Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933853AbaFJAM0 (ORCPT ); Mon, 9 Jun 2014 20:12:26 -0400 Received: from mail-pa0-f52.google.com ([209.85.220.52]:62740 "EHLO mail-pa0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932345AbaFJAMZ (ORCPT ); Mon, 9 Jun 2014 20:12:25 -0400 Message-ID: <1402359051.22759.7.camel@debian> Subject: Re: [PATCH] mm/vmscan.c: avoid recording the original scan targets in shrink_lruvec() From: Chen Yucong To: Minchan Kim Cc: mgorman@suse.de, mhocko@suse.cz, hannes@cmpxchg.org, akpm@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org Date: Tue, 10 Jun 2014 08:10:51 +0800 In-Reply-To: <20140609232459.GA8171@bbox> References: <1402320436-22270-1-git-send-email-slaoub@gmail.com> <20140609232459.GA8171@bbox> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.4.4-3 Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2014-06-10 at 08:24 +0900, Minchan Kim wrote: > Hello, > > On Mon, Jun 09, 2014 at 09:27:16PM +0800, Chen Yucong wrote: > > Via https://lkml.org/lkml/2013/4/10/334 , we can find that recording the > > original scan targets introduces extra 40 bytes on the stack. This patch > > is able to avoid this situation and the call to memcpy(). At the same time, > > it does not change the relative design idea. > > > > ratio = original_nr_file / original_nr_anon; > > > > If (nr_file > nr_anon), then ratio = (nr_file - x) / nr_anon. > > x = nr_file - ratio * nr_anon; > > > > if (nr_file <= nr_anon), then ratio = nr_file / (nr_anon - x). > > x = nr_anon - nr_file / ratio; > > Nice cleanup! > > Below one nitpick. > > > If both nr_file and nr_anon are zero, then the nr_anon could be zero > if HugePage are reclaimed so that it could pass the below check > > if (nr_reclaimed < nr_to_reclaim || scan_adjusted) > > The Mel Gorman's patch has already handled this situation you're describing. It's called: mm: vmscan: use proportional scanning during direct reclaim and full scan at DEF_PRIORITY thx! cyc -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/