全量同步测试增加download过程审计输出

scripts/manual_sync/README.md

@@ -21,8 +21,8 @@ They are meant for **hands-on validation / acceptance runs**, not for CI.
 - Writes:
   - run log
   - audit report JSON
-  - run meta JSON (includes durations)
-  - short summary Markdown (includes durations)
+  - run meta JSON (includes durations + download_stats)
+  - short summary Markdown (includes durations + download_stats)
   - RocksDB key statistics (`db_stats --exact`)
   - RRDP repo state dump (`rrdp_state_dump`)
 
@@ -35,6 +35,24 @@ They are meant for **hands-on validation / acceptance runs**, not for CI.
   - base vs delta report JSON
   - base vs delta `rrdp_state_dump` TSV
   - and includes a **duration comparison** (base vs delta) if the base meta JSON is available
+  - delta meta JSON includes download_stats copied from delta report JSON
+
+## Audit report fields (report.json)
+
+The `rpki` binary writes an audit report JSON with:
+
+- `format_version: 2`
+- `downloads`: per-download RRDP/rsync events (URI, timestamps, duration, ok/fail, error, bytes, objects stats)
+- `download_stats`: aggregate counters (by kind)
+
+These are useful for diagnosing why a run is slow (e.g. RRDP snapshot vs delta vs rsync fallback).
+
+## Meta fields (meta.json)
+
+The scripts generate `*_meta.json` next to `*_report.json` and include:
+
+- `durations_secs`: wall-clock duration breakdown for the script steps
+- `download_stats`: copied from `report_json.download_stats`
 
 ## Usage
 

scripts/manual_sync/delta_sync.sh

@@ -266,6 +266,7 @@ base_state = parse_rrdp_state_tsv(base_state_path)
 delta_state = parse_rrdp_state_tsv(delta_state_path)
 
 base_meta = load_optional_json(base_meta_path_s)
+download_stats = delta.get("download_stats") or {}
 delta_meta = {
   "recorded_at_utc": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
   "tal_url": os.environ["TAL_URL"],
@@ -283,6 +284,7 @@ delta_meta = {
     "rrdp_state_dump": int(os.environ["STATE_DURATION_S"]),
     "total_script": int(os.environ["TOTAL_DURATION_S"]),
   },
+  "download_stats": download_stats,
 }
 delta_meta_path.write_text(json.dumps(delta_meta, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
 

scripts/manual_sync/full_sync.sh

@@ -106,6 +106,7 @@ summary_path = Path(sys.argv[3])
 rep = json.loads(report_path.read_text(encoding="utf-8"))
 
 now = datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
+download_stats = rep.get("download_stats") or {}
 meta = {
   "recorded_at_utc": now,
   "tal_url": os.environ["TAL_URL"],
@@ -129,6 +130,7 @@ meta = {
     "aspas": len(rep["aspas"]),
     "audit_publication_points": len(rep["publication_points"]),
   },
+  "download_stats": download_stats,
 }
 
 meta_path.write_text(json.dumps(meta, ensure_ascii=False, indent=2) + "\n", encoding="utf-8")
@@ -153,6 +155,25 @@ for k,v in meta["durations_secs"].items():
   lines.append(f"| {k} | {v} |\\n")
 lines.append("\\n")
 
+lines.append("## Download Stats\\n\\n")
+lines.append("- raw events: `report_json.downloads`\\n")
+lines.append("- aggregated: `report_json.download_stats` (copied into meta.json)\\n\\n")
+
+def fmt_u(v):
+  if v is None:
+    return ""
+  return str(v)
+
+by_kind = download_stats.get("by_kind") or {}
+lines.append("| kind | ok | fail | duration_ms_total | bytes_total | objects_count_total | objects_bytes_total |\\n")
+lines.append("|---|---:|---:|---:|---:|---:|---:|\\n")
+for kind in sorted(by_kind.keys()):
+  st = by_kind[kind] or {}
+  lines.append(
+    f"| {kind} | {st.get('ok_total',0)} | {st.get('fail_total',0)} | {st.get('duration_ms_total',0)} | {fmt_u(st.get('bytes_total'))} | {fmt_u(st.get('objects_count_total'))} | {fmt_u(st.get('objects_bytes_total'))} |\\n"
+  )
+lines.append("\\n")
+
 summary_path.write_text("".join(lines), encoding="utf-8")
 print(summary_path)
 PY