Can you share the rebalance mount point log file (something like
'etc-glusterd-mount-<VOL>.log') ? Also letting us know about your
glusterfs
version will also help.
Btw, rebalance is a 'entry' based operation and not size based (yes size
too
matters for the files which are supposed to be rebalanced), as the rebalance
thread will traverse through the whole volume checking if the file has to be
migrated.
Regards,
Amar
On Tue, Aug 23, 2011 at 4:12 AM, Joseph <zm.joyride at gmail.com> wrote:
> Hi,
>
> I ran the gluster volume rebalance command after add more bricks to the
> exist volume.
> The existing data is about 3T.
>
> However, the rebalance failed after running for a day, while still in
"fix
> layout" stage,
> and it continue to fail a few times after I manually start rebalance
> again.....
>
> Do you have any idea how to fix that?
>
> Thanks
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://gluster.org/cgi-bin/mailman/listinfo/gluster-users
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://supercolony.gluster.org/pipermail/gluster-users/attachments/20110825/8055496a/attachment.html>