From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755627AbXJHNIh (ORCPT ); Mon, 8 Oct 2007 09:08:37 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752084AbXJHNI3 (ORCPT ); Mon, 8 Oct 2007 09:08:29 -0400 Received: from mx2.suse.de ([195.135.220.15]:34743 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751839AbXJHNI2 (ORCPT ); Mon, 8 Oct 2007 09:08:28 -0400 From: Andi Kleen Organization: SUSE Linux Products GmbH, Nuernberg, GF: Markus Rex, HRB 16746 (AG Nuernberg) To: Ingo Molnar Subject: Re: [PATCH] [5/6] scheduler: Protect important kernel threads against normalize_rt Date: Mon, 8 Oct 2007 15:08:23 +0200 User-Agent: KMail/1.9.6 Cc: linux-kernel@vger.kernel.org References: <200710071059.126674000@suse.de> <200710081433.34845.ak@suse.de> <20071008124350.GA5779@elte.hu> In-Reply-To: <20071008124350.GA5779@elte.hu> MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200710081508.23950.ak@suse.de> Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Monday 08 October 2007 14:43:50 Ingo Molnar wrote: > > * Andi Kleen wrote: > > > softlockup is the same. Just think about it. > > > > If you ever renormalize it and then run a fifo thread it will starve > > and then eventually kill the box. > > > > And starving CPU unplug is also equally bad. > > yeah, agreed. I ended up doing the change below. I considered doing it this way too. But it means that if keventd (or another workqueue thread) starts looping for some reason you cannot renormalize it. Might be not a good thing and impact debuggability. I think it's better to only protect special threads. -Andi