Files
ScadaBridge/src/ZB.MOM.WW.ScadaBridge.AuditLog/Central/SiteAuditReconciliationOptions.cs
T

88 lines
4.0 KiB
C#

namespace ZB.MOM.WW.ScadaBridge.AuditLog.Central;
/// <summary>
/// Tuning knobs for the central <see cref="SiteAuditReconciliationActor"/> singleton.
/// Defaults mirror the M6 Bundle B brief: pull every 5 minutes per site, 256 rows per
/// batch, declare a site "stalled" after two consecutive pull cycles return non-empty
/// AND <c>MoreAvailable=true</c> (the backlog is not draining).
/// </summary>
/// <remarks>
/// <para>
/// Per the M6 plan the reconciliation actor is the fallback when push telemetry is
/// lost; it is intentionally low-frequency. Lowering
/// <see cref="ReconciliationIntervalSeconds"/> in production trades MS SQL load for
/// fresher self-healing — keep the default unless a deployment can prove the extra
/// load is acceptable.
/// </para>
/// <para>
/// <see cref="StalledAfterNonDrainingCycles"/> = 2 because a single non-draining
/// cycle can happen on a surge (e.g. a backed-up site replays its hot queue); the
/// stalled signal should only fire when the backlog persists across cycles, which is
/// the symptom the central health surface is asking us to detect.
/// </para>
/// </remarks>
public sealed class SiteAuditReconciliationOptions
{
/// <summary>
/// Period of the reconciliation tick. Each tick visits every known site once.
/// </summary>
public int ReconciliationIntervalSeconds { get; set; } = 300;
/// <summary>
/// Test-only override for finer control over the tick cadence than
/// whole-second resolution allows. When non-null, takes precedence over
/// <see cref="ReconciliationIntervalSeconds"/> AND bypasses the
/// <see cref="ReconciliationInterval"/> minimum clamp (so tests can use
/// millisecond cadences). Production config exposes
/// <see cref="ReconciliationIntervalSeconds"/> only and never sets this
/// knob — but because the options class is <c>Bind</c>-ed wholesale, a
/// config value at <c>AuditLog:Reconciliation:ReconciliationIntervalOverride</c>
/// WOULD bind if present; operators must not set it.
/// </summary>
public TimeSpan? ReconciliationIntervalOverride { get; set; }
/// <summary>
/// Minimum interval the config-bound <see cref="ReconciliationIntervalSeconds"/>
/// can resolve to. Clamps a misconfigured <c>ReconciliationIntervalSeconds: 0</c>
/// (or a negative value) away from <see cref="TimeSpan.Zero"/>, which would make
/// Akka's <c>ScheduleTellRepeatedlyCancelable</c> spin. The test-only
/// <see cref="ReconciliationIntervalOverride"/> bypasses this clamp so unit tests
/// can still drop the cadence to milliseconds.
/// </summary>
private static readonly TimeSpan MinConfiguredInterval = TimeSpan.FromSeconds(1);
/// <summary>
/// Resolves the effective tick interval, honouring the test override when
/// set. Falls back to <see cref="ReconciliationIntervalSeconds"/>, clamped to at
/// least <see cref="MinConfiguredInterval"/> so a zero/negative config value can
/// never yield <see cref="TimeSpan.Zero"/> (which would spin the scheduler).
/// </summary>
public TimeSpan ReconciliationInterval
{
get
{
if (ReconciliationIntervalOverride is { } overrideValue)
{
return overrideValue;
}
var resolved = TimeSpan.FromSeconds(ReconciliationIntervalSeconds);
return resolved < MinConfiguredInterval ? MinConfiguredInterval : resolved;
}
}
/// <summary>
/// Maximum number of <see cref="ZB.MOM.WW.ScadaBridge.Commons.Entities.Audit.AuditEvent"/>
/// rows requested in a single <c>PullAuditEvents</c> RPC call.
/// </summary>
public int BatchSize { get; set; } = 256;
/// <summary>
/// Number of consecutive non-draining cycles (events returned AND
/// <c>MoreAvailable=true</c>) that must accumulate for a site before the actor
/// publishes <c>SiteAuditTelemetryStalledChanged(Stalled: true)</c> on the
/// EventStream.
/// </summary>
public int StalledAfterNonDrainingCycles { get; set; } = 2;
}