Re: a joint letter on low latency and Linux

[Benno Senoner]

Paul Barton Davis wrote:
>>(I'll note that on my SMP machine, I'm running MP3 decoders much of the
>>time, and in practice very rarely hear any dropouts.  So the folks who
>>are painting such a dire picture of the state of Multimedia are
>>overstating their case a little, I think.)
>
>I purposely did *not* use the term multimedia to describe what most of
>the signees are up to. As I've stated many times, simple playback and
>record of audio+MIDI (+video? don't know) under Linux works fine. One
>might even say "very well".

No video is currently not reliable under current Linux kernels:
at 30fsp = 33ms per frame , when you play an MPEG video from disk,
the disk I/O causes occasional latency spikes which are bigger than
then above 33msecs , thus causing constant frame losses.

The problem of video is in almost all cases the video HW uses a double
buffering approach, thus giving you only the time to render one frame in the
off-screen buffer ( 33msecs).

It's only on audio cards where we have the privilege to set up a 64KB hw buffer
which means 370msecs of total buffersize which is even enough to overcome the
crappy 100ms latencies which Linux delivers.
(of course 300msecs is far from realtime, playing an MP3 is ok because we don't
care if, after pressing the PLAY button, it takes 100-200msecs for the sound to
start)

I can already immagine the frustration of the developers of LinDVD (commercial
software DVD player) because they will unable to guarantee dropout free video 
on current kernels. (random syslog activity and other stuff can cause latency
peaks)
I prefer the old videotape over a DVD which loses frames.

(BTW my Celeron 366 can happily decode a DVD (pure SW) under windows,
and this is one of the few reasons I keep that "OS" on my HD)

Benno.