Sounds like you want to explore the auto-in settings, which can prevent new OSDs from being automatically accepted into the cluster. Should turn up if you search ceph.com/docs. :) -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com
On Thu, Apr 10, 2014 at 1:45 PM, <cws...@physics.wisc.edu> wrote: > Hi All, > Is there a way to prepare the drives of multiple OSD and then bring them > into the CRUSH map all at once? > > Right now I'm using: > > ceph-deploy --overwrite-conf disk prepare --zap-disk $NODE:$DEV </dev/null > ceph-deploy disk activate $NODE:$DEV </dev/null > > and have noticed that each successive format gets slower and slower as the > other OSDs become active on the node. > > I'd hoped to keep the OSDs quiet so that the formats would proceed > quickly, then turn them all on at once. > > I've tried "ceph osd reweight osdnum 0" for the new OSDs and that appears > to keep them from being written. However, there are preexisting OSDs on > the node and they start churning like mad, slowing down the formats of the > other drives anyway. (Looks like my controller cannot actually handle all > drives at maximum usage.) > > Thanks for the help! > Chad. > > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
