[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20100424112217.e2efb61b.kamezawa.hiroyu@jp.fujitsu.com>
Date: Sat, 24 Apr 2010 11:22:17 +0900
From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To: Peter Zijlstra <peterz@...radead.org>
Cc: Greg Thelen <gthelen@...gle.com>,
Daisuke Nishimura <nishimura@....nes.nec.co.jp>,
Vivek Goyal <vgoyal@...hat.com>, balbir@...ux.vnet.ibm.com,
Andrea Righi <arighi@...eler.com>,
Trond Myklebust <trond.myklebust@....uio.no>,
Suleiman Souhlal <suleiman@...gle.com>,
"Kirill A. Shutemov" <kirill@...temov.name>,
Andrew Morton <akpm@...ux-foundation.org>,
containers@...ts.linux-foundation.org,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH -mmotm 1/5] memcg: disable irq at page cgroup lock
On Fri, 23 Apr 2010 22:57:06 +0200
Peter Zijlstra <peterz@...radead.org> wrote:
> On Fri, 2010-04-23 at 13:17 -0700, Greg Thelen wrote:
> > +static void mem_cgroup_begin_page_cgroup_reassignment(void)
> > +{
> > + VM_BUG_ON(mem_cgroup_account_move_ongoing);
> > + mem_cgroup_account_move_ongoing = true;
> > + synchronize_rcu();
> > +}
>
> btw, you know synchronize_rcu() is _really_ slow?
>
IIUC, this is called once per an event when task is moved and we have
to move accouting information...and once per an event when we call
rmdir() to destroy cgroup.
So, this is not frequenctly called.
(hooks to migration in this patch is removable.)
Thanks,
-Kame
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists