Actions
Bug #15858
closedapparent scrub reservation leak
Status:
Can't reproduce
Priority:
Urgent
Assignee:
-
Category:
-
Target version:
-
% Done:
0%
Source:
other
Tags:
lrc
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
On osd.62 on the long running teuthology cluster, it seems that a reservation got stuck preventing a scrub on pg 0.bd3 from running. No apparent evidence from the remaining logs about how it happened (pending scrubs seems to have been 1 since the oldest log, so the leak happened before that).
Some things that may be interesting:
- manual scrubs and repairs were run to fix some inconsistent pgs
- there was a rebalance
Updated by Samuel Just almost 8 years ago
Marking osd.62 down (not stopping the process, just running ceph osd down 62) unblocked the scrub. Whatever it was was not strictly speaking a leak, the scrub reservation process must have stalled somehow?
Updated by Samuel Just over 7 years ago
- Status changed from New to Can't reproduce
Actions