[LAU] Realtime Kernel

Arda Eden ardaeden at gmail.com
Tue Mar 18 15:02:35 EDT 2008


Hmm,
So this is all about my kernel:
Linux melinda 2.6.18.8-86 #2 SMP Mon Feb 11 00:50:59 EET 2008 i686 mobile
AMD Athlon(tm) XP-M 2200+ GNU/Linux

Is it possible to patch it in order to make it a RT kernel ?


On Tue, Mar 18, 2008 at 8:59 PM, Mark Knecht <markknecht at gmail.com> wrote:

> On Tue, Mar 18, 2008 at 11:41 AM, Arda Eden <ardaeden at gmail.com> wrote:
> > So what does a realtime kernel change ? Makes my latency 1 ms ?
> >
> >
> >
> >
> > On Tue, Mar 18, 2008 at 8:38 PM, Arnold Krille <arnold at arnoldarts.de>
> wrote:
> >
> > >
> > >
> > >
> > > Am Dienstag, 18. März 2008 schrieb Mark Knecht:
> > >
> > > > On Tue, Mar 18, 2008 at 11:25 AM, Arda Eden <ardaeden at gmail.com>
> wrote:
> > > > > So is it really necessary to have a realtime kernel in order to
> use
> > linux
> > > > > audio applications without any latencies or xruns ?
> > > > It is not possible to use ANY kernel with NO latencies. EVERY kernel
> > > > has latencies. The question is how low do you want the latencies to
> > > > be? If you can exist with 50mS or higher you might get away with a
> > > > standard kernel. If you want to run with 1.2mS latency then you will
> > > > absolutely have to have a real-time enabled kernel.
> > >
> > > Still it has to be noted that you can achieve 5ms latency without a
> > > RT-kernel... Even with an el-cheapo builtin soundcard...
> > >
> > > Arnold
>
> Absolutely. The most recent kernels are often quite good. However I
> would say that the difference between a standard kernel running 5mS
> and a RT kernel running 5mS is that the RT kernel is far more likely
> to meet the 5mS requirement under heavy system loads while the
> standard kernel may, at times, give a bit too much time to non-rt
> threads and not get back to your audio thread as fast as someone might
> want.
>
> If you want the highest reliability means of meeting your RT
> requirements all the time then use the RT kernel. If you are just
> doing home recording and can accept an occasional xrun (i.e. - a
> glitch in the recorded data) then stick with the standard kernel for
> as long as it works for you.
>
> Just my view,
> Mark
>



-- 
Arda EDEN
Cumhuriyet University
Faculty of Fine Arts
Department of Music Technology
Sivas/TURKEY
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://lists.linuxaudio.org/pipermail/linux-audio-user/attachments/20080318/435c807e/attachment.htm 


More information about the Linux-audio-user mailing list