From: Justin Piszcz <jpiszcz@lucidpixels.com>
To: Jesse Barnes <jesse.barnes@intel.com>
Cc: Andi Kleen <andi@firstfloor.org>,
linux-kernel@vger.kernel.org,
"Eric W. Biederman" <ebiederm@xmission.com>
Subject: Re: [PATCH] trim memory not covered by WB MTRRs
Date: Wed, 6 Jun 2007 18:39:16 -0400 (EDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0706061838200.3563@p34.internal.lan> (raw)
In-Reply-To: <200706061528.44070.jesse.barnes@intel.com>
On Wed, 6 Jun 2007, Jesse Barnes wrote:
> On Wednesday, June 6, 2007 3:26 pm Justin Piszcz wrote:
>> Nope, I booted with only netconsole= options. I have a lot of HW in
>> the box and I guess the buffer is too small. Not sure where to
>> change it in the kernel. Looking..
>
> It's called "kernel log buffer size" and it's in "General setup".
>
> Jesse
>
Seems stable & fast so far, except when it hit swap :)
top - 18:38:13 up 5 min, 6 users, load average: 38.56, 12.65, 4.52
Tasks: 227 total, 64 running, 163 sleeping, 0 stopped, 0 zombie
Cpu0 : 0.0%us, 23.9%sy, 0.0%ni, 0.0%id, 72.7%wa, 0.0%hi, 3.4%si, 0.0%st
Cpu1 : 0.0%us, 23.5%sy, 0.0%ni, 1.0%id, 75.5%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu2 : 0.0%us, 24.1%sy, 0.0%ni, 0.0%id, 75.9%wa, 0.0%hi, 0.0%si, 0.0%st
Cpu3 : 0.0%us, 23.6%sy, 0.0%ni, 0.0%id, 76.4%wa, 0.0%hi, 0.0%si, 0.0%st
Mem: 8039576k total, 7998988k used, 40588k free, 12k buffers
Swap: 16787768k total, 879324k used, 15908444k free, 16316k cached
Tested with
$ stress --vm 32 --vm-bytes 250M
and
$ stress --vm 64 --vm-bytes 250M
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
248 root 10 -5 0 0 0 D 18 0.0 0:07.81 kswapd0
3788 war 18 0 256m 115m 164 D 3 1.5 0:01.32 stress
3800 war 18 0 256m 7300 160 R 3 0.1 0:00.58 stress
3801 war 18 0 256m 34m 160 R 3 0.4 0:02.48 stress
3808 war 18 0 256m 217m 164 R 3 2.8 0:01.16 stress
559 root 10 -5 0 0 0 D 2 0.0 0:00.15 md0_raid1
3771 war 18 0 256m 174m 164 R 2 2.2 0:01.30 stress
3785 war 18 0 256m 30m 164 R 2 0.4 0:01.42 stress
3813 war 18 0 256m 34m 164 R 2 0.4 0:01.06 stress
3787 war 18 0 256m 24m 160 R 2 0.3 0:00.25 stress
3794 war 18 0 256m 40m 160 R 2 0.5 0:00.14 stress
3778 war 18 0 256m 109m 164 R 2 1.4 0:01.23 stress
3783 war 18 0 256m 185m 164 R 2 2.4 0:01.29 stress
3799 war 18 0 256m 172m 164 R 2 2.2 0:01.07 stress
3816 war 18 0 256m 203m 160 R 2 2.6 0:00.39 stress
3819 war 18 0 256m 144m 160 R 2 1.8 0:00.40 stress
3820 war 18 0 256m 147m 160 R 2 1.9 0:00.39 stress
3825 war 18 0 256m 91m 164 R 2 1.2 0:01.16 stress
3777 war 18 0 256m 29m 164 R 1 0.4 0:01.05 stress
3779 war 18 0 256m 197m 164 R 1 2.5 0:01.29 stress
3805 war 18 0 256m 216m 160 R 1 2.8 0:00.36 stress
3812 war 18 0 256m 30m 164 R 1 0.4 0:01.14 stress
3830 war 18 0 256m 176m 164 R 1 2.3 0:01.17 stress
3831 war 18 0 256m 64m 164 R 1 0.8 0:01.40 stress
3769 war 18 0 256m 43m 164 R 1 0.6 0:01.23 stress
3770 war 18 0 256m 169m 164 R 1 2.2 0:01.18 stress
3773 war 18 0 256m 44m 160 R 1 0.6 0:00.29 stress
3774 war 18 0 256m 21m 160 R 1 0.3 0:00.21 stress
3780 war 18 0 256m 167m 164 R 1 2.1 0:01.33 stress
3781 war 18 0 256m 143m 164 R 1 1.8 0:01.35 stress
3798 war 18 0 256m 153m 164 R 1 1.9 0:01.16 stress
3807 war 18 0 256m 31m 164 R 1 0.4 0:01.17 stress
3817 war 18 0 256m 185m 160 R 1 2.4 0:00.40 stress
3822 war 18 0 256m 200m 160 R 1 2.6 0:00.41 stress
3824 war 18 0 256m 8684 160 R 1 0.1 0:00.16 stress
3827 war 18 0 256m 103m 164 R 1 1.3 0:00.95 stress
3828 war 18 0 256m 1976 160 R 1 0.0 0:00.19 stress
2026 daemon 30 15 30580 436 372 D 1 0.0 0:02.10 bindgraph.pl
3768 war 18 0 256m 81m 164 R 1 1.0 0:01.84 stress
3772 war 18 0 256m 158m 164 R 1 2.0 0:01.11 stress
3782 war 18 0 256m 180m 164 R 1 2.3 0:01.25 stress
3786 war 18 0 256m 173m 164 R 1 2.2 0:01.13 stress
3790 war 18 0 256m 20m 164 R 1 0.3 0:01.10 stress
3791 war 18 0 256m 36m 164 R 1 0.5 0:01.80 stress
3796 war 18 0 256m 111m 164 R 1 1.4 0:01.04 stress
3797 war 18 0 256m 120m 164 R 1 1.5 0:01.12 stress
3803 war 18 0 256m 129m 160 R 1 1.6 0:01.98 stress
3804 war 18 0 256m 234m 160 R 1 3.0 0:00.40 stress
3806 war 18 0 256m 49m 164 R 1 0.6 0:00.99 stress
3809 war 18 0 256m 54m 164 R 1 0.7 0:01.16 stress
3814 war 18 0 256m 38m 164 R 1 0.5 0:00.97 stress
3815 war 18 0 256m 69m 164 R 1 0.9 0:01.06 stress
246 root 15 0 0 0 0 D 0 0.0 0:00.01 pdflush
3687 war 15 0 18012 896 560 R 0 0.0 0:00.88 top
3775 war 18 0 256m 153m 164 R 0 2.0 0:01.14 stress
3776 war 18 0 256m 55m 164 R 0 0.7 0:01.34 stress
3784 war 18 0 256m 13m 164 R 0 0.2 0:00.96 stress
3789 war 18 0 256m 46m 164 R 0 0.6 0:01.54 stress
3792 war 18 0 256m 12m 164 R 0 0.2 0:01.00 stress
3793 war 18 0 256m 44m 164 R 0 0.6 0:00.96 stress
3795 war 18 0 256m 196m 164 R 0 2.5 0:01.06 stress
3802 war 18 0 256m 22m 160 R 0 0.3 0:02.70 stress
3810 war 18 0 256m 40m 164 R 0 0.5 0:01.06 stress
3818 war 18 0 256m 146m 160 R 0 1.9 0:00.34 stress
3829 war 18 0 256m 130m 164 R 0 1.7 0:01.11 stress
247 root 15 0 0 0 0 D 0 0.0 0:00.01 pdflush
554 root 10 -5 0 0 0 D 0 0.0 0:00.01 md2_raid1
3811 war 18 0 256m 61m 160 R 0 0.8 0:05.85 stress
3821 war 18 0 256m 136m 160 R 0 1.7 0:00.37 stress
3823 war 18 0 256m 204m 160 R 0 2.6 0:00.34 stress
3826 war 18 0 256m 95m 164 R 0 1.2 0:01.03 stress
next prev parent reply other threads:[~2007-06-06 22:39 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-06-06 19:29 [PATCH] trim memory not covered by WB MTRRs Jesse Barnes
2007-06-06 20:26 ` Justin Piszcz
2007-06-06 20:28 ` Jesse Barnes
2007-06-06 20:31 ` Jesse Barnes
2007-06-06 20:37 ` Justin Piszcz
2007-06-06 20:50 ` Jesse Barnes
2007-06-06 21:26 ` Justin Piszcz
2007-06-06 21:53 ` Justin Piszcz
2007-06-06 22:03 ` Justin Piszcz
2007-06-06 22:05 ` Jesse Barnes
2007-06-06 22:07 ` Justin Piszcz
2007-06-06 22:13 ` Justin Piszcz
2007-06-06 22:24 ` Jesse Barnes
2007-06-06 22:26 ` Justin Piszcz
2007-06-06 22:28 ` Jesse Barnes
2007-06-06 22:31 ` Justin Piszcz
2007-06-06 22:35 ` Justin Piszcz
2007-06-06 22:37 ` Randy Dunlap
2007-06-06 22:46 ` Justin Piszcz
2007-06-06 22:54 ` Justin Piszcz
2007-06-06 23:11 ` Randy Dunlap
2007-06-06 23:15 ` Justin Piszcz
2007-06-06 23:34 ` Jesse Barnes
2007-06-07 8:10 ` Justin Piszcz
2007-06-06 22:39 ` Justin Piszcz [this message]
2007-06-06 22:57 ` Justin Piszcz
2007-06-06 23:20 ` Jesse Barnes
2007-06-06 23:24 ` Justin Piszcz
2007-06-06 23:27 ` Jesse Barnes
2007-06-07 8:51 ` Andi Kleen
2007-06-07 8:53 ` Justin Piszcz
2007-06-07 9:55 ` Satyam Sharma
2007-06-07 17:33 ` Jesse Barnes
2007-06-07 7:45 ` Eric W. Biederman
2007-06-07 17:30 ` Jesse Barnes
2007-06-08 23:13 ` Eric W. Biederman
2007-06-12 15:39 ` Jesse Barnes
2007-06-07 8:16 ` Andi Kleen
2007-06-07 17:35 ` Jesse Barnes
2007-06-07 17:40 ` Justin Piszcz
2007-06-07 14:41 ` Pavel Machek
2007-06-08 0:20 ` Andrew Morton
2007-06-08 1:33 ` Jesse Barnes
2007-06-08 21:15 ` Andrew Morton
2007-06-08 21:28 ` Jesse Barnes
2007-06-13 1:11 ` Eric W. Biederman
2007-06-13 2:29 ` Jesse Barnes
2007-06-13 22:19 ` Eric W. Biederman
2007-06-20 11:22 ` Helge Hafting
2007-06-20 14:37 ` Andi Kleen
2007-06-07 22:30 Jesse Barnes
2007-06-07 22:50 ` Justin Piszcz
2007-06-07 22:53 ` Justin Piszcz
2007-06-07 23:00 ` Justin Piszcz
2007-06-08 8:20 ` Justin Piszcz
2007-06-12 14:50 ` Pavel Machek
2007-06-12 15:29 ` Jesse Barnes
2007-06-12 15:48 ` Andi Kleen
2007-06-12 21:30 ` Pavel Machek
2007-06-12 21:31 ` Justin Piszcz
2007-06-12 21:38 ` Ray Lee
2007-06-12 21:55 ` Pavel Machek
2007-06-13 0:25 ` Ray Lee
2007-06-13 8:22 ` Pavel Machek
2007-06-14 19:38 ` Pim Zandbergen
2007-06-14 20:26 ` Justin Piszcz
2007-06-14 21:18 ` Jesse Barnes
2007-06-14 21:21 ` Justin Piszcz
2007-06-14 21:26 ` Jesse Barnes
2007-06-15 10:21 ` Pim Zandbergen
2007-06-15 16:20 ` Jesse Barnes
2007-06-21 14:24 ` Pim Zandbergen
2007-06-21 14:28 ` Justin Piszcz
2007-06-25 16:31 ` Pim Zandbergen
2007-06-25 16:34 ` Justin Piszcz
2007-06-15 10:17 ` Pim Zandbergen
2007-06-15 10:34 ` Justin Piszcz
2007-06-15 17:28 ` Jesse Barnes
2007-06-20 13:55 ` Pim Zandbergen
2007-06-21 19:40 ` Yinghai Lu
2007-06-21 19:56 ` Jesse Barnes
[not found] <fa.i7vJP3lxWAlyOLjcsqOWPKlixD8@ifi.uio.no>
[not found] ` <fa.3ijVoClbWNHWrMhDABWjNPxp+wo@ifi.uio.no>
[not found] ` <fa.ZqgSvRGj/scOmd0AwnU6e21Gcwc@ifi.uio.no>
[not found] ` <fa.oNsjw768fkDpx3oef91fjAQs1Iw@ifi.uio.no>
[not found] ` <fa.x8ZCt4n0yXI1llhRq4wfjNfqK4w@ifi.uio.no>
2007-06-08 1:57 ` Robert Hancock
[not found] <8tyOc-8f0-17@gated-at.bofh.it>
2007-06-13 6:52 ` Bodo Eggert
2007-06-13 16:19 ` Dave Jones
2007-06-25 21:34 Jesse Barnes
2007-06-25 21:45 ` Justin Piszcz
2007-06-25 22:01 ` Andrew Morton
2007-06-25 22:05 ` Jesse Barnes
2007-06-25 22:29 ` Justin Piszcz
2007-06-25 23:34 ` Andi Kleen
2007-06-25 23:36 ` Jesse Barnes
2007-06-26 0:54 ` Eric W. Biederman
2007-06-26 3:29 ` Jesse Barnes
2007-06-26 3:30 ` Jesse Barnes
2007-06-26 15:03 ` Andi Kleen
2007-06-26 15:07 ` Jesse Barnes
2007-06-26 15:18 ` Jesse Barnes
2007-06-26 15:39 ` Andi Kleen
2007-06-26 15:54 ` Yinghai Lu
2007-06-26 16:06 ` Eric W. Biederman
2007-06-26 17:38 ` Andi Kleen
2007-06-26 18:55 ` Yinghai Lu
2007-06-26 15:02 ` Andi Kleen
2007-06-26 15:38 ` Jesse Barnes
2007-06-27 10:44 ` Pim Zandbergen
2007-06-27 11:22 ` Andi Kleen
2007-06-27 11:40 ` Pim Zandbergen
2007-06-27 11:44 ` Justin Piszcz
2007-06-27 14:22 ` Mauro Giachero
2007-06-27 15:04 ` Jesse Barnes
2007-06-27 16:00 ` Pim Zandbergen
2007-06-27 16:07 ` Jesse Barnes
2007-06-27 16:22 ` Jesse Barnes
2007-06-27 17:02 ` Pim Zandbergen
2007-06-27 17:06 ` Jesse Barnes
2007-06-27 17:17 ` Pim Zandbergen
2007-07-05 12:12 ` Pavel Machek
2007-07-05 12:16 ` Justin Piszcz
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=Pine.LNX.4.64.0706061838200.3563@p34.internal.lan \
--to=jpiszcz@lucidpixels.com \
--cc=andi@firstfloor.org \
--cc=ebiederm@xmission.com \
--cc=jesse.barnes@intel.com \
--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;
as well as URLs for NNTP newsgroup(s).