Ceph

01/08/2024

07:31 PM Ceph Bug #63966 (New): deleting snapshot from disk with unfinished migration causes corruption / qemu crash

we've discovered scenario in which data can get corrupted (and VM using RBD volume crashes).
steps to reproduce:
... Nikola Ciprich

11/10/2023

07:45 AM Ceph Bug #63503 (New): data corruption after rbd migration

we're struggling with strange issue which I think might be a bug
causing snapshot data corruption while migrating RB... Nikola Ciprich

03/08/2023

07:56 PM RADOS Bug #56896: crash: int OSD::shutdown(): assert(end_time - start_time_func < cct->_conf->osd_fast_shutdown_timeout)

Hi, just reporting, that I just hit this problem on few OSDs in 17.2.5 Nikola Ciprich

04/29/2022

07:54 AM Ceph Bug #55494: krbd - crash in 5.4.173 (octopus 14.2.22)

sorry, I mean't nautilus, not octopus.. Nikola Ciprich

07:41 AM Ceph Bug #55494 (New): krbd - crash in 5.4.173 (octopus 14.2.22)

Hi, while prefilling krbd mapped volume using dd, I got kernel panic (backtrace attached)
I haven't found similar me... Nikola Ciprich

03/29/2021

05:36 AM RADOS Bug #50032 (New): used space in ceph df reported incorrectly for filestore OSDs

Hi, I noticed, that when filestore OSDs are used, used space is reported incorrectly:
filestore:
POOL ... Nikola Ciprich

02/27/2021

06:55 PM mgr Bug #49535 (Duplicate): nautilus: mgr/balancer: KeyError messages in balancer module

we've encountered balancer crashes on one of our clusters. I wonder if it might be caused by filestore OSD, since it'... Nikola Ciprich

08/05/2020

01:41 PM mgr Bug #42721: mgr/balancer: KeyError messages in balancer module

got it, this other problem was caused by empty buckets:
-28 0 host vfnjazv1-ssd-test ... Nikola Ciprich

06/24/2020

04:38 AM rbd Bug #45986: importing rbd diff does not apply zero sequences correctly

you're right, I was setting this using ceph config set osd ..., but this is apparently not the right way to do it.. w... Nikola Ciprich

06/18/2020

08:24 AM rbd Bug #45986: importing rbd diff does not apply zero sequences correctly

one more update, after disabling rbd_skip_partial_discard (and restarting OSDs) I'm still able to reproduce the probl... Nikola Ciprich