RE: [Xen-devel] Questions about xenoprof semantics

["Santos, Jose Renato G" <joserenato.santos@xxxxxx>]

> -----Original Message-----
> From: xen-devel-bounces@xxxxxxxxxxxxxxxxxxx 
> [mailto:xen-devel-bounces@xxxxxxxxxxxxxxxxxxx] On Behalf Of 
> Jae-Wan Jang
> Sent: Wednesday, September 06, 2006 10:37 PM
> To: xen-devel@xxxxxxxxxxxxxxxxxxx
> Subject: [Xen-devel] Questions about xenoprof semantics
> 
> Hi, folks
> 
> I am figuring out network bottleneck in domU using xenoprof.
> 
> When I see the results, I can see the number of samples in 
> dom0 and domU differs.
> 
> If the number of samples in domU is more than that in dom0, 
> can I safely assume that domU is running longer than dom0?
> 
  Yes, if you are using UNHALTED clock cycles as the hardware
  event, the total number
  of samples in each domain should be proportional to the
  number of busy clock cycles used in the domain context
  (including user level, kernel and xen code). If you see
  2x the number of samples in one domain, it means its
  CPU utilization is also 2x.

  Renato
  Renato

> Thanks in advance.
> 
> 
> -- 
> 
> Jae-Wan Jang
> jwjang@xxxxxxxxxxxxxxxxxx
> +82-42-869-3559
> http://camars.kaist.ac.kr/~jwjang
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-devel
> 

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