Files
orca/internal/cli/metrics.go
T
Jon Chery ed91d68fbf feat(P10): observability expansion — metrics + security headers (REQ-159)
New metrics:
- orca_jobs_running / orca_jobs_failed / orca_jobs_complete (gauges)
- orca_audit_chain_head (gauge, chain integrity)
- orca_drift_events_total, orca_ssh_errors_total (counters)
- orca_txn_apply_total, orca_txn_rollback_total (counters)
- orca_acl_denials_total (counter)

Security headers on metrics + healthz endpoints:
- X-Content-Type-Options: nosniff
- X-Frame-Options: DENY

New file: docs/metrics.md (Prometheus reference + scrape config)

---ci---
project: orca
phase: 10
milestone: v0.13
status: complete
requirements:
  covered: [159]
---/ci---
2026-08-10 13:44:04 +00:00

155 lines
4.3 KiB
Go

package cli
import (
"context"
"database/sql"
"errors"
"fmt"
"net/http"
"os"
"os/signal"
"sync"
"syscall"
"time"
"github.com/spf13/cobra"
"git.cloudinit.dev/coreci/orca/internal/model"
"git.cloudinit.dev/coreci/orca/internal/store"
"git.cloudinit.dev/coreci/orca/internal/transport"
)
var metricsAddr string
var metricsCmd = &cobra.Command{
Use: "metrics",
Short: "Run the orca metrics endpoint (Prometheus text exposition)",
Long: `Start a standalone HTTP server exposing Prometheus text-exposition
metrics at /metrics and a liveness probe at /healthz. Designed to run on the
CLI host or a designated metrics host; polls cluster state periodically and
updates gauges. No orca daemon required (R-001).`,
RunE: func(cmd *cobra.Command, args []string) error {
log := newLogger()
m := transport.NewMetrics()
db, closer, err := openDB()
if err != nil {
log.Warn("metrics: open db failed, gauges will stay 0", "err", err)
db = nil
closer = func() error { return nil }
}
defer closer()
var pollWG sync.WaitGroup
pollCtx, pollCancel := context.WithCancel(cmd.Context())
defer func() {
pollCancel()
pollWG.Wait()
}()
pollWG.Add(1)
go func() {
defer pollWG.Done()
pollLoop(pollCtx, m, db, log)
}()
mux := http.NewServeMux()
mux.HandleFunc("/metrics", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("X-Content-Type-Options", "nosniff")
w.Header().Set("X-Frame-Options", "DENY")
w.Header().Set("Content-Type", "text/plain; version=0.0.4; charset=utf-8")
if err := m.WritePrometheus(w); err != nil {
log.Warn("metrics: write exposition failed", "err", err)
}
})
mux.HandleFunc("/healthz", func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("X-Content-Type-Options", "nosniff")
w.Header().Set("X-Frame-Options", "DENY")
w.WriteHeader(http.StatusOK)
_, _ = w.Write([]byte("ok\n"))
})
srv := &http.Server{
Addr: metricsAddr,
Handler: mux,
}
errCh := make(chan error, 1)
go func() {
err := srv.ListenAndServe()
if err != nil && !errors.Is(err, http.ErrServerClosed) {
errCh <- err
}
}()
fmt.Fprintf(cmd.OutOrStdout(), "✓ orca metrics listening on %s\n", metricsAddr)
fmt.Fprintln(cmd.OutOrStdout(), " /metrics - Prometheus text exposition")
fmt.Fprintln(cmd.OutOrStdout(), " /healthz - liveness probe")
fmt.Fprintln(cmd.OutOrStdout(), " press Ctrl+C to stop")
ctx, stop := signal.NotifyContext(cmd.Context(), os.Interrupt, syscall.SIGTERM)
defer stop()
select {
case <-ctx.Done():
fmt.Fprintln(cmd.OutOrStdout(), "\nshutting down...")
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
return srv.Shutdown(shutdownCtx)
case err := <-errCh:
return fmt.Errorf("metrics server: %w", err)
}
},
}
func pollLoop(ctx context.Context, m *transport.Metrics, db *sql.DB, log interface{ Warn(string, ...any) }) {
if db == nil {
return
}
ticker := time.NewTicker(15 * time.Second)
defer ticker.Stop()
refresh(ctx, m, db, log)
for {
select {
case <-ctx.Done():
return
case <-ticker.C:
refresh(ctx, m, db, log)
}
}
}
func refresh(ctx context.Context, m *transport.Metrics, db *sql.DB, log interface{ Warn(string, ...any) }) {
if nodes, err := store.NewNodeRepo(db).List(ctx); err != nil {
log.Warn("metrics: node list failed", "err", err)
} else {
m.SetGauge("nodes_total", float64(len(nodes)))
}
if jobs, err := store.NewJobRepo(db).List(ctx); err != nil {
log.Warn("metrics: job list failed", "err", err)
} else {
m.SetGauge("allocs_total", float64(len(jobs)))
// REQ-159 / P10: jobs by state.
byState := make(map[model.JobStatus]int, 8)
for _, j := range jobs {
byState[j.Status]++
}
// Set total + per-state counts using simple gauge names.
running := byState[model.JobStatusRunning]
failed := byState[model.JobStatusFailed]
complete := byState[model.JobStatusComplete]
m.SetGauge("orca_jobs_running", float64(running))
m.SetGauge("orca_jobs_failed", float64(failed))
m.SetGauge("orca_jobs_complete", float64(complete))
}
// REQ-159 / P10: audit chain head gauge.
if head, err := store.NewAuditRepo(db).ChainHead(ctx); err == nil && head != "" {
m.SetGauge("orca_audit_chain_head", 1)
}
}
func init() {
metricsCmd.Flags().StringVar(&metricsAddr, "addr", ":9100", "listen address for the metrics HTTP server")
rootCmd.AddCommand(metricsCmd)
}