Gilles Chanteperdrix wrote:
> You will observe some differences only if you put some load on your
> system. The usual way of putting some load on your system is to use dd
> or the cache calibrator. See TROUBLESHOOTING.
> 

Thanks for the hint but the values for the CONFIG_PREEMPT case are still
at least 5% above the non-CONFIG_PREEMPT values. I did several testruns
and the result were reobservable. How much improvments with additional
fine granular Kernel Preemptability can one expect?

Thanks in advance,
Markus Franke
begin:vcard
fn:Markus Franke
n:Franke;Markus
adr;quoted-printable:;;Vettersstra=C3=9Fe 64/722;Chemnitz;Saxony;09126;Germany
email;internet:[EMAIL PROTECTED]
x-mozilla-html:FALSE
url:http://www.tu-chemnitz.de/~franm
version:2.1
end:vcard

_______________________________________________
Xenomai-help mailing list
[email protected]
https://mail.gna.org/listinfo/xenomai-help

Reply via email to