Files
lmxopcua/src/ZB.MOM.WW.OtOpcUa.Admin/Program.cs
Joseph Doherty ef53553e9d OTel Prometheus exporter wiring — RedundancyMetrics meter now scraped at /metrics. Closes task #201. Picked Prometheus over OTLP per the earlier recommendation (pull-based means no OTel Collector deployment required for the common K8s/containers case; the endpoint ASP.NET-hosts inside the Admin app already, so one less moving part). Adds two NuGet refs to the Admin csproj: OpenTelemetry.Extensions.Hosting 1.15.2 (stable) + OpenTelemetry.Exporter.Prometheus.AspNetCore 1.15.2-beta.1 (the exporter has historically been beta-only; rest of the OTel ecosystem treats it as production-acceptable + it's what the upstream OTel docs themselves recommend for AspNetCore hosts). Program.cs gains a Metrics:Prometheus:Enabled toggle (defaults true; setting to false disables both the MeterProvider registration + the scrape endpoint entirely for locked-down deployments). When enabled, AddOpenTelemetry().WithMetrics() registers a MeterProvider that subscribes to the "ZB.MOM.WW.OtOpcUa.Redundancy" meter (the exact MeterName constant on RedundancyMetrics) + wires AddPrometheusExporter. MapPrometheusScrapingEndpoint() appends a /metrics handler producing the Prometheus text-format output; deliberately NOT authenticated because scrape jobs typically run on a trusted network + operators who need auth wrap the endpoint behind a reverse-proxy basic-auth gate per fleet-ops convention. appsettings.json declares the toggle with Enabled: true so the default deploy gets metrics automatically — turning off is the explicit action. Future meters (resilience tracker + host status + auth probe) just AddMeter("Name") alongside the existing call to start flowing through the same endpoint without more infrastructure. Admin project builds 0 errors; Admin.Tests 92/92 passing (unchanged — the OTel pipeline runs at request time, not test time). Still-pending work that was NOT part of #201's scope: an equivalent setup for the Server project (different MeterNames — the Polly pipeline builder's tracker + host-status publisher) + a metrics cheat-sheet in docs/observability.md documenting each meter's tag set + expected alerting thresholds. Those are natural follow-ups when fleet-ops starts building dashboards.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 00:41:16 -04:00

118 lines
4.7 KiB
C#

using Microsoft.AspNetCore.Authentication;
using Microsoft.AspNetCore.Authentication.Cookies;
using Microsoft.EntityFrameworkCore;
using OpenTelemetry.Metrics;
using Serilog;
using ZB.MOM.WW.OtOpcUa.Admin.Components;
using ZB.MOM.WW.OtOpcUa.Admin.Hubs;
using ZB.MOM.WW.OtOpcUa.Admin.Security;
using ZB.MOM.WW.OtOpcUa.Admin.Services;
using ZB.MOM.WW.OtOpcUa.Configuration;
var builder = WebApplication.CreateBuilder(args);
builder.Host.UseSerilog((ctx, cfg) => cfg
.MinimumLevel.Information()
.WriteTo.Console()
.WriteTo.File("logs/otopcua-admin-.log", rollingInterval: RollingInterval.Day));
builder.Services.AddRazorComponents().AddInteractiveServerComponents();
builder.Services.AddHttpContextAccessor();
builder.Services.AddSignalR();
builder.Services.AddAuthentication(CookieAuthenticationDefaults.AuthenticationScheme)
.AddCookie(o =>
{
o.Cookie.Name = "OtOpcUa.Admin";
o.LoginPath = "/login";
o.ExpireTimeSpan = TimeSpan.FromHours(8);
});
builder.Services.AddAuthorizationBuilder()
.AddPolicy("CanEdit", p => p.RequireRole(AdminRoles.ConfigEditor, AdminRoles.FleetAdmin))
.AddPolicy("CanPublish", p => p.RequireRole(AdminRoles.FleetAdmin));
builder.Services.AddCascadingAuthenticationState();
builder.Services.AddDbContext<OtOpcUaConfigDbContext>(opt =>
opt.UseSqlServer(builder.Configuration.GetConnectionString("ConfigDb")
?? throw new InvalidOperationException("ConnectionStrings:ConfigDb not configured")));
builder.Services.AddScoped<ClusterService>();
builder.Services.AddScoped<GenerationService>();
builder.Services.AddScoped<EquipmentService>();
builder.Services.AddScoped<UnsService>();
builder.Services.AddScoped<NamespaceService>();
builder.Services.AddScoped<DriverInstanceService>();
builder.Services.AddScoped<NodeAclService>();
builder.Services.AddScoped<PermissionProbeService>();
builder.Services.AddScoped<AclChangeNotifier>();
builder.Services.AddScoped<ReservationService>();
builder.Services.AddScoped<DraftValidationService>();
builder.Services.AddScoped<AuditLogService>();
builder.Services.AddScoped<HostStatusService>();
builder.Services.AddScoped<ClusterNodeService>();
builder.Services.AddSingleton<RedundancyMetrics>();
builder.Services.AddScoped<EquipmentImportBatchService>();
builder.Services.AddScoped<ZB.MOM.WW.OtOpcUa.Configuration.Services.ILdapGroupRoleMappingService,
ZB.MOM.WW.OtOpcUa.Configuration.Services.LdapGroupRoleMappingService>();
// Cert-trust management — reads the OPC UA server's PKI store root so rejected client certs
// can be promoted to trusted via the Admin UI. Singleton: no per-request state, just
// filesystem operations.
builder.Services.Configure<CertTrustOptions>(builder.Configuration.GetSection(CertTrustOptions.SectionName));
builder.Services.AddSingleton<CertTrustService>();
// LDAP auth — parity with ScadaLink's LdapAuthService (decision #102).
builder.Services.Configure<LdapOptions>(
builder.Configuration.GetSection("Authentication:Ldap"));
builder.Services.AddScoped<ILdapAuthService, LdapAuthService>();
// SignalR real-time fleet status + alerts (admin-ui.md §"Real-Time Updates").
builder.Services.AddHostedService<FleetStatusPoller>();
// OpenTelemetry Prometheus exporter — Meter stream from RedundancyMetrics + any future
// Admin-side instrumentation lands on the /metrics endpoint Prometheus scrapes. Pull-based
// means no OTel Collector deployment required for the common deploy-in-a-K8s case; appsettings
// Metrics:Prometheus:Enabled=false disables the endpoint entirely for locked-down deployments.
var metricsEnabled = builder.Configuration.GetValue("Metrics:Prometheus:Enabled", true);
if (metricsEnabled)
{
builder.Services.AddOpenTelemetry()
.WithMetrics(m => m
.AddMeter(RedundancyMetrics.MeterName)
.AddPrometheusExporter());
}
var app = builder.Build();
app.UseSerilogRequestLogging();
app.UseStaticFiles();
app.UseAuthentication();
app.UseAuthorization();
app.UseAntiforgery();
app.MapPost("/auth/logout", async (HttpContext ctx) =>
{
await ctx.SignOutAsync(CookieAuthenticationDefaults.AuthenticationScheme);
ctx.Response.Redirect("/");
});
app.MapHub<FleetStatusHub>("/hubs/fleet");
app.MapHub<AlertHub>("/hubs/alerts");
if (metricsEnabled)
{
// Prometheus scrape endpoint — expose instrumentation registered in the OTel MeterProvider
// above. Emits text-format metrics at /metrics; auth is intentionally NOT required (Prometheus
// scrape jobs typically run on a trusted network). Operators who need auth put the endpoint
// behind a reverse-proxy basic-auth gate per fleet-ops convention.
app.MapPrometheusScrapingEndpoint();
}
app.MapRazorComponents<App>().AddInteractiveServerRenderMode();
await app.RunAsync();
public partial class Program;