[LAD] [ANNOUNCE] Safe real-time on the desktop by default; Desktop/audio RT developers, read this!

Lennart Poettering mzynq at 0pointer.de
Fri Jun 19 20:03:23 UTC 2009

On Fri, 19.06.09 20:39, Chris Cannam (cannam at all-day-breakfast.com) wrote:

> On Fri, Jun 19, 2009 at 7:13 PM, Lennart Poettering<mzynq at 0pointer.de> wrote:
> > Questions?
> Is it safe to assume that the PulseAudio libraries will use this
> method to acquire real-time scheduling for the audio callback thread
> of any application that uses the PulseAudio callback API directly?

Uh. I thought about that. Not sure if we really should do that
though. In many cases, the app's IO callback might not really be that
well suited for execution in RT. And then it might end up being killed
by RLIMIT_RTTIME or so. Dunno. Maybe that would not even be a problemn
and we could just make all IO threads RT at prio 1 or so. I am a bit
afraid that such a thing might backfire and we fuck up the scheduling
for everyone else too.

I really don't know. Maybe just make it easily accessible would be a
good idea, but not enable by default. But OTOH RT is not a magic wand,
so I wouldn't want to create the illusion that just making a broken
app RT fixes all issues magically.


Lennart Poettering                        Red Hat, Inc.
lennart [at] poettering [dot] net
http://0pointer.net/lennart/           GnuPG 0x1A015CC4

More information about the Linux-audio-dev mailing list