Hi list, Our current setup has OSDs with their journal sharing the same disk as the data, and we've reached the point we're outgrowing this setup. We're currently vacating disks in order to replace them with SSDs and recreate the OSD journals on the SSDs in a 5:1 ratio of spinners to SSDs. I've read in a few places that it's possible to move the OSD journals without losing data on the OSDs, which is great, however none of the stuff I've read seems to cover our case. We installed Ceph using ceph-deploy, putting the journals on the same disks. ceph-deploy doesn't populate a ceph.conf file fully, so we don't have e.g. individual OSD entries in there. If I'm understanding this correctly, the Ceph disks are automounted by udev rules from /lib/udev/rules.d/95-ceph-osd.rules, and this mounts the OSD disk (partition 1) then mounts the journal under /journal (partition 2 of the same disk). That's all well and good, but as I now want to move the journal, how do I go about telling Ceph where the new journals are located so they can be mounted in the right location? Do I need to populate ceph.conf with individual entries for all OSDs or is there a way I can make udev do all the heavy lifting? Regards Dane
 |