On 25 January 2018 at 04:53, Warren Wang <Warren.Wang@xxxxxxxxxxx> wrote: > The other thing I can think of is if you have OSDs locking up and getting corrupted, there is a severe XFS bug where the kernel will throw a NULL pointer dereference under heavy memory pressure. Again, it's due to memory issues, but you will see the message in your kernel logs. I think that's the one I was thinking of too - IIRC it only happens with larger XFS block sizes though, at some point it must have been default or recommended to use "-n size=64k" with Ceph on filesystem creation. We first hit that whilst my whole team was sitting in the keynotes of the OpenStack Summit in Sydney... good times o_0. -- Cheers, ~Blairo _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |