feat: add Prometheus metrics to listener service

Add an optional Prometheus metrics HTTP endpoint to the listener for
monitoring deployment operations. Includes four metrics:

- homelab_deploy_deployments_total (counter with status/action/error_code)
- homelab_deploy_deployment_duration_seconds (histogram with action/success)
- homelab_deploy_deployment_in_progress (gauge)
- homelab_deploy_info (gauge with hostname/tier/role/version)

New CLI flags: --metrics-enabled, --metrics-addr (default :9972)
New NixOS options: metrics.enable, metrics.address, metrics.openFirewall

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
2026-02-07 07:58:22 +01:00
parent 56365835c7
commit 79db119d1c
10 changed files with 613 additions and 9 deletions

View File

@@ -0,0 +1,84 @@
package metrics
import (
"context"
"fmt"
"log/slog"
"net/http"
"time"
"github.com/prometheus/client_golang/prometheus"
"github.com/prometheus/client_golang/prometheus/promhttp"
)
// ServerConfig holds configuration for the metrics server.
type ServerConfig struct {
Addr string
Logger *slog.Logger
}
// Server serves Prometheus metrics over HTTP.
type Server struct {
httpServer *http.Server
registry *prometheus.Registry
collector *Collector
logger *slog.Logger
}
// NewServer creates a new metrics server.
func NewServer(cfg ServerConfig) *Server {
logger := cfg.Logger
if logger == nil {
logger = slog.Default()
}
registry := prometheus.NewRegistry()
collector := NewCollector(registry)
mux := http.NewServeMux()
mux.Handle("/metrics", promhttp.HandlerFor(registry, promhttp.HandlerOpts{
Registry: registry,
}))
mux.HandleFunc("/health", func(w http.ResponseWriter, _ *http.Request) {
w.WriteHeader(http.StatusOK)
_, _ = w.Write([]byte("ok"))
})
return &Server{
httpServer: &http.Server{
Addr: cfg.Addr,
Handler: mux,
ReadHeaderTimeout: 10 * time.Second,
},
registry: registry,
collector: collector,
logger: logger,
}
}
// Collector returns the metrics collector.
func (s *Server) Collector() *Collector {
return s.collector
}
// Start starts the HTTP server in a goroutine.
func (s *Server) Start() error {
s.logger.Info("starting metrics server", "addr", s.httpServer.Addr)
go func() {
if err := s.httpServer.ListenAndServe(); err != nil && err != http.ErrServerClosed {
s.logger.Error("metrics server error", "error", err)
}
}()
return nil
}
// Shutdown gracefully shuts down the server.
func (s *Server) Shutdown(ctx context.Context) error {
s.logger.Info("shutting down metrics server")
if err := s.httpServer.Shutdown(ctx); err != nil {
return fmt.Errorf("failed to shutdown metrics server: %w", err)
}
return nil
}