From: Justin Piszcz <jpiszcz@lucidpixels.com>
To: Jesse Barnes <jesse.barnes@intel.com>
Cc: Randy Dunlap <randy.dunlap@oracle.com>,
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: Thu, 7 Jun 2007 04:10:38 -0400 (EDT) [thread overview]
Message-ID: <Pine.LNX.4.64.0706070410090.28913@p34.internal.lan> (raw)
In-Reply-To: <200706061634.00937.jesse.barnes@intel.com>
On Wed, 6 Jun 2007, Jesse Barnes wrote:
> On Wednesday, June 6, 2007 4:15 pm Justin Piszcz wrote:
>> On Wed, 6 Jun 2007, Randy Dunlap wrote:
>>> On Wed, 6 Jun 2007 18:54:37 -0400 (EDT) Justin Piszcz wrote:
>>>> Hm, not sure if it was from the patch or what but I ran this:
>>>>
>>>> 1. swapoff -a
>>>> 2. ./eatmem
>>>
>>> You usually have to access the allocated memory, like:
>>>
>>> *d = 1.0;
>>>
>>> for it to actually be allocated (AFAIK).
>>>
>>>> }
>>>>
>>>> return 0;
>>>> }
>>>>
>>>> Any idea why the OOM killer can or does not kill it?
>>>
>>> What are the values of /proc/sys/vm/overcommit* ?
>>>
>>> See Documentation/vm/overcommit-accounting .
>>
>> They should be the defaults as I do not change them:
>>
>> p34:~# find /proc/|grep -i overcommit
>> /proc/sys/vm/overcommit_memory
>> /proc/sys/vm/overcommit_ratio
>> find: /proc/5128: No such file or directory
>> p34:~# cat /proc/sys/vm/overcommit_memory
>> 0
>> p34:~# cat /proc/sys/vm/overcommit_ratio
>> 50
>> p34:~#
>>
>>
>> Comments?
>
> You can be sure your memory is available if reported in /proc/meminfo or
> at boot, since those represent the actual kernel data structures used
> for memory allocation:
>
> [ 0.000000] On node 0 totalpages: 2061783
>
> That corresponds to 2061783*4k = 8445063168 bytes or ~8053M. Is that
> fairly close to what's actually installed in the machine?
>
> Note that your boot also mentions this:
>
> [ 106.449661] mtrr: no more MTRRs available
>
> which indicates that things like X may not be able to map the
> framebuffer with the 'write-combine' attribute, which will hurt
> performance. I've heard reports that turning of 'Intel QST fan
> control' in your BIOS settings will prevent all your MTRRs from being
> used (improperly, probably another BIOS bug) so that X will perform
> well. But if you don't use X on this machine, you don't have to worry
> about it. The other option would be to remap your MTRRs by hand to
> free one up for X, you can do that by combining the last one or two
> entries into a single MTRR using the API described in
> Documentation/mtrr.txt before you start X.
>
> Jesse
>
FYI--
[ 106.449661] mtrr: no more MTRRs available
This has always occurred, even with mem=8832M setting.
Justin.
next prev parent reply other threads:[~2007-06-07 8:10 UTC|newest]
Thread overview: 118+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-06-06 19:29 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 [this message]
2007-06-06 22:39 ` Justin Piszcz
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.4.64.0706070410090.28913@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 \
--cc=randy.dunlap@oracle.com \
/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®