Re: [patch] Re: MP3 skippety skip skipageness

Rik van Riel (riel@nl.linux.org)
Fri, 19 Mar 1999 17:04:42 +0100 (CET)

On Fri, 19 Mar 1999, Stephen C. Tweedie wrote:
> On Thu, 18 Mar 1999 19:43:38 +0100 (CET), Rik van Riel
> <riel@nl.linux.org> said:
>
> > MP3 playing during FS reads work great, yes. But the
> > problem is that clustered readins also cause larger
> > amounts of FS writing on smaller machines, and that's
> > where things start to break down.
>
> Umm, the readin algorithms really have very litte impact on the
> amount of write IO we generate or the way in which we submit it.
> It does obviously impact the disk scheduling of the submitted
> writes, of course.

OK, then where does the MP3 skipping come from and why
don't people see it as much on 2.0?

> Frankly, Unix has really never supported disk IO stream bandwidth
> reservation. If mp3 needs it, it should be buffering disk IO
> itself. "mpg123 -b 1024" works wonders here.

Sure, that works. But why is it needed now where people
didn't need it on a 2.0 system?

Rik -- Open Source: you deserve to be in control of your data.
+-------------------------------------------------------------------+
| Linux Memory Management site: http://humbolt.geo.uu.nl/Linux-MM/ |
| Nederlandse Linux documentatie: http://www.nl.linux.org/ |
+-------------------------------------------------------------------+

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/