From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S937101AbXGSKmz (ORCPT ); Thu, 19 Jul 2007 06:42:55 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756492AbXGSKmq (ORCPT ); Thu, 19 Jul 2007 06:42:46 -0400 Received: from cantor.suse.de ([195.135.220.2]:39093 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755019AbXGSKmp (ORCPT ); Thu, 19 Jul 2007 06:42:45 -0400 From: Andi Kleen Organization: SUSE Linux Products GmbH, Nuernberg, GF: Markus Rex, HRB 16746 (AG Nuernberg) To: Christoph Hellwig Subject: Re: [PATCH] [33/58] x86_64: Avoid too many remote cpu references due to /proc/stat Date: Thu, 19 Jul 2007 12:41:28 +0200 User-Agent: KMail/1.9.6 Cc: kiran@scalex86.org, patches@x86-64.org, linux-kernel@vger.kernel.org References: <200707191154.642492000@suse.de> <20070719095519.10E4C14E11@wotan.suse.de> <20070719102149.GA7322@infradead.org> In-Reply-To: <20070719102149.GA7322@infradead.org> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200707191241.28383.ak@suse.de> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Thursday 19 July 2007 12:21:49 Christoph Hellwig wrote: > On Thu, Jul 19, 2007 at 11:55:19AM +0200, Andi Kleen wrote: > > > > From: Ravikiran G Thirumalai > > Too many remote cpu references due to /proc/stat. > > > > On x86_64, with newer kernel versions, kstat_irqs is a bit of a problem. > > On every call to kstat_irqs, the process brings in per-cpu data from all > > online cpus. Doing this for NR_IRQS, which is now 256 + 32 * NR_CPUS > > results in (256+32*63) * 63 remote cpu references on a 64 cpu config. > > /proc/stat is parsed by common commands like top, who etc, causing > > lots of cacheline transfers > > > > This statistic seems useless. Other 'big iron' arches disable this. > > Can we disable computing/reporting this statistic? This piece of > > statistic is not human readable on x86_64 anymore, > > > > If not, can we optimize computing this statistic so as to avoid > > too many remote references (patch to follow) > > If we disable this on x86_64 we should just kill it completely for consistency. I guess it's fine on UP only architectures. I will change it to !CONFIG_SMP unless someone complains. -Andi