From owner-freebsd-stable@FreeBSD.ORG Thu Dec 15 17:59:16 2011 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0725310656EA for ; Thu, 15 Dec 2011 17:59:16 +0000 (UTC) (envelope-from daniel@digsys.bg) Received: from smtp-sofia.digsys.bg (smtp-sofia.digsys.bg [193.68.3.230]) by mx1.freebsd.org (Postfix) with ESMTP id 8423C8FC15 for ; Thu, 15 Dec 2011 17:59:15 +0000 (UTC) Received: from [192.168.100.122] (varna2.digsys.bg [193.68.0.70]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBFHx2bM003300 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NO); Thu, 15 Dec 2011 19:59:07 +0200 (EET) (envelope-from daniel@digsys.bg) Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: text/plain; charset=us-ascii From: Daniel Kalchev In-Reply-To: Date: Thu, 15 Dec 2011 19:59:01 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <20111213073615.GA69641@icarus.home.lan> <4EE7093E.4050006@digsys.bg> To: Attilio Rao X-Mailer: Apple Mail (2.1251.1) Cc: freebsd-stable@freebsd.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 17:59:16 -0000 On Dec 15, 2011, at 6:26 PM, Attilio Rao wrote: > 2011/12/13 Daniel Kalchev : >>=20 >>=20 >> On 13.12.11 09:36, Jeremy Chadwick wrote: >>>=20 >>> I personally would find it interesting if someone with a higher-end = system >>> (e.g. 2 physical CPUs, with 6 or 8 cores per CPU) was to do the same = test >>> (changing -jX to -j{numofcores} of course). >>=20 >>=20 >> Is 4 way 8 core Opteron ok? That is 32 cores, 64GB RAM. >>=20 >> Testing with buildworld in my opinion is not adequate, as it involves = way >> too much I/O. Any advice on proper testing methodology? >=20 > I'm sure that I/O and pmap subsystem contention (because of > buildworld) and TLB shootdown overhead (because of 32 CPUs) will be so > overwhelming that you are not really going to benchmark the scheduler > activity at all. Can't pmap / TLB be tuned for 32 CPUs and 64GB of RAM? >=20 > However I still don't get what you want to verify exactly? The obvious: is SCHED_ULE better or worse than SCHED_4BSD on such = platform.=20 Problem is how to test "interactivity" -- that is a blade server and = doesn't really have a display and keyboard, nor does it have X etc. I have spare pair of those, that might be put to crunch tests to see how = things compare for different scenarios - but I need ideas what to test, = really. Daniel=