LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Balbir Singh <balbir@linux.vnet.ibm.com>
To: Johannes Weiner <hannes@cmpxchg.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
	Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
	linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: memcg: save 20% of per-page memcg memory overhead
Date: Thu, 3 Feb 2011 20:32:47 +0530	[thread overview]
Message-ID: <20110203150247.GD16409@balbir.in.ibm.com> (raw)
In-Reply-To: <1296743166-9412-1-git-send-email-hannes@cmpxchg.org>

* Johannes Weiner <hannes@cmpxchg.org> [2011-02-03 15:26:01]:

> This patch series removes the direct page pointer from struct
> page_cgroup, which saves 20% of per-page memcg memory overhead (Fedora
> and Ubuntu enable memcg per default, openSUSE apparently too).
> 
> The node id or section number is encoded in the remaining free bits of
> pc->flags which allows calculating the corresponding page without the
> extra pointer.
> 
> I ran, what I think is, a worst-case microbenchmark that just cats a
> large sparse file to /dev/null, because it means that walking the LRU
> list on behalf of per-cgroup reclaim and looking up pages from
> page_cgroups is happening constantly and at a high rate.  But it made
> no measurable difference.  A profile reported a 0.11% share of the new
> lookup_cgroup_page() function in this benchmark.

Wow! defintely worth a deeper look.

> 
> 	Hannes

-- 
	Three Cheers,
	Balbir

      parent reply	other threads:[~2011-02-03 15:02 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-02-03 14:26 Johannes Weiner
2011-02-03 14:26 ` [patch 1/5] memcg: no uncharged pages reach page_cgroup_zoneinfo Johannes Weiner
2011-02-04  0:01   ` KAMEZAWA Hiroyuki
2011-02-04  9:26     ` Johannes Weiner
2011-02-04  9:23       ` KAMEZAWA Hiroyuki
2011-02-04  4:16   ` Balbir Singh
2011-02-03 14:26 ` [patch 2/5] memcg: change page_cgroup_zoneinfo signature Johannes Weiner
2011-02-04  0:03   ` KAMEZAWA Hiroyuki
2011-02-03 14:26 ` [patch 3/5] memcg: fold __mem_cgroup_move_account into caller Johannes Weiner
2011-02-04  0:07   ` KAMEZAWA Hiroyuki
2011-02-04  0:53     ` Daisuke Nishimura
2011-02-03 14:26 ` [patch 4/5] memcg: condense page_cgroup-to-page lookup points Johannes Weiner
2011-02-04  0:10   ` KAMEZAWA Hiroyuki
2011-02-03 14:26 ` [patch 5/5] memcg: remove direct page_cgroup-to-page pointer Johannes Weiner
2011-02-04  0:19   ` KAMEZAWA Hiroyuki
2011-02-04  9:51     ` Johannes Weiner
2011-02-03 15:02 ` Balbir Singh [this message]

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=20110203150247.GD16409@balbir.in.ibm.com \
    --to=balbir@linux.vnet.ibm.com \
    --cc=akpm@linux-foundation.org \
    --cc=hannes@cmpxchg.org \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=nishimura@mxp.nes.nec.co.jp \
    --subject='Re: memcg: save 20% of per-page memcg memory overhead' \
    /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

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).