On 8/30/22 09:51, Wissem MIMOUNA wrote:
Hi Stefan,
We don’t have automatic conversion going on , and the «
bluestore_fsck_quick_fix_on_mount » is not set .
So we did an offline compaction as suggested but this didn’t fix the
problem os osd crush .
In the meantime we are rebuilding all OSDs on the cluster and it seems
it improve the cluster overall performance and has removed the slow ops
, so far …
But still I can’t figure out why same OSDs may still encounter random
crush . Here below the last log from a crashed OSD :
We avoided Ceph on Ubuntu Bionic because of this bug [1] (glibc bug
caused deadlock in openvswitch). This might be completely unrelated to
the issue you are hitting, but maybe not. If you can consistently
reproduce this issue on a host, it might be worth to see if comment in
#15 [2] fixes the issue for you.
Gr. Stefan
[1]: https://bugs.launchpad.net/ubuntu/+source/openvswitch/+bug/1839592
[2]:
https://bugs.launchpad.net/ubuntu/+source/openvswitch/+bug/1839592/comments/15
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
