From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Loopback performance from kernel 2.6.12 to 2.6.37 Date: Mon, 08 Nov 2010 16:06:25 +0100 Message-ID: <1289228785.2820.203.camel@edumazet-laptop> References: <1288954189.28003.178.camel@firesoul.comx.local> <1288988955.2665.297.camel@edumazet-laptop> <1289213926.15004.19.camel@firesoul.comx.local> <1289214289.2820.188.camel@edumazet-laptop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: netdev To: Jesper Dangaard Brouer Return-path: Received: from mail-ww0-f44.google.com ([74.125.82.44]:39776 "EHLO mail-ww0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754847Ab0KHPGb (ORCPT ); Mon, 8 Nov 2010 10:06:31 -0500 Received: by wwb18 with SMTP id 18so11978wwb.1 for ; Mon, 08 Nov 2010 07:06:30 -0800 (PST) In-Reply-To: <1289214289.2820.188.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: Le lundi 08 novembre 2010 =C3=A0 12:04 +0100, Eric Dumazet a =C3=A9crit= : > Le lundi 08 novembre 2010 =C3=A0 11:58 +0100, Jesper Dangaard Brouer = a > =C3=A9crit : > > On Fri, 2010-11-05 at 21:29 +0100, Eric Dumazet wrote: > > > Le vendredi 05 novembre 2010 =C3=A0 11:49 +0100, Jesper Dangaard = Brouer a > > > =C3=A9crit : > > > > Hi Eric, > > > >=20 > > > > A colleague send me a link to someone who has done some quite e= xtensive > > > > performance measurements across different kernel versions. > > > >=20 > > > > I noticed that the loopback performance has gotten quite bad: > > > >=20 > > > > http://www.phoronix.com/scan.php?page=3Darticle&item=3Dlinux_26= 12_2637&num=3D6 > > > >=20 > > > > I though you might be interested in the link. > > > >=20 > > > > See you around :-) > > >=20 > > > Hi ! > > >=20 > > > Problem is : I have no idea what test they exactly use, > > > do you have info about it ? > >=20 > > Its called the Phoronix test-suite, their website is: > > http://www.phoronix-test-suite.com/?k=3Dhome > >=20 > > On my Ubuntu workstation their software comes as a software package= : > > sudo aptitude install phoronix-test-suite > >=20 > > They seem to be related to the test/review site: > > http://www.phoronix.com/ > >=20 > >=20 > >=20 > > > This probably can be explained very fast. > >=20 > > The loopback test seems to be the only real networking test they do= =2E > > It looks like they just copy a very big fil via loopback, and recor= d the > > time it took... quite simple. > >=20 > > Their tests seems to be focused on CPU util/speed, graphics/games. > >=20 > >=20 > > The thing that caught my attention, was that they seemed interested= in > > doing performance regression testing on all kernel versions... > >=20 > > So, I though, it would be great if someone else would do automated > > performance regression testing for us :-), Too bad they only have = a > > very simple network test. > >=20 > >=20 >=20 >=20 CC netdev, if you dont mind. Their network test is basically : netcat -l 9999 >/dev/null & time dd if=3D/dev/zero bs=3D1M count=3D10000 | netcat 127.0.0.1 9999 They say it takes 38 seconds on their "super fast" processor On my dev machine, not super fast (E5540 @2.53GHz), I get 8 or 9 seconds, even if only one CPU is online, all others offline. Go figure... maybe an artifact of the virtualization they use. I suspect some problem with the ticket spinlocks and a call to hypervisor to say 'I am spinning on a spinlock, see if you need to do something useful', or maybe ACPI problem (going to/from idle)