[Gluster-users] Solaris 10 client NFS performance very poor
Dan Bretherton
d.a.bretherton at reading.ac.uk
Mon Jul 16 19:33:18 UTC 2012
Hello Avati,
Thanks for your quick response. I had planned to upgrade to 3.3 at some
point, mainly to take advantage of the NFS memory leak fix.
I am worried about upgrading after bad experiences with 3.1.0 and
3.2.0. Does anyone have any experience of upgrading from 3.2.6 to 3.3.0?
-Dan.
On 07/16/2012 08:21 PM, Anand Avati wrote:
> There were a lot of changes in NFS filehandle management in 3.3.0. Can
> you check if these performance issue has been addressed with those
> changes?
>
> Avati
>
> On Mon, Jul 16, 2012 at 11:42 AM, Dan Bretherton
> <d.a.bretherton at reading.ac.uk <mailto:d.a.bretherton at reading.ac.uk>>
> wrote:
>
> Dear All,
> I am having a lot of trouble accessing GlusterFS 3.2.6 volumes
> from Solaris 10 NFS clients. Volumes can be mounted but I/O
> performance is so poor that the volumes are practically unusable.
> Doing cd or ls can take a very long time and often hangs, with
> repeated errors like the following.
>
> mars etc # cd /users/rle
> NFS server glusterfs not responding still trying
> NFS server glusterfs ok
>
> I am using the mount options recommended in the GlusterFS 3.2
> Administration Guide. I also tried adding mount options
> rsize=32768,wsize=32768 but it didn't seem to make any difference.
> These are fixed mounts; automount doesn't work at all with
> GlusterFS volumes on Solaris 10. I have no performance problems
> with my Linux NFS clients. Can anyone suggest a way to improve
> GlusterFS access from Solaris 10?
>
> Regards,
> Dan.
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org <mailto: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/20120716/b34575ef/attachment.html>
More information about the Gluster-users
mailing list