That is the expected behavior. RBD is emulating a real device, you wouldn't expect good things to happen if you were to plug the same drive into two different machines at once (perhaps with some soldering). There is no built in mechanism for two machines to access the same block device concurrently, you would need to add a bunch of extra stuff in the same way that ocfs or gfs has. CephFS on the other hand is a parallel filesystem designed for multiple concurrent client access and does have such mechanisms (with limits, read the docs).
On May 1, 2013, at 11:19 AM, Yudong Guang <guangyudongb...@gmail.com> wrote: > Hi, > > I've been trying to use block device recently. I have a running cluster with > 2 machines and 3 OSDs. > > On a client machine, let's say A, I created a rbd image using `rbd create` , > then formatted, mounted and wrote something in it, everything was working > fine. > > However, problem occurred when I tried to use this image on the other client, > let's say B, on which I mapped the same image that created on A. I found that > any changes I made on any of them cannot be shown on the other client, but if > I unmap the device and then map again, the changes will be shown. > > I tested the same thing with ceph fs, but there was no such problem. Every > change made on one client can be shown on the other client instantly. > > I wonder whether this kind of behavior of RADOS block device is normal or > not. Is there any way that we can read and write on the same image on > multiple clients? > > Any idea is appreciated. > > Thanks > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
