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-users] Disk I/O performance with GPLPV 10.0.142

To: Ian Tobin <itobin@xxxxxxxxxxxxx>
Subject: Re: [Xen-users] Disk I/O performance with GPLPV 10.0.142
From: Nathan O'Sullivan <nathan@xxxxxxxxxxxxxx>
Date: Fri, 18 Dec 2009 06:44:19 +1100
Cc: xen-users@xxxxxxxxxxxxxxxxxxx
Delivery-date: Thu, 17 Dec 2009 11:46:42 -0800
Envelope-to: www-data@xxxxxxxxxxxxxxxxxxx
In-reply-to: <039E0B4AA9103344A80DA55DDDC76A9323976C@xxxxxxxxxxxxxxxxxxxxxx>
List-help: <mailto:xen-users-request@lists.xensource.com?subject=help>
List-id: Xen user discussion <xen-users.lists.xensource.com>
List-post: <mailto:xen-users@lists.xensource.com>
List-subscribe: <http://lists.xensource.com/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=subscribe>
List-unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-users>, <mailto:xen-users-request@lists.xensource.com?subject=unsubscribe>
References: <039E0B4AA9103344A80DA55DDDC76A9323976C@xxxxxxxxxxxxxxxxxxxxxx>
Sender: xen-users-bounces@xxxxxxxxxxxxxxxxxxx
User-agent: Thunderbird (X11/20090817)
Ian Tobin wrote:

Hi James


Ive setup a windows 2003 guest and thought id do a performance test.


Nework is great, much faster.


When i run nbench and do an i/o test on the disk using a 100mb thread i get much slower performance using the GPLPV drivers than i do when not using them.  Is there a setting that needs to be changed?







The impression I get is that before installing GPLPV, many benchmarks on Windows get "tricked" by some sort of caching effect on the dom0 side. If you try a more realistic test you will probably find that performance is actually better.
Xen-users mailing list
<Prev in Thread] Current Thread [Next in Thread>