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-ia64-devel

RE: [Xen-ia64-devel] [PATCH] Add support to physdev_ops

To: "Alex Williamson" <alex.williamson@xxxxxx>
Subject: RE: [Xen-ia64-devel] [PATCH] Add support to physdev_ops
From: "Tian, Kevin" <kevin.tian@xxxxxxxxx>
Date: Fri, 21 Apr 2006 11:11:30 +0800
Cc: xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Thu, 20 Apr 2006 20:12:19 -0700
Envelope-to: www-data@xxxxxxxxxxxxxxxxxx
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>
Sender: xen-ia64-devel-bounces@xxxxxxxxxxxxxxxxxxx
Thread-index: AcZk7nOS0bMQW2H6Tamg3EIyG2IsfQAABSIA
Thread-topic: [Xen-ia64-devel] [PATCH] Add support to physdev_ops
>From: Alex Williamson [mailto:alex.williamson@xxxxxx]
>Sent: 2006年4月21日 10:51
>
>On Thu, 2006-04-20 at 17:01 +0800, Tian, Kevin wrote:
>
>> 2. This patch has no obvious performance influence (Why
>> I say 'obvious' is because latest p2m tree seems not very
>> stable even without this patch. The output drifts with -10-+10%
>> range... It's also possible due to my test environment. )
>
>Hi Kevin,
>
>   I ran some performance tests from xen-ia64-unstable on this patch
>today and also didn't see any obvious performance difference.  My
>results for wget for network and bonnie++ for disk were very consistent
>between runs though.  It's nice to see that iosapic virtualization
>appears to have such minimal overhead.  Thanks,
>
>       Alex
>

Hi, Alex,
        Thanks for test with the patch. It's good to see your data always 
consistent, and that proves my environment really a bit messed. 

        Currently the minimal overhead is because dom0 has seldom 
access to RTE entries at run-time. Later when EOI is also virtualized, 
the overhead may increase. Just guess, and we can see exact 
influence later when final part is ready.

        I'll resend the patch with Isaku's comment.

Thanks,
Kevin

_______________________________________________
Xen-ia64-devel mailing list
Xen-ia64-devel@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-ia64-devel

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