From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754996Ab2EUMdB (ORCPT ); Mon, 21 May 2012 08:33:01 -0400 Received: from mail-bk0-f46.google.com ([209.85.214.46]:41244 "EHLO mail-bk0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754587Ab2EUMdA (ORCPT ); Mon, 21 May 2012 08:33:00 -0400 Date: Mon, 21 May 2012 14:32:46 +0200 From: Ingo Molnar To: "Shai Fultheim (Shai@ScaleMP.com)" Cc: Vlad Zolotarov , Thomas Gleixner , linux-kernel , Ingo Molnar , "H. Peter Anvin" , Ido Yariv Subject: Re: [PATCH v3 0/2] Move x86_cpu_to_apicid to the __read_mostly section Message-ID: <20120521123246.GB17065@gmail.com> References: <1337527148.6093.14.camel@vlad> <20120521090638.GE31407@gmail.com> <9B14D1490DDECA4E974F6B9FC9EBAB317D295F4D11@VMBX108.ihostexchange.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <9B14D1490DDECA4E974F6B9FC9EBAB317D295F4D11@VMBX108.ihostexchange.net> 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 * Shai Fultheim (Shai@ScaleMP.com) wrote: > Ingo, > > The reason for this, as you pointed out, is the 'cache line' > size (4096 bytes). We see significant false sharing is we do > not move this next to each other. Which write-often variable caused the many cache flushes/fills? cpu_to_apicid is read mostly. I.e. it might make more sense to identify the frequenty *modified* percpu variables, and move them to a separate section. I *think* most percpu variables are read mostly, so it would be more maintainable in the long run to figure out the frequently modified ones, not the frequently not modified ones. Thanks, Ingo