From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758735AbYC0KIr (ORCPT ); Thu, 27 Mar 2008 06:08:47 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752508AbYC0KIj (ORCPT ); Thu, 27 Mar 2008 06:08:39 -0400 Received: from mx2.mail.elte.hu ([157.181.151.9]:53060 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751638AbYC0KIi (ORCPT ); Thu, 27 Mar 2008 06:08:38 -0400 Date: Thu, 27 Mar 2008 11:08:02 +0100 From: Ingo Molnar To: Jens Axboe Cc: linux-kernel@vger.kernel.org, npiggin@suse.de, paulus@samba.org, tglx@linutronix.de, mingo@redhat.com, tony.luck@intel.com Subject: Re: [PATCH 0/5] Generic smp_call_function(), improvements, and smp_call_function_single() Message-ID: <20080327100802.GD15003@elte.hu> References: <1205927772-31401-1-git-send-email-jens.axboe@oracle.com> <20080321095343.GA21409@elte.hu> <20080321131558.GA15355@kernel.dk> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080321131558.GA15355@kernel.dk> User-Agent: Mutt/1.5.17 (2007-11-01) 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: 0.0001] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Jens Axboe wrote: > which is pretty much identical to io-cpu-affinity, except it uses > kernel threads for completion. > > The reason why I dropped the kthread approach is that it was slower. > Time from signal to run was about 33% faster with IPI than with > wake_up_process(). Doing benchmark runs, and the IPI approach won > hands down in cache misses as well. with irq threads we'll have all irq context run in kthread context again. Could you show me how you measured the performance of the kthread approach versus the raw-IPI approach? we can do a million kthread context switches per CPU per second, so kthread context-switch cost cannot be a true performance limit, unless you micro-benchmarked this. Ingo