Files
ScadaBridge/src/ScadaLink.HealthMonitoring/CentralHealthAggregator.cs
T
Joseph Doherty 295150751f feat(scripts): realign Test Run with runtime API, add anonymous-object calls and instance binding
The Test Run sandbox and Monaco analysis modelled a script API that had
drifted from the site runtime's ScriptGlobals, so real scripts failed to
compile in Test Run. Realign both to the runtime surface
(Instance/Scripts/ExternalSystem/Attributes/Children/Parent) and drop the
duplicate ScriptHost stub so the two cannot diverge again.

- Script calls (Scripts.CallShared, Instance.CallScript, Route.To().Call)
  accept an anonymous object instead of a hand-built dictionary, via a
  shared ScriptArgs normalizer; existing dictionary calls still compile.
- Test Run can optionally bind to a deployed instance, so Instance/
  Attributes/CallScript route to it cross-site; adds site-side
  RouteToGetAttributes/RouteToSetAttributes handlers.
- Adds Test Run panels to the API method and template script editors.
- Fixes the TestDatabaseQuery seed script, which queried a table that
  never existed.

Also commits unrelated in-progress work already in the tree: the health
monitoring report loop, site streaming changes, and the Admin/Design
data-connection and SMTP page reorganization.
2026-05-16 03:37:56 -04:00

160 lines
5.7 KiB
C#

using System.Collections.Concurrent;
using Microsoft.Extensions.Hosting;
using Microsoft.Extensions.Logging;
using Microsoft.Extensions.Options;
using ScadaLink.Commons.Messages.Health;
namespace ScadaLink.HealthMonitoring;
/// <summary>
/// Central-side aggregator that receives health reports from all sites,
/// tracks latest metrics in memory, and detects offline sites.
/// No persistence — display-only for Central UI consumption.
/// </summary>
public class CentralHealthAggregator : BackgroundService, ICentralHealthAggregator
{
private readonly ConcurrentDictionary<string, SiteHealthState> _siteStates = new();
private readonly HealthMonitoringOptions _options;
private readonly ILogger<CentralHealthAggregator> _logger;
private readonly TimeProvider _timeProvider;
public CentralHealthAggregator(
IOptions<HealthMonitoringOptions> options,
ILogger<CentralHealthAggregator> logger,
TimeProvider? timeProvider = null)
{
_options = options.Value;
_logger = logger;
_timeProvider = timeProvider ?? TimeProvider.System;
}
/// <summary>
/// Process an incoming health report from a site.
/// Only replaces stored state if incoming sequence number is greater than last received.
/// Auto-marks previously offline sites as online.
/// </summary>
public void ProcessReport(SiteHealthReport report)
{
var now = _timeProvider.GetUtcNow();
_siteStates.AddOrUpdate(
report.SiteId,
_ =>
{
_logger.LogInformation("Site {SiteId} registered with sequence #{Seq}", report.SiteId, report.SequenceNumber);
return new SiteHealthState
{
SiteId = report.SiteId,
LatestReport = report,
LastReportReceivedAt = now,
LastHeartbeatAt = now,
LastSequenceNumber = report.SequenceNumber,
IsOnline = true
};
},
(_, existing) =>
{
if (report.SequenceNumber <= existing.LastSequenceNumber)
{
_logger.LogDebug(
"Rejecting stale report from site {SiteId}: seq {Incoming} <= {Last}",
report.SiteId, report.SequenceNumber, existing.LastSequenceNumber);
return existing;
}
var wasOffline = !existing.IsOnline;
existing.LatestReport = report;
existing.LastReportReceivedAt = now;
existing.LastHeartbeatAt = now;
existing.LastSequenceNumber = report.SequenceNumber;
existing.IsOnline = true;
if (wasOffline)
{
_logger.LogInformation("Site {SiteId} is back online (seq #{Seq})", report.SiteId, report.SequenceNumber);
}
return existing;
});
}
/// <summary>
/// Bumps the last-seen timestamp for a site already known via a prior
/// SiteHealthReport. Heartbeats from sites we have not yet received a
/// full report from are ignored — registration only happens on report.
/// </summary>
public void MarkHeartbeat(string siteId, DateTimeOffset receivedAt)
{
if (!_siteStates.TryGetValue(siteId, out var state))
return;
if (receivedAt > state.LastHeartbeatAt)
state.LastHeartbeatAt = receivedAt;
if (!state.IsOnline)
{
state.IsOnline = true;
_logger.LogInformation("Site {SiteId} is back online (heartbeat)", siteId);
}
}
/// <summary>
/// Get the current health state for all known sites.
/// </summary>
public IReadOnlyDictionary<string, SiteHealthState> GetAllSiteStates()
{
return new Dictionary<string, SiteHealthState>(_siteStates);
}
/// <summary>
/// Get the current health state for a specific site, or null if unknown.
/// </summary>
public SiteHealthState? GetSiteState(string siteId)
{
_siteStates.TryGetValue(siteId, out var state);
return state;
}
/// <summary>
/// Background task that periodically checks for offline sites.
/// </summary>
protected override async Task ExecuteAsync(CancellationToken stoppingToken)
{
_logger.LogInformation(
"Central health aggregator started, offline timeout {Timeout}s",
_options.OfflineTimeout.TotalSeconds);
// Check at half the offline timeout interval for timely detection
var checkInterval = TimeSpan.FromMilliseconds(_options.OfflineTimeout.TotalMilliseconds / 2);
using var timer = new PeriodicTimer(checkInterval);
while (await timer.WaitForNextTickAsync(stoppingToken).ConfigureAwait(false))
{
CheckForOfflineSites();
}
}
internal void CheckForOfflineSites()
{
var now = _timeProvider.GetUtcNow();
foreach (var kvp in _siteStates)
{
var state = kvp.Value;
if (!state.IsOnline) continue;
// Use LastHeartbeatAt — heartbeats arrive every ~5s from any
// healthy site node, so OfflineTimeout only fires when no node
// can reach central, not during single-node failovers.
var elapsed = now - state.LastHeartbeatAt;
if (elapsed > _options.OfflineTimeout)
{
state.IsOnline = false;
_logger.LogWarning(
"Site {SiteId} marked offline — no signal for {Elapsed}s (timeout: {Timeout}s)",
state.SiteId, elapsed.TotalSeconds, _options.OfflineTimeout.TotalSeconds);
}
}
}
}