From alsa-devel-owner@alsa.jcu.cz  Mon Jan 18 23:24:06 1999
Received: from keg.cs.vu.nl (root@keg.cs.vu.nl [130.37.24.4])
	by marvin.jcu.cz (8.9.1a/8.9.1) with ESMTP id XAA15984
	for <alsa-devel@alsa.jcu.cz>; Mon, 18 Jan 1999 23:21:54 +0100
Received: from localhost by keg.cs.vu.nl with esmtp
	(Smail3.1.28.1 #56) id m102N3O-0007EDC; Mon, 18 Jan 99 23:21 +0100
Date: Mon, 18 Jan 1999 23:21:50 +0100 (MET)
From: Andy Lo A Foe <arloafoe@cs.vu.nl>
To: alsa-devel@alsa.jcu.cz
Subject: Re: RTLinux/ALSA mix
In-Reply-To: <001001be4323$1daf59e0$91934ac1@w98bg>
Message-ID: <Pine.GSO.4.05.9901182317001.9789-100000@keg.cs.vu.nl>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Reply-To: alsa-devel@alsa.jcu.cz
Sender: alsa-devel-owner@alsa.jcu.cz
Precedence: list

On Mon, 18 Jan 1999, Benjamin GOLINVAUX wrote:

> So... does anyone feel interested about this integration of ALSA drivers in
> a real-time linux kernel extension ?

With sched_setscheduler()  you can already achieve very good latency ( <
3ms I think). I'm working on a user land application (AlsaPlayer) that allows
for "real-time" pitch control on PCM data with the added option of adding
effects to it (echo implemented for now). The early alpha code is at
http://orbital.xs4all.nl/pub/alsa/. I haven't really done much with it the
last few weeks but as soon as exams finish I'll work on it full-time.

> I don't claim it IS possible, I'm just wondering... BeOS engineers told me
> they were able to reduce soft-latency (excluding any sound-hardware latency
> such as fifo's, ...) to less than 1ms...

Yes, why not. It can be done (I think :). The only problem I see however
is that to use realtime scheduling on Linux you would have to run all
realtime audio apps as superuser..

Andy
--
Andy Lo A Foe, arloafoe@cs.vu.nl |  Linux v2.1.125  | PII 233 
http://www.cs.vu.nl/~arloafoe    | GSM: 0622-440695 | Bebox 133
http://orbital.xs4all.nl/andy    |   ICQ: 7472949   | IRC: Adnans


