From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755618AbZCDAvQ (ORCPT ); Tue, 3 Mar 2009 19:51:16 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752379AbZCDAu6 (ORCPT ); Tue, 3 Mar 2009 19:50:58 -0500 Received: from mx3.mail.elte.hu ([157.181.1.138]:41780 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750875AbZCDAu5 (ORCPT ); Tue, 3 Mar 2009 19:50:57 -0500 Date: Wed, 4 Mar 2009 01:50:36 +0100 From: Ingo Molnar To: "H. Peter Anvin" Cc: Rusty Russell , Tejun Heo , tglx@linutronix.de, x86@kernel.org, linux-kernel@vger.kernel.org, jeremy@goop.org, cpw@sgi.com, nickpiggin@yahoo.com.au, ink@jurassic.park.msu.ru Subject: Re: [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Message-ID: <20090304005036.GD11782@elte.hu> References: <1235445101-7882-1-git-send-email-tj@kernel.org> <20090224141217.GA17287@elte.hu> <49A40624.4000100@kernel.org> <200903041033.09502.rusty@rustcorp.com.au> <49ADC80F.6010200@zytor.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <49ADC80F.6010200@zytor.com> User-Agent: Mutt/1.5.18 (2008-05-17) X-ELTE-VirusStatus: clean X-ELTE-SpamScore: -1.5 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-1.5 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.3 -1.5 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * H. Peter Anvin wrote: > Rusty Russell wrote: >> On Wednesday 25 February 2009 01:07:24 Tejun Heo wrote: >>> it always >>> saves a 2MB TLB entry for all the non-NUMA machines out there. >> >> Note that everyone keeps talking about "a" TLB entry; I wanted to make >> sure (esp. for those of us reading from the sidelines), it's not: it's >> up to num_possible_cpus() TLB entries. Of course, many paths won't access >> other CPU's data, but it'd be interesting (and pretty easy) to actually >> instrument how rare this is... >> > > Actually it's up to the number of actual CPUs in the system... > obviously there isn't any data allocated for non-present CPUs. well, we allocate percpu data for each possible CPU. In the overwhelming majority of cases that means all actual CPUs. Ingo