Subject: Re: [linux-audio-dev] atomic xchg
From: David Olofson (audiality_AT_swipnet.se)
Date: to loka 14 1999 - 20:55:41 EDT
On Fri, 15 Oct 1999, Bill Gribble wrote:
> I'm just not convinced that this is the case. We're talking about
> data rates in the several-MB-per-sec range here, and I just don't
> believe that the latency of a thread sleep/wakeup is going to kill
> you, particularly not if your system is designed to use a sensible
> amount of buffering and POSIX RT scheduling priorities.
On the contrary, this is exactly the problem we're dealing with. Low
latency real time processing by definition means low buffering. This
is why I originally intended to support user space SCHED_FIFO only for
debugging purposes and non-critical applications. The *real*
implementation would use RTLinux... There, I have _worst case_
scheduling jitter less than a single sample period, while SHED_FIFO -
despite Ingo's great work - is still just good enough for reliable
real time audio. Latency is certainly not low enough for multiplying
with some factor 2 or more.
//David
·A·U·D·I·A·L·I·T·Y· P r o f e s s i o n a l L i n u x A u d i o
- - ------------------------------------------------------------- - -
·Rock Solid David Olofson:
·Low Latency www.angelfire.com/or/audiality ·Audio Hacker
·Plug-Ins audiality_AT_swipnet.se ·Linux Advocate
·Open Source ·Singer/Composer
This archive was generated by hypermail 2b28 : pe maalis 10 2000 - 07:27:59 EST