Re: [linux-audio-dev] HELP:porting linux audio driver to RTLinux(rtlinux core driver)

From: Jan Depner <eviltwin69@email-addr-hidden>
Date: Fri Apr 08 2005 - 17:52:25 EEST

On Fri, 2005-04-08 at 14:30, Lee Revell wrote:
> On Fri, 2005-04-08 at 09:24 -0500, Jan Depner wrote:
> > > Personally I think you're wasting your time. Ingo's RT preempt patches
> > > let you do hard realtime with Linux using the existing driver base.
> > >
> >
> > I'm not sure why he's trying to do this because for audio the latest
> > patched kernels appear to be more than adequate. That said, I don't
> > think you can get a guaranteed 15 microsecond interrupt response with
> > anyone's patches to the standard kernel. I wouldn't call what we have
> > now hard real-time. More like soft real-time. Maybe when MontaVista
> > gets done...
>
> Hard realtime has nothing to do with how short the deadlines are, it's
> about being able to *guarantee* that you can meet some deadline, IOW the
> ability to guarantee that every code path in the kernel is
> deterministic. And the RT preempt kernel absolutely can do hard
> realtime, down to about 50 usecs (which is the length of time the timer
> interrupt, the longest non preemptible path in the kernel, takes to
> run).
>

    I do know what hard real-time is - I used to do hard real-time
airborne magnetics/navigation data acquisition systems. That's why I
said guaranteed. You can get 15 microsecond guaranteed out of RT-Linux
though (depending on the hardware of course). However, I'll believe 50
microseconds when I see it run for 30 days doing fairly high bandwidth
data acquisition. BTW, where did you see someone say that they were
guaranteeing 50 microsecond interrupt response? I'd like to read up on
that.

> Right now all the work that various people have done to enable hard
> realtime on Linux is being ported to the RT preempt kernel. When
> MontaVista and others get all their patches in we should be able to meet
> even smaller RT constraints.

    That's what I'm hoping for. I could probably live with 50
microseconds for most things but there are some systems that require
better.

Jan
Received on Sat Apr 9 00:15:15 2005

This archive was generated by hypermail 2.1.8 : Sat Apr 09 2005 - 00:15:15 EEST