From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755071AbaHENMf (ORCPT ); Tue, 5 Aug 2014 09:12:35 -0400 Received: from zene.cmpxchg.org ([85.214.230.12]:58354 "EHLO zene.cmpxchg.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754765AbaHENMe (ORCPT ); Tue, 5 Aug 2014 09:12:34 -0400 Date: Tue, 5 Aug 2014 09:12:23 -0400 From: Johannes Weiner To: Michal Hocko Cc: Andrew Morton , Hugh Dickins , linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org Subject: Re: [patch] mm: memcontrol: avoid charge statistics churn during page migration Message-ID: <20140805131223.GA14734@cmpxchg.org> References: <1407184469-20741-1-git-send-email-hannes@cmpxchg.org> <20140805122434.GD15908@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20140805122434.GD15908@dhcp22.suse.cz> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Aug 05, 2014 at 02:24:34PM +0200, Michal Hocko wrote: > On Mon 04-08-14 16:34:29, Johannes Weiner wrote: > > Charge migration currently disables IRQs twice to update the charge > > statistics for the old page and then again for the new page. > > > > But migration is a seemless transition of a charge from one physical > > page to another one of the same size, so this should be a non-event > > from an accounting point of view. Leave the statistics alone. > > Moving stats to mem_cgroup_commit_charge sounds logical to me but does > this work properly even for the fuse replace page cache case when old > and new pages can already live in different memcgs? We don't migrate if the new page is already charged.