feat(scadabridge): add ScadaBridgeTelemetry meter + 4 instruments; register with OTel

This commit is contained in:
Joseph Doherty
2026-06-01 16:41:52 -04:00
parent bbc9f09268
commit fe25ac3e51
3 changed files with 130 additions and 1 deletions
@@ -0,0 +1,94 @@
using System.Diagnostics.Metrics;
namespace ZB.MOM.WW.ScadaBridge.Commons.Observability;
/// <summary>
/// Central <see cref="Meter"/> + instrument definitions for ScadaBridge's application
/// telemetry, modelled on OtOpcUa's <c>OtOpcUaTelemetry</c>. Modules emit through these
/// pre-created instruments so a single OpenTelemetry / Prometheus binding in
/// <c>Host</c> (registered via <c>AddZbTelemetry</c> with this meter named in
/// <c>ZbTelemetryOptions.Meters</c>) catches everything. No exporter is required —
/// instruments are no-op until a listener attaches, so tests and dev hosts pay nothing
/// for instrumentation that nobody scrapes.
///
/// Instrument names follow the OpenTelemetry semantic convention pattern
/// <c>scadabridge.&lt;subsystem&gt;.&lt;event&gt;</c>. This task defines the instruments and
/// their emit helpers; four later tasks wire the actual emit points. Until those land the
/// helpers are dormant but inert — calling them is safe and simply records against a meter
/// that nothing observes.
/// </summary>
public static class ScadaBridgeTelemetry
{
/// <summary>The meter name registered with OTel via <c>ZbTelemetryOptions.Meters</c>.</summary>
public const string MeterName = "ZB.MOM.WW.ScadaBridge";
/// <summary>Singleton <see cref="Meter"/> all instruments hang off.</summary>
private static readonly Meter Meter = new(MeterName);
// ---------------- Counters ----------------
/// <summary>Incremented each time a deployment is successfully applied.</summary>
private static readonly Counter<long> _deploymentsApplied =
Meter.CreateCounter<long>("scadabridge.deployments.applied", unit: "1",
description: "Deployments applied.");
/// <summary>Incremented for each inbound API request, tagged with the API method.</summary>
private static readonly Counter<long> _inboundApiRequests =
Meter.CreateCounter<long>("scadabridge.inbound_api.requests", unit: "1",
description: "Inbound API requests, tagged by method.");
// ---------------- Observable gauges ----------------
/// <summary>Current count of open site connections, mutated via <see cref="Interlocked"/>.</summary>
private static long _siteConnectionsUp;
/// <summary>Provider that yields the live StoreAndForward queue depth; set by a later task.</summary>
private static Func<long>? _queueDepthProvider;
#pragma warning disable IDE0052 // Held to keep the observable gauges alive for the meter's lifetime.
/// <summary>Gauge reporting the number of currently open site connections.</summary>
private static readonly ObservableGauge<long> _siteConnectionUp =
Meter.CreateObservableGauge<long>("scadabridge.site.connection.up",
() => Interlocked.Read(ref _siteConnectionsUp),
description: "Number of currently open site connections.");
/// <summary>Gauge reporting the current StoreAndForward queue depth via the registered provider.</summary>
private static readonly ObservableGauge<long> _storeAndForwardQueueDepth =
Meter.CreateObservableGauge<long>("scadabridge.store_and_forward.queue.depth",
() => Volatile.Read(ref _queueDepthProvider) is { } p ? p() : 0L,
unit: "items",
description: "Current StoreAndForward queue depth.");
#pragma warning restore IDE0052
// ---------------- Emit helpers ----------------
/// <summary>Records that a deployment was applied.</summary>
public static void RecordDeploymentApplied() => _deploymentsApplied.Add(1);
/// <summary>Records an inbound API request for the given <paramref name="method"/>.</summary>
/// <param name="method">The API method the request targeted.</param>
public static void RecordInboundApiRequest(string method) =>
_inboundApiRequests.Add(1, new KeyValuePair<string, object?>("method", method));
/// <summary>Records that a site connection opened (increments the up-count gauge).</summary>
public static void SiteConnectionOpened() => Interlocked.Increment(ref _siteConnectionsUp);
/// <summary>Records that a site connection closed (decrements the up-count gauge).</summary>
public static void SiteConnectionClosed() => Interlocked.Decrement(ref _siteConnectionsUp);
/// <summary>
/// Registers the provider the StoreAndForward queue-depth gauge reads on each observation.
/// A later task supplies a provider that reads the real StoreAndForward depth. A null
/// provider is ignored so the gauge falls back to reporting 0.
/// </summary>
/// <param name="provider">A callback returning the current queue depth.</param>
public static void SetQueueDepthProvider(Func<long> provider)
{
if (provider is null)
{
return;
}
Volatile.Write(ref _queueDepthProvider, provider);
}
}
@@ -2,6 +2,7 @@ using ZB.MOM.WW.ScadaBridge.AuditLog;
using ZB.MOM.WW.ScadaBridge.ClusterInfrastructure;
using ZB.MOM.WW.ScadaBridge.Communication;
using ZB.MOM.WW.ScadaBridge.Commons.Interfaces.Services;
using ZB.MOM.WW.ScadaBridge.Commons.Observability;
using ZB.MOM.WW.ScadaBridge.DataConnectionLayer;
using ZB.MOM.WW.ScadaBridge.ExternalSystemGateway;
using ZB.MOM.WW.ScadaBridge.HealthMonitoring;
@@ -122,12 +123,14 @@ public static class SiteServiceRegistration
// the always-on Prometheus exporter. Mount the /metrics scrape endpoint per role
// with app.MapZbMetrics(). The same `?? "central"` SiteId default Program.cs uses
// is applied here so the Resource attribute matches the log-enricher value.
// Meters left empty — application instruments are a deferred follow-on.
// The application meter is named so OTel observes its instruments; emit points are
// wired by follow-on tasks (the instruments are no-op until a listener attaches).
services.AddZbTelemetry(o =>
{
o.ServiceName = "scadabridge";
o.SiteId = config["ScadaBridge:Node:SiteId"] ?? "central";
o.NodeRole = config["ScadaBridge:Node:Role"];
o.Meters = [ScadaBridgeTelemetry.MeterName];
});
}
}
@@ -0,0 +1,32 @@
using ZB.MOM.WW.ScadaBridge.Commons.Observability;
namespace ZB.MOM.WW.ScadaBridge.Host.Tests;
/// <summary>
/// Infrastructure-free guards for <see cref="ScadaBridgeTelemetry"/>: the meter name is the
/// stable value registered with OTel, and the emit helpers are safe to call (they are no-op
/// until follow-on tasks wire real emit points and a listener attaches).
/// </summary>
public class ScadaBridgeTelemetryTests
{
[Fact]
public void MeterName_IsStableValue()
{
Assert.Equal("ZB.MOM.WW.ScadaBridge", ScadaBridgeTelemetry.MeterName);
}
[Fact]
public void EmitHelpers_DoNotThrow()
{
var ex = Record.Exception(() =>
{
ScadaBridgeTelemetry.RecordDeploymentApplied();
ScadaBridgeTelemetry.RecordInboundApiRequest("X");
ScadaBridgeTelemetry.SiteConnectionOpened();
ScadaBridgeTelemetry.SiteConnectionClosed();
ScadaBridgeTelemetry.SetQueueDepthProvider(() => 5);
});
Assert.Null(ex);
}
}