From: Tom Sightler <ttsig@tuxyturvy.com>
To: Andrea Arcangeli <andrea@suse.de>
Cc: Andrew Morton <akpm@osdl.org>,
mjy@geizhals.at, Linux-Kernel <linux-kernel@vger.kernel.org>
Subject: Re: CONFIG_PREEMPT and server workloads
Date: Thu, 18 Mar 2004 18:54:30 -0500 [thread overview]
Message-ID: <1079654070.3758.26.camel@localhost.localdomain> (raw)
In-Reply-To: <20040318153731.GG2246@dualathlon.random>
On Thu, 2004-03-18 at 10:37, Andrea Arcangeli wrote:
> On Thu, Mar 18, 2004 at 10:20:23AM -0500, Tom Sightler wrote:
> > Well, I reported an issue on my laptop several weeks ago where network
> > activity via my aironet wireless adapter would use 60-70% of the CPU but
> > only when PREEMPT was enabled. Looking back over the list I see other
>
> sounds like a preempt bug triggering in a softirq, or maybe an SMP bug
> triggering in UP.
>
> I certainly agree with Andrew that preempt cannot cause a 60/70%
> slowdown with a network card at least (if you do nothing but spinlocking
> in a loop then it's possible a 60/70% slowdown instead but the system
> time that a wifi card should take is nothing compared to the idle/user
> time).
Actually, I managed to get two bugs mixed together, my system had a
problem with PREEMPT and ACPI but this certainly seems to be fixed in
the current kernels, at least in 2.6.3-mm2 (my current everyday kernel)
and 2.6.5-rc1-mm2 (just a quick test tonight). Somehow the combination
of PREEMPT and any little applet that used ACPI (battery monitor) would
use a lot of CPU, then using the aironet adapter caused the CPU to
spike. Turning off either PREEMPT or ACPI would get rid of the
problem. I forgot about the ACPI part being in the mix.
I still think the aironet driver acts strange, but I'm not really sure
how to describe it. In 2.6.3-mm2 which I transfer a file top will show
60% of the cpu time in 'irq' whatever that means. It seems vmstat still
calls this idle. Perhaps I'm interpreting those numbers wrong.
When I enable preempt on the same system my network performance with the
aironet driver drops tremendously, probably by 75%, and the rest of the
systems seems to crawl. Somehow without preempt this isn't a problem,
even though it shows 60% of the time in 'irq' the rest of the system
feels responsive. What would be the proper way to track down this type
of problem?
I'm having more problems with 2.6.5-rc1-mm2 and the aironet card. It
seems to preform poorly no matter if preempt is on or off. I'm still
looking into that. I don't think the drivers has changed significantly
between the two version so I'm hoping I just made a mistake.
Later,
Tom
next prev parent reply other threads:[~2004-03-19 0:00 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-03-18 4:00 CONFIG_PREEMPT and server workloads Marinos J. Yannikos
2004-03-18 5:12 ` Andrew Morton
2004-03-18 6:03 ` Andrea Arcangeli
2004-03-18 9:50 ` Andrew Morton
2004-03-18 14:51 ` Andrea Arcangeli
2004-03-18 15:34 ` Robert Love
2004-03-18 16:01 ` Andrea Arcangeli
2004-03-18 17:39 ` Andrew Morton
2004-03-18 17:58 ` Andrea Arcangeli
2004-03-18 18:26 ` Andrew Morton
2004-03-18 18:38 ` Andrea Arcangeli
2004-03-18 18:47 ` Andrew Morton
2004-03-18 19:01 ` Andrea Arcangeli
2004-03-18 17:48 ` Robert Love
2004-03-18 18:00 ` Andrea Arcangeli
2004-03-20 10:48 ` Jamie Lokier
2004-03-19 2:17 ` Nick Piggin
[not found] ` <20040319050948.GN2045@holomorphy.com>
2004-03-20 12:14 ` Andrea Arcangeli
2004-03-20 14:51 ` William Lee Irwin III
2004-03-20 15:03 ` Andrea Arcangeli
2004-03-20 15:09 ` William Lee Irwin III
2004-03-24 13:57 ` Takashi Iwai
2004-03-24 14:52 ` Andrea Arcangeli
2004-03-24 15:11 ` William Lee Irwin III
2004-03-18 15:20 ` Tom Sightler
2004-03-18 15:37 ` Andrea Arcangeli
2004-03-18 23:54 ` Tom Sightler [this message]
2004-03-18 15:39 ` Robert Love
2004-03-18 15:28 ` Takashi Iwai
2004-03-18 15:40 ` Robert Love
2004-03-18 15:42 ` Andrea Arcangeli
2004-03-18 19:01 ` Andrew Morton
2004-03-18 19:08 ` Takashi Iwai
2004-03-18 19:18 ` Andrew Morton
2004-03-18 19:20 ` Takashi Iwai
2004-03-18 19:43 ` Andrea Arcangeli
2004-03-18 19:50 ` Takashi Iwai
2004-03-18 19:24 ` Robert Love
2004-03-19 22:03 ` Valdis.Kletnieks
2004-03-19 22:12 ` Robert Love
2004-03-24 15:00 ` Takashi Iwai
2004-03-18 19:16 ` Takashi Iwai
2004-03-18 19:29 ` Andrew Morton
2004-03-18 19:48 ` Chris Mason
2004-03-19 11:37 ` Takashi Iwai
2004-03-19 13:46 ` Chris Mason
2004-03-19 14:06 ` Takashi Iwai
[not found] ` <20040318221006.74246648.akpm@osdl.org>
2004-03-19 10:30 ` Takashi Iwai
2004-03-23 9:14 ` Dipankar Sarma
2004-03-19 17:22 ` Dipankar Sarma
2004-03-19 18:03 ` Andrew Morton
2004-03-20 12:24 ` Andrea Arcangeli
2004-03-20 13:13 ` Dipankar Sarma
2004-03-18 19:39 ` Andrea Arcangeli
2004-03-18 22:32 ` Andrew Morton
2004-03-18 22:54 ` Chris Mason
2004-03-18 23:57 ` Andrew Morton
2004-03-19 20:46 ` Takashi Iwai
2004-03-19 21:08 ` Andrew Morton
2004-03-19 3:07 ` Eric St-Laurent
2004-03-19 11:23 ` Takashi Iwai
2004-03-19 13:35 ` Chris Mason
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=1079654070.3758.26.camel@localhost.localdomain \
--to=ttsig@tuxyturvy.com \
--cc=akpm@osdl.org \
--cc=andrea@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mjy@geizhals.at \
/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