From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751724AbaEVFDl (ORCPT ); Thu, 22 May 2014 01:03:41 -0400 Received: from mga09.intel.com ([134.134.136.24]:4009 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751168AbaEVFDk (ORCPT ); Thu, 22 May 2014 01:03:40 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.98,884,1392192000"; d="scan'208";a="515815210" Message-ID: <537D852B.8070106@linux.intel.com> Date: Wed, 21 May 2014 22:03:39 -0700 From: "H. Peter Anvin" User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.5.0 MIME-Version: 1.0 To: Fengguang Wu , Andy Lutomirski CC: Jet Chen , LKML , lkp@01.org Subject: Re: [x86, vdso] cfda7bb9ecb: +14.7% will-it-scale.per_thread_ops References: <537AEF2D.9040207@intel.com> <20140522015448.GA23196@localhost> In-Reply-To: <20140522015448.GA23196@localhost> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/21/2014 06:54 PM, Fengguang Wu wrote: >>> >>> test case: nhm4/will-it-scale/sched_yield >>> >>> 3d7ee969bffcc98 cfda7bb9ecbf9d96264bb5bad >>> --------------- ------------------------- >>> 5497021 ~ 0% +14.7% 6303424 ~ 0% TOTAL >>> will-it-scale.per_thread_ops >>> 0.54 ~ 0% +5.6% 0.57 ~ 0% TOTAL will-it-scale.scalability >>> 6209483 ~ 0% +1.6% 6305917 ~ 0% TOTAL >>> will-it-scale.per_process_ops >>> 2455 ~ 5% +16.9% 2870 ~ 5% TOTAL cpuidle.C1-NHM.usage >>> 8829 ~ 7% +15.2% 10169 ~10% TOTAL >>> slabinfo.kmalloc-64.active_objs >>> 24.13 ~12% +48.9% 35.93 ~14% TOTAL time.user_time >>> 393 ~ 0% -3.0% 382 ~ 1% TOTAL time.system_time >>> >> >> Is this a speedup or a slowdown? > > It's a speedup. The will-it-scale/sched_yield test case's throughput > increased by +14.7% (multi-thread case) and +1.6% (multi-process case). > > However the CPU %user time increased more, by +48.9%. > That would be consistent with spending less time in the kernel, no? But I agree... that is completely bizarre. That checkin should have absolutely zero effect on performance. -hpa