Re: [PATCH 2 of 4] Introduce i386 fibril scheduling

[bert hubert]

On Fri, Feb 02, 2007 at 03:17:57PM -0800, Linus Torvalds wrote:

> threads. But you need to look at what it is we parallelize here, and ask 
> yourself why we're doing what we're doing, and why people aren't *already* 
> just using a separate thread for it.

Partially this is for the bad reason that creating "i/o threads" (or even
processes) has a bad stigma to it, and additionally has always felt crummy.

On the first reason, the 'pain' of creating threads is actually rather
minor, so this feeling may have been wrong. The main thing is that you don't
wantonly create a thousand i/o threads, whereas you conceivably might want
to have a thousand outstanding i/o requests. At least I know I want to have
that ability.

Secondly, the actual mechanics of i/o processes isn't trivial, and feels
wasteful with lots of additional copying, or in the case of threads,
queueing and posting.

	Bert

-- 
http://www.PowerDNS.com      Open source, database driven DNS Software 
http://netherlabs.nl              Open and Closed source services
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/