From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1761581AbYEETNO (ORCPT ); Mon, 5 May 2008 15:13:14 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751884AbYEETM6 (ORCPT ); Mon, 5 May 2008 15:12:58 -0400 Received: from relay1.sgi.com ([192.48.171.29]:55173 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1750885AbYEETM4 (ORCPT ); Mon, 5 May 2008 15:12:56 -0400 Date: Mon, 5 May 2008 12:12:56 -0700 (PDT) From: Christoph Lameter X-X-Sender: clameter@schroedinger.engr.sgi.com To: Mike Travis cc: arges@linux.vnet.ibm.com, phil.el@wanadoo.fr, mpjohn@us.ibm.com, Jack Steiner , Paul Jackson , Ingo Molnar , Andrew Morton , LKML Subject: Re: Hotplug CPU support for Oprofile In-Reply-To: <481F5965.6070305@sgi.com> Message-ID: References: <1210012443.6374.23.camel@snuffleupagus> <481F5965.6070305@sgi.com> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The allocpercpu approach creates a pointer array and results in objects distributed over all of memory. A cpu alloc approach would place dynamically allocated per cpu objects together which is better for memory consumption (no need to align) and performance (same TLB entry, neigboring memory cells, possible shared cachelines).