init monlet repo with stage 0-2 (docs, contract, agent MVP)

agent/internal/metrics/metrics.go

@@ -0,0 +1,152 @@
+package metrics
+
+import (
+	"context"
+	"errors"
+	"net/http"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+)
+
+type Metrics struct {
+	Registry *prometheus.Registry
+
+	CheckRuns        *prometheus.CounterVec
+	CheckSkipped     *prometheus.CounterVec
+	CheckDuration    *prometheus.HistogramVec
+	CheckStatus      *prometheus.GaugeVec
+	CheckExitCode    *prometheus.GaugeVec
+	CheckLastRun     *prometheus.GaugeVec
+	CheckLastSuccess *prometheus.GaugeVec
+	CheckInterval    *prometheus.GaugeVec
+	ChecksConfigured prometheus.Gauge
+	SpoolDepth       prometheus.Gauge
+	SpoolBytes       prometheus.Gauge
+	SendAttempts     *prometheus.CounterVec
+	SendFailures     *prometheus.CounterVec
+	EventsAccepted   prometheus.Counter
+	EventsDedup      prometheus.Counter
+	LastHeartbeat    prometheus.Gauge
+	BuildInfo        *prometheus.GaugeVec
+}
+
+// StatusCode maps a CheckResultEvent status string to a numeric gauge value.
+func StatusCode(status string) float64 {
+	switch status {
+	case "ok":
+		return 0
+	case "warning":
+		return 1
+	case "critical":
+		return 2
+	default:
+		return 3
+	}
+}
+
+func New() *Metrics {
+	reg := prometheus.NewRegistry()
+	m := &Metrics{Registry: reg}
+	m.CheckRuns = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_check_runs_total",
+		Help: "Number of check runs by id and status.",
+	}, []string{"check_id", "status"})
+	m.CheckSkipped = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_check_skipped_total",
+		Help: "Number of ticks skipped due to overlap.",
+	}, []string{"check_id"})
+	m.CheckDuration = prometheus.NewHistogramVec(prometheus.HistogramOpts{
+		Name:    "monlet_agent_check_duration_seconds",
+		Help:    "Check execution duration.",
+		Buckets: prometheus.DefBuckets,
+	}, []string{"check_id"})
+	m.SpoolDepth = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_spool_events",
+		Help: "Current spool depth in events.",
+	})
+	m.SpoolBytes = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_spool_bytes",
+		Help: "Current spool size in bytes.",
+	})
+	m.SendAttempts = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_send_attempts_total",
+		Help: "Outbound send attempts by kind.",
+	}, []string{"kind"})
+	m.SendFailures = prometheus.NewCounterVec(prometheus.CounterOpts{
+		Name: "monlet_agent_send_failures_total",
+		Help: "Outbound send failures by kind.",
+	}, []string{"kind"})
+	m.EventsAccepted = prometheus.NewCounter(prometheus.CounterOpts{
+		Name: "monlet_agent_events_accepted_total",
+		Help: "Events accepted by the server.",
+	})
+	m.EventsDedup = prometheus.NewCounter(prometheus.CounterOpts{
+		Name: "monlet_agent_events_deduplicated_total",
+		Help: "Events the server reported as duplicates.",
+	})
+	m.CheckStatus = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_check_status",
+		Help: "Last observed status per check: 0=ok,1=warning,2=critical,3=unknown.",
+	}, []string{"check_id"})
+	m.CheckExitCode = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_check_exit_code",
+		Help: "Last exit code per check.",
+	}, []string{"check_id"})
+	m.CheckLastRun = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_check_last_run_timestamp_seconds",
+		Help: "Unix timestamp of the last completed run per check.",
+	}, []string{"check_id"})
+	m.CheckLastSuccess = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_check_last_success_timestamp_seconds",
+		Help: "Unix timestamp of the last ok run per check.",
+	}, []string{"check_id"})
+	m.CheckInterval = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_check_interval_seconds",
+		Help: "Configured interval per check.",
+	}, []string{"check_id"})
+	m.ChecksConfigured = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_checks_configured",
+		Help: "Number of checks configured.",
+	})
+	m.LastHeartbeat = prometheus.NewGauge(prometheus.GaugeOpts{
+		Name: "monlet_agent_last_heartbeat_timestamp_seconds",
+		Help: "Unix timestamp of the last successful heartbeat ack.",
+	})
+	m.BuildInfo = prometheus.NewGaugeVec(prometheus.GaugeOpts{
+		Name: "monlet_agent_build_info",
+		Help: "Constant 1 with build labels.",
+	}, []string{"version", "mode"})
+	reg.MustRegister(m.CheckRuns, m.CheckSkipped, m.CheckDuration,
+		m.CheckStatus, m.CheckExitCode, m.CheckLastRun, m.CheckLastSuccess,
+		m.CheckInterval, m.ChecksConfigured,
+		m.SpoolDepth, m.SpoolBytes,
+		m.SendAttempts, m.SendFailures,
+		m.EventsAccepted, m.EventsDedup,
+		m.LastHeartbeat, m.BuildInfo)
+	return m
+}
+
+// Serve blocks until ctx is done; the listener is closed on shutdown.
+func (m *Metrics) Serve(ctx context.Context, addr string) error {
+	mux := http.NewServeMux()
+	mux.Handle("/metrics", promhttp.HandlerFor(m.Registry, promhttp.HandlerOpts{}))
+	srv := &http.Server{Addr: addr, Handler: mux, ReadHeaderTimeout: 5 * time.Second}
+
+	errCh := make(chan error, 1)
+	go func() { errCh <- srv.ListenAndServe() }()
+
+	select {
+	case <-ctx.Done():
+		shutCtx, cancel := context.WithTimeout(context.Background(), 3*time.Second)
+		defer cancel()
+		_ = srv.Shutdown(shutCtx)
+		return nil
+	case err := <-errCh:
+		if errors.Is(err, http.ErrServerClosed) {
+			return nil
+		}
+		return err
+	}
+}