Project

General

Profile

Bug #38155

PG stuck in undersized+degraded+remapped+backfill_toofull+peered

Added by David Zafman about 4 years ago. Updated over 3 years ago.

Status:
Duplicate
Priority:
Normal
Assignee:
Category:
-
Target version:
-
% Done:

0%

Source:
Development
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

dzafman-2019-02-02_15:37:09-rados-wip-zafman-testing2-distro-basic-smithi/3542711

Something like this happened before and it was related to last_peering_reset. The PG 2.0 was the one with state undersized+degraded+remapped+backfill_toofull+peered at the end of the test.

2019-02-03 00:26:41.905 7fe32cd40700 20 osd.0 pg_epoch: 47 pg[2.0( v 43'1200 (43'1100,43'1200] local-lis/les=41/42 n=600 ec=23/23 lis/c 41/41 les/c/f 42/42/0 44/44/44) [0] r=0 lpr=44 pi=[41,44)/1 luod=0'0 crt=43'1200 lcod 43'1199 mlcod 0'0 peered mbc={}] set_last_peering_reset 47
2019-02-03 00:26:41.905 7fe32cd40700 20 osd.0 pg_epoch: 47 pg[2.0( v 43'1200 (43'1100,43'1200] local-lis/les=41/42 n=600 ec=23/23 lis/c 41/41 les/c/f 42/42/0 44/44/44) [0] r=0 lpr=47 pi=[41,44)/1 luod=0'0 crt=43'1200 lcod 43'1199 mlcod 0'0 peered mbc={}] set_last_peering_reset 47
2019-02-03 00:26:41.905 7fe32cd40700 10 osd.0 pg_epoch: 47 pg[2.0( v 43'1200 (43'1100,43'1200] local-lis/les=41/42 n=600 ec=23/23 lis/c 41/41 les/c/f 42/42/0 47/47/47) [1,0] r=1 lpr=47 pi=[41,47)/1 crt=43'1200 lcod 43'1199 unknown NOTIFY mbc={}] do_peering_event: epoch_sent: 46 epoch_requested: 46 MNotifyRec 2.0 from 1 notify: (query:46 sent:46 2.0( v 38'600 (38'500,38'600] local-lis/les=36/37 n=600 ec=23/23 lis/c 36/36 les/c/f 37/37/0 44/44/44)) features: 0x3ffddff8ffacffff ([36,43] intervals=([41,43] acting 0,2)) +create_info
2019-02-03 00:26:41.905 7fe32cd40700 10 osd.0 pg_epoch: 47 pg[2.0( v 43'1200 (43'1100,43'1200] local-lis/les=41/42 n=600 ec=23/23 lis/c 41/41 les/c/f 42/42/0 47/47/47) [1,0] r=1 lpr=47 pi=[41,47)/1 crt=43'1200 lcod 43'1199 unknown NOTIFY mbc={}] old_peering_msg reply_epoch 46 query_epoch 46 last_peering_reset 47

Related issues

Duplicates RADOS - Bug #24452: Backfill hangs in a test case in master not mimic Resolved 06/07/2018

History

#1 Updated by David Zafman about 4 years ago

  • Related to Bug #24452: Backfill hangs in a test case in master not mimic added

#2 Updated by David Zafman over 3 years ago

  • Duplicates Bug #24452: Backfill hangs in a test case in master not mimic added

#3 Updated by David Zafman over 3 years ago

  • Related to deleted (Bug #24452: Backfill hangs in a test case in master not mimic)

#4 Updated by David Zafman over 3 years ago

  • Status changed from New to Duplicate

I'm assuming that the fix for 24452 also fixed this issue. So marking duplicate.

Also available in: Atom PDF