Re: KVM performance

[Avi Kivity <avi-atKUWr5tajBWk0Htik3J/w@public.gmane.org>]

Tim Chen wrote:
> Hi,
>
> I did some testing of KVM on my woodcrest machine.  And I found that
> building a 2.6.19 kernel with identical configuration takes 845 sec on a
> guest and 210 sec on the host.  So the compile is about 4X slower on the
> guest :(
>
> The guest ran with 2.6.19 kernel and host ran with a 2.6.20-rc5 kernel.
> The guest file image is created with raw format.  Wonder if people see
> similar performance figure?  
>
>   


http://virt.kernelnewbies.org/KVM/Performance cites a 2.5X difference, 
but for a different cpu.

It's probably better to use an lvm volume rather than a raw file, and to 
give the guest ample memory.  In addition, quite a few performance 
optimizations are missing from kvm:

- after modifying a pte, kvm doesn't preload the modified pte into 
shadow, but instead lets the guest fault it in
- disk access is blocking instead of non-blocking.  this will be fixed 
by merging qemu-cvs, which uses aio for disk access.
- better heuristics for recycling page tables are needed
- prefaulting for common access patterns can help
- kvm currently saves the entire fpu state on every exit, even if it has 
not been modified


-- 
Do not meddle in the internals of kernels, for they are subtle and quick to panic.


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys - and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV