Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1764300AbXIXQsW (ORCPT ); Mon, 24 Sep 2007 12:48:22 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1763342AbXIXQnU (ORCPT ); Mon, 24 Sep 2007 12:43:20 -0400 Received: from mga11.intel.com ([192.55.52.93]:15700 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763382AbXIXQnS (ORCPT ); Mon, 24 Sep 2007 12:43:18 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.20,292,1186383600"; d="scan'208";a="320727940" Date: Mon, 24 Sep 2007 09:43:17 -0700 (PDT) From: Tong Li X-X-Sender: tongli@tongli.jf.intel.com To: Peter Zijlstra cc: Mike Galbraith , Ingo Molnar , dimm , linux-kernel@vger.kernel.org, Srivatsa Vaddagiri Subject: Re: [git] CFS-devel, group scheduler, fixes In-Reply-To: <20070924135158.1359013b@twins> Message-ID: References: <1190144190.5204.24.camel@earth> <20070918201622.GA1632@elte.hu> <1190183324.9737.7.camel@Homer.simpson.net> <1190188261.9185.21.camel@Homer.simpson.net> <1190191368.8687.5.camel@Homer.simpson.net> <1190264114.6411.4.camel@Homer.simpson.net> <1190272507.27867.20.camel@Homer.simpson.net> <20070920075155.GA31641@elte.hu> <1190275870.9232.6.camel@Homer.simpson.net> <1190455308.7404.19.camel@Homer.simpson.net> <1190531662.11524.15.camel@Homer.simpson.net> <1190628609.6389.14.camel@Homer.simpson.net> <20070924122422.75562c41@twins> <1190630535.7406.2.camel@Homer.simpson.net> <1190632934.7853.1.camel@Homer.simpson.net> <20070924135158.1359013b@twins> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1598 Lines: 43 On Mon, 24 Sep 2007, Peter Zijlstra wrote: > On Mon, 24 Sep 2007 13:22:14 +0200 Mike Galbraith wrote: > >> On Mon, 2007-09-24 at 12:42 +0200, Mike Galbraith wrote: >>> On Mon, 2007-09-24 at 12:24 +0200, Peter Zijlstra wrote: >>> >>>> how about something like: >>>> >>>> s64 delta = (s64)(vruntime - min_vruntime); >>>> if (delta > 0) >>>> min_vruntime += delta; >>>> >>>> That would rid us of most of the funny conditionals there. >>> >>> That still left me with negative min_vruntimes. The pinned hogs didn't >>> lock my box up, but I quickly got the below, so hastily killed it. >> >> Shouldn't the max() in place_entity() be the max_vruntime() that my >> lysdexia told me it was when I looked at it earlier? ;-) >> > > probably, my tree doesn't have that max anymore so I'm not sure. > Last time I looked, I thought the max() in place_entity() was fine and the problem seemed to be in set_task_cpu() that was causing the negative vruntimes: if (likely(new_rq->cfs.min_vruntime)) p->se.vruntime -= old_rq->cfs.min_vruntime - new_rq->cfs.min_vruntime; I think it's fine we get rid of sync_vruntime(). I need to think more about how to make global fairness work based on this--it seems to be more complicated than if we had sync_vruntime(). tong - 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/