Bug #1984
osd: failed assert, got into finish_recovery_ops without any recovery ops active?
Source:
Tags:
Backport:
Regression:
No
Severity:
3 - minor
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):
Description
osd/PG.cc: In function 'void PG::finish_recovery_op(const hobject_t&, bool)', in thread '7f1fdab26700'
osd/PG.cc: 1553: FAILED assert(recovery_ops_active > 0)
ceph version 0.40-206-g6c275c8 (6c275c8195a8ae04e8a492d043fa6dfd60cecd82)
1: (PG::finish_recovery_op(hobject_t const&, bool)+0xfc) [0x678e1c]
2: (ReplicatedPG::do_backfill(MOSDPGBackfill*)+0x6d7) [0x4e4b37]
3: (OSD::dequeue_op(PG*)+0x2bc) [0x574bbc]
4: (ThreadPool::worker()+0x6e6) [0x62cec6]
5: (ThreadPool::WorkThread::entry()+0xd) [0x59341d]
6: (()+0x6d8c) [0x7f1fe9103d8c]
7: (clone()+0x6d) [0x7f1fe774004d]
From Martin, on the mailing list, with a log.
History
#2 Updated by Sage Weil almost 12 years ago
- Assignee set to Sage Weil
#3 Updated by Sage Weil almost 12 years ago
Hmm, we still haven't seen this in our thrashing in qa. I'll start thrashing on some of the new hardware.
#4 Updated by Sage Weil almost 12 years ago
- Status changed from New to Can't reproduce