Project

General

Profile

Actions
Copy link

Bug #1191

closed

FAILED assert(!missing.is_missing(soid))

Added by ar Fred almost 13 years ago. Updated almost 13 years ago.

Status:
Can't reproduce
Priority:
Normal
Assignee:
Samuel Just
Category:
-
Target version:
-
% Done:

0%

Source:
Tags:
Backport:
Regression:
Severity:
Reviewed:
Affected Versions:
ceph-qa-suite:
Pull request ID:
Crash signature (v1):
Crash signature (v2):

Description

In 30 seconds, that error happened on 4 out of 8 OSDs. This is with today's stable branch.

That happend after some btrfs related problems. I had to restart the whole cluster, ceph then took approx 5-10 minutes to reach the 100% active+clean, all OSDs up+in state. And then in a matter of seconds after ceph being up+repaired my osds started to crash one after the other.

osd/ReplicatedPG.cc: In function 'void ReplicatedPG::sub_op_modify(MOSDSubOp*)', in thread '0x7fb7b7da2700'
osd/ReplicatedPG.cc: 3058: FAILED assert(!missing.is_missing(soid))
 ceph version  (commit:)
 1: (ReplicatedPG::sub_op_modify(MOSDSubOp*)+0x8e2) [0x4bd5e2]
 2: (OSD::dequeue_op(PG*)+0x3a5) [0x51e4d5]
 3: (ThreadPool::worker()+0x2a6) [0x61a726]
 4: (ThreadPool::WorkThread::entry()+0xd) [0x539bcd]
 5: (()+0x6d8c) [0x7fb7c5e6fd8c]
 6: (clone()+0x6d) [0x7fb7c4abd04d]

This looks a lot like [[http://marc.info/?l=ceph-devel&m=129192415004110&w=2]]

I'm also attaching the osd log.

Files

osd.8.log (148 KB) osd.8.log ar Fred, 06/16/2011 08:02 AM
Actions
Copy link

Also available in: Atom PDF