WARNING - OLD ARCHIVES

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/
   
 
 
Xen 
 
Home Products Support Community News
 
   
 

xen-devel

RE: [Xen-devel] unusual domU memory performance

To: "Bryan D. Payne" <bryan@xxxxxxxxxxxx>, "Keir Fraser" <Keir.Fraser@xxxxxxxxxxxx>
Subject: RE: [Xen-devel] unusual domU memory performance
From: "Tian, Kevin" <kevin.tian@xxxxxxxxx>
Date: Mon, 14 Nov 2005 21:53:30 +0800
Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Mon, 14 Nov 2005 13:53:43 +0000
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
List-help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-id: Xen developer discussion <xen-devel.lists.xensource.com>
List-post: <mailto:xen-devel@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/cgi-bin/mailman/listinfo/xen-devel>, <mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AcXpIUlSThr0YAPXSuq4gUddLgug/QAALkcg
Thread-topic: [Xen-devel] unusual domU memory performance
>From: Bryan D. Payne
>Sent: 2005年11月14日 21:42
>
>> What CPUs are the domains running on? This is most likely an
>> artefact of the machine architecture, and nothing to do with Xen.
>
>Interesting.  The system is running with a single AMD Athlon 64 3500+
>processor (note that both dom0 and domU are compiled as 32-bit
>systems).  There is a total of 2GB of RAM in the system, I have 1500
>allocated to dom0 and 256 to domU.
>
>I had been contemplating this being an artifact of the system, but
>couldn't come up with any reasonable explanation in my mind.  It just
>seems off that if one program is being a resource hog, the other
>wouldn't speed up.  However, I couldn't help but wonder if this was
>somehow stressing Xen in such a way as to cause some unusual
>behavior.  Anyway, if it's not Xen, then I shall keep looking
>elsewhere :-)
>
>Thanks,
>-bryan

How about make a test by simply loop without compare stuff? If that infinite 
loop without doing actual job also has same effect as what you see, maybe we 
can put the light on schedule stuff (both dom0 and domU on same UP). The direct 
result of your experiment is that dom0 gets more chance to run... Maybe that 
indicates dom0 can service more requests from domU under some conditions?

Thanks,
Kevin

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-devel

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