Hi !
We are running a ceph 12.2.7 Cluster and use it for RBDs.
We have now a few new servers installed with Ubuntu 18.
The default kernel version is v4.15.0.
When we create a new rbd and map/xfs-format/mount it, everything looks fine.
But if we want to map/mount a rbd that has already data in it, it takes a
very long time (>5minutes) - sometimes to map, sometimes to mount it.
There seems to be a process taking 100% of a cpu core during that "hang":
3103 root 20 0 0 0 0 R 100.0 0.0 0:04.65
kworker/11:1
With the "ukuu" tool, we have tested some other kernel versions :
v4.16.18 - same behavior
v4.18.5 - same behavior
And then an older kernel :
4.4.152-0404152-generic - rbd map/mount/umount/unmap - looks fine !
In the ceph.conf there is the line "rbd default features = 3" already
(on all Servers).
Is there a need to further debug this, or did we miss some
parameter/feature that
needs to be set differently on newer Kernels ?
Br,
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
