Skip to content

[https://nvbugs/6115560][fix] catch OSError in config_file_lock for NFS compatibility #11960

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

Merged
chang-l merged 2 commits into from
May 28, 2026
Merged

[https://nvbugs/6115560][fix] catch OSError in config_file_lock for NFS compatibility #11960

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a44604b
fix: catch OSError in config_file_lock for NFS compatibility
sara4dev Mar 5, 2026
fd6ccbc
[https://nvbugs/6115560][fix] narrow OSError catch to lock-related er…
chang-l May 23, 2026
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
17 changes: 14 additions & 3 deletions tensorrt_llm/_torch/model_config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
import contextlib
import errno
import json
import os
import tempfile
Expand Down Expand Up @@ -86,8 +87,14 @@ def config_file_lock(timeout: int = 10):
try:
with lock:
yield
except (PermissionError, filelock.Timeout):
# Fallback to tempdir
except (PermissionError, OSError, filelock.Timeout) as e:
# Fallback to tempdir when primary lock path is unusable (e.g.,
# NFS locking failures like ENOLCK/ESTALE, permission issues,
# or lock acquisition timeouts)
if isinstance(e,
OSError) and e.errno not in (errno.EACCES, errno.EPERM,
errno.ENOLCK, errno.ESTALE):
raise
tmp_dir = Path(tempfile.gettempdir())
tmp_dir.mkdir(parents=True, exist_ok=True)
tmp_lock_path = tmp_dir / "_remote_code.lock"
Expand All @@ -101,7 +108,11 @@ def config_file_lock(timeout: int = 10):
)
# proceed without lock
yield
except (PermissionError) as e:
except (PermissionError, OSError) as e:
if isinstance(
e, OSError) and e.errno not in (errno.EACCES, errno.EPERM,
errno.ENOLCK, errno.ESTALE):
raise
logger.warning(
f"tempdir config lock unavailable due to OS/permission issue: {e}, proceeding without lock"
)
Expand Down
Loading