On Monday 30 May 2005 20:58, Majid Salame wrote:
> > UML uses multiple processes for it's buisness.
> With Skas UML is just one process as it appears on the Host, or do you mean
> something else.
No, it's at least two (+ possible service threads): one is the thread
executing kernel code, which pt
Title: RE: [uml-devel] Slower system call with SMP
Yes. And I am trying fork stress test.
Majid.
> -Original Message-
> From: Jeff Dike [mailto:[EMAIL PROTECTED]]
> Sent: Tuesday, May 31, 2005 9:58 AM
> To: Salame, Majid [CAR:2V62:EXCH]
> Cc: user-m
> 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 loo
Title: RE: [uml-devel] Slower system call with SMP
> UML uses multiple processes for it's buisness.
With Skas UML is just one process as it appears on the Host, or do you mean something else.
>When host is
> SMP, these can be mapped to different cpu's, and when
>
> Doe that make sense ? Doing the same test by disabling SMP on the host,
> and
> results are much faster.
> NOTE SMP is turned off for the UML.
This is a shot from the hip, but
UML uses multiple processes for it's buisness. When host is SMP, these can
be mapped to different cpu's, and when inter
Title: 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.
NOTE SMP is
