From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753923AbZBYAC0 (ORCPT ); Tue, 24 Feb 2009 19:02:26 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751592AbZBYACR (ORCPT ); Tue, 24 Feb 2009 19:02:17 -0500 Received: from smtp1.linux-foundation.org ([140.211.169.13]:52227 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751527AbZBYACQ (ORCPT ); Tue, 24 Feb 2009 19:02:16 -0500 Date: Tue, 24 Feb 2009 16:01:03 -0800 From: Andrew Morton To: Mel Gorman Cc: linux-mm@kvack.org, penberg@cs.helsinki.fi, riel@redhat.com, kosaki.motohiro@jp.fujitsu.com, cl@linux-foundation.org, hannes@cmpxchg.org, npiggin@suse.de, linux-kernel@vger.kernel.org, ming.m.lin@intel.com, yanmin_zhang@linux.intel.com Subject: Re: [PATCH 20/20] Get rid of the concept of hot/cold page freeing Message-Id: <20090224160103.df238662.akpm@linux-foundation.org> In-Reply-To: <20090224115126.GB25151@csn.ul.ie> References: <1235344649-18265-1-git-send-email-mel@csn.ul.ie> <1235344649-18265-21-git-send-email-mel@csn.ul.ie> <20090223013723.1d8f11c1.akpm@linux-foundation.org> <20090223233030.GA26562@csn.ul.ie> <20090223155313.abd41881.akpm@linux-foundation.org> <20090224115126.GB25151@csn.ul.ie> X-Mailer: Sylpheed version 2.2.4 (GTK+ 2.8.20; i486-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 24 Feb 2009 11:51:26 +0000 Mel Gorman wrote: > > > Almost the opposite with steady improvements almost all the way through. > > > > > > With the patch applied, we are still using hot/cold information on the > > > allocation side so I'm somewhat surprised the patch even makes much of a > > > difference. I'd have expected the pages being freed to be mostly hot. > > > > Oh yeah. Back in the ancient days, hot-cold-pages was using separate > > magazines for hot and cold pages. Then Christoph went and mucked with > > it, using a single queue. That might have affected things. > > > > It might have. The impact is that requests for cold pages can get hot pages > if there are not enough cold pages in the queue so readahead could prevent > an active process getting cache hot pages. I don't think that would have > showed up in the microbenchmark though. We switched to doing non-temporal stores in copy_from_user(), didn't we? That would rub out the benefit which that microbenchmark demonstrated?