On Mon, 17 Sep 2012 12:13:07 +0930, Vladimir Bashkirtsev <vladimir@xxxxxxxxxxxxxxx> wrote: > Dear devs, > > We just had an incident where two instances of the same VM started up > on different hosts and mounted the same RBD image. Image had ext4 > partition and it became corrupted quickly. Therefore it would be good > to have some setting in RBD info like max_simultaneous_mounts which > will dictate how many simultaneous mounts of the same RBD image may be > in existence. Obviously such glusterfs would not have such issue in > RBD image but old trusty extfs fails miserably. It may be hard to > implement in ceph due to distributed nature. Then basic check in > QEMU-RBD driver would be good as well. > > Regards, > Vladimir This is what locking and fencing of rbd images is intended to address. The original discussion: http://comments.gmane.org/gmane.comp.file-systems.ceph.devel/7094 The current status: http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/9210 Josh -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
