Re: [Xen-devel] Video Presentation on PCI Express x16 VGA Pass Through to Xen-based Windows XP Home Edition HVM Virtual Machine

["Mr. Teo En Ming (Zhang Enming)" <space.time.universe@xxxxxxxxx>]

Attached in this email are three JPEG screenshots showing disk I/O benchmark results for pvops dom0 kernels 2.6.30-rc3, 2.6.31-rc6, and 2.6.31.1.

-- 
Mr. Teo En Ming (Zhang Enming) Dip(Mechatronics) BEng(Hons)(Mechanical Engineering)
Alma Maters:
(1) Singapore Polytechnic
(2) National University of Singapore
Blog URL: http://teo-en-ming-aka-zhang-enming.blogspot.com
Email: space.time.universe@xxxxxxxxx
MSN: teoenming@xxxxxxxxxxx
Mobile Phone: +65-9648-9798
Street: Bedok Reservoir Road
Republic of Singapore

On Thu, Oct 8, 2009 at 9:36 PM, Mr. Teo En Ming (Zhang Enming) <space.time.universe@xxxxxxxxx> wrote:

Dear Jeremy and all,

I had previously tried pvops dom0 kernel 2.6.31-final but I could not get it to boot successfully so I guess it
had some bugs.

Today I just tried pvops dom 0 kernel 2.6.31.1. It compiled, booted up and started winxp home domU successfully!

So I guess bugs which were present in 2.6.31 were resolved in 2.6.31.1. I did not set any dom0_mem for 2.6.31.1.

--
Mr. Teo En Ming (Zhang Enming) Dip(Mechatronics) BEng(Hons)(Mechanical Engineering)
Alma Maters:
(1) Singapore Polytechnic
(2) National University of Singapore
Blog URL: http://teo-en-ming-aka-zhang-enming.blogspot.com
Email: space.time.universe@xxxxxxxxx
MSN: teoenming@xxxxxxxxxxx
Mobile Phone: +65-9648-9798
Street: Bedok Reservoir Road
Republic of Singapore

On Wed, Sep 16, 2009 at 7:40 AM, Jeremy Fitzhardinge <jeremy@xxxxxxxx> wrote:

On 09/11/09 19:52, Mr. Teo En Ming (Zhang Enming) wrote:
> Hi,
>

> I have tried pvops dom 0 kernel 2.6.31 final from Jeremy's tree.
>
> But it gave me a USB host controller died error.
>
> Please refer to the error output here:
>
> http://teo-en-ming-aka-zhang-enming.blogspot.com/2009/09/error-with-pv-ops-dom-0-kernel-2631.html
>

Do you have CONFIG_SWIOTLB enabled?  I'm presuming you must because Xen
always configures it, but these crashes look like something is amiss
with it.

Also, try a new kernel - as of today - because I just fixed a pretty
serious bug.  However it should only affect reliability when doing guest
IO, not just normal bootup.  (It may have some bearing on your
performance regression.)

   J

Attachment: disk io - 2.6.30-rc3.JPG
Description: JPEG image

Attachment: disk io - 2.6.31.1.JPG
Description: JPEG image

Attachment: disk io - 2.6.31-rc6.JPG
Description: JPEG image

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