From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756620AbXHBPEQ (ORCPT ); Thu, 2 Aug 2007 11:04:16 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752353AbXHBPEE (ORCPT ); Thu, 2 Aug 2007 11:04:04 -0400 Received: from mx3.mail.elte.hu ([157.181.1.138]:59871 "EHLO mx3.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750818AbXHBPEB (ORCPT ); Thu, 2 Aug 2007 11:04:01 -0400 Date: Thu, 2 Aug 2007 17:03:50 +0200 From: Ingo Molnar To: Martin Roehricht Cc: linux-kernel@vger.kernel.org Subject: Re: Scheduling the highest priority task Message-ID: <20070802150350.GA3030@elte.hu> References: <8KLFD-G9-5@gated-at.bofh.it> <46B19CA1.7050204@felicis.org> <20070802114012.GA4067@elte.hu> <46B1F182.3010608@felicis.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <46B1F182.3010608@felicis.org> User-Agent: Mutt/1.5.14 (2007-02-12) X-ELTE-VirusStatus: clean X-ELTE-SpamScore: -1.0 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-1.0 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.1.7-deb -1.0 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org * Martin Roehricht wrote: > On 08/02/2007 01:40 PM, Ingo Molnar wrote: > >in the SMP migration code, the 'old scheduler' indeed picks the lowest > >priority one, _except_ if that task is running on another CPU or is too > >'cache hot': > > But why is it, that the scheduler picks the lowest priority one? I > thought sched_find_first_bit() picks the index of the lowest order bit > in the bitmap and thus the highest priority job. Is that wrong? What > needs to be changed to let the scheduler pick the highest priority > task from a given runqueue? I am very confused ... it first picks the lowest index (i.e. the highest priority active priority-queue), but within those tasks (each task in that priority queue has equal priority) the load-balancer has freedom to pick any. Based on performance data we went for picking from the tail of the queue. Ingo