bugfix AS block leaks

Author: zccjjj

fastdeploy/engine/sched/resource_manager_v1.py

@@ -1070,9 +1070,12 @@ def _allocate_decode_and_extend():
                                     self.cache_manager.num_cpu_blocks > 0
                                     or self.config.cache_config.kvcache_storage_backend
                                 ):
-                                    if not self.cache_manager.can_allocate_gpu_blocks(
+                                    can_schedule_block_num_threshold = self._get_can_schedule_prefill_threshold_block(
                                         (request.need_prefill_tokens + self.config.cache_config.block_size - 1)
                                         // self.config.cache_config.block_size
+                                    )
+                                    if not self.cache_manager.can_allocate_gpu_blocks(
+                                        can_schedule_block_num_threshold
                                     ):  # to prevent block allocation for matching in hierarchical cache and cause dead lock
                                         break
                             success = self.get_prefix_cached_blocks(request)
@@ -1150,9 +1153,12 @@ def _allocate_decode_and_extend():
                                     self.cache_manager.num_cpu_blocks > 0
                                     or self.config.cache_config.kvcache_storage_backend
                                 ):
-                                    if not self.cache_manager.can_allocate_gpu_blocks(
+                                    can_schedule_block_num_threshold = self._get_can_schedule_prefill_threshold_block(
                                         (request.need_prefill_tokens + self.config.cache_config.block_size - 1)
                                         // self.config.cache_config.block_size
+                                    )
+                                    if not self.cache_manager.can_allocate_gpu_blocks(
+                                        can_schedule_block_num_threshold
                                     ):  # to prevent block allocation for matching in hierarchical cache and cause dead lock
                                         break
                             success = self.get_prefix_cached_blocks(request)
@@ -1196,6 +1202,7 @@ def _allocate_decode_and_extend():
                                 )
                             request.status = RequestStatus.RUNNING_PREFILL
                         else:
+                            # Warnig: _free_blocks before update_cache_blocks may cause storage blocks leak
                             if self.config.cache_config.enable_prefix_caching:
                                 self._free_blocks(request)
                             break