From: William Lee Irwin III <wli@holomorphy.com>
To: Denis Vlasenko <vda@port.imtp.ilyichevsk.odessa.ua>
Cc: linux-kernel@vger.kernel.org
Subject: Re: top hogs CPU in 2.6: kallsyms_lookup is very slow
Date: Thu, 16 Sep 2004 04:45:15 -0700 [thread overview]
Message-ID: <20040916114515.GP9106@holomorphy.com> (raw)
In-Reply-To: <200409161428.27425.vda@port.imtp.ilyichevsk.odessa.ua>
On Thu, Sep 16, 2004 at 02:28:26PM +0300, Denis Vlasenko wrote:
> I see 2.6.9-rc2 being slower than 2.4.27-rc3
> on a Pentium 66, 80 MB RAM.
> Specifically:
> top on idle machine sucks ~40% CPU while in 2.4
> it takes only ~6%
> I recompiled 2.6 with HZ=100 and with slab debugging
> off. This helped a bit (wget was slow too),
> but top still hogs CPU.
> I did 'strace -T -tt top b n 1' under both kernels,
> postprocessed it a bit:
The following patches in -mm are likely to help top(1).
kallsyms-data-size-reduction--lookup-speedup.patch
kallsyms data size reduction / lookup speedup
inconsistent-kallsyms-fix.patch
Inconsistent kallsyms fix
kallsyms-correct-type-char-in-proc-kallsyms.patch
kallsyms: correct type char in /proc/kallsyms
kallsyms-fix-sparc-gibberish.patch
kallsyms: fix sparc gibberish
As for all syscalls/etc. being slower by 50%-100%, I suggest toning
down HZ (we desperately need to go tickless) and seeing if it persists.
Also please check that time isn't twice as fast as it should be in 2.6.
-- wli
next prev parent reply other threads:[~2004-09-16 11:51 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-16 11:28 top hogs CPU in 2.6: kallsyms_lookup is very slow Denis Vlasenko
2004-09-16 11:45 ` William Lee Irwin III [this message]
2004-09-16 11:57 ` Denis Vlasenko
2004-09-16 12:17 ` William Lee Irwin III
2004-09-16 12:31 ` Denis Vlasenko
2004-09-17 8:57 ` Denis Vlasenko
2004-09-17 11:03 ` William Lee Irwin III
2004-09-17 12:34 ` Denis Vlasenko
2004-09-17 13:33 ` William Lee Irwin III
2004-09-17 20:36 ` Denis Vlasenko
2004-09-17 21:32 ` William Lee Irwin III
[not found] ` <200409172155.29561.vda@port.imtp.ilyichevsk.odessa.ua>
2004-09-18 13:57 ` [PATCH] trivial patch for 2.4: always inline __constant_* Denis Vlasenko
2004-09-18 14:03 ` [PATCH] trivial patch for 2.4: resolve megaraid_info name collision Denis Vlasenko
2004-09-18 14:02 ` Marcelo Tosatti
2004-09-18 15:05 ` [PATCH] trivial patch for 2.4: always inline __constant_* Marcelo Tosatti
2004-09-17 9:01 ` top hogs CPU in 2.6: kallsyms_lookup is very slow Denis Vlasenko
2004-09-17 10:55 ` William Lee Irwin III
2004-09-17 11:27 ` Paulo Marques
2004-09-17 11:21 ` Denis Vlasenko
2004-09-17 12:10 ` William Lee Irwin III
2004-09-17 13:04 ` Denis Vlasenko
2004-09-17 13:55 ` Larry McVoy
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=20040916114515.GP9106@holomorphy.com \
--to=wli@holomorphy.com \
--cc=linux-kernel@vger.kernel.org \
--cc=vda@port.imtp.ilyichevsk.odessa.ua \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.