Re: [LAT] [LAU] Are RT-patches needed anymore? (Was Re: >= 2.6.27 RT ETA?)

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
To: <linux-audio-tuning@...>
Date: Tuesday, February 3, 2009 - 3:04 pm

Il giorno Mon, 02 Feb 2009 15:07:58 -0800
Fernando Lopez-Lezcano ha scritto:

> > I use "lmms" every now and then. I have never been able to get

Hi all,

I tried lmms using alsa output with SCHED_RR[1] (chrt) and reniced I/O
(cfq, iorenice) and I found out cpu usage (the one reported by lmms)
dropped significantly. After rescheduling many tracks that used 100%
cpu and still clicked got to play nicely with little cpu usage. System
stability had no issues. LMMS is already threaded and threading support
is improving with 0.4.x versions[2].

Having made some experiments with realtime scheduling and after reading
your words I'll try asking some questions someone here could perhaps
answer:
- what's the difference between running some app realtime, say
"jackd -R", as opposed to "chrt -r" that same app?[3]
- how can I identify the audio thread and change scheduling/nice
priority of that single thread?
- given audio threads already are highest priority, isn't it better to
also schedule SCHED_RR all audio processes (with lower priority than
jackd and other audio threads) so no other process can eat cpu time
up?
- apart from irq threads, is there any other big improvement a -rt
kernel gives over "vanilla"[4] ones?
- does enabling "preempt RCU" make a big difference?

Sorry if some questions are trivial or already got answered somewhere
else, I looked around and found nothing relevant concerning these
questions. I'm not a kernel expert and just digging my way trying
to learn.

Bye, Nicola.

[1] imho SCHED_RR is better than SCHED_FIFO
[2]
http://sourceforge.net/mailarchive/message.php?msg_name=200902020056.296...
[3] it seems to me that using chrt to reschedule a process just
reschedules one thread, while lanching the same app scheduled with
chrt -r in the first place gets all threads scheduled realtime.
[4] I use "stock" debian kernels reconfigured with forced
preemption (low-latency desktop) and 300Hz timer and get pretty low
latency (1.5ms) with no xruns at all even under heavy desktop usage
_______________________________________________
Linux-audio-tuning mailing list
Linux-audio-tuning@lists.linuxaudio.org
http://lists.linuxaudio.org/listinfo/linux-audio-tuning

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
[LAT] Hello, Gilberto Borges, (Wed Jul 30, 9:39 pm)
[LAT] Hyper Threading, Jaromír Mikeš, (Wed Sep 17, 10:43 pm)
[LAT] amd64: kernels? base system?, james of jwm-art net, (Tue Dec 2, 5:53 pm)
Re: [LAT] [LAU] Are RT-patches needed anymore? (Was Re: &gt;..., Fernando Lopez-Lezcano, (Mon Feb 2, 11:08 pm)
Re: [LAT] 2.6.29-rt1, Robin Gareus, (Sat Mar 28, 1:18 pm)
[LAT] RT kernel for audio and dynamic vs static ticks, Lars-Erik Helander, (Mon Jan 18, 12:50 pm)
Re: [LAT] 2.6.29-rt1, Fernando Lopez-Lezcano, (Sat Mar 28, 6:11 pm)
Re: [LAT] 2.6.29-rt1, Ray Rashif, (Wed Apr 8, 2:54 am)
Re: [LAT] [LAU] Are RT-patches needed anymore? (Was Re: >..., dieeasy, (Tue Feb 3, 3:04 pm)
Re: [LAT] [LAU] Are RT-patches needed anymore? (Was Re: &gt;..., Fernando Lopez-Lezcano, (Tue Feb 3, 6:11 pm)
Re: [LAT] amd64: kernels? base system?, Daniel James, (Wed Dec 3, 11:17 am)
Re: [LAT] amd64: kernels? base system?, james of jwm-art net, (Wed Dec 3, 3:29 pm)
Re: [LAT] Hyper Threading, Robin Gareus, (Thu Sep 18, 2:53 pm)
Re: [LAT] Hyper Threading, Jaromír Mikeš, (Thu Sep 18, 7:45 pm)
Re: [LAT] Hello, Andy Farnell, (Wed Jul 30, 10:00 pm)
Re: [LAT] Hello, Marcos Guglielmetti, (Wed Jul 30, 11:00 pm)
Re: [LAT] Hello, Daniel James, (Tue Aug 5, 3:12 pm)
Re: [LAT] Hello / kernels, Marcos Guglielmetti, (Wed Aug 6, 8:53 am)
Re: [LAT] Hello / kernels, Robin Gareus, (Thu Aug 7, 5:05 pm)
Re: [LAT] Hello / kernels, Marcos Guglielmetti, (Wed Aug 6, 3:36 pm)