> > A disk partition should be accessed through the same posix-locks > subvolume. That is the condition to be met. This restriction is so > that processes use the same locking translator. > Perhaps the VM, if it can access the host machine partition, will use the locking translator automatically via host FUSE? > > Can a virtual machine mount a partition that is already mounted by a > host OS? Any idea? I think we should ask the list about this. Xen can, but I'm not so sure about OpenVZ. The main benefit for this approach I think, will be saving the localhost routing done by host machine, which would translate to saving CPU cycles. -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://zresearch.com/pipermail/gluster-users/attachments/20090309/0df6072c/attachment.htm>
