<div dir="ltr"><div><div>May I suggest running: <a href="https://github.com/avati/perf-test/blob/master/perf-test.sh">https://github.com/avati/perf-test/blob/master/perf-test.sh</a><br></div>This has reasonable number of different workloads and it also gives out numbers.<br><br></div>We probably need to generate a report based on a baseline and the daily run so that we can take a look at it when the numbers don't look right.<br></div><div class="gmail_extra"><br><div class="gmail_quote">On Mon, Aug 29, 2016 at 5:55 PM, Nigel Babu <span dir="ltr"><<a href="mailto:nigelb@redhat.com" target="_blank">nigelb@redhat.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="HOEnZb"><div class="h5">On Mon, Aug 29, 2016 at 01:49:52PM +0200, Niels de Vos wrote:<br>
> On Mon, Aug 29, 2016 at 05:01:18PM +0530, Nigel Babu wrote:<br>
> > Hello folks,<br>
> ><br>
> > I've had chats with Manoj and Ambarish about performance testing and what we<br>
> > can do upstream. Niels today solved half my problem by pointing out that we can<br>
> > get physical nodes on CentOS CI. The general idea is to run iozone[1] and<br>
> > smallfile[2] on a fixed frequency for master (to begin with).<br>
> ><br>
> > Does this sound like a good idea? If so, read on.<br>
> ><br>
> > For this to happens a few things need to happen:<br>
> > * I'll need some help from a few people who can read the reports and coordinate<br>
> > fixes. That is, someone needs to "own" performance for upstream.<br>
> > * I need some help in generating the right reports so we can figure out if our<br>
> > performance went up or down.<br>
><br>
> The provisioning in the CentOS CI does not allow us to select certain<br>
> systems (yet). So you would get different performance results, depending<br>
> on the hardware that the reservation request returns:<br>
> <a href="https://wiki.centos.org/QaWiki/PubHardware" rel="noreferrer" target="_blank">https://wiki.centos.org/<wbr>QaWiki/PubHardware</a><br>
><br>
> Also, these physical machines do not have additional disks. The single<br>
> SSD that these systems have, is completely used by the installation, no<br>
> free space to partition to our liking, no additional disks available.<br>
><br>
> I welcome any additional testing that we can run regulary, but to call<br>
> it 'performance testing' might be a little pre-mature. At least the<br>
> performance results should be marked as 'unoptimized' or similar.<br>
><br>
> HTH,<br>
> Niels<br>
><br>
<br>
</div></div>The goal of this testing, to begin with, wouldn't be to get absolute numbers<br>
but to try and catch decrease in performance, if that makes sense. In essence,<br>
it's regression testing but for performance.<br>
<br>
Thank you for raising the fact that it may be inconsistent, I'll talk to the<br>
Centos CI folks and see what's the best way forward for us before we get here.<br>
But let's work with the assumption that I'll sort out the infra side of things.<br>
<div class="HOEnZb"><div class="h5"><br>
<br>
><br>
> ><br>
> > [1]: <a href="http://www.iozone.org/" rel="noreferrer" target="_blank">http://www.iozone.org/</a><br>
> > [2]: <a href="https://github.com/bengland2/smallfile" rel="noreferrer" target="_blank">https://github.com/bengland2/<wbr>smallfile</a><br>
> ><br>
> > --<br>
> > nigelb<br>
> > ______________________________<wbr>_________________<br>
> > Gluster-devel mailing list<br>
> > <a href="mailto:Gluster-devel@gluster.org">Gluster-devel@gluster.org</a><br>
> > <a href="http://www.gluster.org/mailman/listinfo/gluster-devel" rel="noreferrer" target="_blank">http://www.gluster.org/<wbr>mailman/listinfo/gluster-devel</a><br>
<br>
<br>
<br>
--<br>
nigelb<br>
______________________________<wbr>_________________<br>
Gluster-devel mailing list<br>
<a href="mailto:Gluster-devel@gluster.org">Gluster-devel@gluster.org</a><br>
<a href="http://www.gluster.org/mailman/listinfo/gluster-devel" rel="noreferrer" target="_blank">http://www.gluster.org/<wbr>mailman/listinfo/gluster-devel</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr">Pranith<br></div></div>
</div>