[Gluster-devel] 3.4.0alpha3 performances

[Anand Avati]

On Tue, May 7, 2013 at 8:17 PM, Emmanuel Dreyfus <manu at netbsd.org> wrote:

> Anand Avati <anand.avati at gmail.com> wrote:
>
> > Just _ONE_ fxattrop took 64 SECONDS to complete?? Are you certain
> > hangar:/export/wd3a
> > is on healthy hardware?
>
> I get the same kind of lattency issue on all bricks. How can I track the
> probmemdown further?
>
>
I'm wondering if this is because of the fsync() patch in AFR. Can you check
if you are seeing similar perf fluctuations in a non-replicated volume?

Avati
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-devel/attachments/20130507/a082b431/attachment-0001.html>