I think option 2 should be reliable. On Wed, Jul 29, 2015 at 9:00 PM, Kenneth Waegeman <kenneth.waegeman@xxxxxxxx> wrote: > Hi all, > > We are considering to migrate all our OSDs of our EC pool from KeyValue to > Filestore. Does someone has experience with this? What would be a good > procedure? > > We have Erasure Code using k+m: 10+3, with host-level failure domain on 14 > servers. Our pool is 30% filled. > > I was thinking: > We set the weight of 1/2 of the OSDS on each host to 0 and let the cluster > migrate the data > We then remove these OSDS, and re-add them > We do then the same with the other OSDS > (Or we do it in 3 times with 1/3 of the OSDS) > > Another option: > We repeatedly; > Remove all KV OSDS of 2 servers (m=3) > Re-add all those OSDS with filestore > Wait for data to rebalance > > Does someone know what would be the best way? Are there things we should not > forget or be careful with ? > > Thank you very much! > > Kenneth > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com -- Best Regards, Wheat _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com