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>,
linux-mm <linux-mm@kvack.org>, Li Zefan <lizf@cn.fujitsu.com>
Subject: Re: [RFC][BUGFIX] memcg: rmdir doesn't return
Date: Wed, 17 Jun 2009 14:54:14 +0530 [thread overview]
Message-ID: <20090617092414.GI7646@balbir.in.ibm.com> (raw)
In-Reply-To: <20090617180555.98f88d09.kamezawa.hiroyu@jp.fujitsu.com>
* KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-06-17 18:05:55]:
> On Wed, 17 Jun 2009 13:05:21 +0530
> Balbir Singh <balbir@linux.vnet.ibm.com> wrote:
>
> > * KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> [2009-06-17 15:27:48]:
>
> > > And even if release_agent() is called, it will do rmdir and see -EBUSY.
> >
> > Because of hierarchy? But we need to cleanup hierarchy before rmdir()
> > no?
> >
>
> Assume following (I think my patch in git explains this.)
>
> /cgroup/A/01
> /02
> /03
> /04
> A and 01,02,03,04 is under hierarchy.
>
> Now, 04 has no task and it can be removed by rmdir.
> Case 1) 01,02,03 hits memory limit heavily and hirerchical memory recalim
> walks. In this case, 04's css refcnt is got/put very often.
> Case 2) read statistics of cgroup/A very frequently, this means
> css_put/get is called very often agatinst 04.
>
> Case 3)....
>
> 04's refcnt is put/get when other group under hierarchy is busy and
> rmdir against 04 returns -EBUSY in some amount of possiblitly.
>
Yes, agreed! We did design hierarchy that way. Thanks for the detailed
explanation!
--
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:[~2009-06-17 9:23 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-06-12 5:33 Daisuke Nishimura
2009-06-12 6:19 ` KAMEZAWA Hiroyuki
2009-06-15 2:50 ` Daisuke Nishimura
2009-06-15 3:02 ` KAMEZAWA Hiroyuki
2009-06-15 8:17 ` KAMEZAWA Hiroyuki
2009-06-16 2:47 ` Daisuke Nishimura
2009-06-16 5:00 ` KAMEZAWA Hiroyuki
2009-06-16 6:38 ` Daisuke Nishimura
2009-06-16 6:48 ` KAMEZAWA Hiroyuki
2009-06-16 8:44 ` KAMEZAWA Hiroyuki
2009-06-17 4:56 ` Balbir Singh
2009-06-17 5:11 ` KAMEZAWA Hiroyuki
2009-06-17 5:49 ` Balbir Singh
2009-06-17 6:27 ` KAMEZAWA Hiroyuki
2009-06-17 7:35 ` Balbir Singh
2009-06-17 9:05 ` KAMEZAWA Hiroyuki
2009-06-17 9:24 ` Balbir Singh [this message]
2009-06-18 3:03 ` Daisuke Nishimura
2009-06-18 3:21 ` 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=20090617092414.GI7646@balbir.in.ibm.com \
--to=balbir@linux.vnet.ibm.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.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