[Gluster-users] Gluster vs NFS export sync

Franco Broi franco.broi at iongeo.com
Fri Jul 11 02:16:52 UTC 2014


On Thu, 2014-07-10 at 21:02 -0400, James wrote: 
> On Thu, Jul 10, 2014 at 8:40 PM, Franco Broi <franco.broi at iongeo.com> wrote:
> > Is there any way to make Gluster emulate the behaviour of a NFS
> > filesystem exported with the sync option? By that I mean is it possible
> > to write a file from one client and guarantee that the data will be
> > instantly available on close to all other clients?
> 
> 
> Gluster native writes are already synchronous.

On my Gluster system if I open, write, fsync and close a file from one
client and very soon after try to open the file on another client, the
data written by the first client may or may not be there. This is the
same behaviour as for NFS disks exported async and is not unexpected.

If I repeat the test on NFS disks exported sync, the second node always
immediately sees the data written by the first. The problem is, I have a
an application which depends on this behaviour.





More information about the Gluster-users mailing list