Yes. And I am trying fork stress test.

Majid.

> -----Original Message-----
> From: Jeff Dike [mailto:jdike@addtoit.com]
> Sent: Tuesday, May 31, 2005 9:58 AM
> To: Salame, Majid [CAR:2V62:EXCH]
> Cc: user-mode-linux-devel@lists.sourceforge.net
> Subject: Re: [uml-devel] Slower system call with SMP
>
>
> > The cost of a system call it seems to be higher when
> > Running a RHE host with dual CPU (SMP turned on) and the image is
> > patched with skas patch.
> >
> > Doe that make sense ? Doing the same test by disabling SMP on the
> > host, and results are much faster.
>
> What exactly was the test?  A getpid loop?
>
>                               Jeff
>
>