Ok, thanks for the detailed answer, I already assumed so. But how do the OSD's then find their mon's? I believe this again has to be in ceph.conf, right? wogri -- http://www.wogri.at On Oct 9, 2013, at 21:36 , Gregory Farnum <greg@xxxxxxxxxxx> wrote: > Previously the Ceph startup scripts required an enumeration of the > daemons in the ceph.conf in order to start them. We've been doing a > lot of incremental work since last October or so to make the system do > more self-bootstrapping, and by the time we released Dumpling that got > far enough to be used as the default configuration system (although it > wasn't only for Dumpling). > Now all the startup scripts will look in the default paths (or those > specified by a ceph.conf in /etc/ceph, I believe) for anything that > "looks like" a daemon, and start them up if they're present. This was > the natural evolution of doing things like setting up udev rules that > automatically ran any OSDs that have been created on a freshly > plugged-in disk (which is how all the ceph-disk-[prepare|activate] > stuff works). > In general we find that this is easier to maintain since users are > less likely to have conflicting ceph.confs across multiple nodes, and > it doesn't present the illusion that a monolithic config file is > necessary — but you are of course free to do otherwise if you prefer! > -Greg > Software Engineer #42 @ http://inktank.com | http://ceph.com > > > On Wed, Oct 9, 2013 at 12:30 PM, Wolfgang Hennerbichler <wogri@xxxxxxxxx> wrote: >> I would also love to see this answered, this is sometimes asked during my geek on duty shift and I don't know a real answer to this, and I myself always do it old-(bobtail)-style. >> >> Wolfgang >> -- >> http://www.wogri.at >> >> On Oct 9, 2013, at 13:54 , su kucherova <su.kucherova@xxxxxxxxx> wrote: >> >>> Hi >>> >>> When I compare the /etc/ceph.conf for the latest release-dumpling and previous releases I find they are different. >>> >>> in the older release we had [osd],[mon],[msd] in the ceph.conf >>> now i dont seem them.Where are these values stored now? >>> How does ceph figure out the partitions of osd and journal >>> >>> Thanks >>> Su >>> _______________________________________________ >>> ceph-users mailing list >>> ceph-users@xxxxxxxxxxxxxx >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users@xxxxxxxxxxxxxx >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |