szha commented on a change in pull request #12572: Make Gluon download function
to be atomic
URL: https://github.com/apache/incubator-mxnet/pull/12572#discussion_r218485916
##########
File path: python/mxnet/gluon/utils.py
##########
@@ -242,23 +280,35 @@ def download(url, path=None, overwrite=False,
sha1_hash=None, retries=5, verify_
dirname = os.path.dirname(os.path.abspath(os.path.expanduser(fname)))
if not os.path.exists(dirname):
os.makedirs(dirname)
- while retries+1 > 0:
+ while retries + 1 > 0:
# Disable pyling too broad Exception
# pylint: disable=W0703
try:
- print('Downloading %s from %s...'%(fname, url))
+ print('Downloading {} from {}...'.format(fname, url))
r = requests.get(url, stream=True, verify=verify_ssl)
if r.status_code != 200:
- raise RuntimeError("Failed downloading url %s"%url)
- with open(fname, 'wb') as f:
+ raise RuntimeError('Failed downloading url {}'.format(url))
+ # create uuid for temporary files
+ random_uuid = str(uuid.uuid4())
+ with open('{}.{}'.format(fname, random_uuid), 'wb') as f:
for chunk in r.iter_content(chunk_size=1024):
if chunk: # filter out keep-alive new chunks
f.write(chunk)
+ # if the target file exists(created by other processes),
+ # delete the temporary file
+ if os.path.exists(fname):
Review comment:
check for file hash too, as the existing file might be an aborted incomplete
download.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
With regards,
Apache Git Services
