All of lore.kernel.org
 help / color / mirror / Atom feed
From: "KAMEZAWA Hiroyuki" <kamezawa.hiroyu@jp.fujitsu.com>
To: balbir@linux.vnet.ibm.com
Cc: "KAMEZAWA Hiroyuki" <kamezawa.hiroyu@jp.fujitsu.com>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"nishimura@mxp.nes.nec.co.jp" <nishimura@mxp.nes.nec.co.jp>
Subject: Re: [RFC][PATCH 5/5] memcg: drain per cpu stock
Date: Mon, 31 Aug 2009 21:09:55 +0900 (JST)	[thread overview]
Message-ID: <360d07ecdf467c2e15231f420375ffee.squirrel@webmail-b.css.fujitsu.com> (raw)
In-Reply-To: <20090831111146.GJ4770@balbir.in.ibm.com>

Balbir Singh さんは書きました:
> * KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-08-28
> 13:28:09]:
>
>>
>> Add function for dropping per-cpu stock of charges.
>> This is called when
>> 	- cpu is unplugged.
>> 	- force_empty
>> 	- recalim seems to be not easy.
>>
>> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
>
> The complexity of this patch and additional code make percpu_counter
> more attractive. Why not work on percpu_counter if that is not as good
> as we expect it to be and in turn help other exploiters as well.

- percpu counter is slow.
- percpu counter is "counter". we use res_counter not as counter but as
  accounting for "limit". This "borrow" charges is core of this patch.
- Adding "flush" ops for percpu counter will be much more mess.
- This implementation handles mem->res and mem->memsw at the same time.
  This reduces much overhead.

Thanks,
-Kame


WARNING: multiple messages have this Message-ID (diff)
From: "KAMEZAWA Hiroyuki" <kamezawa.hiroyu@jp.fujitsu.com>
To: balbir@linux.vnet.ibm.com
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"nishimura@mxp.nes.nec.co.jp" <nishimura@mxp.nes.nec.co.jp>
Subject: Re: [RFC][PATCH 5/5] memcg: drain per cpu stock
Date: Mon, 31 Aug 2009 21:09:55 +0900 (JST)	[thread overview]
Message-ID: <360d07ecdf467c2e15231f420375ffee.squirrel@webmail-b.css.fujitsu.com> (raw)
In-Reply-To: <20090831111146.GJ4770@balbir.in.ibm.com>

Balbir Singh さんは書きました:
> * KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-08-28
> 13:28:09]:
>
>>
>> Add function for dropping per-cpu stock of charges.
>> This is called when
>> 	- cpu is unplugged.
>> 	- force_empty
>> 	- recalim seems to be not easy.
>>
>> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
>
> The complexity of this patch and additional code make percpu_counter
> more attractive. Why not work on percpu_counter if that is not as good
> as we expect it to be and in turn help other exploiters as well.

- percpu counter is slow.
- percpu counter is "counter". we use res_counter not as counter but as
  accounting for "limit". This "borrow" charges is core of this patch.
- Adding "flush" ops for percpu counter will be much more mess.
- This implementation handles mem->res and mem->memsw at the same time.
  This reduces much overhead.

Thanks,
-Kame

--
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:[~2009-08-31 12:09 UTC|newest]

Thread overview: 71+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-08-28  4:20 [RFC][PATCH 0/5] memcg: reduce lock conetion KAMEZAWA Hiroyuki
2009-08-28  4:20 ` KAMEZAWA Hiroyuki
2009-08-28  4:23 ` [RFC][PATCH 1/5] memcg: change for softlimit KAMEZAWA Hiroyuki
2009-08-28  4:23   ` KAMEZAWA Hiroyuki
2009-08-28  7:20   ` Balbir Singh
2009-08-28  7:20     ` Balbir Singh
2009-08-28  7:35     ` KAMEZAWA Hiroyuki
2009-08-28  7:35       ` KAMEZAWA Hiroyuki
2009-08-28 13:26       ` Balbir Singh
2009-08-28 13:26         ` Balbir Singh
2009-08-28 14:29         ` KAMEZAWA Hiroyuki
2009-08-28 14:29           ` KAMEZAWA Hiroyuki
2009-08-28 14:40           ` KAMEZAWA Hiroyuki
2009-08-28 14:40             ` KAMEZAWA Hiroyuki
2009-08-28 14:46             ` Balbir Singh
2009-08-28 15:06               ` KAMEZAWA Hiroyuki
2009-08-28 15:06                 ` KAMEZAWA Hiroyuki
2009-08-28 15:08                 ` Balbir Singh
2009-08-28 15:08                   ` Balbir Singh
2009-08-28 15:12                   ` KAMEZAWA Hiroyuki
2009-08-28 15:12                     ` KAMEZAWA Hiroyuki
2009-08-28 15:15                     ` Balbir Singh
2009-08-28 15:15                       ` Balbir Singh
2009-08-28 14:45           ` Balbir Singh
2009-08-28 14:45             ` Balbir Singh
2009-08-28 14:58             ` KAMEZAWA Hiroyuki
2009-08-28 14:58               ` KAMEZAWA Hiroyuki
2009-08-28 15:07               ` Balbir Singh
2009-08-28 15:07                 ` Balbir Singh
2009-08-28  4:24 ` [RFC][PATCH 2/5] memcg: uncharge in batched manner KAMEZAWA Hiroyuki
2009-08-28  4:24   ` KAMEZAWA Hiroyuki
2009-08-28  4:53   ` KAMEZAWA Hiroyuki
2009-08-28  4:53     ` KAMEZAWA Hiroyuki
2009-08-28  4:55     ` KAMEZAWA Hiroyuki
2009-08-28  4:55       ` KAMEZAWA Hiroyuki
2009-08-28 15:10   ` Balbir Singh
2009-08-28 15:10     ` Balbir Singh
2009-08-28 15:21     ` KAMEZAWA Hiroyuki
2009-08-28 15:21       ` KAMEZAWA Hiroyuki
2009-08-28 16:03       ` Balbir Singh
2009-08-28 16:03         ` Balbir Singh
2009-08-31 11:02   ` Balbir Singh
2009-08-31 11:02     ` Balbir Singh
2009-08-31 11:59     ` KAMEZAWA Hiroyuki
2009-08-31 11:59       ` KAMEZAWA Hiroyuki
2009-08-31 12:10       ` Balbir Singh
2009-08-31 12:14         ` KAMEZAWA Hiroyuki
2009-08-31 12:14           ` KAMEZAWA Hiroyuki
2009-08-31 12:23           ` Balbir Singh
2009-08-31 14:36             ` KAMEZAWA Hiroyuki
2009-08-31 14:36               ` KAMEZAWA Hiroyuki
2009-08-28  4:25 ` [RFC][PATCH 3/5] memcg: unmap, truncate, invalidate uncharege in batch KAMEZAWA Hiroyuki
2009-08-28  4:25   ` KAMEZAWA Hiroyuki
2009-08-31 11:02   ` Balbir Singh
2009-08-31 11:02     ` Balbir Singh
2009-08-28  4:27 ` [RFC][PATCH 4/5] memcg: per-cpu charge stock KAMEZAWA Hiroyuki
2009-08-28  4:27   ` KAMEZAWA Hiroyuki
2009-08-31 11:10   ` Balbir Singh
2009-08-31 11:10     ` Balbir Singh
2009-08-31 12:07     ` KAMEZAWA Hiroyuki
2009-08-31 12:07       ` KAMEZAWA Hiroyuki
2009-08-28  4:28 ` [RFC][PATCH 5/5] memcg: drain per cpu stock KAMEZAWA Hiroyuki
2009-08-28  4:28   ` KAMEZAWA Hiroyuki
2009-08-31 11:11   ` Balbir Singh
2009-08-31 11:11     ` Balbir Singh
2009-08-31 12:09     ` KAMEZAWA Hiroyuki [this message]
2009-08-31 12:09       ` KAMEZAWA Hiroyuki
2009-08-28  4:28 ` [RFC][PATCH 0/5] memcg: reduce lock conetion Balbir Singh
2009-08-28  4:28   ` Balbir Singh
2009-08-28  4:33   ` KAMEZAWA Hiroyuki
2009-08-28  4:33     ` 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=360d07ecdf467c2e15231f420375ffee.squirrel@webmail-b.css.fujitsu.com \
    --to=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nishimura@mxp.nes.nec.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 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.