Actions
Bug #141
closedERESTARTSYS on mds update operations cause bad results
% Done:
0%
Source:
Tags:
Backport:
Regression:
Severity:
Reviewed:
Affected Versions:
ceph-qa-suite:
Crash signature (v1):
Crash signature (v2):
Description
- process does a create
- gets signal and returns ERESTARTSYS before reply comes back
- kernel retries the operation
- original request completes
- new request gets EEXIST or similar bad result
Can we tell which signal is pending? If so, how do we clear the pending signal and continue ourselves?
Or do we drop the ability to abort mds requests?
Updated by Greg Farnum almost 14 years ago
It seems pretty important to me that users be able to abort MDS requests -- if for some reason part of the filesystem goes down you don't want your local machine to be stuck waiting for it for an unknown length of time!
Updated by Yehuda Sadeh almost 14 years ago
I assume that switching to wait_for_completion_killable() fixed this one?
related commit: 0ec773c7f9ecbff4b75c3c6897f2a95787e06c34
Actions