Project

General

Profile

Actions

Bug #17704

closed

osd: leaked pg refs on shutdown

Added by tao ning over 7 years ago. Updated almost 7 years ago.

Status:
Resolved
Priority:
Normal
Assignee:
-
Category:
OSD
Target version:
-
% Done:

0%

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

Description

with Bug#7891

-26> 2016-10-24 14:51:51.945056 7f95c5cb7700 -1 osd.10 6192 pgid 7.21 has ref count of 2
-25> 2016-10-24 14:51:51.946411 7f95c5cb7700 -1 osd/OSD.cc: In function 'int OSD::shutdown()' thread 7f95c5cb7700 time 2016-10-24 14:51:51.945059
osd/OSD.cc: 2427: FAILED assert(0)
ceph version 9.2.1 (752b6a3020c3de74e07d2a8b4c5e48dab5a6b6fd)
1: (ceph::__ceph_assert_fail(char const*, char const*, int, char const*)+0x85) [0x7f95f39af0b5]
2: (OSD::shutdown()+0x16a5) [0x7f95f33e4265]
3: (OSD::handle_signal(int)+0x131) [0x7f95f33e48a1]
4: (SignalHandler::entry()+0x127) [0x7f95f38bab77]
5: (()+0x7dc5) [0x7f95f1a41dc5]
6: (clone()+0x6d) [0x7f95f02e828d]
NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.

environment:
-6 1.07396 root ssd
-5 0.35799 host node-110-ssd
11 0.35799 osd.11 up 1.00000 1.00000
-7 0.35799 host node-112-ssd
10 0.35799 osd.10 up 1.00000 1.00000
-8 0.35799 host node-111-ssd
9 0.35799 osd.9 up 1.00000 1.00000
-1 16.36395 root default
-2 5.45398 host node-111
0 1.81799 osd.0 down 0 1.00000
1 1.81799 osd.1 down 0 1.00000
2 1.81799 osd.2 up 1.00000 1.00000
-3 5.45499 host node-112
3 1.81799 osd.3 up 1.00000 1.00000
4 1.81799 osd.4 up 1.00000 1.00000
5 1.81799 osd.5 up 1.00000 1.00000
-4 5.45499 host node-110
6 1.81799 osd.6 down 0 1.00000
8 1.81799 osd.8 up 1.00000 1.00000
7 1.81799 osd.7 up 1.00000 1.00000

pool 7 'volumes_ssd' replicated size 3 min_size 2 crush_ruleset 1 object_hash rjenkins pg_num 128 pgp_num 128 last_change 6393 flags hashpspool,incomplete_clones tier_of 1 cache_mode writeback target_bytes 268435456000 hit_set bloom{false_positive_probability: 0.05, target_size: 0, seed: 0} 0s x0 stripe_width 0


Files

ceph-osd.10.log.rar (240 KB) ceph-osd.10.log.rar error log tao ning, 10/26/2016 03:10 AM

Related issues 1 (0 open1 closed)

Related to Ceph - Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'ResolvedGreg Farnum05/15/2017

Actions
Actions #1

Updated by huang jun over 7 years ago

do you got core dump file?
if yes, you can print the refs and see why did it leaked.

Actions #2

Updated by tao ning over 7 years ago

huang jun wrote:

do you got core dump file?
if yes, you can print the refs and see why did it leaked.

only find log
I feel the same as Bug#7891, it has not been resolved?

Actions #3

Updated by Casey Bodley almost 7 years ago

  • Related to Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2' added
Actions #4

Updated by Josh Durgin almost 7 years ago

  • Status changed from New to Resolved

There have been fixes for some causes of this like https://github.com/ceph/ceph/pull/15214. Please reopen if you see this again.

Actions

Also available in: Atom PDF