollInterval = TimeSpan.FromSeconds(10);
|
|
|
|
private readonly ISiteHealthCollector _collector;
|
|
private readonly SiteStreamManager _streamManager;
|
|
private readonly ILogger<SiteStreamAlarmDropReporter> _logger;
|
|
private readonly TimeSpan _pollInterval;
|
|
|
|
/// <summary>Initializes a new instance of <see cref="SiteStreamAlarmDropReporter"/>.</summary>
|
|
/// <param name="collector">The site health collector that receives the drop count.</param>
|
|
/// <param name="streamManager">The site stream manager whose alarm-queue drop count is sampled.</param>
|
|
/// <param name="logger">Logger instance.</param>
|
|
/// <param name="pollInterval">Poll interval override; defaults to <see cref="DefaultPollInterval"/> (10 s).</param>
|
|
public SiteStreamAlarmDropReporter(
|
|
ISiteHealthCollector collector,
|
|
SiteStreamManager streamManager,
|
|
ILogger<SiteStreamAlarmDropReporter> logger,
|
|
TimeSpan? pollInterval = null)
|
|
{
|
|
_collector = collector ?? throw new ArgumentNullException(nameof(collector));
|
|
_streamManager = streamManager ?? throw new ArgumentNullException(nameof(streamManager));
|
|
_logger = logger ?? throw new ArgumentNullException(nameof(logger));
|
|
_pollInterval = pollInterval ?? DefaultPollInterval;
|
|
}
|
|
|
|
/// <inheritdoc />
|
|
protected override async Task ExecuteAsync(CancellationToken stoppingToken)
|
|
{
|
|
// Immediate first probe so the first health report after start carries a
|
|
// real snapshot instead of a zero.
|
|
Probe();
|
|
|
|
while (!stoppingToken.IsCancellationRequested)
|
|
{
|
|
try
|
|
{
|
|
await Task.Delay(_pollInterval, stoppingToken).ConfigureAwait(false);
|
|
}
|
|
catch (OperationCanceledException)
|
|
{
|
|
break;
|
|
}
|
|
|
|
Probe();
|
|
}
|
|
}
|
|
|
|
private void Probe()
|
|
{
|
|
try
|
|
{
|
|
_collector.SetSiteStreamAlarmDropCount(_streamManager.AlarmPublishDroppedCount);
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
// Catch-all is deliberate: the hosted service must survive every class
|
|
// of probe failure so the next tick gets a chance.
|
|
_logger.LogWarning(ex, "SiteStreamAlarmDropReporter probe failed; next tick will retry.");
|
|
}
|
|
}
|
|
}
|