some supplement: #2:ceph support heterogeneous nodes. #3.I think if you add an OSD by hand,you should set the `osd crush reweigth` to 0 first and then increase it to suit the disk size.and degrade the priority , thread of recover and backfill.just like this: osd_max_backfills 1 osd_recovery_max_active 1 osd_backfill_scan_min = 4 osd_backfill_scan_max = 32 osd recovery threads = 1 osd recovery op priority = 1 This ensures that in the process of adding nodes the cluster still maintain good performance when the data recovery. 2016-04-09 20:53 GMT+08:00 <ceph@xxxxxxxxxxxxxx>: > Without knowing proxmox specific stuff .. > > #1: just create an OSD the regular way > #2: it is safe; However, you may, either create a spoof > (osd_crush_chooseleaf_type = 0), or underuse your cluster > (osd_crush_chooseleaf_type = 1) > > On 09/04/2016 14:39, Mad Th wrote: >> We have a 3 node proxmox/ceph cluster ... each with 4 x4 TB disks >> >> 1) If we want to add more disks , what are the things that we need to be >> careful about? >> >> >> Will the following steps automatically add it to ceph.conf? >> ceph-disk zap /dev/sd[X] >> pveceph createosd /dev/sd[X] -journal_dev /dev/sd[Y] >> >> where X is new disk and Y is the journal disk. >> >> 2) Is it safe to run different number of OSDs in the cluster, say one >> server with 5 OSD and other two servers with 4OSD ? Though we have plan to >> add one OSD to each server. >> >> >> 3) How do we safely add the new OSD to an existing storage pool? >> >> >> >> _______________________________________________ >> 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
 |