Add a default timeout for filelock (#2391)

File lock operations did not have an associated timeout, which could
present problems when trying to debug an issue since nothing would be
logged if we could not acquire the lock and would wait forever.

Author: edevil

src/huggingface_hub/constants.py

@@ -49,6 +49,9 @@ def _as_int(value: Optional[str]) -> Optional[int]:
 SAFETENSORS_INDEX_FILE = "model.safetensors.index.json"
 SAFETENSORS_MAX_HEADER_LENGTH = 25_000_000
 
+# Timeout of aquiring file lock and logging the attempt
+FILELOCK_LOG_EVERY_SECONDS = 10
+
 # Git-related constants
 
 DEFAULT_REVISION = "main"

src/huggingface_hub/utils/_fixes.py

@@ -18,8 +18,13 @@
 from typing import Callable, Generator, Optional, Union
 
 import yaml
-from filelock import BaseFileLock, FileLock
+from filelock import BaseFileLock, FileLock, Timeout
 
+from .. import constants
+from . import logging
+
+
+logger = logging.get_logger(__name__)
 
 # Wrap `yaml.dump` to set `allow_unicode=True` by default.
 #
@@ -80,8 +85,14 @@ def _set_write_permission_and_retry(func, path, excinfo):
 @contextlib.contextmanager
 def WeakFileLock(lock_file: Union[str, Path]) -> Generator[BaseFileLock, None, None]:
     """A filelock that won't raise an exception if release fails."""
-    lock = FileLock(lock_file)
-    lock.acquire()
+    lock = FileLock(lock_file, timeout=constants.FILELOCK_LOG_EVERY_SECONDS)
+    while True:
+        try:
+            lock.acquire()
+        except Timeout:
+            logger.info("still waiting to acquire lock on %s", lock_file)
+        else:
+            break
 
     yield lock