From mboxrd@z Thu Jan 1 00:00:00 1970 From: Dave Hansen Subject: Re: [Results] [RFC PATCH v4 00/40] mm: Memory Power Management Date: Tue, 12 Nov 2013 09:34:33 -0800 Message-ID: <528266A9.2040901@sr71.net> References: <20130925231250.26184.31438.stgit@srivatsabhat.in.ibm.com> <52437128.7030402@linux.vnet.ibm.com> <20130925164057.6bbaf23bdc5057c42b2ab010@linux-foundation.org> <52442F6F.5020703@linux.vnet.ibm.com> <5281E09B.3060303@linux.vnet.ibm.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <5281E09B.3060303@linux.vnet.ibm.com> Sender: owner-linux-mm@kvack.org To: "Srivatsa S. Bhat" , Andrew Morton Cc: mgorman@suse.de, hannes@cmpxchg.org, tony.luck@intel.com, matthew.garrett@nebula.com, riel@redhat.com, arjan@linux.intel.com, srinivas.pandruvada@linux.intel.com, willy@linux.intel.com, kamezawa.hiroyu@jp.fujitsu.com, lenb@kernel.org, rjw@sisk.pl, gargankita@gmail.com, paulmck@linux.vnet.ibm.com, svaidy@linux.vnet.ibm.com, andi@firstfloor.org, isimatu.yasuaki@jp.fujitsu.com, santosh.shilimkar@ti.com, kosaki.motohiro@gmail.com, linux-pm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, maxime.coquelin@stericsson.com, loic.pallardy@stericsson.com, amit.kachhap@linaro.org, thomas.abraham@linaro.org, markgross@thegnar.org List-Id: linux-pm@vger.kernel.org On 11/12/2013 12:02 AM, Srivatsa S. Bhat wrote: > I performed experiments on an IBM POWER 7 machine and got actual power-savings > numbers (upto 2.6% of total system power) from this patchset. I presented them > at the Kernel Summit but forgot to post them on LKML. So here they are: "upto"? What was it, actually? Essentially what you've told us here is that you have a patch that tries to do some memory power management and that it accomplishes that. But, to what degree? Was your baseline against a kernel also booted with numa=fake=1, or was it a kernel booted normally? 1. What is the theoretical power savings from memory? 2. How much of the theoretical numbers can your patch reach? 3. What is the performance impact? Does it hurt ebizzy? You also said before: > On page 40, the paper shows the power-consumption breakdown for an IBM p670 > machine, which shows that as much as 40% of the system energy is consumed by > the memory sub-system in a mid-range server. 2.6% seems pretty awful for such an invasive patch set if you were expecting 40%. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756509Ab3KLRf3 (ORCPT ); Tue, 12 Nov 2013 12:35:29 -0500 Received: from www.sr71.net ([198.145.64.142]:49913 "EHLO blackbird.sr71.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754002Ab3KLRf0 (ORCPT ); Tue, 12 Nov 2013 12:35:26 -0500 Message-ID: <528266A9.2040901@sr71.net> Date: Tue, 12 Nov 2013 09:34:33 -0800 From: Dave Hansen User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:24.0) Gecko/20100101 Thunderbird/24.1.0 MIME-Version: 1.0 To: "Srivatsa S. Bhat" , Andrew Morton CC: mgorman@suse.de, hannes@cmpxchg.org, tony.luck@intel.com, matthew.garrett@nebula.com, riel@redhat.com, arjan@linux.intel.com, srinivas.pandruvada@linux.intel.com, willy@linux.intel.com, kamezawa.hiroyu@jp.fujitsu.com, lenb@kernel.org, rjw@sisk.pl, gargankita@gmail.com, paulmck@linux.vnet.ibm.com, svaidy@linux.vnet.ibm.com, andi@firstfloor.org, isimatu.yasuaki@jp.fujitsu.com, santosh.shilimkar@ti.com, kosaki.motohiro@gmail.com, linux-pm@vger.kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, maxime.coquelin@stericsson.com, loic.pallardy@stericsson.com, amit.kachhap@linaro.org, thomas.abraham@linaro.org, markgross@thegnar.org Subject: Re: [Results] [RFC PATCH v4 00/40] mm: Memory Power Management References: <20130925231250.26184.31438.stgit@srivatsabhat.in.ibm.com> <52437128.7030402@linux.vnet.ibm.com> <20130925164057.6bbaf23bdc5057c42b2ab010@linux-foundation.org> <52442F6F.5020703@linux.vnet.ibm.com> <5281E09B.3060303@linux.vnet.ibm.com> In-Reply-To: <5281E09B.3060303@linux.vnet.ibm.com> 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 11/12/2013 12:02 AM, Srivatsa S. Bhat wrote: > I performed experiments on an IBM POWER 7 machine and got actual power-savings > numbers (upto 2.6% of total system power) from this patchset. I presented them > at the Kernel Summit but forgot to post them on LKML. So here they are: "upto"? What was it, actually? Essentially what you've told us here is that you have a patch that tries to do some memory power management and that it accomplishes that. But, to what degree? Was your baseline against a kernel also booted with numa=fake=1, or was it a kernel booted normally? 1. What is the theoretical power savings from memory? 2. How much of the theoretical numbers can your patch reach? 3. What is the performance impact? Does it hurt ebizzy? You also said before: > On page 40, the paper shows the power-consumption breakdown for an IBM p670 > machine, which shows that as much as 40% of the system energy is consumed by > the memory sub-system in a mid-range server. 2.6% seems pretty awful for such an invasive patch set if you were expecting 40%.