From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Gregory Haskins" Subject: Re: [PATCH 2/2] sched: prioritize non-migratable tasks over migratableones Date: Wed, 23 Apr 2008 07:11:42 -0600 Message-ID: <480EFD4E.BA47.005A.0@novell.com> References: <20080423111313.4981.37345.stgit@novell1.haskins.net> <20080423111334.4981.19638.stgit@novell1.haskins.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 8BIT Cc: "Ingo Molnar" , "Dmitry Adamushko" , , To: "Steven Rostedt" Return-path: Received: from sinclair.provo.novell.com ([137.65.248.137]:48839 "EHLO sinclair.provo.novell.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751610AbYDWNLL convert rfc822-to-8bit (ORCPT ); Wed, 23 Apr 2008 09:11:11 -0400 In-Reply-To: Content-Disposition: inline Sender: linux-rt-users-owner@vger.kernel.org List-ID: >>> On Wed, Apr 23, 2008 at 8:58 AM, in message , Steven Rostedt wrote: > > I'm not giving an Ack on this patch (not yet). My main concern here is > that this is performing on a verge of policy change. As you stated, this > is a known issue. One that can be avoided by giving RT tasks different > priorities. It is known that two tasks with the same priority fighting > for the same CPUS (even if one is migratable and one is not) has > non-deterministic behaviour. > > This patch needs a bit of running through the grind to see what effects it > has before going in. Perfectly reasonable stance, Steve. Thanks for the review! -Greg