From: Bob McElrath <bob+linux-kernel@mcelrath.org>
To: linux-kernel@vger.kernel.org
Subject: process load and swapping
Date: Fri, 25 Oct 2002 09:35:42 -0500 [thread overview]
Message-ID: <20021025143541.GC13482@draal.physics.wisc.edu> (raw)
[-- Attachment #1: Type: text/plain, Size: 1538 bytes --]
I have been experiencing the following behavior on my alpha with many
kernel versions (2.4 series, latest is 2.4.19 with Ingo's O(1) scheduler
patch).
I'm running apache and zope, and when I load a zope page, the load jumps
to ~12 and the computer starts skipping. That is, about once every 2s
the music (xmms) stops for ~0.5s and then comes back. This repeats
every 2s until zope is finished creating the page (which takes sometimes
longer than a minute). When the computer "skips", not only does the
music stop, but the mouse stops moving (i.e. I move it continuously and
it pauses for 0.5s every 2s). This happens both at the console in X and
on virtual terminals (ssh'ed from another computer). It's as if it's
not servicing interrupts for 0.5s. Or does scheduling not occur when
the kernel decides to load N pages from swap, no matter how large N is?
This is totally due to swap use. If I turn off all swap ('swapoff -a'),
the response of zope is speedy. This behavior has happened with all
kernel versions I have used, at least since 2.4.17.
So, any ideas? I know there have been arguments about the 'swappiness'
of this kernel, but the load going to 12 and interrupts not being
serviced is totally quantitative and totally repeatable...
Cheers,
-- Bob
Bob McElrath
Univ. of Wisconsin at Madison, Department of Physics
"The surest way to corrupt a youth is to instruct him to hold in higher
esteem those who think alike than those who think differently."
-- Nietzsche
[-- Attachment #2: Type: application/pgp-signature, Size: 240 bytes --]
reply other threads:[~2002-10-25 14:30 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20021025143541.GC13482@draal.physics.wisc.edu \
--to=bob+linux-kernel@mcelrath.org \
--cc=linux-kernel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®