parallel backfill, persist scanned exposure, random-sample DNS queue

- scanner.run now persists exposure_state/detail/capabilities for scanned
  assets (previously only the index was written).
- Backfill runs a bounded worker pool (16) so it verifies reachable assets
  without saturating the DB pool; DB_MAX_CONNS raised for the live test.
- CNAME enrichment queue is now a bounded random sample instead of a FIFO.
  The FIFO filled with the first N hostnames seen at startup and dropped the
  rest, so CNAME discovery only ever saw stale hostnames; random replacement
  gives representative coverage at bounded memory (same fix as the prober).

Verified live:
- all four known-public resources scan + index (DO, AWS s3-<region>, GCS,
  Azure container path), 38-1000 objects each.
- backfill of every CT-discovered 'reachable' asset (725) and 'auth_required'
  (12) completed with 0 listable: those are MRAP/non-bucket 400s and
  list-denied buckets, confirming the checks are actually running.
This commit is contained in:
StasonJatham committed 2026-09-22 15:09:34 +02:00
1 parent 62a7d2eb2e
commit 171c9b37eb
6 files changed
+196 -57

No files matched your search

+23 -6
View File
@@ -8,9 +8,12 @@ import (
"embed"
"encoding/json"
"io/fs"
"log/slog"
"net/http"
"strconv"
"strings"
"sync/atomic"
"time"
"tea.karlcom.de/karl/bucketeer/internal/scan"
"tea.karlcom.de/karl/bucketeer/internal/store"
@@ -111,19 +114,33 @@ func New(s Store, cfg Config) http.Handler {
}
writeJSON(w, cfg.Scanner.Scan(r.Context(), target))
})
var backfillRunning atomic.Bool
mux.HandleFunc("/api/reprobe", func(w http.ResponseWriter, r *http.Request) {
if r.Method != http.MethodPost {
http.Error(w, "POST only", http.StatusMethodNotAllowed)
return
}
q := r.URL.Query()
limit, _ := strconv.Atoi(q.Get("limit"))
rep, err := cfg.Scanner.Backfill(r.Context(), strings.TrimSpace(q.Get("exposure")), limit)
if err != nil {
http.Error(w, err.Error(), http.StatusInternalServerError)
if !backfillRunning.CompareAndSwap(false, true) {
http.Error(w, "backfill already running", http.StatusConflict)
return
}
writeJSON(w, rep)
q := r.URL.Query()
limit, _ := strconv.Atoi(q.Get("limit"))
exposure := strings.TrimSpace(q.Get("exposure"))
go func() {
defer backfillRunning.Store(false)
start := time.Now()
rep, err := cfg.Scanner.Backfill(context.Background(), exposure, limit)
if err != nil {
slog.Warn("backfill failed", "event", "backfill", "error", err)
return
}
slog.Info("backfill complete", "event", "backfill", "exposure", exposure,
"probed", rep.Probed, "readable", rep.Readable, "listable", rep.Listable,
"indexed", rep.Indexed, "errors", rep.Errors, "took", time.Since(start).String())
}()
w.WriteHeader(http.StatusAccepted)
writeJSON(w, map[string]any{"started": true, "exposure": exposure, "limit": limit})
})
}
mux.HandleFunc("/api/stats", func(w http.ResponseWriter, r *http.Request) {