From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
To: balbir@linux.vnet.ibm.com
Cc: kosaki.motohiro@jp.fujitsu.com, linux-mm@kvack.org,
Sudhir Kumar <skumar@linux.vnet.ibm.com>,
YAMAMOTO Takashi <yamamoto@valinux.co.jp>,
Bharata B Rao <bharata@in.ibm.com>,
Paul Menage <menage@google.com>,
lizf@cn.fujitsu.com, linux-kernel@vger.kernel.org,
David Rientjes <rientjes@google.com>,
Pavel Emelianov <xemul@openvz.org>,
Dhaval Giani <dhaval@linux.vnet.ibm.com>,
Rik van Riel <riel@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Subject: Re: [PATCH 4/4] Memory controller soft limit reclaim on contention (v3)
Date: Wed, 4 Mar 2009 09:07:21 +0900 (JST) [thread overview]
Message-ID: <20090304084928.FD57.A69D9226@jp.fujitsu.com> (raw)
In-Reply-To: <20090303111713.GQ11421@balbir.in.ibm.com>
Hi Balbir
> > > > kswapd's roll is increasing free pages until zone->pages_high in "own node".
> > > > mem_cgroup_soft_limit_reclaim() free one (or more) exceed page in any node.
> > > >
> > > > Oh, well.
> > > > I think it is not consistency.
> > > >
> > > > if mem_cgroup_soft_limit_reclaim() is aware to target node and its pages_high,
> > > > I'm glad.
> > >
> > > Yes, correct the role of kswapd is to keep increasing free pages until
> > > zone->pages_high and the first set of pages to consider is the memory
> > > controller over their soft limits. We pass the zonelist to ensure that
> > > while doing soft reclaim, we focus on the zonelist associated with the
> > > node. Kamezawa had concernes over calling the soft limit reclaim from
> > > __alloc_pages_internal(), did you prefer that call path?
> >
> > I read your patch again.
> > So, mem_cgroup_soft_limit_reclaim() caller place seems in balance_pgdat() is better.
> >
> > Please imazine most bad scenario.
> > CPU0 (kswapd) take to continue shrinking.
> > CPU1 take another activity and charge memcg conteniously.
> > At that time, balance_pgdat() don't exit very long time. then
> > mem_cgroup_soft_limit_reclaim() is never called.
> >
>
> Yes, true... that is why I added the hooks in __alloc_pages_internal()
> in the first two revisions, but Kamezawa objected to them. In the
> scenario that you mention that balance_pgdat() is busy, if we are
> under global system memory pressure, even after freeing memory from
> soft limited cgroups, we don't have sufficient free memory. We need to
> go reclaim from the whole system. An administrator can easily avoid
> the above scenario by using hard limits on the cgroup running on CPU1.
I agree with soft limit implementation is difficult.
but I still don't like soft limit in __alloc_pages_internal().
if it does, kswapd reclaim the pages from global LRU *before*
shrinking soft limit.
again, linux reclaim policy is
free < pages_low: run kswapd
free < pages_min: foreground reclaim via __alloc_pages_internal()
then, if soft limit reclaim put into __alloc_pages_internal(),
free < pages_low: run kswapd
free < pages_min: soft limit reclaim and
foreground reclaim via __alloc_pages_internal()
it seems unintetional behavior.
In addition, I still strongly oppose againt global lock although
soft limit shrinking don't put into __alloc_pages_internal().
I think it doesn't depend on caller place.
next prev parent reply other threads:[~2009-03-04 0:07 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-03-01 6:29 [PATCH 0/4] Memory controller soft limit patches (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 1/4] Memory controller soft limit documentation (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 2/4] Memory controller soft limit interface (v3) Balbir Singh
2009-03-02 2:03 ` KAMEZAWA Hiroyuki
2009-03-02 4:46 ` Balbir Singh
2009-03-02 5:35 ` KAMEZAWA Hiroyuki
2009-03-02 6:07 ` Balbir Singh
2009-03-02 6:19 ` KAMEZAWA Hiroyuki
2009-03-02 6:29 ` Balbir Singh
2009-03-01 6:30 ` [PATCH 3/4] Memory controller soft limit organize cgroups (v3) Balbir Singh
2009-03-01 6:30 ` [PATCH 4/4] Memory controller soft limit reclaim on contention (v3) Balbir Singh
2009-03-02 3:08 ` KOSAKI Motohiro
2009-03-02 4:44 ` Balbir Singh
2009-03-03 2:43 ` KOSAKI Motohiro
2009-03-03 11:17 ` Balbir Singh
2009-03-04 0:07 ` KOSAKI Motohiro [this message]
2009-03-02 0:24 ` [PATCH 0/4] Memory controller soft limit patches (v3) KAMEZAWA Hiroyuki
2009-03-02 4:40 ` Balbir Singh
2009-03-02 5:32 ` KAMEZAWA Hiroyuki
2009-03-02 6:05 ` Balbir Singh
2009-03-02 6:18 ` KAMEZAWA Hiroyuki
2009-03-02 17:52 ` Balbir Singh
2009-03-03 0:03 ` KAMEZAWA Hiroyuki
2009-03-03 11:23 ` Balbir Singh
2009-03-02 6:21 ` KAMEZAWA Hiroyuki
2009-03-02 6:36 ` Balbir Singh
2009-03-02 7:06 ` KAMEZAWA Hiroyuki
2009-03-02 7:17 ` KAMEZAWA Hiroyuki
2009-03-02 12:42 ` Balbir Singh
2009-03-02 14:04 ` KAMEZAWA Hiroyuki
2009-03-02 17:41 ` Balbir Singh
2009-03-02 23:59 ` KAMEZAWA Hiroyuki
2009-03-03 11:12 ` Balbir Singh
2009-03-03 11:50 ` KAMEZAWA Hiroyuki
2009-03-03 13:14 ` Balbir Singh
2009-03-05 9:04 ` KAMEZAWA Hiroyuki
2009-03-05 9:13 ` KAMEZAWA Hiroyuki
2009-03-05 15:26 ` Balbir Singh
2009-03-05 23:53 ` KAMEZAWA Hiroyuki
2009-03-06 3:23 ` 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=20090304084928.FD57.A69D9226@jp.fujitsu.com \
--to=kosaki.motohiro@jp.fujitsu.com \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=bharata@in.ibm.com \
--cc=dhaval@linux.vnet.ibm.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.com \
--cc=menage@google.com \
--cc=riel@redhat.com \
--cc=rientjes@google.com \
--cc=skumar@linux.vnet.ibm.com \
--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;
as well as URLs for NNTP newsgroup(s).