Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756025Ab2F2Qas (ORCPT ); Fri, 29 Jun 2012 12:30:48 -0400 Received: from mx1.redhat.com ([209.132.183.28]:37136 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754249Ab2F2Qar (ORCPT ); Fri, 29 Jun 2012 12:30:47 -0400 Date: Fri, 29 Jun 2012 18:30:33 +0200 From: Petr Holasek To: Johannes Weiner Cc: Hugh Dickins , Andrew Morton , Andrea Arcangeli , Chris Wright , Izik Eidus , Rik van Riel , linux-kernel@vger.kernel.org, linux-mm@kvack.org, Anton Arapov Subject: Re: [PATCH v2] KSM: numa awareness sysfs knob Message-ID: <20120629163033.GA11327@stainedmachine.redhat.com> References: <1340970592-25001-1-git-send-email-pholasek@redhat.com> <20120629160510.GA10082@cmpxchg.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20120629160510.GA10082@cmpxchg.org> 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 Content-Length: 1324 Lines: 30 On Fri, 29 Jun 2012, Johannes Weiner wrote: > On Fri, Jun 29, 2012 at 01:49:52PM +0200, Petr Holasek wrote: > > Introduces new sysfs boolean knob /sys/kernel/mm/ksm/merge_nodes > > which control merging pages across different numa nodes. > > When it is set to zero only pages from the same node are merged, > > otherwise pages from all nodes can be merged together (default behavior). > > Is it conceivable that admins may (in the future) want to merge only > across nodes that are below a given distance threshold? > > I'm not asking to implement this, just whether the knob can be > introduced such that it's future-compatible. Make it default to a > Very High Number and only allow setting it to 0 for now e.g.? And > name it max_node_merge_distance (I'm bad at names)? > > What do you think? I started with exactly same idea as you described above in the first RFC, link: https://lkml.org/lkml/2011/11/30/91 But this approach turned out to be more complicated than it looked (see two last emails in thread) and complexity of solution would rise a lot. Regards, Petr H -- 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/