All of lore.kernel.org
 help / color / mirror / Atom feed
From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"nishimura@mxp.nes.nec.co.jp" <nishimura@mxp.nes.nec.co.jp>,
	"xemul@openvz.org" <xemul@openvz.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Dave Hansen <haveblue@us.ibm.com>,
	ryov@valinux.co.jp
Subject: Re: [PATCH 1/12] memcg avoid accounting special mappings not on LRU
Date: Fri, 26 Sep 2008 15:02:13 +0530	[thread overview]
Message-ID: <48DCAC1D.9020802@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080926181726.359c77a8.kamezawa.hiroyu@jp.fujitsu.com>

KAMEZAWA Hiroyuki wrote:
> On Fri, 26 Sep 2008 13:55:54 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
> 
>> KAMEZAWA Hiroyuki wrote:
>>> There are not-on-LRU pages which can be mapped and they are not worth to
>>> be accounted. (becasue we can't shrink them and need dirty codes to handle
>>> specical case) We'd like to make use of usual objrmap/radix-tree's protcol
>>> and don't want to account out-of-vm's control pages.
>>>
>>> When special_mapping_fault() is called, page->mapping is tend to be NULL 
>>> and it's charged as Anonymous page.
>>> insert_page() also handles some special pages from drivers.
>>>
>>> This patch is for avoiding to account special pages.
>>>
>> Hmm... I am a little concerned that with these changes actual usage will much
>> more than what we report in memory.usage_in_bytes. Why not move them to
>> non-reclaimable LRU list as unevictable pages (once those patches go in, we can
>> push this as well). 
> 
> Because they are not on LRU ...i.e. !PageLRU(page)
> 

I understand.. Thanks for clarifying.. my concern is w.r.t accounting, we
account it in RSS (file RSS).

-- 
	Balbir

WARNING: multiple messages have this Message-ID (diff)
From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: "linux-mm@kvack.org" <linux-mm@kvack.org>,
	"nishimura@mxp.nes.nec.co.jp" <nishimura@mxp.nes.nec.co.jp>,
	"xemul@openvz.org" <xemul@openvz.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Dave Hansen <haveblue@us.ibm.com>,
	ryov@valinux.co.jp
Subject: Re: [PATCH 1/12] memcg avoid accounting special mappings not on LRU
Date: Fri, 26 Sep 2008 15:02:13 +0530	[thread overview]
Message-ID: <48DCAC1D.9020802@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080926181726.359c77a8.kamezawa.hiroyu@jp.fujitsu.com>

KAMEZAWA Hiroyuki wrote:
> On Fri, 26 Sep 2008 13:55:54 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
> 
>> KAMEZAWA Hiroyuki wrote:
>>> There are not-on-LRU pages which can be mapped and they are not worth to
>>> be accounted. (becasue we can't shrink them and need dirty codes to handle
>>> specical case) We'd like to make use of usual objrmap/radix-tree's protcol
>>> and don't want to account out-of-vm's control pages.
>>>
>>> When special_mapping_fault() is called, page->mapping is tend to be NULL 
>>> and it's charged as Anonymous page.
>>> insert_page() also handles some special pages from drivers.
>>>
>>> This patch is for avoiding to account special pages.
>>>
>> Hmm... I am a little concerned that with these changes actual usage will much
>> more than what we report in memory.usage_in_bytes. Why not move them to
>> non-reclaimable LRU list as unevictable pages (once those patches go in, we can
>> push this as well). 
> 
> Because they are not on LRU ...i.e. !PageLRU(page)
> 

I understand.. Thanks for clarifying.. my concern is w.r.t accounting, we
account it in RSS (file RSS).

-- 
	Balbir

--
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>

  reply	other threads:[~2008-09-26  9:34 UTC|newest]

Thread overview: 125+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-09-25  6:11 [PATCH 0/12] memcg updates v5 KAMEZAWA Hiroyuki
2008-09-25  6:13 ` [PATCH 1/12] memcg avoid accounting special mappings not on LRU KAMEZAWA Hiroyuki
2008-09-26  8:25   ` Balbir Singh
2008-09-26  8:25     ` Balbir Singh
2008-09-26  9:17     ` KAMEZAWA Hiroyuki
2008-09-26  9:17       ` KAMEZAWA Hiroyuki
2008-09-26  9:32       ` Balbir Singh [this message]
2008-09-26  9:32         ` Balbir Singh
2008-09-26  9:55         ` KAMEZAWA Hiroyuki
2008-09-26  9:55           ` KAMEZAWA Hiroyuki
2008-09-25  6:14 ` [PATCH 2/12] memcg move charege() call to swapped-in page under lock_page() KAMEZAWA Hiroyuki
2008-09-26  8:36   ` Balbir Singh
2008-09-26  8:36     ` Balbir Singh
2008-09-26  9:18     ` KAMEZAWA Hiroyuki
2008-09-26  9:18       ` KAMEZAWA Hiroyuki
2008-09-25  6:15 ` [PATCH 3/12] memcg make root cgroup unlimited KAMEZAWA Hiroyuki
2008-09-26  8:41   ` Balbir Singh
2008-09-26  8:41     ` Balbir Singh
2008-09-26  9:21     ` KAMEZAWA Hiroyuki
2008-09-26  9:21       ` KAMEZAWA Hiroyuki
2008-09-26  9:29       ` Balbir Singh
2008-09-26  9:29         ` Balbir Singh
2008-09-26  9:59         ` KAMEZAWA Hiroyuki
2008-09-26  9:59           ` KAMEZAWA Hiroyuki
2008-09-25  6:16 ` [PATCH 4/12] memcg make page->mapping NULL before calling uncharge KAMEZAWA Hiroyuki
2008-09-26  9:47   ` Balbir Singh
2008-09-26  9:47     ` Balbir Singh
2008-09-26 10:07     ` KAMEZAWA Hiroyuki
2008-09-26 10:07       ` KAMEZAWA Hiroyuki
2008-09-25  6:17 ` [PATCH 5/12] memcg make page_cgroup->flags atomic KAMEZAWA Hiroyuki
2008-09-27  6:58   ` Balbir Singh
2008-09-27  6:58     ` Balbir Singh
2008-09-25  6:18 ` [PATCH 6/12] memcg optimize percpu stat KAMEZAWA Hiroyuki
2008-09-26  9:53   ` Balbir Singh
2008-09-26  9:53     ` Balbir Singh
2008-09-25  6:27 ` [PATCH 7/12] memcg add function to move account KAMEZAWA Hiroyuki
2008-09-26  7:30   ` Daisuke Nishimura
2008-09-26  7:30     ` Daisuke Nishimura
2008-09-26  9:24     ` KAMEZAWA Hiroyuki
2008-09-26  9:24       ` KAMEZAWA Hiroyuki
2008-09-27  7:56   ` Balbir Singh
2008-09-27  7:56     ` Balbir Singh
2008-09-27  8:35     ` kamezawa.hiroyu
2008-09-27  8:35       ` kamezawa.hiroyu
2008-09-25  6:29 ` [PATCH 8/12] memcg rewrite force empty to move account to root KAMEZAWA Hiroyuki
2008-09-25  6:32 ` [PATCH 9/12] memcg allocate all page_cgroup at boot KAMEZAWA Hiroyuki
2008-09-25 18:40   ` Dave Hansen
2008-09-25 18:40     ` Dave Hansen
2008-09-26  1:17     ` KAMEZAWA Hiroyuki
2008-09-26  1:17       ` KAMEZAWA Hiroyuki
2008-09-26  1:22       ` KAMEZAWA Hiroyuki
2008-09-26  1:22         ` KAMEZAWA Hiroyuki
2008-09-26  1:00   ` Daisuke Nishimura
2008-09-26  1:00     ` Daisuke Nishimura
2008-09-26  1:43     ` KAMEZAWA Hiroyuki
2008-09-26  1:43       ` KAMEZAWA Hiroyuki
2008-09-26  2:05       ` KAMEZAWA Hiroyuki
2008-09-26  2:05         ` KAMEZAWA Hiroyuki
2008-09-26  5:54         ` Daisuke Nishimura
2008-09-26  5:54           ` Daisuke Nishimura
2008-09-26  6:54           ` KAMEZAWA Hiroyuki
2008-09-26  6:54             ` KAMEZAWA Hiroyuki
2008-09-27  3:47           ` KAMEZAWA Hiroyuki
2008-09-27  3:47             ` KAMEZAWA Hiroyuki
2008-09-27  3:25       ` KAMEZAWA Hiroyuki
2008-09-27  3:25         ` KAMEZAWA Hiroyuki
2008-09-26  2:21   ` [PATCH(fixed) " KAMEZAWA Hiroyuki
2008-09-26  2:21     ` KAMEZAWA Hiroyuki
2008-09-26  2:25     ` [PATCH(fixed) 10/12] free page cgroup from LRU in lazy KAMEZAWA Hiroyuki
2008-09-26  2:25       ` KAMEZAWA Hiroyuki
2008-09-26  2:28       ` [PATCH(fixed) 11/12] free page cgroup from LRU in add KAMEZAWA Hiroyuki
2008-09-26  2:28         ` KAMEZAWA Hiroyuki
2008-10-01  4:03   ` [PATCH 9/12] memcg allocate all page_cgroup at boot Balbir Singh
2008-10-01  4:03     ` Balbir Singh
2008-10-01  5:07     ` KAMEZAWA Hiroyuki
2008-10-01  5:07       ` KAMEZAWA Hiroyuki
2008-10-01  5:30       ` Balbir Singh
2008-10-01  5:30         ` Balbir Singh
2008-10-01  5:41         ` KAMEZAWA Hiroyuki
2008-10-01  5:41           ` KAMEZAWA Hiroyuki
2008-10-01  6:12           ` KAMEZAWA Hiroyuki
2008-10-01  6:12             ` KAMEZAWA Hiroyuki
2008-10-01  6:26             ` Balbir Singh
2008-10-01  6:26               ` Balbir Singh
2008-10-01  5:32       ` KAMEZAWA Hiroyuki
2008-10-01  5:32         ` KAMEZAWA Hiroyuki
2008-10-01  5:59         ` Balbir Singh
2008-10-01  5:59           ` Balbir Singh
2008-10-01  6:17           ` KAMEZAWA Hiroyuki
2008-10-01  6:17             ` KAMEZAWA Hiroyuki
2008-09-25  6:33 ` [PATCH 10/12] memcg free page_cgroup from LRU in lazy KAMEZAWA Hiroyuki
2008-09-25  6:35 ` [PATCH 11/12] memcg add to " KAMEZAWA Hiroyuki
2008-09-25  6:36 ` [PATCH 12/12] memcg: fix race at charging swap-in KAMEZAWA Hiroyuki
2008-09-26  2:32 ` [PATCH 0/12] memcg updates v5 Daisuke Nishimura
2008-09-26  2:32   ` Daisuke Nishimura
2008-09-26  2:58   ` KAMEZAWA Hiroyuki
2008-09-26  2:58     ` KAMEZAWA Hiroyuki
2008-09-26  3:04     ` KAMEZAWA Hiroyuki
2008-09-26  3:04       ` KAMEZAWA Hiroyuki
2008-09-26  3:00       ` Daisuke Nishimura
2008-09-26  3:00         ` Daisuke Nishimura
2008-09-26  4:05         ` KAMEZAWA Hiroyuki
2008-09-26  4:05           ` KAMEZAWA Hiroyuki
2008-09-26  5:24           ` Daisuke Nishimura
2008-09-26  5:24             ` Daisuke Nishimura
2008-09-26  9:28             ` KAMEZAWA Hiroyuki
2008-09-26  9:28               ` KAMEZAWA Hiroyuki
2008-09-26 10:43             ` KAMEZAWA Hiroyuki
2008-09-26 10:43               ` KAMEZAWA Hiroyuki
2008-09-27  2:53               ` KAMEZAWA Hiroyuki
2008-09-27  2:53                 ` KAMEZAWA Hiroyuki
2008-09-26  8:18 ` Balbir Singh
2008-09-26  8:18   ` Balbir Singh
2008-09-26  9:22   ` KAMEZAWA Hiroyuki
2008-09-26  9:22     ` KAMEZAWA Hiroyuki
2008-09-26  9:31     ` Balbir Singh
2008-09-26  9:31       ` Balbir Singh
2008-09-26 10:36       ` KAMEZAWA Hiroyuki
2008-09-26 10:36         ` KAMEZAWA Hiroyuki
2008-09-27  3:19         ` KAMEZAWA Hiroyuki
2008-09-27  3:19           ` KAMEZAWA Hiroyuki
2008-09-29  3:02           ` Balbir Singh
2008-09-29  3:02             ` Balbir Singh
2008-09-29  3:27             ` KAMEZAWA Hiroyuki
2008-09-29  3:27               ` 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=48DCAC1D.9020802@linux.vnet.ibm.com \
    --to=balbir@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=haveblue@us.ibm.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nishimura@mxp.nes.nec.co.jp \
    --cc=ryov@valinux.co.jp \
    --cc=xemul@openvz.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 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.