From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751996AbaJ0KIL (ORCPT ); Mon, 27 Oct 2014 06:08:11 -0400 Received: from mx2.parallels.com ([199.115.105.18]:48337 "EHLO mx2.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751551AbaJ0KIJ (ORCPT ); Mon, 27 Oct 2014 06:08:09 -0400 Date: Mon, 27 Oct 2014 13:08:02 +0300 From: Vladimir Davydov To: Johannes Weiner CC: Andrew Morton , Michal Hocko , , , Subject: Re: [patch] mm: memcontrol: shorten the page statistics update slowpath Message-ID: <20141027100802.GA12335@esperanza> References: <1414158020-25347-1-git-send-email-hannes@cmpxchg.org> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <1414158020-25347-1-git-send-email-hannes@cmpxchg.org> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 24, 2014 at 09:40:20AM -0400, Johannes Weiner wrote: > While moving charges from one memcg to another, page stat updates must > acquire the old memcg's move_lock to prevent double accounting. That > situation is denoted by an increased memcg->move_accounting. However, > the charge moving code declares this way too early for now, even > before summing up the RSS and pre-allocating destination charges. > > Shorten this slowpath mode by increasing memcg->move_accounting only > right before walking the task's address space with the intention of > actually moving the pages. > > Signed-off-by: Johannes Weiner Reviewed-by: Vladimir Davydov > --- > mm/memcontrol.c | 21 ++++++++------------- > 1 file changed, 8 insertions(+), 13 deletions(-) > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c > index c50176429fa3..23cf27cca370 100644 > --- a/mm/memcontrol.c > +++ b/mm/memcontrol.c > @@ -5263,8 +5263,6 @@ static void __mem_cgroup_clear_mc(void) > > static void mem_cgroup_clear_mc(void) > { > - struct mem_cgroup *from = mc.from; > - > /* > * we must clear moving_task before waking up waiters at the end of > * task migration. > @@ -5275,8 +5273,6 @@ static void mem_cgroup_clear_mc(void) > mc.from = NULL; > mc.to = NULL; > spin_unlock(&mc.lock); > - > - atomic_dec(&from->moving_account); > } > > static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, > @@ -5310,15 +5306,6 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, > VM_BUG_ON(mc.moved_charge); > VM_BUG_ON(mc.moved_swap); > > - /* > - * Signal mem_cgroup_begin_page_stat() to take > - * the memcg's move_lock while we're moving > - * its pages to another memcg. Then wait for > - * already started RCU-only updates to finish. > - */ > - atomic_inc(&from->moving_account); > - synchronize_rcu(); > - > spin_lock(&mc.lock); > mc.from = from; > mc.to = memcg; > @@ -5450,6 +5437,13 @@ static void mem_cgroup_move_charge(struct mm_struct *mm) > struct vm_area_struct *vma; > > lru_add_drain_all(); > + /* > + * Signal mem_cgroup_begin_page_stat() to take the memcg's > + * move_lock while we're moving its pages to another memcg. > + * Then wait for already started RCU-only updates to finish. > + */ > + atomic_inc(&mc.from->moving_account); > + synchronize_rcu(); > retry: > if (unlikely(!down_read_trylock(&mm->mmap_sem))) { > /* > @@ -5482,6 +5476,7 @@ retry: > break; > } > up_read(&mm->mmap_sem); > + atomic_dec(&mc.from->moving_account); > } > > static void mem_cgroup_move_task(struct cgroup_subsys_state *css, > -- > 2.1.2 >