Hi Sage, a couple of months ago (maybe last year) I was able to change the assignment of Directorlies and Files of CephFS to different pools back and forth (with cephfs set_layout as well as with setfattr). Now (with ceph v0.81 and Kernel 3.10 an the client side) neither 'cephfs set_layout' nor 'setfattr' works anymore: # mount | grep ceph ceph-fuse on /mnt/ceph-fuse type fuse.ceph-fuse (rw,nosuid,nodev,allow_other,default_permissions) 192.168.113.52:6789:/ on /mnt/cephfs type ceph (name=admin,key=client.admin) # ls -l /mnt/cephfs total 0 -rw-r--r-- 1 root root 0 Aug 18 21:06 file -rw-r--r-- 1 root root 0 Aug 18 21:10 file2 -rw-r--r-- 1 root root 0 Aug 18 21:11 file3 drwxr-xr-x 1 root root 0 Aug 18 20:54 sas-r2 drwxr-xr-x 1 root root 0 Aug 18 20:54 ssd-r2 # getfattr -d -m - /mnt/cephfs getfattr: Removing leading '/' from absolute path names # file: mnt/cephfs ceph.dir.entries="5" ceph.dir.files="3" ceph.dir.layout="stripe_unit=4194304 stripe_count=1 object_size=4194304 pool=SAS-r2" ceph.dir.rbytes="0" ceph.dir.rctime="0.090" ceph.dir.rentries="1" ceph.dir.rfiles="0" ceph.dir.rsubdirs="1" ceph.dir.subdirs="2" # setfattr -n ceph.dir.layout.pool -v SSD-r2 /mnt/cephfs setfattr: /mnt/cephfs: Invalid argument # ceph osd dump | grep pool pool 0 'data' replicated size 3 min_size 2 crush_ruleset 0 object_hash rjenkins pg_num 8064 pgp_num 8064 last_change 1 flags hashpspool crash_replay_interval 45 stripe_width 0 pool 1 'metadata' replicated size 3 min_size 2 crush_ruleset 0 object_hash rjenkins pg_num 8064 pgp_num 8064 last_change 1 flags hashpspool stripe_width 0 pool 2 'rbd' replicated size 3 min_size 2 crush_ruleset 0 object_hash rjenkins pg_num 8064 pgp_num 8064 last_change 1 flags hashpspool stripe_width 0 pool 3 'SSD-r2' replicated size 2 min_size 2 crush_ruleset 3 object_hash rjenkins pg_num 6000 pgp_num 6000 last_change 404 flags hashpspool stripe_width 0 pool 4 'SAS-r2' replicated size 2 min_size 2 crush_ruleset 4 object_hash rjenkins pg_num 6000 pgp_num 6000 last_change 408 flags hashpspool stripe_width 0 pool 5 'SSD-r3' replicated size 3 min_size 2 crush_ruleset 3 object_hash rjenkins pg_num 4000 pgp_num 4000 last_change 413 flags hashpspool stripe_width 0 pool 6 'SAS-r3' replicated size 3 min_size 2 crush_ruleset 4 object_hash rjenkins pg_num 4000 pgp_num 4000 last_change 416 flags hashpspool stripe_width 0 # getfattr -d -m - /mnt/cephfs/ssd-r2 getfattr: Removing leading '/' from absolute path names # file: mnt/cephfs/ssd-r2 ceph.dir.entries="0" ceph.dir.files="0" ceph.dir.rbytes="0" ceph.dir.rctime="0.090" ceph.dir.rentries="1" ceph.dir.rfiles="0" ceph.dir.rsubdirs="1" # setfattr -n ceph.dir.layout.pool -v SSD-r2 /mnt/cephfs/ssd-r2 setfattr: /mnt/cephfs/ssd-r2: Invalid argument # cephfs /mnt/cephfs/ssd-r2 set_layout -p 3 -s 4194304 -u 4194304 -c 1 Error setting layout: (22) Invalid argument Any recommendations ? Is this a bug, or a new feature ? Do I have to use a newer Kernel ? Kind Regards, -Dieter On Sat, Aug 31, 2013 at 02:26:48AM +0200, Sage Weil wrote: > On Fri, 30 Aug 2013, Joao Pedras wrote: > > > > Greetings all! > > > > I am bumping into a small issue and I am wondering if someone has any > > insight on it. > > > > I am trying to use a pool other than 'data' for cephfs. Said pool has id #3 > > and I have run 'ceph mds add_data_pool 3'. > > > > After mounting cephfs seg faults when trying to set the layout: > > > > $> cephfs /path set_layout -p 3 > > > > Segmentation fault > > > > Actually plainly running 'cephfs /path set_layout' without more options will > > seg fault as well. > > > > Version is 0.61.8 on ubuntu 12.04. > > > > A question that comes to mind here is if there is a way of accomplishing > > this when using ceph-fuse (<3.x kernels). > > You can adjust this more easily using the xattr interface: > > getfattr -n ceph.dir.layout <dir> > setfattr -n ceph.dir.layout.pool -v mypool > getfattr -n ceph.dir.layout <dir> > > The interface tests are probably a decent reference given this isn't > explicitly documented anywhere: > > https://github.com/ceph/ceph/blob/master/qa/workunits/misc/layout_vxattrs.sh > > sage > _______________________________________________ > ceph-users mailing list > ceph-users at lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |