Skip to content

Fix: get_stats blocks main thread on storage failure #13550

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
UranusSeven wants to merge 2 commits into from
Closed

Fix: get_stats blocks main thread on storage failure #13550

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
020b343
Fix: avoid blocking main thread on hicache get_stats
UranusSeven Nov 17, 2025
94d8053
Merge branch 'main' into get_stats_blocks_main_thread_on_storage_failure
UranusSeven Nov 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion python/sglang/srt/mem_cache/hicache_storage.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@

import torch

from python.sglang.srt.metrics.collector import StorageMetrics
from sglang.srt.mem_cache.memory_pool_host import HostKVCache

logger = logging.getLogger(__name__)
Expand Down Expand Up @@ -162,7 +163,7 @@ def batch_exists(
def clear(self) -> None:
pass

def get_stats(self):
def get_stats(self) -> Optional[StorageMetrics]:
return None


Expand Down
30 changes: 18 additions & 12 deletions python/sglang/srt/mem_cache/storage/hf3fs/storage_hf3fs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -486,18 +486,24 @@ def close(self) -> None:
logger.error(f"close HiCacheHF3FS: {e}")
logger.info("close HiCacheHF3FS")

@synchronized()
def get_stats(self):
storage_metrics = StorageMetrics()
storage_metrics.prefetch_pgs.extend(self.prefetch_pgs)
storage_metrics.backup_pgs.extend(self.backup_pgs)
storage_metrics.prefetch_bandwidth.extend(self.prefetch_bandwidth)
storage_metrics.backup_bandwidth.extend(self.backup_bandwidth)
self.prefetch_pgs.clear()
self.backup_pgs.clear()
self.prefetch_bandwidth.clear()
self.backup_bandwidth.clear()
return storage_metrics
def get_stats(self) -> Optional[StorageMetrics]:
# Acquire lock without blocking
if not self.lock.acquire(blocking=False):
return None

try:
storage_metrics = StorageMetrics()
storage_metrics.prefetch_pgs.extend(self.prefetch_pgs)
storage_metrics.backup_pgs.extend(self.backup_pgs)
storage_metrics.prefetch_bandwidth.extend(self.prefetch_bandwidth)
storage_metrics.backup_bandwidth.extend(self.backup_bandwidth)
self.prefetch_pgs.clear()
self.backup_pgs.clear()
self.prefetch_bandwidth.clear()
self.backup_bandwidth.clear()
return storage_metrics
finally:
self.lock.release()

def register_mem_pool_host(self, mem_pool_host: HostKVCache):
super().register_mem_pool_host(mem_pool_host)
Expand Down
Loading