8095c8efbe
Both nodes of a site cluster were sending health reports. The standby node (without the DeploymentManager singleton) reported 0 instances and no connections, overwriting the active node's data in the aggregator. Added IsActiveNode flag to ISiteHealthCollector, set by DeploymentManagerActor on PreStart/PostStop. HealthReportSender skips sending when the node is not active. Also ensured EnsureDclConnections is called during startup batch creation so data connections survive container restarts.
75 lines
2.7 KiB
C#
75 lines
2.7 KiB
C#
using Microsoft.Extensions.Hosting;
|
|
using Microsoft.Extensions.Logging;
|
|
using Microsoft.Extensions.Options;
|
|
using ScadaLink.Commons.Messages.Health;
|
|
|
|
namespace ScadaLink.HealthMonitoring;
|
|
|
|
/// <summary>
|
|
/// Periodically collects a SiteHealthReport and sends it to central via Akka remoting.
|
|
/// Sequence numbers are monotonic, starting at 1, and reset on service restart.
|
|
/// </summary>
|
|
public class HealthReportSender : BackgroundService
|
|
{
|
|
private readonly ISiteHealthCollector _collector;
|
|
private readonly IHealthReportTransport _transport;
|
|
private readonly HealthMonitoringOptions _options;
|
|
private readonly ILogger<HealthReportSender> _logger;
|
|
private readonly string _siteId;
|
|
private long _sequenceNumber;
|
|
|
|
public HealthReportSender(
|
|
ISiteHealthCollector collector,
|
|
IHealthReportTransport transport,
|
|
IOptions<HealthMonitoringOptions> options,
|
|
ILogger<HealthReportSender> logger,
|
|
ISiteIdentityProvider siteIdentityProvider)
|
|
{
|
|
_collector = collector;
|
|
_transport = transport;
|
|
_options = options.Value;
|
|
_logger = logger;
|
|
_siteId = siteIdentityProvider.SiteId;
|
|
}
|
|
|
|
/// <summary>
|
|
/// Current sequence number (for testing).
|
|
/// </summary>
|
|
public long CurrentSequenceNumber => Interlocked.Read(ref _sequenceNumber);
|
|
|
|
protected override async Task ExecuteAsync(CancellationToken stoppingToken)
|
|
{
|
|
_logger.LogInformation(
|
|
"Health report sender starting for site {SiteId}, interval {Interval}s",
|
|
_siteId, _options.ReportInterval.TotalSeconds);
|
|
|
|
using var timer = new PeriodicTimer(_options.ReportInterval);
|
|
|
|
while (await timer.WaitForNextTickAsync(stoppingToken).ConfigureAwait(false))
|
|
{
|
|
try
|
|
{
|
|
// Only the active node (running the DeploymentManager singleton) sends health reports.
|
|
// The standby node has no instance/connection data and would overwrite the active's report.
|
|
if (!_collector.IsActiveNode)
|
|
continue;
|
|
|
|
var seq = Interlocked.Increment(ref _sequenceNumber);
|
|
var report = _collector.CollectReport(_siteId);
|
|
|
|
// Replace the placeholder sequence number with our monotonic one
|
|
var reportWithSeq = report with { SequenceNumber = seq };
|
|
|
|
_transport.Send(reportWithSeq);
|
|
|
|
_logger.LogInformation("Sent health report #{Seq} for site {SiteId}", seq, _siteId);
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
_logger.LogError(ex, "Failed to send health report for site {SiteId}", _siteId);
|
|
// Continue sending — don't let a single failure stop reporting
|
|
}
|
|
}
|
|
}
|
|
}
|