From alsa-devel-owner@alsa.jcu.cz  Mon Oct  5 14:20:19 1998
Received: from entry.jcu.cz (IDENT:perex@entry.jcu.cz [160.217.1.111])
	by marvin.jcu.cz (8.9.1a/8.9.1) with SMTP id OAA23670;
	Mon, 5 Oct 1998 14:20:15 +0200
Date: Mon, 5 Oct 1998 14:20:11 +0200 (CEST)
From: Jaroslav Kysela <perex@jcu.cz>
To: alsa-devel@jcu.cz
cc: Thomas Sailer <sailer@ife.ee.ethz.ch>
Subject: Re: PCM mixing draft v0.2
In-Reply-To: <3618B20E.8AD559F5@ife.ee.ethz.ch>
Message-ID: <Pine.LNX.3.96.981005141757.4893L-100000@entry.jcu.cz>
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, 5 Oct 1998, Thomas Sailer wrote:

> Jaroslav Kysela wrote:
> 
> > OK. Looks like main problem is good scheduler. I see that in both cases is
> > main delay caused by task scheduler now. Current Linux scheduler is
> > probably limited with system clock (100Hz on i386). This means that delay
> > should be up to 20ms (or I missed something?). Other delay should be added
> > by effects, filters, conversions etc, but this must be done in both cases.
> 
> I don't quite see what problems ppl have with the Linux scheduler.
> The basic sched tick is indeed 100Hz on i386, but that doesn't mean
> it can only reschedule at 10ms boundaries. If your driver wants it,
> Linux can also reschedule at the end of a sound driver interrupt for
> example (see the need_resched stuff).

You mean probably wake_up() call. ALSA uses it, but I still assume that on
high load system should be latency between user and kernel space about 20ms...

							Jaroslav

-----
Jaroslav Kysela <perex@jcu.cz>
Academic Computer Centre, University of South Bohemia
Branisovska 31, C. Budejovice, CZ-370 05 Czech Republic



