Tom Verdaat пишет: > 3. Is anybody doing this already and willing to share their experience? Relative yes. Before ceph I was use drbd+ocfs2 (with o2cb stack), now both this servers are inside of VM's with same ocfs2. There are same like over drbd, but just remeber to turn rbd cache to "off" (RTFM). I just not solve (while?) problem with VMs reboot on ceph hard works (one of nodes restart or just recovery, even if size=3 on 3 nodes - data is ready). IMHO there are OCFS2 internal heartbeat (heartbeat=local) problem, but there are just my IMHO. I will make tests about this problem soon. But, even in case of reboot or killing qemu - OCFS2 still clean (usually nothing fixed by fsck), so data integrity is good. I not trying GFS2, but this considered slower then OCFS2. Also GFS2 is "too RedHat's" - there absent in some of distros and hard to install [userspace] self via large number of dependences. OCFS2 also present in 2 ways: O2CB stack (internal) and user stack. O2CB is good, kernel-side, but have no byte range locking feature. User stack have byte range locking - over userspace support, but required many userspace stuff too (present at least in Oracle linux or SuSE, but I use Gentoo and simple heartbeat, no corosync, so I don't want to work too much). So, if you need no byte-range locking, I suggest to use OCFS2 with simple O2CB stack. -- WBR, Dzianis Kahanovich AKA Denis Kaganovich, http://mahatma.bspu.unibel.by/ _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |