From: David Mansfield <david@cobite.com>
To: Linus Torvalds <torvalds@transmeta.com>
Cc: William Lee Irwin III <wli@holomorphy.com>,
Kernel Mailing List <linux-kernel@vger.kernel.org>,
Jeff Garzik <jgarzik@mandrakesoft.com>
Subject: Re: Scheduler ( was: Just a second ) ...
Date: Tue, 18 Dec 2001 12:21:54 -0500 (EST) [thread overview]
Message-ID: <Pine.LNX.4.33.0112181216341.1237-100000@admin> (raw)
In-Reply-To: <Pine.LNX.4.33.0112172153410.2416-100000@penguin.transmeta.com>
>
> audio_devs[devc->dev]->min_fragment = 5;
>
Generally speaking, you want to be able to specify about a 1ms fragment,
speaking as a realtime audio programmer (no offense Victor...). However,
1ms is 128 bytes at 16bit stereo, but only 32 bytes at 8bit mono. Nobody
does 8bit mono, but that's probably why it's there. A lot of drivers seem
to have 128 byte as minimum fragment size. Even the high end stuff like
the RME hammerfall only go down to 64 byte fragment PER CHANNEL, which is
the same as 128 bytes for stereo in the SB 16.
> Raising that min_fragment thing from 5 to 10 would make the minimum DMA
> buffer go from 32 bytes to 1kB, which is a _lot_ more reasonable (what,
> at 2*2 bytes per sample and 44kHz would mean that a 1kB DMA buffer empties
> in less than 1/100th of a second, but at least it should be < 200 irqs/sec
> rather than >400).
Note that the ALSA drivers allow the app to set watermarks for wakeup,
while allowing flexibility in fragment size and number. You can
essentially say, wake me up when there are at least n fragments empty, and
put me to sleep if m fragments are full.
David
--
/==============================\
| David Mansfield |
| david@cobite.com |
\==============================/
next prev parent reply other threads:[~2001-12-18 17:22 UTC|newest]
Thread overview: 83+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20011217200946.D753@holomorphy.com>
2001-12-18 4:27 ` Linus Torvalds
2001-12-18 4:55 ` William Lee Irwin III
2001-12-18 6:09 ` Linus Torvalds
2001-12-18 6:34 ` Jeff Garzik
2001-12-18 12:23 ` Rik van Riel
2001-12-18 14:29 ` Alan Cox
2001-12-18 17:07 ` Linus Torvalds
2001-12-18 15:51 ` Martin Josefsson
2001-12-18 17:08 ` Linus Torvalds
2001-12-18 16:16 ` Roger Larsson
2001-12-18 17:16 ` Herman Oosthuysen
2001-12-18 17:16 ` Linus Torvalds
2001-12-18 17:21 ` David Mansfield [this message]
2001-12-18 17:27 ` Linus Torvalds
2001-12-18 17:54 ` Andreas Dilger
2001-12-18 18:27 ` Doug Ledford
2001-12-18 18:52 ` Andreas Dilger
2001-12-18 19:03 ` Doug Ledford
2001-12-19 9:19 ` Peter Wächtler
2001-12-19 11:05 ` Helge Hafting
2001-12-21 20:23 ` Rob Landley
2001-12-18 18:35 ` Linus Torvalds
2001-12-18 18:58 ` Alan Cox
2001-12-18 19:31 ` Gerd Knorr
2001-12-18 18:25 ` William Lee Irwin III
2001-12-18 14:21 ` Adam Schrotenboer
2001-12-18 18:13 ` Davide Libenzi
[not found] <Pine.LNX.4.33.0112181508001.3410-100000@penguin.transmeta.com>
2001-12-20 3:50 ` Rik van Riel
2001-12-20 4:04 ` Ryan Cumming
2001-12-20 5:52 ` Linus Torvalds
2001-12-20 5:39 ` David S. Miller
2001-12-20 5:58 ` Linus Torvalds
2001-12-20 6:01 ` David S. Miller
2001-12-20 22:40 ` Troels Walsted Hansen
2001-12-20 23:55 ` Chris Ricker
2001-12-20 23:59 ` CaT
2001-12-21 0:06 ` Davide Libenzi
2001-12-20 11:29 ` Rik van Riel
2001-12-20 11:34 ` David S. Miller
[not found] <20011218020456.A11541@redhat.com>
2001-12-18 16:50 ` Linus Torvalds
2001-12-18 16:56 ` Rik van Riel
2001-12-18 17:18 ` Linus Torvalds
2001-12-18 19:04 ` Alan Cox
2001-12-18 21:02 ` Larry McVoy
2001-12-18 21:18 ` Rik van Riel
2001-12-18 21:14 ` David S. Miller
2001-12-18 21:17 ` Larry McVoy
2001-12-18 21:19 ` Rik van Riel
2001-12-18 21:30 ` David S. Miller
2001-12-19 16:50 ` Daniel Phillips
2001-12-18 19:11 ` Mike Galbraith
2001-12-18 19:15 ` Rik van Riel
2001-12-18 17:55 ` Davide Libenzi
2001-12-18 19:43 ` Alexander Viro
2001-12-18 5:59 V Ganesh
-- strict thread matches above, loose matches on Subject: below --
2001-12-18 5:11 Thierry Forveille
2001-12-17 21:41 ` John Heil
2001-12-18 14:31 ` Alan Cox
2001-12-16 0:13 Just a second Linus Torvalds
2001-12-17 22:48 ` Scheduler ( was: Just a second ) Davide Libenzi
2001-12-17 22:53 ` Linus Torvalds
2001-12-17 23:15 ` Davide Libenzi
2001-12-17 23:18 ` Linus Torvalds
2001-12-17 23:39 ` Davide Libenzi
2001-12-17 23:52 ` Benjamin LaHaise
2001-12-18 1:11 ` Linus Torvalds
2001-12-18 1:46 ` H. Peter Anvin
2001-12-18 5:54 ` Benjamin LaHaise
2001-12-18 6:10 ` Linus Torvalds
2001-12-18 1:54 ` Rik van Riel
2001-12-18 2:35 ` Linus Torvalds
2001-12-18 2:51 ` David Lang
2001-12-18 3:08 ` Davide Libenzi
2001-12-18 3:19 ` Davide Libenzi
2001-12-18 14:09 ` Alan Cox
2001-12-18 9:12 ` John Heil
2001-12-18 15:34 ` degger
2001-12-18 18:35 ` Mike Kravetz
2001-12-18 18:48 ` Davide Libenzi
2001-12-18 16:50 ` Mike Kravetz
2001-12-18 17:22 ` Linus Torvalds
2001-12-18 17:50 ` Davide Libenzi
2001-12-18 17:00 ` Linus Torvalds
2001-12-18 19:17 ` Alan Cox
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=Pine.LNX.4.33.0112181216341.1237-100000@admin \
--to=david@cobite.com \
--cc=jgarzik@mandrakesoft.com \
--cc=linux-kernel@vger.kernel.org \
--cc=torvalds@transmeta.com \
--cc=wli@holomorphy.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®