From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Wagner Subject: Re: Some benchmark results Date: Thu, 28 Aug 2014 08:11:47 +0200 Message-ID: <53FEC823.5030709@monom.org> References: <53FAFBA8.3050009@monom.org> <1657147.MGSNxR1uXh@bs8> Mime-Version: 1.0 Content-Type: text/plain; charset=windows-1252 Content-Transfer-Encoding: QUOTED-PRINTABLE To: Bernhard Schiffner , linux-rt-users@vger.kernel.org Return-path: Received: from mail-we0-f173.google.com ([74.125.82.173]:36306 "EHLO mail-we0-f173.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751235AbaH1GLw (ORCPT ); Thu, 28 Aug 2014 02:11:52 -0400 Received: by mail-we0-f173.google.com with SMTP id t60so254987wes.32 for ; Wed, 27 Aug 2014 23:11:50 -0700 (PDT) In-Reply-To: <1657147.MGSNxR1uXh@bs8> Sender: linux-rt-users-owner@vger.kernel.org List-ID: Hi Bernhard, On 08/25/2014 04:14 PM, Bernhard Schiffner wrote: > Am Montag, 25. August 2014, 11:02:32 schrieb Daniel Wagner: >> Hi, >> >> I wanted to know how good or bad mainline vs RT is, therefore I let >> MMTests torture my laptop for a while. I selected a few of the suppo= rted >> benchmarks by MMTests in order to keep to a reasonable time frame. >> >> The aim was to see the impact of normal (no RT) workloads with diffe= rent >> preempt configurations on mainline and RT patched kernel. I tried to= not >> to change other configuration flags except the preempt one. There ar= e >> some small difference due to dependencies but the rest looks ok to m= e. >> >> http://www.monom.org/rt/mmtests/ >> >> Suggestion, improvements, comments? >> >> cheers, >> daniel >> >> -- >> To unsubscribe from this list: send the line "unsubscribe linux-rt-u= sers" in >> the body of a message to majordomo@vger.kernel.org >> More majordomo info at http://vger.kernel.org/majordomo-info.html >=20 > Hi Daniel, >=20 > I had a first look at the above mentioned page. >=20 > The thing I'am complety missing in the huge amount of numbers is: Wha= t is your=20 > demand, your primary topic to solve in or with RT? Thanks looking at the numbers and the feedback from you. I really appreciate that. To your question: My goal is to help out to get this patch set merged into mainline. I know an ambitious goal and I might be too incompetent (I may suffering from the Dunning=96Kruger effect. but hey, I am not th= e one who recognize this). So I figured the best thing is to start playing with different loads an= d see how they compare to mainline and trying to understand why they are different. > And as I interprete the numbers: a RT kernel is a little bit more CPU= -hungry=20 > then normal and this is nothing new. Sure, I am well aware that RT is 'a little bit more CPU-hungry', but I wondered how much is a little and what are the effects of it? I am doing those tests for myself to get a better understanding. I just shared the results in case someone else finds them interesting. I shoul= d have stated that more clearly to avoid burning time from you. Sorry about that. cheers, daniel -- To unsubscribe from this list: send the line "unsubscribe linux-rt-user= s" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html