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] scaling problem with writable pagetables

To: Andrew Theurer <habanero@xxxxxxxxxx>
Subject: Re: [Xen-devel] scaling problem with writable pagetables
From: Keir Fraser <Keir.Fraser@xxxxxxxxxxxx>
Date: Thu, 16 Feb 2006 08:54:33 +0000
Cc: xen-devel@xxxxxxxxxxxxxxxxxxx
Delivery-date: Thu, 16 Feb 2006 09:08:12 +0000
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <43F377D3.3020905@xxxxxxxxxx>
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>
References: <43F377D3.3020905@xxxxxxxxxx>
Sender: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx

On 15 Feb 2006, at 18:49, Andrew Theurer wrote:

Below are per-function ratios of CPU time rev8830/rev8830-lock-reduction (derived from oprofile diffs)

SDET:

9.84/1   restore_all_guest

Kind of odd, since that function contains no locking. Perhaps VCPUs are blocked so long that, by the time they get the CPU there is an event pending and the hypercall gets preempted?

What do the perfctr numbers look like for #hypercalls and #exceptions? Also worth adding one to __hypercall_create_continuation as that'll count #preemptions.

 -- Keir


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

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