This is an archived copy of the Xen.org mailing list, which we have preserved to ensure that existing links to archives are not broken. The live archive, which contains the latest emails, can be found at http://lists.xen.org/
Home Products Support Community News


RE: [Xen-ia64-devel] Time for hybrid virtualization?

To: Alex Williamson <alex.williamson@xxxxxx>
Subject: RE: [Xen-ia64-devel] Time for hybrid virtualization?
From: Kayvan Sylvan <kayvan@xxxxxxxxx>
Date: Thu, 24 Jan 2008 13:19:03 -0800
Accept-language: en-US
Acceptlanguage: en-US
Cc: xen-ia64-devel <xen-ia64-devel@xxxxxxxxxxxxxxxxxxx>
Delivery-date: Thu, 24 Jan 2008 13:19:28 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
In-reply-to: <1201207442.6826.49.camel@lappy>
List-help: <mailto:xen-ia64-devel-request@lists.xensource.com?subject=help>
List-id: Discussion of the ia64 port of Xen <xen-ia64-devel.lists.xensource.com>
List-post: <mailto:xen-ia64-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-ia64-devel>, <mailto:xen-ia64-devel-request@lists.xensource.com?subject=unsubscribe>
References: <1200528127.6773.88.camel@lappy><1200592688.7657.72.camel@bling> <20080118062441.GA2564@saphi> <1200699825.7133.32.camel@lappy> <51CFAB8CB6883745AE7B93B3E084EBE201670748@xxxxxxxxxxxxxxxxxxxxxxxxxxxx> <1200994146.4795b762d3648@xxxxxxxxxxx> <1201025874.6751.44.camel@lappy> <1201179494.47988b665cbbd@xxxxxxxxxxx> <DF0031A8C0149E41802BAFD18D6C4B701294E636F1@xxxxxxxxxxxxxxxxxxxxxx> <1201207442.6826.49.camel@lappy>
Sender: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AcheydpenhasOffCSvGxd7k2ww6c7wAACC8g
Thread-topic: [Xen-ia64-devel] Time for hybrid virtualization?
For the Montecito chip, running the RE-AIM7 compute workload, we have the 
following preliminary summary:

Native vs. Xen performace
At 2-CPU, the overhead was 13%.
At 4-CPU, the overhead was 17%
At 8-cpu, overhead was 28%
At 16-cpu, the overhead was 173%

Not quite sure why the performance dropped off so radically in the 16-CPU case.

I'm trying to get equivalent numbers for x86_64 and the Montvale chip.


-----Original Message-----
From: Alex Williamson [mailto:alex.williamson@xxxxxx]
Sent: Thursday, January 24, 2008 12:44 PM
To: Kayvan Sylvan
Cc: tgingold@xxxxxxx; xen-ia64-devel
Subject: RE: [Xen-ia64-devel] Time for hybrid virtualization?

On Thu, 2008-01-24 at 08:20 -0800, Kayvan Sylvan wrote:
> We (myself and my colleagues at Platform Solutions) are working on
> this exactly.
> We will send some results to the list soon, but I think we can confirm
> Alex's experience with HVM configurations. Our preliminary results are
> about 13-15% overhead.
> I am racking a Montvale system in about 15 minutes to do some more
> benchmarks today.

Hi Kayvan,

   That's good news.  If you get Montecito vs Montvale results that
would be interesting too.   Does anyone have suggestions for other easy
to run and setup benchmarks?  Kernel builds seem to be fairly
virtualization friendly.  Thanks,


Alex Williamson                             HP Open Source & Linux Org.

Xen-ia64-devel mailing list

<Prev in Thread] Current Thread [Next in Thread>