From alsa-user-owner@alsa.jcu.cz  Thu Feb 11 23:59:15 1999
Received: from galjas.cs.vu.nl (root@galjas.cs.vu.nl [130.37.24.13])
	by marvin.jcu.cz (8.9.1a/8.9.1) with ESMTP id XAA27106
	for <alsa-user@alsa.jcu.cz>; Thu, 11 Feb 1999 23:57:24 +0100
Received: from localhost by galjas.cs.vu.nl with esmtp
	(Smail3.1.28.1 #49) id m10B52w-0006O0C; Thu, 11 Feb 99 23:57 +0100
Date: Thu, 11 Feb 1999 23:57:22 +0100 (MET)
From: Andy Lo A Foe <arloafoe@cs.vu.nl>
To: alsa-user@alsa.jcu.cz
Subject: Re: Recommendation for ALSA compat non-CreativeLabs PCI sound card?
In-Reply-To: <003d01be5601$b7ad5a60$9be1fec3@default>
Message-ID: <Pine.GSO.4.05.9902112348420.16840-100000@galjas.cs.vu.nl>
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Reply-To: alsa-user@alsa.jcu.cz
Sender: alsa-user-owner@alsa.jcu.cz
Precedence: list

On Thu, 11 Feb 1999, Udo Giacomozzi wrote:

> BTW, what do you mean with 3ms latency? recording->playback latency? That
> would be perfect as I am working on a realtime soundapp! :-)

Loopback latency (i.e. record and then playback).
See alsa-lib/test/latency.c for a nice latency test program. 
I think I clocked playback latency at 0.7ms last night on my box with
the latest build of AlsaPlayer. This was with a AWe64 Gold card, dunno
if my calculations were correct:

32 byte fragments
4 fragments max
1 low watermark level

44Khz 16 bit stereo playback of mp3

SCHED_FIFO scheduling on the streamer thread

((32 * 4) / 44K * 2 (16bit) * 2(stereo)) * 1000ms ~~ 0.7ms

This is with playback from RAM/dcache! So if these figures are correct
ALSA really rocks hard! :)

--- esound question ---
Is esound 0.2.7 working correctly for you with the latest ALSA driver?

Thanks,

Andy
--
Andy Lo A Foe, arloafoe@cs.vu.nl |   Linux v2.2.1   | PII 266 
http://www.cs.vu.nl/~arloafoe    | GSM: 0622-440695 | Bebox 133
http://orbital.xs4all.nl/andy    |   ICQ: 7472949   | IRCNet: Adnans


