linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Hirokazu Takahashi <taka@valinux.co.jp>
To: kamezawa.hiroyu@jp.fujitsu.com
Cc: linux-mm@kvack.org, balbir@linux.vnet.ibm.com, xemul@openvz.org,
	hugh@veritas.com, yamamoto@valinux.co.jp
Subject: Re: [Preview] [PATCH] radix tree based page cgroup [0/6]
Date: Thu, 06 Mar 2008 19:03:04 +0900 (JST)	[thread overview]
Message-ID: <20080306.190304.83917780.taka@valinux.co.jp> (raw)
In-Reply-To: <20080305205137.5c744097.kamezawa.hiroyu@jp.fujitsu.com>

Hi,

> Hi, this is the latest version of radix-tree based page cgroup patch.
> 
> I post this now because recent major changes are included in 2.6.25-rc4.
> (I admit I should do more tests on this set.)
> 
> Almost all are rewritten and adjusted to rc4's logic.
> I feel this set is simpler than previous one.
> 
> Patch series is following.
> [1/6] page cgroup definition
> [2/6] patch against charge/uncharge 
> [3/6] patch against move_list
> [4/6] patch against migration
> [5/6] radix tree based page_cgroup
> [6/6] boost by per-cpu cache.
> 
>  * force_empty patch is dropped because it's unnecessary.
>  * vmalloc patch is dropped. we always use kmalloc in this version.
> 
> TODO:
>   - add freeing page_cgroup routine. it seems necessary sometimes.
>     (I have one and will be added to this set in the next post.)

I doubt page_cgroups can be freed effectively since most of the pages
are used and each of them has its corresponding page_cgroup when you
need more free memory.

In this case, right after some page_cgroup freed when the corresponding
pages are released, these pages are reallocated and page_cgroups are
also reallocated and assigned to them. It will only give us meaningless
overhead.

And I think it doesn't make sense to free page_cgroups to make much more
free memory if there are a lot of free memory,

I guess freeing page_cgroup routine will be fine when making hugetlb
pages.

>   - Logic check again.
> 
> Thanks,
> -Kame


Thanks,
Hirokazu Takahashi.

--
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/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2008-03-06 10:03 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-05 11:51 KAMEZAWA Hiroyuki
2008-03-05 11:55 ` [Preview] [PATCH] radix tree based page cgroup [1/6] KAMEZAWA Hiroyuki
2008-03-05 11:57 ` [Preview] [PATCH] radix tree based page cgroup [2/6] charge and uncharge KAMEZAWA Hiroyuki
2008-03-05 11:57 ` [Preview] [PATCH] radix tree based page cgroup [3/6] move_lists KAMEZAWA Hiroyuki
2008-03-05 12:01   ` [Preview] [PATCH] radix tree based page cgroup [6/6] boost by per-cpu KAMEZAWA Hiroyuki
2008-03-05 12:00 ` [Preview] [PATCH] radix tree based page cgroup [5/6] radix-tree-page-cgroup KAMEZAWA Hiroyuki
2008-03-06  0:28 ` [Preview] [PATCH] radix tree based page cgroup [4/6] migraton KAMEZAWA Hiroyuki
2008-03-06 10:03 ` Hirokazu Takahashi [this message]
2008-03-06 11:26   ` [Preview] [PATCH] radix tree based page cgroup [0/6] KAMEZAWA Hiroyuki

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=20080306.190304.83917780.taka@valinux.co.jp \
    --to=taka@valinux.co.jp \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=hugh@veritas.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=xemul@openvz.org \
    --cc=yamamoto@valinux.co.jp \
    /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