Re: [PATCH 1/4] memcg: do not try to drain per-cpu caches withoutpages
From: Michal Hocko
Date: Fri Jul 22 2011 - 06:23:39 EST
On Fri 22-07-11 11:58:15, Michal Hocko wrote:
> On Fri 22-07-11 18:28:22, KAMEZAWA Hiroyuki wrote:
> > On Fri, 22 Jul 2011 11:19:36 +0200
> > Michal Hocko <mhocko@xxxxxxx> wrote:
> > > On Fri 22-07-11 08:44:13, KAMEZAWA Hiroyuki wrote:
> > > > On Thu, 21 Jul 2011 13:36:06 +0200
> > > > By 2 methods
> > > >
> > > > - just check nr_pages.
> > >
> > > Not sure I understand which nr_pages you mean. The one that comes from
> > > the charging path or stock->nr_pages?
> > > If you mean the first one then we do not have in the reclaim path where
> > > we call drain_all_stock_async.
> > >
> > stock->nr_pages.
> > > > - drain "local stock" without calling schedule_work(). It's fast.
> > >
> > > but there is nothing to be drained locally in the paths where we call
> > > drain_all_stock_async... Or do you mean that drain_all_stock shouldn't
> > > use work queue at all?
> > I mean calling schedule_work against local cpu is just waste of time.
> > Then, drain it directly and move local cpu's stock->nr_pages to res_counter.
> got it. Thanks for clarification. Will repost the updated version.