Re: [Question] PARSEC benchmark has smaller execution time in VM than in native?

[Dario Faggioli <dario.faggioli@citrix.com>]

[-- Attachment #1.1: Type: text/plain, Size: 1730 bytes --]

On Tue, 2016-03-01 at 22:51 +0100, Sander Eikelenboom wrote:
> Tuesday, March 1, 2016, 9:39:25 PM, you wrote:
> 
> > On Tue, Mar 01, 2016 at 02:52:14PM -0500, Meng Xu wrote:
> > > 
> > > > I dont think I have exhausted all the options here, but it
> > > > looked like
> > > > two last changes did improve performance, but was still not
> > > > comparable to
> > > > HVM case.
> > > > I am trying to find where regression had happened. Performance
> > > > on newer
> > > > kernel (I tried 4.5.0-rc4+) was close or better than HVM.
>
> Just a perhaps silly thought .. but could there be something in the 
> time-measuring that could differ and explain the slightly surprising
> results ?
>
I was about to say the exact same thing. In fact, when I can, I always
try to measure time either from the host, or even from outside, rather
than inside the VM itself.

The host should be fine, although that, in Xen, means measuring in
Dom0, which thing may be affected by virtualization as well so, from
this point of view, outside would be preferrable.

However, measuring from outside (and not even from the host, in certain
case) is not always possible and/or comes with a price.

So, it really depends on the benchmark and on the use case, and in a
bunch of them measuring from the guest is actually fine and/or is what
one wants. However, do at least consider that as an option for the
issue being reported.

Thanks and Regards,
Dario
-- 
<<This happens because I choose it to happen!>> (Raistlin Majere)
-----------------------------------------------------------------
Dario Faggioli, Ph.D, http://about.me/dario.faggioli
Senior Software Engineer, Citrix Systems R&D Ltd., Cambridge (UK)


[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 181 bytes --]

[-- Attachment #2: Type: text/plain, Size: 126 bytes --]

_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel