Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 20 Feb 2002 11:21:51 +0100
From:      eberkut <eberkut@minithins.net>
To:        hackers@freebsd.org
Subject:   Re: Task activation delays: FreeBSD versus Linux?
Message-ID:  <200202201051.g1KApOu346887@logs-wc.proxy.aol.com>

next in thread | raw e-mail | index | archive | help
20/02/02 10:57:50, Terry Lambert <tlambert2@mindspring.com> a écrit:

>What is it?
>
>You left off the URL.  Looking on the site, it's not
>posted to the front, and the search function does not
>locate the article.
>
>To answer your questions, you'll have to provide more
>information.  A Linux patch number doesn't cut it.
>
>I expect that this is talking about exec pre-forking; if
>so, then yes, it can yield some minor speedup, but you
>should not expect much in common applications which fork
>and do not exec (e.g. Apache).  There are a number of
>micro-benchmarks that could make this approach look good,
>though...

No, the andrew morton's low latency patch (and the robert
love's preempt patch) try to make the kernel himself
preemptible to reduce latency. There is two different
approaches :

"Robert Love: The model we use is to allow the kernel to be
preempted at any time when it is not locked.  Under this
design, when an event occurs that causes a higher priority
task to become runnable, the system will preempt the current
task and run the higher priority task."

http://kerneltrap.org/node.php?id=1
http://www.tech9.net/rml/linux/

"Andrew Morton: The approach taken by these patches is
basically cooperative multitasking. The developer identifies
sections of long-running kernel code and changes them so that
they will yield the CPU to another task if the scheduler says
that it's time to do that. Most of the complexity here is in
being able to back out of any locking before yielding, and in
cleanly reacquiring locking state when the interrupted task
resumes."

http://kerneltrap.org/node.php?id=10
http://www.zip.com.au/~akpm/linux/schedlat.html

So I think that the final question is : Is the FreeBSD kernel
preemptible ? Does he compete on latency ? Is it yet another
gruik hack from linux ? ;)

--eberkut
ex diffinientium cognitione diffiniti resultat cognitio
. Prelude : http://prelude.sf.net
. CNS : http://minithins.net
. SpeKa : http://www.speka.net


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-hackers" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200202201051.g1KApOu346887>