Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756510AbXKSPyU (ORCPT ); Mon, 19 Nov 2007 10:54:20 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754526AbXKSPyL (ORCPT ); Mon, 19 Nov 2007 10:54:11 -0500 Received: from e6.ny.us.ibm.com ([32.97.182.146]:52085 "EHLO e6.ny.us.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753529AbXKSPyJ (ORCPT ); Mon, 19 Nov 2007 10:54:09 -0500 Date: Mon, 19 Nov 2007 21:36:47 +0530 From: Srivatsa Vaddagiri To: Ingo Molnar Cc: dmitry.adamushko@gmail.com, a.p.zijlstra@chello.nl, dhaval@linux.vnet.ibm.com, linux-kernel@vger.kernel.org, efault@gmx.de, skumar@linux.vnet.ibm.com, Balbir Singh Subject: Re: [PATCH 2/2] sched: Improve fairness of cpu allocation for task groups Message-ID: <20071119160647.GV3359@linux.vnet.ibm.com> Reply-To: vatsa@linux.vnet.ibm.com References: <20071119122713.GA28777@linux.vnet.ibm.com> <20071119123051.GC28777@linux.vnet.ibm.com> <20071119131201.GB31491@elte.hu> <20071119150312.GA2365@linux.vnet.ibm.com> <20071119152258.GB31426@elte.hu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20071119152258.GB31426@elte.hu> User-Agent: Mutt/1.5.11 Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1282 Lines: 33 On Mon, Nov 19, 2007 at 04:22:58PM +0100, Ingo Molnar wrote: > > * Srivatsa Vaddagiri wrote: > > > - inc/dec_load() takes a load input instead of task pointer input as their > > 2nd arg > > - inc/dec_nr_running don't call inc/dec_load. Instead, > > - enqueue/dequeue_task class callbacks call inc/dec_load > > - [Unintended/will-fix change] min/max tunables added in > > /proc/sys/kernel > > > > All of above changes (except last, which I will fix) should have zero > > functional+runtime effect for !CONFIG_FAIR_GROUP_SCHED case. So I > > don't see how I can split Patch 2/2 further. > > ok, as long as it's NOP for the CONFIG_FAIR_GROUP_SCHED, we could try > it. Ok ..thx. I was begining to make changes to avoid even the above minor changes for !CONFIG_FAIR_GROUP_SCHED case, but it doesn't look neat, hence will drop that effort. I am fixing other problems observed with Patch 1/2 (usage of a mutex to serialize create/destroy groups) and will resend the series very soon. -- Regards, vatsa - To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/