From: Johannes Weiner <hannes@cmpxchg.org>
To: Hiroyuki Kamezawa <kamezawa.hiroyuki@gmail.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
Balbir Singh <balbir@linux.vnet.ibm.com>,
Ying Han <yinghan@google.com>, Michal Hocko <mhocko@suse.cz>,
Andrew Morton <akpm@linux-foundation.org>,
Rik van Riel <riel@redhat.com>,
Minchan Kim <minchan.kim@gmail.com>,
KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Mel Gorman <mgorman@suse.de>, Greg Thelen <gthelen@google.com>,
Michel Lespinasse <walken@google.com>,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [patch 0/8] mm: memcg naturalization -rc2
Date: Thu, 2 Jun 2011 12:00:07 +0200 [thread overview]
Message-ID: <20110602100007.GB20725@cmpxchg.org> (raw)
In-Reply-To: <BANLkTikztP6RoyBgMqUHgrzJFLZrHMCs=Q@mail.gmail.com>
On Thu, Jun 02, 2011 at 06:06:51PM +0900, Hiroyuki Kamezawa wrote:
> 2011/6/2 Johannes Weiner <hannes@cmpxchg.org>:
> > On Thu, Jun 02, 2011 at 08:52:47AM +0900, Hiroyuki Kamezawa wrote:
> >> 2011/6/1 Johannes Weiner <hannes@cmpxchg.org>:
> >
> > The patch series is not a performance optimization. But I can include
> > it to prove there are no regressions.
> >
> yes, it's helpful.
Okay.
> >> Hmm, how about splitting patch 2/8 into small patches and see what happens in
> >> 3.2 or 3.3 ? While that, we can make softlimit works better.
> >> (and once we do 2/8, our direction will be fixed to the direction to
> >> remove global LRU.)
> >
> > Do you have specific parts in mind that could go stand-alone?
> >
> > One thing I can think of is splitting up those parts:
> >
> > 1. move /target/ reclaim to generic code
> >
> > 2. convert /global/ reclaim from global lru to hierarchy reclaim
> > including root_mem_cgroup
>
> Hmm, at brief look
> patch 2/8
> - hierarchy walk rewrite code should be stand alone and can be merged
> 1st, as clean-up
You mean introducing mem_cgroup_hierarchy_walk() and make use of it in
mem_cgroup_hierarchical_reclaim() as a first step?
> - root cgroup LRU handling was required for performance. I think we
> removed tons of
> atomic ops and can remove that special handling personally. But this change of
> root cgroup handling should be in separate patch. with performance report.
I disagree.
With view on the whole patch series, linking ungrouped process pages
to the root_mem_cgroup is traded against
1. linking ungrouped process pages to the global LRU
2. linking grouped process pages to both the global LRU and the
memcg LRU
The comparison you propose is neither fair nor relevant because it
would never make sense to merge that patch without the others.
--
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/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2011-06-02 10:00 UTC|newest]
Thread overview: 110+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-01 6:25 Johannes Weiner
2011-06-01 6:25 ` [patch 1/8] memcg: remove unused retry signal from reclaim Johannes Weiner
2011-06-01 6:25 ` [patch 2/8] mm: memcg-aware global reclaim Johannes Weiner
2011-06-02 13:59 ` Hiroyuki Kamezawa
2011-06-02 15:01 ` Johannes Weiner
2011-06-02 16:14 ` Hiroyuki Kamezawa
2011-06-02 17:29 ` Johannes Weiner
2011-06-09 14:01 ` Michal Hocko
2011-06-07 12:25 ` Christoph Hellwig
2011-06-08 9:30 ` Johannes Weiner
2011-06-09 9:26 ` Christoph Hellwig
2011-06-09 16:57 ` Johannes Weiner
2011-06-09 13:12 ` Michal Hocko
2011-06-09 13:45 ` Johannes Weiner
2011-06-09 15:48 ` Minchan Kim
2011-06-09 17:23 ` Johannes Weiner
2011-06-09 23:41 ` Minchan Kim
2011-06-09 23:47 ` Minchan Kim
2011-06-10 0:34 ` Johannes Weiner
2011-06-10 0:48 ` Minchan Kim
2011-08-11 20:39 ` Ying Han
2011-08-11 21:09 ` Johannes Weiner
2011-08-29 7:15 ` Ying Han
2011-08-29 7:22 ` Ying Han
2011-08-29 7:57 ` Johannes Weiner
2011-08-30 6:08 ` Ying Han
2011-08-29 19:04 ` Johannes Weiner
2011-08-29 20:36 ` Ying Han
2011-08-29 21:05 ` Johannes Weiner
2011-08-30 7:07 ` Ying Han
2011-08-30 15:14 ` Johannes Weiner
2011-08-31 22:58 ` Ying Han
2011-09-21 8:44 ` Johannes Weiner
2011-08-29 8:07 ` Johannes Weiner
2011-06-01 6:25 ` [patch 3/8] memcg: reclaim statistics Johannes Weiner
2011-06-01 6:25 ` [patch 4/8] memcg: rework soft limit reclaim Johannes Weiner
2011-06-02 5:37 ` Ying Han
2011-06-02 21:55 ` Ying Han
2011-06-03 5:25 ` Ying Han
2011-06-09 15:00 ` Michal Hocko
2011-06-10 7:36 ` Michal Hocko
2011-06-15 22:57 ` Ying Han
2011-06-16 0:33 ` Ying Han
2011-06-16 11:45 ` Michal Hocko
2011-06-15 22:48 ` Ying Han
2011-06-16 11:41 ` Michal Hocko
2011-06-01 6:25 ` [patch 5/8] memcg: remove unused soft limit code Johannes Weiner
2011-06-13 9:26 ` Michal Hocko
2011-06-01 6:25 ` [patch 6/8] vmscan: change zone_nr_lru_pages to take memcg instead of scan control Johannes Weiner
2011-06-02 13:30 ` Hiroyuki Kamezawa
2011-06-02 14:28 ` Johannes Weiner
2011-06-13 9:29 ` Michal Hocko
2011-06-01 6:25 ` [patch 7/8] vmscan: memcg-aware unevictable page rescue scanner Johannes Weiner
2011-06-02 13:27 ` Hiroyuki Kamezawa
2011-06-02 14:27 ` Johannes Weiner
2011-06-02 21:02 ` Ying Han
2011-06-02 22:01 ` Hiroyuki Kamezawa
2011-06-02 22:19 ` Johannes Weiner
2011-06-02 23:15 ` Hiroyuki Kamezawa
2011-06-03 5:08 ` Ying Han
2011-06-13 9:42 ` Michal Hocko
2011-06-13 10:30 ` Johannes Weiner
2011-06-13 11:18 ` Michal Hocko
2011-07-19 22:47 ` Ying Han
2011-07-20 0:36 ` Johannes Weiner
2011-08-29 7:28 ` Ying Han
2011-08-29 7:59 ` Johannes Weiner
2011-06-01 6:25 ` [patch 8/8] mm: make per-memcg lru lists exclusive Johannes Weiner
2011-06-02 13:16 ` Hiroyuki Kamezawa
2011-06-02 14:24 ` Johannes Weiner
2011-06-02 15:54 ` Hiroyuki Kamezawa
2011-06-02 17:57 ` Johannes Weiner
2011-06-08 15:04 ` Michal Hocko
2011-06-07 12:42 ` Christoph Hellwig
2011-06-08 8:54 ` Johannes Weiner
2011-06-09 9:23 ` Christoph Hellwig
2011-08-11 20:33 ` Ying Han
2011-08-12 8:34 ` Johannes Weiner
2011-08-12 17:08 ` Ying Han
2011-08-12 19:17 ` Johannes Weiner
2011-08-15 3:01 ` Ying Han
2011-08-15 1:34 ` Ying Han
2011-08-15 9:39 ` Johannes Weiner
2011-06-01 23:52 ` [patch 0/8] mm: memcg naturalization -rc2 Hiroyuki Kamezawa
2011-06-02 0:35 ` Greg Thelen
2011-06-09 1:13 ` Rik van Riel
2011-06-02 4:05 ` Ying Han
2011-06-02 7:50 ` Johannes Weiner
2011-06-02 15:51 ` Ying Han
2011-06-02 17:51 ` Johannes Weiner
2011-06-08 3:45 ` Ying Han
2011-06-08 3:53 ` Ying Han
2011-06-08 15:32 ` Johannes Weiner
2011-06-09 3:52 ` Ying Han
2011-06-09 8:35 ` Johannes Weiner
2011-06-09 17:36 ` Ying Han
2011-06-09 18:36 ` Johannes Weiner
2011-06-09 21:38 ` Ying Han
2011-06-09 22:30 ` Ying Han
2011-06-09 23:31 ` Johannes Weiner
2011-06-10 0:17 ` Ying Han
2011-06-02 7:33 ` Johannes Weiner
2011-06-02 9:06 ` Hiroyuki Kamezawa
2011-06-02 10:00 ` Johannes Weiner [this message]
2011-06-02 12:59 ` Hiroyuki Kamezawa
2011-06-09 1:15 ` Rik van Riel
2011-06-09 8:43 ` Johannes Weiner
2011-06-09 9:31 ` Christoph Hellwig
2011-06-13 9:47 ` Michal Hocko
2011-06-13 10:35 ` Johannes Weiner
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=20110602100007.GB20725@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=gthelen@google.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kamezawa.hiroyuki@gmail.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.cz \
--cc=minchan.kim@gmail.com \
--cc=nishimura@mxp.nes.nec.co.jp \
--cc=riel@redhat.com \
--cc=walken@google.com \
--cc=yinghan@google.com \
/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