diff --git a/vectordb_bench/backend/runner/read_write_runner.py b/vectordb_bench/backend/runner/read_write_runner.py
index 4c7cb7cd..e4e7d0fc 100644
--- a/vectordb_bench/backend/runner/read_write_runner.py
+++ b/vectordb_bench/backend/runner/read_write_runner.py
@@ -83,19 +83,20 @@ def run_read_write(self):
     def run_search_by_sig(self, q):
         res = []
         total_batch = math.ceil(self.data_volume / self.insert_rate)
-        batch = 1
+        batch = 0
         recall = 'x'
 
         for idx, stage in enumerate(self.search_stage):
             target_batch = int(total_batch * stage)
             while q.get(block=True):
+                batch += 1
                 if batch >= target_batch:
                     perc = int(stage * 100)
                     log.info(f"Insert {perc}% done, total batch={total_batch}")
                     log.info(f"[{batch:5}/{total_batch}] Serial search - {perc}% start")
                     recall, ndcg, p99 =self.serial_search_runner.run()
 
-                    if idx < len(self.search_stage):
+                    if idx < len(self.search_stage) - 1:
                         stage_search_dur = (self.data_volume  * (self.search_stage[idx + 1] - stage) // self.insert_rate) // len(self.concurrencies)
                         if stage_search_dur < 30:
                             log.warning(f"Search duration too short, please reduce concurrency count or insert rate, or increase dataset volume: dur={stage_search_dur}, concurrencies={len(self.concurrencies)}, insert_rate={self.insert_rate}")
@@ -108,6 +109,4 @@ def run_search_by_sig(self, q):
                     max_qps = self.run_by_dur(stage_search_dur)
                     res.append((perc, max_qps, recall))
                     break
-
-                batch += 1
         return res