Joseph Doherty
55 lines
3.0 KiB
C#
55 lines
3.0 KiB
C#
using ZB.MOM.WW.ScadaBridge.Commons.Messages.Health;
|
|
|
|
namespace ZB.MOM.WW.ScadaBridge.HealthMonitoring;
|
|
|
|
/// <summary>
|
|
/// Interface for central-side health aggregation.
|
|
/// Consumed by Central UI to display site health dashboards.
|
|
/// </summary>
|
|
public interface ICentralHealthAggregator
|
|
{
|
|
/// <summary>
|
|
/// Processes an incoming health report from a site and updates the aggregated state.
|
|
/// </summary>
|
|
/// <param name="report">The health report received from the site.</param>
|
|
void ProcessReport(SiteHealthReport report);
|
|
|
|
/// <summary>
|
|
/// Bumps the last-seen timestamp for a site, keeping it marked online
|
|
/// between full 30s reports when heartbeats are arriving — protects against
|
|
/// the offline threshold firing on a transiently delayed report. Heartbeat
|
|
/// cadence is owned by the Cluster Infrastructure / <c>SiteCommunicationActor</c>
|
|
/// (the application-level heartbeat to central, sent every
|
|
/// <c>CommunicationOptions.TransportHeartbeatInterval</c> — 5s by default);
|
|
/// the 60s <see cref="HealthMonitoringOptions.OfflineTimeout"/> therefore
|
|
/// tolerates several missed heartbeats. A heartbeat for a site with no
|
|
/// aggregator state yet (e.g. just after a central restart/failover)
|
|
/// registers that site as online with no
|
|
/// <see cref="SiteHealthState.LatestReport"/>, so reachable sites are not
|
|
/// shown as "unknown" during the failover window.
|
|
/// </summary>
|
|
/// <param name="siteId">The string identifier of the site that sent the heartbeat.</param>
|
|
/// <param name="receivedAt">The UTC timestamp when the heartbeat was received.</param>
|
|
void MarkHeartbeat(string siteId, DateTimeOffset receivedAt);
|
|
|
|
/// <summary>Returns a snapshot of all currently tracked site health states.</summary>
|
|
/// <returns>A dictionary mapping site id to its current <see cref="SiteHealthState"/>.</returns>
|
|
IReadOnlyDictionary<string, SiteHealthState> GetAllSiteStates();
|
|
/// <summary>Returns the current health state for the specified site, or null if not tracked.</summary>
|
|
/// <param name="siteId">The string identifier of the site to look up.</param>
|
|
/// <returns>The <see cref="SiteHealthState"/> for the site, or null if not yet seen.</returns>
|
|
SiteHealthState? GetSiteState(string siteId);
|
|
|
|
/// <summary>
|
|
/// Removes tracked sites not in <paramref name="knownSiteIds"/> (i.e. deleted
|
|
/// from configuration). The synthetic central id is always retained.
|
|
/// Self-healing: called from the CentralCommunicationActor's periodic site
|
|
/// refresh, so a deleted site disappears within one refresh interval without
|
|
/// needing a dedicated deletion event. Without this the in-memory state only
|
|
/// ever grew, leaving a deleted site as a permanently-offline dashboard tile
|
|
/// (and a live KPI sample source) forever.
|
|
/// </summary>
|
|
/// <param name="knownSiteIds">The identifiers of all currently-configured sites.</param>
|
|
void PruneUnknownSites(IReadOnlyCollection<string> knownSiteIds);
|
|
}
|