From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
Andrew Morton <akpm@linux-foundation.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"lizf@cn.fujitsu.com" <lizf@cn.fujitsu.com>,
"menage@google.com" <menage@google.com>,
KOSAKI Motohiro <m-kosaki@ceres.dti.ne.jp>
Subject: Re: Low overhead patches for the memory cgroup controller (v4)
Date: Mon, 15 Jun 2009 08:14:33 +0530 [thread overview]
Message-ID: <4A35B591.7040504@linux.vnet.ibm.com> (raw)
In-Reply-To: <20090615112300.73ef1d8a.kamezawa.hiroyu@jp.fujitsu.com>
KAMEZAWA Hiroyuki wrote:
> On Mon, 15 Jun 2009 11:18:17 +0900
> Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp> wrote:
>
>> On Mon, 15 Jun 2009 00:07:40 +0530, Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
>>> Here is v4 of the patches, please review and comment
>>>
>>> Feature: Remove the overhead associated with the root cgroup
>>>
>>> From: Balbir Singh <balbir@linux.vnet.ibm.com>
>>>
>>> changelog v4 -> v3
>>> 1. Rebase to mmotm 9th june 2009
>>> 2. Remove PageCgroupRoot, we have account LRU flags to indicate that
>>> we do only accounting and no reclaim.
>> hmm, I prefer the previous version of PCG_ACCT_LRU meaning. It can be
>> used to remove annoying list_empty(&pc->lru) and !pc->mem_cgroup checks.
>>
>>> 3. pcg_default_flags has been used again, since PCGF_ROOT is gone,
>>> we set PCGF_ACCT_LRU only in mem_cgroup_add_lru_list
>> It might be safe, but I don't think it's a good idea to touch PCGF_ACCT_LRU
>> outside of zone->lru_lock.
>>
>> IMHO, the most complicated case is a SwapCache which has been read ahead by
>> a *different* cpu from the cpu doing do_swap_page(). Those SwapCache can be
>> on page_vec and be drained to LRU asymmetrically with do_swap_page().
>> Well, yes it would be safe just because PCGF_ACCT_LRU would not be set
>> if PCGF_USED has not been set, but I don't think it's a good idea to touch
>> PCGF_ACCT_LRU outside of zone->lru_lock anyway.
>>
>>
>> Doesn't a patch like below work for you ?
>> Lightly tested under global memory pressure(w/o memcg's memory pressure)
>> on a small machine(just a bit modified from then though).
>>
OK, so you like the older meaning and implementation, the code seems fine to me,
I like the removal of list_empty() checks that you and Kame have proposed.
--
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>
next prev parent reply other threads:[~2009-06-15 2:43 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-05-15 17:45 [RFC] Low overhead patches for the memory cgroup controller (v2) KAMEZAWA Hiroyuki
2009-05-15 18:16 ` Balbir Singh
2009-05-18 10:11 ` KAMEZAWA Hiroyuki
2009-05-18 10:45 ` Balbir Singh
2009-05-18 16:01 ` KAMEZAWA Hiroyuki
2009-05-19 13:18 ` Balbir Singh
2009-05-31 23:51 ` Balbir Singh
2009-06-01 23:57 ` KAMEZAWA Hiroyuki
2009-06-05 5:31 ` Low overhead patches for the memory cgroup controller (v3) Balbir Singh
2009-06-05 5:51 ` KAMEZAWA Hiroyuki
2009-06-05 9:33 ` Balbir Singh
2009-06-08 0:20 ` Daisuke Nishimura
2009-06-05 6:05 ` Daisuke Nishimura
2009-06-05 9:47 ` Balbir Singh
2009-06-08 0:03 ` Daisuke Nishimura
2009-06-05 6:43 ` Daisuke Nishimura
2009-06-14 18:37 ` Low overhead patches for the memory cgroup controller (v4) Balbir Singh
2009-06-15 2:04 ` KAMEZAWA Hiroyuki
2009-06-15 2:18 ` Daisuke Nishimura
2009-06-15 2:23 ` KAMEZAWA Hiroyuki
2009-06-15 2:44 ` Balbir Singh [this message]
2009-06-15 3:00 ` Balbir Singh
2009-06-15 3:09 ` Daisuke Nishimura
2009-06-15 3:22 ` Balbir Singh
2009-06-15 3:46 ` Daisuke Nishimura
2009-06-15 4:22 ` Balbir Singh
2009-05-17 4:15 ` [RFC] Low overhead patches for the memory cgroup controller (v2) Balbir Singh
2009-06-01 4:25 ` Daisuke Nishimura
2009-06-01 5:01 ` Daisuke Nishimura
2009-06-01 5:49 ` Balbir Singh
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=4A35B591.7040504@linux.vnet.ibm.com \
--to=balbir@linux.vnet.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.com \
--cc=m-kosaki@ceres.dti.ne.jp \
--cc=menage@google.com \
--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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).