Prometheus metrics at /metrics, configured in jarl.yaml

New metrics: section (enabled, listen, allow, token). /metrics is served on
the main listeners, the local socket (root and jarld's user) and optional
metrics-only addresses; a scrape needs an allowed address or the bearer
token. Exports health (named up, problems, drift, backups, blocklists,
DNSSEC phases, token expiry) and, with stats on, named's and Jarl's query
counters since jarld started plus named's process and cache gauges.
docs/metrics.md has example queries and alerts checked with promtool.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

internal/config/config.go

@@ -4,6 +4,7 @@ package config
 import (
 	"bytes"
 	"fmt"
+	"net"
 	"net/netip"
 	"net/url"
 	"os"
@@ -38,6 +39,56 @@ type Config struct {
 	ACME       ACME     `yaml:"acme"`
 	Porkbun    Porkbun  `yaml:"porkbun"`
 	Blocking   Blocking `yaml:"blocking"`
+	Metrics    Metrics  `yaml:"metrics"`
+}
+
+// Metrics configures the Prometheus endpoint /metrics (docs/metrics.md).
+// A scrape is allowed from an address in Allow, or with Token as a bearer
+// token; root and jarld's own user may also scrape on the local socket.
+type Metrics struct {
+	Enabled bool `yaml:"enabled"`
+	// Listen are extra addresses that serve only /metrics, over plain
+	// HTTP. /metrics is always served on the main listeners too.
+	Listen []string `yaml:"listen"`
+	// Allow are the addresses or prefixes that may scrape without a token.
+	Allow []string `yaml:"allow"`
+	// Token, when set, lets any address that sends it as
+	// "Authorization: Bearer TOKEN" scrape.
+	Token string `yaml:"token"`
+}
+
+func (m *Metrics) check() error {
+	if !m.Enabled {
+		return nil
+	}
+	for _, a := range m.Listen {
+		if _, port, err := net.SplitHostPort(a); err != nil || port == "" {
+			return fmt.Errorf("listen %q must be ADDRESS:PORT, e.g. 0.0.0.0:9450", a)
+		}
+	}
+	for _, p := range m.Allow {
+		if _, err := ParsePrefix(p); err != nil {
+			return fmt.Errorf("allow: %v", err)
+		}
+	}
+	if m.Token != "" && (len(m.Token) < 16 || strings.ContainsAny(m.Token, " \t\r\n")) {
+		return fmt.Errorf("token must be at least 16 characters, without spaces (e.g. from 'openssl rand -hex 24')")
+	}
+	if len(m.Allow) == 0 && m.Token == "" {
+		return fmt.Errorf("set allow, token or both, or nobody can scrape")
+	}
+	return nil
+}
+
+// AllowPrefixes returns the parsed allow list.
+func (m *Metrics) AllowPrefixes() []netip.Prefix {
+	var out []netip.Prefix
+	for _, p := range m.Allow {
+		if pf, err := ParsePrefix(p); err == nil {
+			out = append(out, pf.Masked())
+		}
+	}
+	return out
 }
 
 // Blocking configures blocklist downloads (docs/blocking.md). The lists
@@ -323,6 +374,7 @@ func Default() *Config {
 		},
 		ACME:     ACME{HTTPReq: HTTPReq{RequireHTTPS: true}},
 		Blocking: Blocking{Refresh: Duration(24 * time.Hour), MaxDownloadMB: 64, MaxEntries: 1_000_000},
+		Metrics:  Metrics{Allow: []string{"127.0.0.1", "::1"}},
 		Backup:   Backup{Dir: "/var/backups/jarl", Retention: Duration(30 * 24 * time.Hour), KeepAtLeast: 7, WarnAfter: Duration(2 * 24 * time.Hour)},
 	}
 }
@@ -394,6 +446,9 @@ func (c *Config) check() error {
 	if err := c.Blocking.check(); err != nil {
 		return fmt.Errorf("blocking: %w", err)
 	}
+	if err := c.Metrics.check(); err != nil {
+		return fmt.Errorf("metrics: %w", err)
+	}
 	switch c.Log.Format {
 	case "text", "json":
 	default:
@@ -633,4 +688,23 @@ blocking:
   refresh: 24h           # check each list for changes this often (at least 1h)
   max_download_mb: 64    # refuse larger downloads
   max_entries: 1000000   # refuse lists with more domains
+
+# Prometheus metrics at /metrics (docs/metrics.md): named's counters and
+# Jarl's own (blocking, zones, views), plus health gauges to alert on
+# (named up, validation problems, blocklist errors, backup age, DNSSEC
+# steps, token expiry). Off by default. /metrics is served on the
+# addresses in 'listen' at the top of this file; a scrape is allowed from
+# an address in 'allow' below, or with the token. Query counters need
+# stats.enabled.
+metrics:
+  enabled: false
+  # Extra addresses that serve only /metrics, over plain HTTP, e.g.
+  # ["0.0.0.0:9450"] for a Prometheus server elsewhere on the network.
+  listen: []
+  # Addresses or prefixes that may scrape without a token.
+  allow: ["127.0.0.1", "::1"]
+  # A bearer token (at least 16 characters) that lets any address scrape:
+  # in Prometheus, 'authorization: { credentials: TOKEN }'. Keep this file
+  # readable by root and jarld only when you set it.
+  token: ""
 `

internal/config/config_test.go

@@ -87,3 +87,31 @@ func TestStatsConfig(t *testing.T) {
 		}
 	}
 }
+
+func TestMetricsConfig(t *testing.T) {
+	d := Default()
+	if d.Metrics.Enabled || len(d.Metrics.AllowPrefixes()) != 2 || d.Metrics.Token != "" {
+		t.Errorf("defaults = %+v", d.Metrics)
+	}
+	path := filepath.Join(t.TempDir(), "jarl.yaml")
+	for _, tc := range []struct {
+		yaml string
+		ok   bool
+	}{
+		{"metrics: {enabled: true}", true},
+		{"metrics: {enabled: true, listen: [\"0.0.0.0:9450\", \"[::]:9450\"], allow: [10.0.0.5, 192.168.1.0/24]}", true},
+		{"metrics: {enabled: true, allow: [], token: 0123456789abcdef}", true},
+		{"metrics: {enabled: true, allow: []}", false}, // nobody could scrape
+		{"metrics: {enabled: true, token: short}", false},
+		{"metrics: {enabled: true, token: \"has space 0123456789\"}", false},
+		{"metrics: {enabled: true, listen: [\"9450\"]}", false},
+		{"metrics: {enabled: true, allow: [prometheus.lan]}", false},
+		{"metrics: {enabled: false, listen: [nonsense]}", true}, // only checked when enabled
+	} {
+		os.WriteFile(path, []byte(tc.yaml+"\n"), 0o644)
+		_, err := Load(path, false)
+		if (err == nil) != tc.ok {
+			t.Errorf("%s: err = %v, want ok=%v", tc.yaml, err, tc.ok)
+		}
+	}
+}