Project

General

Profile

Actions
Copy link

Bug #18240

closed

Deep scrub errors running cephfs kernel client on jewel

Added by John Spray over 7 years ago. Updated over 6 years ago.

Status:
Can't reproduce
Priority:
High
Assignee:
-
Category:
Correctness/Safety
Target version:
-
% Done:

0%

Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Component(RADOS):
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

I have no idea why this is showing up in kcephfs and knfs tests but not on rados tests. The good news is that at least it's confined to jewel, apparently whatever is going on here is already fixed in master.

http://pulpito.ceph.com/teuthology-2016-12-11_10:20:02-kcephfs-jewel-testing-basic-smithi/625644/


    "2016-12-12 15:29:22.634332 osd.3 172.21.15.38:6800/13355 2 : cluster [ERR]
    deep-scrub 2.3 2:dfd961c9:::100000000aa.00000000:head on disk size
    (3737294) does not match object info size (4149248) adjusted for ondisk to
    (4149248)" in cluster log

http://pulpito.ceph.com/teuthology-2016-12-07_10:20:02-kcephfs-jewel-testing-basic-smithi/613726/
http://pulpito.ceph.com/teuthology-2016-12-07_10:20:02-kcephfs-jewel-testing-basic-smithi/613709/
http://pulpito.ceph.com/teuthology-2016-12-07_10:20:02-kcephfs-jewel-testing-basic-smithi/613708/

Actions
Copy link

Also available in: Atom PDF