Re: [tlug] FreeBSD PREEMPTION (was: empty rows (PostgreSQL))

[Scott Robbins <scottro@example.com>]

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On Mon, Feb 14, 2005 at 01:05:18PM -0500, Josh Glover wrote:
> On Mon, 14 Feb 2005 11:12:46 -0500, Scott Robbins <scottro@example.com> wrote:
> 
> > Anyone put the SCHED_ULE and PREEMPTION in a FreeBSD 5.3-STABLE kernel
> > on a box with a heavy load?  I've put it in, seen no noticeable
> > difference, but I don't have anything really doing much with it.
> 
> Well, I would expect that the PREEMPTION option turns on kernel thread
> preemption (please correct me if I am wrong here, wileyc), so it would
> be expected to make things better for only a specific case of heavy
> loads: where the load is caused by a lot of competing processes making
> lengthy kernel calls.
> 
> I am going quite far out on a limb here, since I have no bloody idea
> what the BSD kernel looks like, but if it is anything like Linux
> (which I rather suspect that it is, at least in a zoomed-out
> architectural view), this is how things work:


Just in a VERY simplified nutshell, what is happening in FreeBSD's 5.x
branch is that there is more concentration on SMP systems--it seems to
be causing, however, some slowness on UP systems.  Both of these kernel
options are supposed to help this. 

However, as you know, I'm not a programmer, and am parroting
information.

If we do keep up with this, we will have to change the subject
line--sigh, I better do it here (unless you have--I'm in mutt and can't
see from where I am if you have or not)

- -- 

Scott

GPG KeyID EB3467D6
( 1B848 077D 66F6 9DB0 FDC2  A409 FA54 D575 EB34 67D6)
gpg --keyserver pgp.mit.edu --recv-keys EB3467D6

Oz: We survived. 
Buffy: Yeah, it was some battle. 
Oz: I meant high school. 

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.0 (FreeBSD)

iD8DBQFCEO4g+lTVdes0Z9YRAmpTAJ9Vbo8KU2a9h86YQBRW5Uez0XCcUwCggAS8
hPK9DeToBxNT70456sO1efQ=
=w+N8
-----END PGP SIGNATURE-----