All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrea Arcangeli <aarcange@redhat.com>
To: Shaohua Li <shaohua.li@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	linux-mm <linux-mm@kvack.org>,
	"Chen, Tim C" <tim.c.chen@intel.com>, Mel Gorman <mel@csn.ul.ie>
Subject: Re: too big min_free_kbytes
Date: Mon, 24 Jan 2011 16:00:34 +0100	[thread overview]
Message-ID: <20110124150033.GB9506@random.random> (raw)
In-Reply-To: <1295841406.1949.953.camel@sli10-conroe>

eOn Mon, Jan 24, 2011 at 11:56:46AM +0800, Shaohua Li wrote:
> Hi,
> With transparent huge page, min_free_kbytes is set too big.
> Before:
> Node 0, zone    DMA32
>   pages free     1812
>         min      1424
>         low      1780
>         high     2136
>         scanned  0
>         spanned  519168
>         present  511496
> 
> After:
> Node 0, zone    DMA32
>   pages free     482708
>         min      11178
>         low      13972
>         high     16767
>         scanned  0
>         spanned  519168
>         present  511496
> This caused different performance problems in our test. I wonder why we
> set the value so big.

It's to enable Mel's anti-frag that keeps pageblocks with movable and
unmovable stuff separated, same as "hugeadm
--set-recommended-min_free_kbytes".

Now that I checked, I'm seeing quite too much free memory with only 4G
of ram... You can see the difference with a "cp /dev/sda /dev/null" in
background interleaving these two commands:

echo always >/sys/kernel/mm/transparent_hugepage/enabled
echo 1000 > /proc/sys/vm/min_free_kbytes

The setting of min_free_kbytes to 67584 leads to 716MB of memory
free. Setting to 1000 leads to 20MB free. I'm afraid losing 716MB on a
4G system is way excessive regardless of THP... can't we just have a
version of anti-frag that reserves a lot fewers pageblocks? Anti-frag
is quite important to avoid slab to fragment everything. I don't think
we can leave it like this.

For now you can workaround with the above echo 1000 > ...

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2011-01-24 15:01 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-01-24  3:56 too big min_free_kbytes Shaohua Li
2011-01-24 15:00 ` Andrea Arcangeli [this message]
2011-01-25 14:35   ` Mel Gorman
2011-01-26 14:17   ` Mel Gorman
2011-01-26 15:23     ` Mel Gorman
2011-01-26 15:42       ` Andrea Arcangeli
2011-01-26 16:36         ` Mel Gorman
2011-01-26 17:42           ` Mel Gorman
2011-01-27 13:40             ` Mel Gorman
2011-01-27 15:27               ` Andrea Arcangeli
2011-01-27 16:03                 ` Mel Gorman
2011-01-27 18:52                   ` Andrea Arcangeli
2011-01-27 20:33                     ` Rik van Riel
2011-01-27 21:31                     ` Mel Gorman
2011-01-27 23:18                       ` Rik van Riel
2011-01-28 10:35                         ` Mel Gorman
2011-01-28 16:28                           ` Andrea Arcangeli
2011-01-28 16:46                             ` Mel Gorman
2011-01-28 17:16                               ` Rik van Riel
2011-01-28 17:46                                 ` Andrea Arcangeli
2011-01-28 18:03                                   ` Rik van Riel
2011-01-28 18:24                                     ` Andrea Arcangeli
2011-01-28 19:34                                       ` Rik van Riel
2011-01-28 19:45                                         ` Andrea Arcangeli
2011-01-28 20:55                                           ` Rik van Riel
2011-01-29 19:45                                             ` Andrea Arcangeli
2011-01-28 17:34                               ` Andrea Arcangeli
2011-01-28 17:10                             ` Rik van Riel
2011-02-03  2:58                 ` Andrea Arcangeli
2011-02-03 13:15                   ` Mel Gorman
2011-02-03 18:59                     ` Andrea Arcangeli
2011-02-03 14:36                   ` Rik van Riel
2011-02-03 19:11                     ` Andrea Arcangeli
2011-02-12  1:28                       ` Simon Kirby
2011-02-14  2:25                   ` Shaohua Li
2011-02-22 14:25                     ` Mel Gorman
2011-02-22 14:42                       ` Andrea Arcangeli
2011-02-22 14:50                         ` Mel Gorman
2011-02-22 14:54                           ` Andrea Arcangeli
2011-02-22 16:04                         ` Mel Gorman
2011-02-22 16:40                           ` Rik van Riel
2011-02-23  5:29                       ` Shaohua Li
2011-02-23 14:45                         ` Andrea Arcangeli
2011-02-24  8:08                           ` Shaohua Li
2011-02-24  9:52                             ` Mel Gorman
2011-02-24  9:57                               ` Mel Gorman
2011-02-24 14:27                                 ` Andrea Arcangeli
2011-02-24 14:04                             ` Andrea Arcangeli
2011-02-25  0:51                               ` Shaohua Li
2011-02-25 12:13                                 ` Mel Gorman
2011-02-12  9:48                 ` alex shi
2011-02-22 14:24                   ` Mel Gorman

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=20110124150033.GB9506@random.random \
    --to=aarcange@redhat.com \
    --cc=akpm@linux-foundation.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=shaohua.li@intel.com \
    --cc=tim.c.chen@intel.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 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.