public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Dave Hansen <haveblue@us.ibm.com>
To: Andi Kleen <ak@suse.de>
Cc: linux-kernel@vger.kernel.org, lse-tech@lists.sourceforge.net,
	akpm@digeo.com
Subject: Re: Horrible L2 cache effects from kernel compile
Date: Wed, 26 Feb 2003 19:24:13 -0800	[thread overview]
Message-ID: <3E5D84DD.2020402@us.ibm.com> (raw)
In-Reply-To: p7365r88heo.fsf@amdsimf.suse.de

Andi Kleen wrote:
> Other numbers may work better for your workload. Please test.
The whole post:
http://marc.theaimsgroup.com/?l=linux-kernel&m=104619044800608&w=2

The number of cycles in d_lookup increased by 10% with your patch.  But,
it looks like lots of stuff was moving around, so I wouldn't take too
much stock in it.

% change       2.5.62        2.5.62-ak-dc
in cycles  cycles(%oftot)  cycles(%oftot)
 +20.685%    6251(0.397%)    9834(0.603%) ext3_get_inode_loc
 +13.296%   16183(1.027%)   21863(1.341%) try_to_wake_up
 +10.560%  130566(8.283%) 166867(10.239%) d_lookup
 +10.202%   12525(0.795%)   15892(0.975%) filemap_nopage
  +5.991%   22127(1.404%)   25793(1.583%) schedule
  +5.581%    8705(0.552%)   10064(0.618%) run_timer_softirq
  +4.246%    7922(0.503%)    8917(0.547%) current_kernel_time
  +4.116%    9196(0.583%)   10324(0.633%) __wake_up
  +3.739%   21650(1.373%)   24123(1.480%) __find_get_block
  +3.631%    7226(0.458%)    8034(0.493%) do_page_cache_readahead
  +3.287%   72668(4.610%)   80239(4.923%) find_get_page
  +2.857%   11435(0.725%)   12518(0.768%) strnlen_user
  -2.184%   35107(2.227%)   34745(2.132%) .text.lock.inode
  -2.200%   17129(1.087%)   16947(1.040%) __fput
  -2.706%   28213(1.790%)   27632(1.695%) start_this_handle
  -2.823%   36539(2.318%)   35703(2.191%) smp_apic_timer_interrupt
  -3.668%   26074(1.654%)   25050(1.537%) load_balance
  -3.844%    8367(0.531%)    8010(0.491%) find_vma
  -4.340%   46642(2.959%)   44211(2.713%) scheduler_tick
  -4.650%    9965(0.632%)    9387(0.576%) default_idle
  -4.667%   14213(0.902%)   13384(0.821%) do_wp_page
  -4.728%   13603(0.863%)   12794(0.785%) mark_offset_tsc
  -4.815%   39748(2.522%)   37319(2.290%) __blk_queue_bounce
  -6.545%   44437(2.819%)   40298(2.473%) x86_profile_hook
  -6.991%   36113(2.291%)   32457(1.991%) __copy_from_user_ll
  -7.660%   16275(1.032%)   14432(0.886%) may_open
 -13.539%   28492(1.807%)   22432(1.376%) get_empty_filp
 -16.257%   10334(0.656%)    7696(0.472%) file_move

-- 
Dave Hansen
haveblue@us.ibm.com


  reply	other threads:[~2003-02-27  3:17 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <3E5ABBC1.8050203@us.ibm.com.suse.lists.linux.kernel>
2003-02-25 16:16 ` Horrible L2 cache effects from kernel compile Andi Kleen
2003-02-27  3:24   ` Dave Hansen [this message]
2003-02-27 16:36   ` Jan Harkes
     [not found] ` <b3ekil$1cp$1@penguin.transmeta.com.suse.lists.linux.kernel>
     [not found]   ` <20030225170546.GA23772@morningstar.nowhere.lie.suse.lists.linux.kernel>
2003-02-25 17:20     ` Andi Kleen
2003-02-26 18:22       ` Jamie Lokier
2003-02-25 18:37 Manfred Spraul
2003-02-25 18:41 ` Dave Hansen
2003-02-25 18:42 ` Andi Kleen
2003-02-25 19:29 ` Martin J. Bligh
2003-02-25 22:18 ` Linus Torvalds
2003-03-03 19:03   ` Benjamin LaHaise
2003-03-03 19:13     ` Linus Torvalds
2003-03-03 23:58       ` Alan Cox
2003-03-03 22:57         ` Andrew Morton
2003-03-03 23:01         ` Benjamin LaHaise
2003-03-03 23:09         ` Linus Torvalds
2003-03-05 20:19         ` dean gaudet
  -- strict thread matches above, loose matches on Subject: below --
2003-02-25  0:41 Dave Hansen
2003-02-25  0:59 ` William Lee Irwin III
2003-02-25  1:01   ` Dave Hansen
2003-02-25  3:15   ` John Levon
2003-02-25  3:15     ` William Lee Irwin III
2003-02-25  3:35     ` Andrew Morton
2003-02-25  4:13       ` Martin J. Bligh
2003-02-25 11:57         ` John Levon
2003-02-25  2:31 ` Linus Torvalds
2003-02-25 17:05   ` John W. M. Stevens

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=3E5D84DD.2020402@us.ibm.com \
    --to=haveblue@us.ibm.com \
    --cc=ak@suse.de \
    --cc=akpm@digeo.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lse-tech@lists.sourceforge.net \
    /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