Re: [Xen-users] OS kernels ports, VT, Pacifica & performance

[Anthony Liguori <aliguori@xxxxxxxxxx>]

Sylvain Coutant wrote:

> Hi all,
>
> First, I'm not sure this post should have been sent to xen-devel or here. 
> Please, any list owner : forward to xen-devel if you read this and feel it 
> should have gone there.
>
> I wonder what will be the advantage, in terms of performance, of having 
> optimized kernels for XenU when VT/Pacifica will be there.
>  
It's pretty much a rule that anytime you optimize something to run in a 
VMM, it's going to improve performance.  The real question is whether 
that performance is noticable.
My initial feeling is that there are going to be some noticable 
performance optimizations one can make for running under VT/Pacifica 
without actually requiring Xen-only modifications (changing page table 
writes for instance to be more like writable page tables).
> AFAIK, using "standard" kernels means emulating peripherals (network card and so on) on dom0. Xen 
> "optimized" or "ported" kernels should have a performance advantage. But has this perf 
> increase already been evaluated ?
>  
There's quite a bit of ongoing research about whether it's possible to 
make native-performance emulated drivers.  The theory is that if you 
choose the right hardware to emulate, you could potentially have a 
emulation model that looks a lot like what a paravirtual driver would 
look like anyway.
Regards,

Anthony Liguori

> Question behind this : does it worth the work to port some other OSes to Xen 
> architecture ?
>
> Regards,
>
> --
> Sylvain COUTANT
>
> ADVISEO
> http://www.adviseo.fr/
> http://www.open-sp.fr/
>
>
>
> _______________________________________________
> Xen-users mailing list
> Xen-users@xxxxxxxxxxxxxxxxxxx
> http://lists.xensource.com/xen-users
>
>  
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users