Files
ScadaBridge/src/ZB.MOM.WW.ScadaBridge.HealthMonitoring/SiteHealthState.cs
T

78 lines
3.9 KiB
C#

using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
namespace ZB.MOM.WW.ScadaBridge.HealthMonitoring;
/// <summary>
/// In-memory state for a single site's health, stored by the central aggregator.
/// Immutable: every state transition produces a new instance which the aggregator
/// installs into its <c>ConcurrentDictionary</c> via an atomic compare-and-swap.
/// This makes handing the reference straight to UI callers safe — a consumer can
/// never observe a torn or half-applied update.
/// </summary>
public sealed record SiteHealthState
{
/// <summary>Gets the unique identifier of the site this state record belongs to.</summary>
public required string SiteId { get; init; }
/// <summary>
/// The latest full <see cref="SiteHealthReport"/> received for the site, or
/// <c>null</c> if the site is known only via heartbeats and has not yet sent
/// a report.
/// </summary>
public SiteHealthReport? LatestReport { get; init; }
/// <summary>
/// Time the latest full <see cref="SiteHealthReport"/> was processed, or
/// <c>null</c> if the site is known only via heartbeats and has not yet sent
/// a report. Used by the UI to surface report staleness during failover;
/// the <c>null</c> case must be rendered as "no report yet" rather than as a
/// timestamp (a <c>default</c> sentinel would display as year-0001).
/// </summary>
public DateTimeOffset? LastReportReceivedAt { get; init; }
/// <summary>
/// Time the most recent signal of any kind (full report OR heartbeat) was
/// received. Drives offline detection — heartbeats from the standby keep the
/// site marked online even when the active node is unable to produce a report
/// (mid-failover, brief stalls). Heartbeat cadence is owned by the Cluster
/// Infrastructure / SiteCommunicationActor (every
/// CommunicationOptions.TransportHeartbeatInterval — 5s by default).
/// </summary>
public DateTimeOffset LastHeartbeatAt { get; init; }
/// <summary>
/// Gets the instant this site was first observed by the aggregator (via a
/// report or a heartbeat); <c>null</c> only for states not built by the
/// aggregator (hand-constructed fixtures). Anchors metrics-staleness for a
/// site that has NEVER delivered a report (review 01 round-2 N3): with
/// <see cref="LastReportReceivedAt"/> null the staleness check previously
/// skipped the site forever. <see cref="LastHeartbeatAt"/> cannot anchor
/// this — every heartbeat advances it.
/// </summary>
public DateTimeOffset? FirstSeenAt { get; init; }
/// <summary>Gets the sequence number of the last accepted health report, used to reject out-of-order duplicates.</summary>
public long LastSequenceNumber { get; init; }
/// <summary>Gets a value indicating whether the site is currently considered online.</summary>
public bool IsOnline { get; init; }
/// <summary>
/// Gets a value indicating whether the site is online (heartbeats still
/// arriving) but has sent no full <see cref="SiteHealthReport"/> within
/// <see cref="HealthMonitoringOptions.MetricsStaleTimeout"/>. This is a signal
/// <em>distinct</em> from liveness: a site whose HealthReportSender died keeps
/// heartbeating and would otherwise show "online with frozen metrics forever".
/// Cleared whenever a fresh report is processed. Heartbeats never set or clear
/// it — they say nothing about the metrics pipeline.
/// </summary>
public bool IsMetricsStale { get; init; }
/// <summary>
/// Gets the instant of the last online↔offline flip, or <c>null</c> if the
/// site has never changed status since it was first observed. Answers "when
/// did this site drop / come back". Not moved by report/heartbeat traffic that
/// leaves the online/offline status unchanged, nor by the metrics-stale flag.
/// </summary>
public DateTimeOffset? LastStatusChangeAt { get; init; }
}