From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754525Ab2KMPO2 (ORCPT ); Tue, 13 Nov 2012 10:14:28 -0500 Received: from mail-ea0-f174.google.com ([209.85.215.174]:35501 "EHLO mail-ea0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751643Ab2KMPO1 (ORCPT ); Tue, 13 Nov 2012 10:14:27 -0500 Date: Tue, 13 Nov 2012 16:14:16 +0100 From: Ingo Molnar To: Mel Gorman Cc: Peter Zijlstra , Andrea Arcangeli , Rik van Riel , Johannes Weiner , Hugh Dickins , Thomas Gleixner , Linus Torvalds , Andrew Morton , Linux-MM , LKML Subject: Re: [RFC PATCH 00/31] Foundation for automatic NUMA balancing V2 Message-ID: <20121113151416.GA20044@gmail.com> References: <1352805180-1607-1-git-send-email-mgorman@suse.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1352805180-1607-1-git-send-email-mgorman@suse.de> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Mel Gorman wrote: > (Since I wrote this changelog there has been another release > of schednuma. I had delayed releasing this series long enough > and decided not to delay further. Of course, I plan to dig > into that new revision and see what has changed.) Thanks, I've picked up a number of cleanups from your series and propagated them into tip:numa/core tree. FYI, in addition to the specific patches to which I replied to earier today, I've also propagated all your: CONFIG_SCHED_NUMA -> CONFIG_BALANCE_NUMA renames thoughout the patches - I fundamentally agree that CONFIG_BALANCE_NUMA is a better, more generic name. My structural criticism of the architecture specific bits of your patch-queue still applies to this version as well. That change inflicted much of the changes that you had to do to Peter's patches. It blew up the size of your tree and forks the code into per architecture variants for no good reason. Had you not done that and had you kept the code generic you'd essentially end up close to where tip:numa/core is today. So if we can clear that core issue up we'll have quite a bit of agreement. I'd also like to add another, structural side note: you mixed new vm-stats bits into the whole queue, needlessly blowing up the size and the mm/ specific portions of the tree. I'd suggest to post and keep those bits separately, preferably on top of what we have already once it has settled down. I'm keeping the 'perf bench numa' bits separate as well. Anyway, I've applied all applicable cleanups from you and picked up Peter's latest code with the modifications I've indicated in that thread, to the latest tip:numa/core tree, which I'll send out for review in the next hour or so. This version is supposed to address all review feedback received so far: it refines the MM specific split-up of the patches, fixes regressions - see the changelogs for more details. I'll (re-)send the full series of the latest patches and any additional feedback will be welcome. Thanks, Ingo