feat: add MonitorServer with /healthz and /varz endpoints

2026-02-22 22:20:44 -05:00
parent f6b38df291
commit f2badc3488
4 changed files with 289 additions and 0 deletions
--- a/src/NATS.Server/Monitoring/VarzHandler.cs
+++ b/src/NATS.Server/Monitoring/VarzHandler.cs
@@ -0,0 +1,119 @@
+using System.Diagnostics;
+using System.Runtime.InteropServices;
+using NATS.Server.Protocol;
+
+namespace NATS.Server.Monitoring;
+
+/// <summary>
+/// Handles building the Varz response from server state and process metrics.
+/// Corresponds to Go server/monitor.go handleVarz function.
+/// </summary>
+public sealed class VarzHandler
+{
+    private readonly NatsServer _server;
+    private readonly NatsOptions _options;
+    private readonly SemaphoreSlim _varzMu = new(1, 1);
+    private DateTime _lastCpuSampleTime;
+    private TimeSpan _lastCpuUsage;
+    private double _cachedCpuPercent;
+
+    public VarzHandler(NatsServer server, NatsOptions options)
+    {
+        _server = server;
+        _options = options;
+        var proc = Process.GetCurrentProcess();
+        _lastCpuSampleTime = DateTime.UtcNow;
+        _lastCpuUsage = proc.TotalProcessorTime;
+    }
+
+    public async Task<Varz> HandleVarzAsync()
+    {
+        await _varzMu.WaitAsync();
+        try
+        {
+            var proc = Process.GetCurrentProcess();
+            var now = DateTime.UtcNow;
+            var uptime = now - _server.StartTime;
+            var stats = _server.Stats;
+
+            // CPU sampling with 1-second cache to avoid excessive sampling
+            if ((now - _lastCpuSampleTime).TotalSeconds >= 1.0)
+            {
+                var currentCpu = proc.TotalProcessorTime;
+                var elapsed = now - _lastCpuSampleTime;
+                _cachedCpuPercent = (currentCpu - _lastCpuUsage).TotalMilliseconds
+                    / elapsed.TotalMilliseconds / Environment.ProcessorCount * 100.0;
+                _lastCpuSampleTime = now;
+                _lastCpuUsage = currentCpu;
+            }
+
+            // Track HTTP request count for /varz
+            stats.HttpReqStats.AddOrUpdate("/varz", 1, (_, v) => v + 1);
+
+            return new Varz
+            {
+                Id = _server.ServerId,
+                Name = _server.ServerName,
+                Version = NatsProtocol.Version,
+                Proto = NatsProtocol.ProtoVersion,
+                GoVersion = $"dotnet {RuntimeInformation.FrameworkDescription}",
+                Host = _options.Host,
+                Port = _options.Port,
+                HttpHost = _options.MonitorHost,
+                HttpPort = _options.MonitorPort,
+                HttpBasePath = _options.MonitorBasePath ?? "",
+                HttpsPort = _options.MonitorHttpsPort,
+                TlsRequired = _options.HasTls && !_options.AllowNonTls,
+                TlsVerify = _options.HasTls && _options.TlsVerify,
+                TlsTimeout = _options.HasTls ? _options.TlsTimeout.TotalSeconds : 0,
+                MaxConnections = _options.MaxConnections,
+                MaxPayload = _options.MaxPayload,
+                MaxControlLine = _options.MaxControlLine,
+                MaxPingsOut = _options.MaxPingsOut,
+                PingInterval = (long)_options.PingInterval.TotalNanoseconds,
+                Start = _server.StartTime,
+                Now = now,
+                Uptime = FormatUptime(uptime),
+                Mem = proc.WorkingSet64,
+                Cpu = Math.Round(_cachedCpuPercent, 2),
+                Cores = Environment.ProcessorCount,
+                MaxProcs = ThreadPool.ThreadCount,
+                Connections = _server.ClientCount,
+                TotalConnections = (ulong)Interlocked.Read(ref stats.TotalConnections),
+                InMsgs = Interlocked.Read(ref stats.InMsgs),
+                OutMsgs = Interlocked.Read(ref stats.OutMsgs),
+                InBytes = Interlocked.Read(ref stats.InBytes),
+                OutBytes = Interlocked.Read(ref stats.OutBytes),
+                SlowConsumers = Interlocked.Read(ref stats.SlowConsumers),
+                SlowConsumerStats = new SlowConsumersStats
+                {
+                    Clients = (ulong)Interlocked.Read(ref stats.SlowConsumerClients),
+                    Routes = (ulong)Interlocked.Read(ref stats.SlowConsumerRoutes),
+                    Gateways = (ulong)Interlocked.Read(ref stats.SlowConsumerGateways),
+                    Leafs = (ulong)Interlocked.Read(ref stats.SlowConsumerLeafs),
+                },
+                Subscriptions = _server.SubList.Count,
+                ConfigLoadTime = _server.StartTime,
+                HttpReqStats = stats.HttpReqStats.ToDictionary(kv => kv.Key, kv => (ulong)kv.Value),
+            };
+        }
+        finally
+        {
+            _varzMu.Release();
+        }
+    }
+
+    /// <summary>
+    /// Formats a TimeSpan as a human-readable uptime string matching Go server format.
+    /// </summary>
+    private static string FormatUptime(TimeSpan ts)
+    {
+        if (ts.TotalDays >= 1)
+            return $"{(int)ts.TotalDays}d{ts.Hours}h{ts.Minutes}m{ts.Seconds}s";
+        if (ts.TotalHours >= 1)
+            return $"{(int)ts.TotalHours}h{ts.Minutes}m{ts.Seconds}s";
+        if (ts.TotalMinutes >= 1)
+            return $"{(int)ts.TotalMinutes}m{ts.Seconds}s";
+        return $"{(int)ts.TotalSeconds}s";
+    }
+}