From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752614AbYLCNqr (ORCPT ); Wed, 3 Dec 2008 08:46:47 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1750758AbYLCNqj (ORCPT ); Wed, 3 Dec 2008 08:46:39 -0500 Received: from mx2.redhat.com ([66.187.237.31]:41105 "EHLO mx2.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750755AbYLCNqi (ORCPT ); Wed, 3 Dec 2008 08:46:38 -0500 Message-ID: <49368DAF.9060206@redhat.com> Date: Wed, 03 Dec 2008 08:46:23 -0500 From: Rik van Riel Organization: Red Hat, Inc User-Agent: Thunderbird 2.0.0.17 (X11/20080915) MIME-Version: 1.0 To: KOSAKI Motohiro CC: akpm@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, mel@csn.ul.ie Subject: Re: [PATCH] vmscan: improve reclaim throuput to bail out patch References: <49316CAF.2010006@redhat.com> <20081130150849.8140.KOSAKI.MOTOHIRO@jp.fujitsu.com> <20081203140419.1D44.KOSAKI.MOTOHIRO@jp.fujitsu.com> In-Reply-To: <20081203140419.1D44.KOSAKI.MOTOHIRO@jp.fujitsu.com> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org KOSAKI Motohiro wrote: > Hi > > I evaluate rvr bailout and skip-freeing patch in this week conteniously. > I'd like to dump first output here. > > > > Rik, could you please review following? > == > vmscan bail out patch move nr_reclaimed variable to struct scan_control. > Unfortunately, indirect access can easily happen cache miss. > More unfortunately, Some architecture (e.g. ia64) don't access global > variable so fast. That is amazing. Especially considering that the scan_control is a local variable on the stack. > if heavy memory pressure happend, that's ok. > cache miss already plenty. it is not observable. > > but, if memory pressure is lite, performance degression is obserbable. > about 4-5% degression. > > Then, this patch introduce temporal local variable. > OK. the degression is disappeared. I can't argue with the numbers, though :) Maybe all the scanning we do ends up evicting the cache lines with the scan_control struct in it from the fast part of the CPU cache? > Signed-off-by: KOSAKI Motohiro Acked-by: Rik van Riel -- All rights reversed.