Subject: Re: Audio interrupt latency
To: None <mycroft@mit.edu>
From: Lennart Augustsson <augustss@cs.chalmers.se>
List: port-arm32
Date: 08/17/1998 09:58:28
> So, even after the latest changes from Mark/whoever, when I do:
> 
> team -vr 1m 13 <heart.raw-sw44 >/dev/sound
> 
> with the source file in NFS, I still get very high (up to 20.5ms)
> interrupt latency the entire time it's talking to the network.  The
> largest value I've seen was:
> 
> Aug 17 01:28:53 chomp /netbsd: audio: play interrupt(400) off relative by 20515 us (49970)
> 
> I haven't explored why, but I thought I'd mention it.
This is not necessarily interrupt latency.  The audio layer detects that
the interrupt is 20.5 ms late, but that could also happen if the sound
chip generates the interrupt too late.  This could possibly happen
if the DMA to the chip is not running at the needed speed.

        -- Lennart