[ceph-users] Re: OSD stop and fails

2021-09-01 Thread Gregory Farnum
This is a new bug AFAICT, but it looks to be an issue in soft state/logic, not disk state. If you are seeing it frequently and can reproduce with "debug osd = 20" set, that would help track down what's going on. I've flagged it for the team but can't investigate it myself. -Greg On Wed, Sep 1,

[ceph-users] Re: OSD stop and fails

2021-08-30 Thread Amudhan P
Gregory, I have raised a ticket already. https://tracker.ceph.com/issues/52445 Amudhan On Tue, Aug 31, 2021 at 12:00 AM Gregory Farnum wrote: > Hmm, this ceph_assert hasn't shown up in my email before. It looks > like there may be a soft-state bug in Octopus. Can you file a ticket > at

[ceph-users] Re: OSD stop and fails

2021-08-30 Thread Gregory Farnum
Hmm, this ceph_assert hasn't shown up in my email before. It looks like there may be a soft-state bug in Octopus. Can you file a ticket at tracker.ceph.com with the bcaktrace and osd log file? We can direct that to the RADOS team to check out. -Greg On Sat, Aug 28, 2021 at 7:13 AM Amudhan P