From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757096Ab2EHV45 (ORCPT ); Tue, 8 May 2012 17:56:57 -0400 Received: from merlin.infradead.org ([205.233.59.134]:53206 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756867Ab2EHV44 convert rfc822-to-8bit (ORCPT ); Tue, 8 May 2012 17:56:56 -0400 Message-ID: <1336514192.8226.52.camel@twins> Subject: Re: [PATCH] sched: Make nr_uninterruptible count a signed value From: Peter Zijlstra To: Diwakar Tundlam Cc: "'Ingo Molnar'" , "'David Rientjes'" , "'linux-kernel@vger.kernel.org'" , Peter De Schrijver Date: Tue, 08 May 2012 23:56:32 +0200 In-Reply-To: <1DD7BFEDD3147247B1355BEFEFE46652379C3DF10C@HQMAIL04.nvidia.com> References: <1DD7BFEDD3147247B1355BEFEFE46652379C3DF10C@HQMAIL04.nvidia.com> Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT X-Mailer: Evolution 3.2.2- Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2012-05-08 at 14:39 -0700, Diwakar Tundlam wrote: > Declare nr_uninterruptible as a signed long to avoid garbage values > seen in cat /proc/sched_debug when a task is moved to the run queue of > a newly online core. This is part of a global counter where only the > total sum over all CPUs matters. Its late here, but do explain how any of this makes any difference what so ever? Since all we do with that field is add/sub the whole sign issue shouldn't matter one way or the other.