From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 02:37:54 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8B124106566C; Sun, 18 Dec 2011 02:37:54 +0000 (UTC) (envelope-from bruce@cran.org.uk) Received: from muon.cran.org.uk (muon.cran.org.uk [IPv6:2a01:348:0:15:5d59:5c40:0:1]) by mx1.freebsd.org (Postfix) with ESMTP id 1B56E8FC12; Sun, 18 Dec 2011 02:37:54 +0000 (UTC) Received: from muon.cran.org.uk (localhost [127.0.0.1]) by muon.cran.org.uk (Postfix) with ESMTP id 223BDE6217; Sun, 18 Dec 2011 02:37:53 +0000 (GMT) DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=cran.org.uk; h=message-id :date:from:mime-version:to:subject:references:in-reply-to :content-type:content-transfer-encoding; s=mail; bh=I57RAsWs1zbv so7bCeVdM/pSSpY=; b=b6xdib3FGaFnhcNsw3HKpuL4Frw9pbafcxRDLlUcF1dV LSQlIiGLb8icVSinnb31b5Y/4+uboqW3AV5yu0K+xR/EmzZqyzjNkgZn3Nypl3lh eRfxB0wmw2hfAUD/5fu8YgI9/UAqU9zBahZncIOTXnciT7/n2wvcJbPXhuEvUYA= DomainKey-Signature: a=rsa-sha1; c=nofws; d=cran.org.uk; h=message-id :date:from:mime-version:to:subject:references:in-reply-to :content-type:content-transfer-encoding; q=dns; s=mail; b=CKJuiw y+HKDldo71dYnwUmH4Sg61hlB5edwnD3fANdRZy6r6HaTq653wVIdL3t1LdL1zfn VWUgIvEAyYeEdSx9L/TYy7J9dmj0qSvuiXN4khsu6ZFZlIUAFnyvXXT/nyUSF+sX gTCE50iAGB2qWGMJqXKqHSnabClkPOMoFA7j4= Received: from [192.168.1.68] (188-220-36-32.zone11.bethere.co.uk [188.220.36.32]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by muon.cran.org.uk (Postfix) with ESMTPSA id CDA1BE6216; Sun, 18 Dec 2011 02:37:52 +0000 (GMT) Message-ID: <4EED5200.20302@cran.org.uk> Date: Sun, 18 Dec 2011 02:37:52 +0000 From: Bruce Cran User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Andrey Chernov , Ivan Klymenko , Doug Barton , "O. Hartmann" , Current FreeBSD , freebsd-stable@FreeBSD.ORG, freebsd-performance@FreeBSD.ORG References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> In-Reply-To: <20111213090051.GA3339@vniz.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 02:37:54 -0000 On 13/12/2011 09:00, Andrey Chernov wrote: > I observe ULE interactivity slowness even on single core machine > (Pentium 4) in very visible places, like 'ps ax' output stucks in the > middle by ~1 second. When I switch back to SHED_4BSD, all slowness is > gone. I'm also seeing problems with ULE on a dual-socket quad-core Xeon machine with 16 logical CPUs. If I run "tar xf somefile.tar" and "make -j16 buildworld" then logging into another console can take several seconds. Sometimes even the "Password:" prompt can take a couple of seconds to appear after typing my username. -- Bruce Cran From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 07:52:50 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D1ACA106564A; Sun, 18 Dec 2011 07:52:50 +0000 (UTC) (envelope-from ache@vniz.net) Received: from vniz.net (vniz.net [194.87.13.69]) by mx1.freebsd.org (Postfix) with ESMTP id 2AF108FC17; Sun, 18 Dec 2011 07:52:45 +0000 (UTC) Received: from localhost (localhost [127.0.0.1]) by vniz.net (8.14.5/8.14.5) with ESMTP id pBI7qhPc045514; Sun, 18 Dec 2011 11:52:43 +0400 (MSK) (envelope-from ache@vniz.net) Received: (from ache@localhost) by localhost (8.14.5/8.14.5/Submit) id pBI7qgIB045513; Sun, 18 Dec 2011 11:52:42 +0400 (MSK) (envelope-from ache) Date: Sun, 18 Dec 2011 11:52:42 +0400 From: Andrey Chernov To: Ian Smith Message-ID: <20111218075241.GA45367@vniz.net> Mail-Followup-To: Andrey Chernov , Ian Smith , Bruce Cran , Ivan Klymenko , Doug Barton , "O. Hartmann" , Current FreeBSD , freebsd-stable@FreeBSD.ORG, freebsd-performance@FreeBSD.ORG References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20111218164924.L64681@sola.nimnet.asn.au> User-Agent: Mutt/1.5.21 (2010-09-15) Cc: Bruce Cran , Ivan Klymenko , Doug Barton , freebsd-stable@FreeBSD.ORG, "O. Hartmann" , Current FreeBSD , freebsd-performance@FreeBSD.ORG Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 07:52:50 -0000 On Sun, Dec 18, 2011 at 05:51:47PM +1100, Ian Smith wrote: > On Sun, 18 Dec 2011 02:37:52 +0000, Bruce Cran wrote: > > On 13/12/2011 09:00, Andrey Chernov wrote: > > > I observe ULE interactivity slowness even on single core machine (Pentium > > > 4) in very visible places, like 'ps ax' output stucks in the middle by ~1 > > > second. When I switch back to SHED_4BSD, all slowness is gone. > > > > I'm also seeing problems with ULE on a dual-socket quad-core Xeon machine > > with 16 logical CPUs. If I run "tar xf somefile.tar" and "make -j16 > > buildworld" then logging into another console can take several seconds. > > Sometimes even the "Password:" prompt can take a couple of seconds to appear > > after typing my username. > > I'd resigned myself to expecting this sort of behaviour as 'normal' on > my single core 1133MHz PIII-M. As a reproducable data point, running > 'dd if=/dev/random of=/dev/null' in one konsole, specifically to heat > the CPU while testing my manual fan control script, hogs it up pretty > much while regularly running the script below in another konsole to > check values - which often gets stuck half way, occasionally pausing > _twice_ before finishing. Switching back to the first konsole (on > another desktop) to kill the dd can also take a couple/few seconds. This issue not about slow machine under load, because the same slow machine under exact the same load, but with SCHED_4BSD is very fast to response interactively. I think we should not misinterpret interactivity with speed. I see no big speed (i.e. compilation time) differences, switching schedulers, but see big _interactivity_ difference. ULE in general tends to underestimate interactive processes in favour of background ones. It perhaps helps to compilation, but looks like slowpoke OS from the interactive user experience. -- http://ache.vniz.net/ From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 13:06:31 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 44465106566B; Sun, 18 Dec 2011 13:06:31 +0000 (UTC) (envelope-from bruce@cran.org.uk) Received: from muon.cran.org.uk (muon.cran.org.uk [IPv6:2a01:348:0:15:5d59:5c40:0:1]) by mx1.freebsd.org (Postfix) with ESMTP id E8FE58FC15; Sun, 18 Dec 2011 13:06:30 +0000 (UTC) Received: from muon.cran.org.uk (localhost [127.0.0.1]) by muon.cran.org.uk (Postfix) with ESMTP id 1F7D9E6217; Sun, 18 Dec 2011 13:06:30 +0000 (GMT) DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=cran.org.uk; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; s=mail; bh=CE3PwiyBFxMN P4zTc90HsRMiDFw=; b=NACr+W25m0muexI8+wm1yE6bU1nUAjs7VqpSHaaIte1m NODToyjY5WJEFYtXhzmm+9yNDUn2sxvrIRUes62OcNdBNAXW+s9k95Ukm1QhRHOi 2fY97x8pZrL+G52iSEACbf7IRsAzqym1DOXwmUXScEXo1i+yYLShkjPC/1WsSZQ= DomainKey-Signature: a=rsa-sha1; c=nofws; d=cran.org.uk; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; q=dns; s=mail; b=UYQWJe SDJtZ2NR0gXrJ+2QIcy7VTd4je7kCbkXZdXAC9VegGI8DZLPhNR9JMH4iu7KSzk6 flV8ZvD3628mmgL58RCVag2p5fjpDlB3soYyhcbTNpSZDn+euUnS3g3Ce+Tt/wvB L5wZLpkueRjPESaAww3xDqQQkgrQUOYGPHha4= Received: from [192.168.1.68] (188-220-36-32.zone11.bethere.co.uk [188.220.36.32]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by muon.cran.org.uk (Postfix) with ESMTPSA id E9B67E61F0; Sun, 18 Dec 2011 13:06:29 +0000 (GMT) Message-ID: <4EEDE554.6050303@cran.org.uk> Date: Sun, 18 Dec 2011 13:06:28 +0000 From: Bruce Cran User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Adrian Chadd References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Current FreeBSD Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 13:06:31 -0000 On 18/12/2011 10:34, Adrian Chadd wrote: > I applaud reppie for trying to make it as easy as possible for people > to use KTR to provide scheduler traces for him to go digging with, so > please, if you have these issues and you can absolutely reproduce > them, please follow his instructions and work with him to get him what > he needs. Who's 'reppie'? -- Bruce Cran From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 13:44:33 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EC67F106566B; Sun, 18 Dec 2011 13:44:33 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 9CD558FC08; Sun, 18 Dec 2011 13:44:33 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RcH2V-0005UK-Q5>; Sun, 18 Dec 2011 14:44:31 +0100 Received: from e178040031.adsl.alicedsl.de ([85.178.40.31] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RcH2V-0005T0-9K>; Sun, 18 Dec 2011 14:44:31 +0100 Message-ID: <4EEDEE38.10802@zedat.fu-berlin.de> Date: Sun, 18 Dec 2011 14:44:24 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: Bruce Cran References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> In-Reply-To: <4EED5200.20302@cran.org.uk> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigF2AFB91AE4784E4B43C44794" X-Originating-IP: 85.178.40.31 Cc: Ivan Klymenko , Doug Barton , freebsd-stable@FreeBSD.ORG, "O. Hartmann" , Current FreeBSD , Andrey Chernov , freebsd-performance@FreeBSD.ORG Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 13:44:34 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigF2AFB91AE4784E4B43C44794 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/18/11 03:37, Bruce Cran wrote: > On 13/12/2011 09:00, Andrey Chernov wrote: >> I observe ULE interactivity slowness even on single core machine >> (Pentium 4) in very visible places, like 'ps ax' output stucks in the >> middle by ~1 second. When I switch back to SHED_4BSD, all slowness is >> gone.=20 >=20 > I'm also seeing problems with ULE on a dual-socket quad-core Xeon > machine with 16 logical CPUs. If I run "tar xf somefile.tar" and "make > -j16 buildworld" then logging into another console can take several > seconds. Sometimes even the "Password:" prompt can take a couple of > seconds to appear after typing my username. >=20 I reported ages ago several problems using SCHED_ULE on FreeBSD 8/9 when doing heavy I/O, either disk or network bound (that time I realised the problem on servers doing heavy disk I/O or net I/O). It was suspected that X could be the problem, but we also have a Dell PowerEdge 1950III running FreeBSD 8.2-STABLE (by next week 9.0-RC[2/3]/STABLE) without X, but the same problems, but no so prominent as with X. The box has 8 cores, 4 cores per socket each and 16 GB RAM, SAS 6/iR controller and two PCI-X attached Broacom NexTreme NICs, so the hardware shouldn't be any kind of trouble. But that time (over the past two years for now), the problem was considered "a personal" problem. Bah! By the beginning of next year my working group expects new hardware. Since we use for Linux for scientific work (due to OpenCL and CUDA on TESLA cards), I can't use the Blade system. The boxes I expect is one Dell Precission T7500, 96 GB RAM, two sockets, two Westmere XEONs each socket with a summary of 12 cores/24 threads. I'll start a dual OS installation with FreeBSD 10 and the most recent Suse (since the development is mostly done by my colleagues on Suse for the C2075 TESLA board, I need Suse Linux). I will then being capable of performing some benchmarks on both boxes on the very same hardware. The other box will be my desk's box, a brand new Sandy-Bridge E CPU (i7-3960X) with 32 GB RAM. I'm also inclined to install a dual boot box (I rejected this up to now since I do not like to install GRUB2 for having multiboot when using GPT on FreeBSD). The box will run with FreeBSD 9 and an Ubuntu or Gentoo Linux, if. I'm unsure in the question of Linux, but I tend to have Gentoo for compiling everything myself. On this box, I also can perform benchmarks with several setups. I see forward getting some help and/or tips to proof the issues we discussed here. Oliver --------------enigF2AFB91AE4784E4B43C44794 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO7e44AAoJEOgBcD7A/5N8JXIH/2jHjjXDyixlNuzilTAjLsCC gIG+hgdaUPpFIgNabsAEKQAyVzds3XnaxKXa6GO4LfZt0HNS0Cvi+HlAsjecVkBA 0zszqtIH69VS9HNjilTb9V3gWtOqZDjcuHAHHTjk1NguCRVhKwysH02LNi4ZABvB ZqabSecsa0aNdWPE3g8FjuItRvG32SpghXh4eYzNdgOqv5mlFbWR4Wh2QogOD5FI YNGWq95ZzAqVpvOj70RgnqRLVzWHRzGO9fEi/ePLABERKn6nJJzJImCU6R4QQU65 n5nWWtdGbTQs38ZL7K3lT4u15bpDq1pn+spkKSAldcFLjfJoNUYm0gptpSYDjxc= =xVHZ -----END PGP SIGNATURE----- --------------enigF2AFB91AE4784E4B43C44794-- From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 19:30:23 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3088A106566B; Sun, 18 Dec 2011 19:30:23 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 869458FC13; Sun, 18 Dec 2011 19:30:22 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so6136989vcb.13 for ; Sun, 18 Dec 2011 11:30:21 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=pEMdRrRcg5AdO9mTsB5TVaSe5Rr8mYJWphMeEd5LAQU=; b=fMxLrJpJs/kTvqbQG2tV/S2y1ll4h8EeAc41ApKIh6AXe1lCNazURdMyop/PEna306 WpeUWl6lohIKrYLLoi+/hM5ExM3EnmhQ8Qmq/UJrjWP6sUR3e2QSciK5F27nAbWQqQNr 1NOQvwFuP7x4jCbqHHHD3J94WljX3eEwxhl58= MIME-Version: 1.0 Received: by 10.220.230.67 with SMTP id jl3mr8014809vcb.60.1324236621811; Sun, 18 Dec 2011 11:30:21 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.26.50 with HTTP; Sun, 18 Dec 2011 11:30:21 -0800 (PST) In-Reply-To: <4EEDEE38.10802@zedat.fu-berlin.de> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <4EEDEE38.10802@zedat.fu-berlin.de> Date: Sun, 18 Dec 2011 11:30:21 -0800 X-Google-Sender-Auth: WbSSY3HSHYssZHOU3fhvNmQzWNs Message-ID: From: Adrian Chadd To: "O. Hartmann" Content-Type: text/plain; charset=ISO-8859-1 Cc: Bruce Cran , Ivan Klymenko , Doug Barton , freebsd-stable@freebsd.org, "O. Hartmann" , Current FreeBSD , Andrey Chernov , freebsd-performance@freebsd.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 19:30:23 -0000 Hi, What Attilllo and others need are KTR traces in the most stripped down example of interactive-busting workload you can find. Eg: if you're doing 32 concurrent buildworlds and trying to test interactivity - fine, but that's going to result in a lot of KTR stuff. If you can reproduce it using a dd via /dev/null and /dev/random (like another poster did) with nothing else running, then even better. If you can do it without X running, even better. I honestly suggest ignoring benchmarks for now and concentrating on interactivity. Adrian From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 10:41:16 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3EFDF106564A; Thu, 15 Dec 2011 10:41:16 +0000 (UTC) (envelope-from gmx@ross.cx) Received: from www81.your-server.de (www81.your-server.de [213.133.104.81]) by mx1.freebsd.org (Postfix) with ESMTP id E745C8FC08; Thu, 15 Dec 2011 10:41:15 +0000 (UTC) Received: from [188.108.237.120] (helo=michael-think) by www81.your-server.de with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.72) (envelope-from ) id 1Rb8kU-0008KX-Lp; Thu, 15 Dec 2011 11:41:14 +0100 Content-Type: text/plain; charset=iso-8859-15; format=flowed; delsp=yes To: "Michael Larabel" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> Date: Thu, 15 Dec 2011 11:41:05 +0100 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: "Michael Ross" Message-ID: In-Reply-To: <4EE9C79B.7080607@phoronix.com> User-Agent: Opera Mail/11.60 (Win32) X-Authenticated-Sender: gmx@ross.cx X-Virus-Scanned: Clear (ClamAV 0.97.3/14124/Wed Dec 14 16:10:02 2011) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, Current FreeBSD , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 10:41:16 -0000 Am 15.12.2011, 11:10 Uhr, schrieb Michael Larabel : > On 12/15/2011 02:48 AM, Michael Ross wrote: >> Anyway these tests were performed on different hardware, FWIW. >> And with different filesystems, different compilers, different GUIs... >> >> > > No, the same hardware was used for each OS. > The picture under the heading "System Hardware / Software" does not reflect that. Motherboard description differs, Chipset description for FreeBSD is empty. Regards, Michael > In terms of the software, the stock software stack for each OS was used. > > -- Michael From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 10:55:21 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D0498106566C; Thu, 15 Dec 2011 10:55:21 +0000 (UTC) (envelope-from michael.larabel@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 9892D8FC16; Thu, 15 Dec 2011 10:55:21 +0000 (UTC) Received: from c-98-193-96-120.hsd1.il.comcast.net ([98.193.96.120] helo=[172.16.93.133]) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1Rb8y8-0001HY-46; Thu, 15 Dec 2011 04:55:20 -0600 Message-ID: <4EE9D214.3070906@phoronix.com> Date: Thu, 15 Dec 2011 04:55:16 -0600 From: Michael Larabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Michael Ross References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: "O. Hartmann" , freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 10:55:21 -0000 On 12/15/2011 04:41 AM, Michael Ross wrote: > Am 15.12.2011, 11:10 Uhr, schrieb Michael Larabel > : > >> On 12/15/2011 02:48 AM, Michael Ross wrote: > >>> Anyway these tests were performed on different hardware, FWIW. >>> And with different filesystems, different compilers, different GUIs... >>> >>> >> >> No, the same hardware was used for each OS. >> > > The picture under the heading "System Hardware / Software" does not > reflect that. > > Motherboard description differs, Chipset description for FreeBSD is > empty. > I was the on that carried out the testing and know that it was on the same system. All of the testing, including the system tables, is fully automated. Under FreeBSD sometimes the parsing of some component strings isn't as nice as Linux and other supported operating systems by the Phoronix Test Suite. For the BSD motherboard string parsing it's grabbing hw.vendor/hw.product from sysctl. Is there a better place to read the motherboard DMI information from? -- Michael > > Regards, > > Michael > > >> In terms of the software, the stock software stack for each OS was used. >> >> -- Michael > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" > From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 11:19:10 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9D734106564A; Thu, 15 Dec 2011 11:19:10 +0000 (UTC) (envelope-from gmx@ross.cx) Received: from www81.your-server.de (www81.your-server.de [213.133.104.81]) by mx1.freebsd.org (Postfix) with ESMTP id 50C488FC12; Thu, 15 Dec 2011 11:19:09 +0000 (UTC) Received: from [188.108.237.120] (helo=michael-think) by www81.your-server.de with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.72) (envelope-from ) id 1Rb9L7-0005Np-8H; Thu, 15 Dec 2011 12:19:07 +0100 Content-Type: text/plain; charset=iso-8859-15; format=flowed; delsp=yes To: "Michael Larabel" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9D214.3070906@phoronix.com> Date: Thu, 15 Dec 2011 12:18:55 +0100 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit From: "Michael Ross" Message-ID: In-Reply-To: <4EE9D214.3070906@phoronix.com> User-Agent: Opera Mail/11.60 (Win32) X-Authenticated-Sender: gmx@ross.cx X-Virus-Scanned: Clear (ClamAV 0.97.3/14124/Wed Dec 14 16:10:02 2011) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: "O. Hartmann" , freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 11:19:10 -0000 Am 15.12.2011, 11:55 Uhr, schrieb Michael Larabel : > On 12/15/2011 04:41 AM, Michael Ross wrote: >> Am 15.12.2011, 11:10 Uhr, schrieb Michael Larabel >> : >> >>> On 12/15/2011 02:48 AM, Michael Ross wrote: >> >>>> Anyway these tests were performed on different hardware, FWIW. >>>> And with different filesystems, different compilers, different GUIs... >>>> >>>> >>> >>> No, the same hardware was used for each OS. >>> >> >> The picture under the heading "System Hardware / Software" does not >> reflect that. >> >> Motherboard description differs, Chipset description for FreeBSD is >> empty. >> > > I was the on that carried out the testing and know that it was on the > same system. No offense. I'm not doubting you. But I didn't know this: > All of the testing, including the system tables, is fully automated. > Under FreeBSD sometimes the parsing of some component strings isn't as > nice as Linux and other supported operating systems by the Phoronix Test > Suite. For the BSD motherboard string parsing it's grabbing > hw.vendor/hw.product from sysctl. so maybe you can understand how I got my impression. NVidia Audio and Realtek Audio. Looks different to me :-) > Is there a better place to read the motherboard DMI information from? > Following Steven Hartlands' suggestion, from one of my machines: /usr/ports/sysutils/dmidecode/#sysctl -a | egrep "hw.vendor|hw.product" /usr/ports/sysutils/dmidecode/#dmidecode -t 2 # dmidecode 2.11 SMBIOS 2.6 present. Handle 0x0002, DMI type 2, 15 bytes Base Board Information Manufacturer: FUJITSU Product Name: D2759 Version: S26361-D2759-A13 WGS04 GS02 Serial Number: 35838599 Asset Tag: - Features: Board is a hosting board Board is removable Location In Chassis: - Chassis Handle: 0x0003 Type: Motherboard Contained Object Handles: 0 Nice. Didn't know about that. Regards, Michael From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 11:41:09 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 607A5106564A; Thu, 15 Dec 2011 11:41:09 +0000 (UTC) (envelope-from hausen@punkt.de) Received: from kagate.punkt.de (kagate.punkt.de [217.29.33.131]) by mx1.freebsd.org (Postfix) with ESMTP id B46488FC0A; Thu, 15 Dec 2011 11:41:08 +0000 (UTC) Received: from hugo10.ka.punkt.de ([217.29.45.10]) by gate1.intern.punkt.de with ESMTP id pBFBS2Se088641; Thu, 15 Dec 2011 12:28:02 +0100 (CET) Received: from [217.29.45.158] ([217.29.45.158]) by hugo10.ka.punkt.de (8.14.2/8.14.2) with ESMTP id pBFBS1ub088347; Thu, 15 Dec 2011 12:28:01 +0100 (CET) (envelope-from hausen@punkt.de) Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: text/plain; charset=windows-1252 From: "Patrick M. Hausen" In-Reply-To: Date: Thu, 15 Dec 2011 12:28:01 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <0F38630E-D884-4B33-B64F-2631218C60E4@punkt.de> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9D214.3070906@phoronix.com> To: "Michael Ross" X-Mailer: Apple Mail (2.1251.1) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Michael Larabel , FreeBSD Stable Mailing List , Current FreeBSD , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 11:41:09 -0000 Hi, all, Am 15.12.2011 um 12:18 schrieb Michael Ross: > Following Steven Hartlands' suggestion, > from one of my machines: >=20 > /usr/ports/sysutils/dmidecode/#sysctl -a | egrep = "hw.vendor|hw.product" >=20 > /usr/ports/sysutils/dmidecode/#dmidecode -t 2 > # dmidecode 2.11 > SMBIOS 2.6 present. >=20 > Handle 0x0002, DMI type 2, 15 bytes > Base Board Information > Manufacturer: FUJITSU > Product Name: D2759 > Version: S26361-D2759-A13 WGS04 GS02 > Serial Number: 35838599 > Asset Tag: - > Features: > Board is a hosting board > Board is removable > Location In Chassis: - > Chassis Handle: 0x0003 > Type: Motherboard > Contained Object Handles: 0 Without the need to install an additional port: datatomb2# kenv =85 smbios.bios.reldate=3D"11/03/2011" smbios.bios.vendor=3D"FUJITSU // American Megatrends Inc." smbios.bios.version=3D"V4.6.4.1 R1.18.0 for D3034-A1x" smbios.chassis.maker=3D"FUJITSU" smbios.chassis.serial=3D"YLAP004857" smbios.chassis.tag=3D"System Asset Tag " smbios.chassis.version=3D"RX100S7R2" smbios.memory.enabled=3D"8388608" smbios.planar.maker=3D"FUJITSU" smbios.planar.product=3D"D3034-A1" smbios.planar.serial=3D"LJ1B-P00996" smbios.planar.version=3D"S26361-D3034-A100 WGS01 GS02" smbios.socket.enabled=3D"1" smbios.socket.populated=3D"1" smbios.system.maker=3D"FUJITSU" smbios.system.product=3D"PRIMERGY RX100 S7" smbios.system.serial=3D"YLAP004857" smbios.system.uuid=3D"f0493081-f5ca-e011-b8a5-a1c4d143da5f" smbios.system.version=3D"GS02" smbios.version=3D"2.7" =85 Kind regards, Patrick --=20 punkt.de GmbH * Kaiserallee 13a * 76133 Karlsruhe Tel. 0721 9109 0 * Fax 0721 9109 100 info@punkt.de http://www.punkt.de Gf: J=FCrgen Egeling AG Mannheim 108285 From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 12:06:08 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0DA9C106566B for ; Thu, 15 Dec 2011 12:06:08 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta05.emeryville.ca.mail.comcast.net (qmta05.emeryville.ca.mail.comcast.net [76.96.30.48]) by mx1.freebsd.org (Postfix) with ESMTP id E02318FC15 for ; Thu, 15 Dec 2011 12:06:07 +0000 (UTC) Received: from omta22.emeryville.ca.mail.comcast.net ([76.96.30.89]) by qmta05.emeryville.ca.mail.comcast.net with comcast id 9Psp1i0011vN32cA5PspGj; Thu, 15 Dec 2011 11:52:49 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta22.emeryville.ca.mail.comcast.net with comcast id 9Q9m1i0071t3BNj8iQ9mXM; Thu, 15 Dec 2011 12:09:47 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id 95117102C19; Thu, 15 Dec 2011 03:52:54 -0800 (PST) Date: Thu, 15 Dec 2011 03:52:54 -0800 From: Jeremy Chadwick To: Michael Larabel Message-ID: <20111215115254.GA21530@icarus.home.lan> References: <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9D214.3070906@phoronix.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EE9D214.3070906@phoronix.com> User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: "O. Hartmann" , Michael Ross , freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 12:06:08 -0000 On Thu, Dec 15, 2011 at 04:55:16AM -0600, Michael Larabel wrote: > On 12/15/2011 04:41 AM, Michael Ross wrote: > >Am 15.12.2011, 11:10 Uhr, schrieb Michael Larabel > >: > > > >>On 12/15/2011 02:48 AM, Michael Ross wrote: > > > >>>Anyway these tests were performed on different hardware, FWIW. > >>>And with different filesystems, different compilers, different GUIs... > >>> > >>> > >> > >>No, the same hardware was used for each OS. > >> > > > >The picture under the heading "System Hardware / Software" does > >not reflect that. > > > >Motherboard description differs, Chipset description for FreeBSD > >is empty. > > > > I was the on that carried out the testing and know that it was on > the same system. > > All of the testing, including the system tables, is fully automated. > Under FreeBSD sometimes the parsing of some component strings isn't > as nice as Linux and other supported operating systems by the > Phoronix Test Suite. For the BSD motherboard string parsing it's > grabbing hw.vendor/hw.product from sysctl. > > Is there a better place to read the motherboard DMI information from? I *think* what you're referring to is SMBIOS strings -- and these are available from kenv(1) / kenv(2), not sysctl. But keep reading for why SMBIOS data is not 100% reliable (greatly depends on the hardware). For actual device strings/etc. for all devices on busses (PCI, AGP, etc.) you can use pciconf -lvcb. That's about as good as it's going to get via software. SMBIOS data (e.g. smbios.{bios,chassis,planar,system}) is never going to give you fully-identifiable data; I can point you to tons of systems where the data inserted there is nonsense, sometimes even just ASCII spaces (and that is the fault of the system vendor/BIOS manufacturer, not FreeBSD). Sometimes identical strings are used across completely different systems/boards (sometimes even server-class boards like ones from Supermicro). And PCI vendor strings don't give you things like speeds, frequency/voltages, etc.. Sometimes this matters. For example (just making something up): "the video benchmark was horrible on FreeBSD", when in fact it turned out that a run of "pciconf -lvcb" showed your PCIe card was running at x4 link speed instead of x16. The best place to get your specifications from are: * The box * The physical hardware (by physically inspecting it) * The user manual / product documentation/ * Purchase orders from whoever bought the hardware * And, of course, operational speed (if possible) from the OS/userland utilities When I read a benchmark/review, I have to assume the person is doing them on a system they have 100% control over, all the way down to the hardware. Thus, they should know what exact hardware they have. Also, when publishing results online, you should take the time to proofread everything (with a 2nd set of eyes if possible) and be patient and thorough. People like accuracy, especially when there's hard data/evidence to back it up that can be made available for download. Try to understand: so many review-esque sites consist of individuals who do not understand even remotely what they're doing. I'm going to give you two examples -- one personal, one word-of-mouth but from someone I trust dearly. I have a "reverse analysis" of Anantech's Intel 510 SSD review that has been sitting in my "draft" folder on my blog for a month now because I'm downright afraid to publish how their data seems completely and totally wrong (with evidence to prove it). I'm afraid/stalling because I want to make absolutely damn sure I'm not missing some key piece of evidence that explains it, and I've had multiple people read it and go "...wow, I didn't notice that, that benchmark data makes no sense", but I'm STILL reluctant. The last thing I want to do is "publish" something that sparks a controversy where it turns out I'm wrong (and I AM wrong, quite often!). As for the other: http://www.overclockers.com/bulldozer-architecture-explained/ The author of this "review" talks about CPU arch and is praised for writing a "wonderful article that speaks the truth". But sadly that doesn't appear to be the case. A colleague of mine is long-time friends with another individual who is getting his Ph.D in computer architecture and recently submit a paper to a journal (and was published/accepted) which has published papers on things like RAID (when it was first introduced as a concept/method), and hardware watchpoints. Said individual read the above "review" and described it as, quote, "the worst article on computer architecture on the entire Internet". One of the amusing quotes (that got me laughing since I did understand it; my understanding of CPUs on a silicon level is limited, I'm just an old 65xxx assembly programmer...) was how the article states "this is the first time AMD has implemented branch prediction". Sigh. Here's the kicker: said individual immediately recognised that the article was a near dry cut-and-paste from one of two commonly-used computer architecture books in college/universities; the first book is basically a "beginner's guide to CPU architecture". The book is also a bit old at that. Individual proceeded to look up where the article author went to school, and noted that said school's CPU architecture course **ends** with that book. The user/viewer demographic of overclockers.com is going to be significantly different from that of phoronix.com -- you know that I'm sure. The point is that you should be aware that there is going to be significant discussions that come from publishing such benchmark comparisons with such a demographic. Things that indicate severe performance differential (e.g. "10x to 100x worse") are going to be focused on and criticised -- and hopefully in a socially-agreeable manner[1] -- and in a much different way than, say, a 3D video card review site ("lol ur pc sux if u spend onl $4000 on it lol"). The first step is to try and figure out what exactly you're seeing and why it's so significantly different when compared to other OSes. [1]: I'm sure by now you know that the BSDs in general tend to harbour a community of folks who are more argumentative/aggressive than, say, Linux (generally speaking). In this thread though, I think all of us really want to assist in some way to figure out what exactly is going on here, scheduler-wise, and see if we can put something together to hand developers who are "responsible" for said code and see what comes of it. Remember, we're all here to try and make things better... I hope. :-) Footnote: It's nice meeting you (indirectly), I was always curious who did the phoronix.com reviews/"stuff" when it came to FreeBSD. Greetings! -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 12:56:03 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 04486106564A; Thu, 15 Dec 2011 12:56:03 +0000 (UTC) (envelope-from sjg@evilcode.net) Received: from mail-iy0-f182.google.com (mail-iy0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 9B0658FC12; Thu, 15 Dec 2011 12:56:02 +0000 (UTC) Received: by iakl21 with SMTP id l21so5157427iak.13 for ; Thu, 15 Dec 2011 04:56:02 -0800 (PST) MIME-Version: 1.0 Received: by 10.42.161.10 with SMTP id r10mr2375060icx.22.1323952367276; Thu, 15 Dec 2011 04:32:47 -0800 (PST) Received: by 10.50.163.106 with HTTP; Thu, 15 Dec 2011 04:32:47 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> Date: Thu, 15 Dec 2011 05:32:47 -0700 Message-ID: From: "Samuel J. Greear" To: Adrian Chadd Content-Type: text/plain; charset=ISO-8859-1 X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, Current FreeBSD , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 12:56:03 -0000 > Well, the only way it's going to get fixed is if someone sits down, > replicates it, and starts to document exactly what it is that these > benchmarks are/aren't doing. > I think you will find that investigation is largely a waste of time, because not only are some of these benchmarks just downright silly, there are huge differences in the environments (compiler versions), etc., etc. leading to a largely apples/oranges comparison. But also the the analysis and reporting of the results by Phoronix is simply moronic to the point of being worse than useful, they are spreading misinformation. Take the first test as an example, Blogbench read. This doesn't raise any red flags, right? At least not until you realize that Blogbench isn't a read test, it's a read/write test. So what they have done here is run a read/write test and then thrown away the write results for both platforms and reported only the read results. If you dig down into the actual results, http://openbenchmarking.org/result/1112113-AR-ORACLELIN37 -- you will see two Blogbench numbers, one for read and another for write. These were both taken from the same Blogbench run, so FreeBSD optimizes writes over reads, that's probably a good thing for your data but a bad thing when someone totally misrepresents benchmark results. Other benchmarks in the Phoronix suite and their representations are similarly flawed, _ALL_ of these results should be ignored and no time should be wasted by any FreeBSD committer further evaluating this garbage. (Yes, I have been down this rabbit hole). Best, Sam From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 13:36:23 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 34DC31065670; Thu, 15 Dec 2011 13:36:23 +0000 (UTC) (envelope-from michael.larabel@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id C962E8FC0C; Thu, 15 Dec 2011 13:36:22 +0000 (UTC) Received: from c-98-193-96-120.hsd1.il.comcast.net ([98.193.96.120] helo=[172.16.93.133]) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1RbBTx-0005eR-HR; Thu, 15 Dec 2011 07:36:21 -0600 Message-ID: <4EE9F7D2.4050607@phoronix.com> Date: Thu, 15 Dec 2011 07:36:18 -0600 From: Michael Larabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Stefan Esser References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9F546.6060503@freebsd.org> In-Reply-To: <4EE9F546.6060503@freebsd.org> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: FreeBSD Stable Mailing List , Current FreeBSD , Michael Ross , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 13:36:23 -0000 On 12/15/2011 07:25 AM, Stefan Esser wrote: > Am 15.12.2011 11:10, schrieb Michael Larabel: >> No, the same hardware was used for each OS. >> >> In terms of the software, the stock software stack for each OS was used. > Just curious: Why did you choose ZFS on FreeBSD, while UFS2 (with > journaling enabled) should be an obvious choice since it is more similar > in concept to ext4 and since that is what most FreeBSD users will use > with FreeBSD? I was running some ZFS vs. UFS tests as well and this happened to have ZFS on when I was running some other tests. > > Did you tune the ZFS ARC (e.g. vfs.zfs.arc_max="6G") for the tests? The OS was left in its stock configuration. > > And BTW: Did your measured run times account for the effect, that Linux > keeps much more dirty data in the buffer cache (FreeBSD has a low limit > on dirty buffers since under realistic load the already cached data is > much more likely to be reused and thus more valuable than freshly > written data; aggressively caching dirty data would significantly reduce > throughput and responsiveness under high load). Given the hardware specs > of the test system, I guess that Linux accepts at least 100 times the > dirty data in the buffer cache, compared to FreeBSD (where this number > is at most in the tens of megabyte range). > > If you did not, then your results do not represent a server load (which > I'd expect relevant, if you are testing against Oracle Linux 6.1 > server), where continuous performance is required. Tests that run on an > idle system starting in a clean state and ignoring background flushing > of the buffer cache after the timed program has stopped are perhaps > useful for a very lowly loaded PC, but not for a system with high load > average as the default. > > I bet that if you compared the systems under higher load (which > admittedly makes it much harder to get sensible numbers for the program > under test) or with reduced buffer cache size (or raise the dirty buffer > limit in FreeBSD accordingly, which ought to be possible with sysctl > and/or boot time tuneables, e.g. "vfs.hidirtybuffers"). > > And a last remark: Single benchmark runs do not provide reliable data. > FreeBSD comes with "ministat" to check the significance of benchmark > results. Each test should be repeated at least 5 times for meaningful > averages with acceptable confidence level. The Phoronix Test Suite runs most tests a minimum of three times and if the standard deviation exceeds 3.5% the run count is dynamically increased, among other safeguards. -- Michael > > Regards, STefan > From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 13:38:24 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 691C21065670 for ; Thu, 15 Dec 2011 13:38:24 +0000 (UTC) (envelope-from se@freebsd.org) Received: from nm14-vm0.bullet.mail.sp2.yahoo.com (nm14-vm0.bullet.mail.sp2.yahoo.com [98.139.91.246]) by mx1.freebsd.org (Postfix) with SMTP id 27CFA8FC12 for ; Thu, 15 Dec 2011 13:38:24 +0000 (UTC) Received: from [98.139.91.66] by nm14.bullet.mail.sp2.yahoo.com with NNFMP; 15 Dec 2011 13:25:31 -0000 Received: from [208.71.42.199] by tm6.bullet.mail.sp2.yahoo.com with NNFMP; 15 Dec 2011 13:25:31 -0000 Received: from [127.0.0.1] by smtp210.mail.gq1.yahoo.com with NNFMP; 15 Dec 2011 13:25:31 -0000 X-Yahoo-Newman-Id: 255449.13797.bm@smtp210.mail.gq1.yahoo.com X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: D.d22ugVM1kW77kJo_KuiJ4ECL6o_d1T5Ot8tz7TqMkZlin sfpHDsvh31_RkqrqtPHcYzl8LRB6hLub297OjeYgJ6cNnZmnUV.0T9SBElQl BaCAkt41gK1QdPUwcV.sql4kxUReZNPG32fY9Mlrs4JnWXzN9h9TDrmXgrj5 IMI3VW2cpFUgvE8PDFu4fU2kKbUna5Y9ugkVhaZ_bsRSJeagYGMGmH0fav7v UEShzLmPeMsl9t6nAfB0yy3WVcLdZNdvNzE7JrxK20S4vZMgdYOzHiS1oMyN yNQ2eKgihkl1mHUBwm4q0tc_ts350EU7VsFSY_sDst7Ohv9LfDxu72pGN42b klqFVdeAwvmf72wdUZXzfhBbSZbXHDYKgoAvjhnyObXUHwiByw7gZ5YDELJf Jly.jDQ.d7PoTBg-- X-Yahoo-SMTP: iDf2N9.swBDAhYEh7VHfpgq0lnq. Received: from [192.168.119.20] (se@81.173.151.71 with plain) by smtp210.mail.gq1.yahoo.com with SMTP; 15 Dec 2011 05:25:30 -0800 PST Message-ID: <4EE9F546.6060503@freebsd.org> Date: Thu, 15 Dec 2011 14:25:26 +0100 From: Stefan Esser User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Michael Larabel References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> In-Reply-To: <4EE9C79B.7080607@phoronix.com> Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: FreeBSD Stable Mailing List , Current FreeBSD , Michael Ross , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 13:38:24 -0000 Am 15.12.2011 11:10, schrieb Michael Larabel: > No, the same hardware was used for each OS. > > In terms of the software, the stock software stack for each OS was used. Just curious: Why did you choose ZFS on FreeBSD, while UFS2 (with journaling enabled) should be an obvious choice since it is more similar in concept to ext4 and since that is what most FreeBSD users will use with FreeBSD? Did you tune the ZFS ARC (e.g. vfs.zfs.arc_max="6G") for the tests? And BTW: Did your measured run times account for the effect, that Linux keeps much more dirty data in the buffer cache (FreeBSD has a low limit on dirty buffers since under realistic load the already cached data is much more likely to be reused and thus more valuable than freshly written data; aggressively caching dirty data would significantly reduce throughput and responsiveness under high load). Given the hardware specs of the test system, I guess that Linux accepts at least 100 times the dirty data in the buffer cache, compared to FreeBSD (where this number is at most in the tens of megabyte range). If you did not, then your results do not represent a server load (which I'd expect relevant, if you are testing against Oracle Linux 6.1 server), where continuous performance is required. Tests that run on an idle system starting in a clean state and ignoring background flushing of the buffer cache after the timed program has stopped are perhaps useful for a very lowly loaded PC, but not for a system with high load average as the default. I bet that if you compared the systems under higher load (which admittedly makes it much harder to get sensible numbers for the program under test) or with reduced buffer cache size (or raise the dirty buffer limit in FreeBSD accordingly, which ought to be possible with sysctl and/or boot time tuneables, e.g. "vfs.hidirtybuffers"). And a last remark: Single benchmark runs do not provide reliable data. FreeBSD comes with "ministat" to check the significance of benchmark results. Each test should be repeated at least 5 times for meaningful averages with acceptable confidence level. Regards, STefan From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 13:48:57 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4CA04106566B for ; Thu, 15 Dec 2011 13:48:57 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta04.westchester.pa.mail.comcast.net (qmta04.westchester.pa.mail.comcast.net [76.96.62.40]) by mx1.freebsd.org (Postfix) with ESMTP id E2A3B8FC1A for ; Thu, 15 Dec 2011 13:48:56 +0000 (UTC) Received: from omta19.westchester.pa.mail.comcast.net ([76.96.62.98]) by qmta04.westchester.pa.mail.comcast.net with comcast id 9Q0n1i00427AodY54RoxXz; Thu, 15 Dec 2011 13:48:57 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta19.westchester.pa.mail.comcast.net with comcast id 9Rov1i00Y1t3BNj3fRov2n; Thu, 15 Dec 2011 13:48:57 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id F0D36102C19; Thu, 15 Dec 2011 05:48:53 -0800 (PST) Date: Thu, 15 Dec 2011 05:48:53 -0800 From: Jeremy Chadwick To: "Samuel J. Greear" Message-ID: <20111215134853.GA24753@icarus.home.lan> References: <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: "O. Hartmann" , Adrian Chadd , Current FreeBSD , FreeBSD Stable Mailing List , freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 13:48:57 -0000 On Thu, Dec 15, 2011 at 05:32:47AM -0700, Samuel J. Greear wrote: > > Well, the only way it's going to get fixed is if someone sits down, > > replicates it, and starts to document exactly what it is that these > > benchmarks are/aren't doing. > > > > I think you will find that investigation is largely a waste of time, > because not only are some of these benchmarks just downright silly, > there are huge differences in the environments (compiler versions), > etc., etc. leading to a largely apples/oranges comparison. But also > the the analysis and reporting of the results by Phoronix is simply > moronic to the point of being worse than useful, they are spreading > misinformation. > > Take the first test as an example, Blogbench read. This doesn't raise > any red flags, right? At least not until you realize that Blogbench > isn't a read test, it's a read/write test. So what they have done here > is run a read/write test and then thrown away the write results for > both platforms and reported only the read results. If you dig down > into the actual results, > http://openbenchmarking.org/result/1112113-AR-ORACLELIN37 -- you will > see two Blogbench numbers, one for read and another for write. These > were both taken from the same Blogbench run, so FreeBSD optimizes > writes over reads, that's probably a good thing for your data but a > bad thing when someone totally misrepresents benchmark results. > > Other benchmarks in the Phoronix suite and their representations are > similarly flawed, _ALL_ of these results should be ignored and no time > should be wasted by any FreeBSD committer further evaluating this > garbage. (Yes, I have been down this rabbit hole). For sake of argument, let's say we throw out the Phoronix benchmarks as a data source (I don't think the benchmark specifically implied or stated "this is all because of SCHED_ULE" though; remember, that's what we're supposed to be focusing on. There may not be a direct correlation between the Phoronix benchmarks and the ULE issue reported here...). That said: thrown out, data ignored, done. Now what? Where are we? We're right back where we were a day or two ago; meaning no closer to solving the dilemma reported by users and SCHED_ULE. Heck, we're not even sure if there is an issue, other than some folks confirming that SCHED_4BSD performs better for them (that's what started this whole thread), and there are at least a couple which have stated this. So given the above semi-devil's-advocate response -- Sam, do you have something positive or progressive to offer so we can move forward on the ULE vs. 4BSD debacle? :-) The smiley is meant to be sincere, not sarcastic. I'm getting to the point where I'm considering formulating a private mail to Jeff Roberson, requesting that he be aware of the discussion that's happening (not that he necessarily follow or read it), and that based on what I can tell we're at a roadblock -- nobody so far is absolutely certain how to "benchmark" and compare ULE vs. 4BSD in multiple ways, so that those of us involved here can run such utilities and provide the data somewhere central for devs to review. I only mention this because so far I haven't seen anyone really say "okay, this is what we should be using for these kinds of tests". Yay nature of the beast. -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 14:28:26 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id D0D4B106564A; Thu, 15 Dec 2011 14:28:26 +0000 (UTC) (envelope-from michael.larabel@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 9EBED8FC13; Thu, 15 Dec 2011 14:28:26 +0000 (UTC) Received: from c-98-193-96-120.hsd1.il.comcast.net ([98.193.96.120] helo=[172.16.93.133]) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1RbCIL-00079g-BN; Thu, 15 Dec 2011 08:28:25 -0600 Message-ID: <4EEA0406.2010002@phoronix.com> Date: Thu, 15 Dec 2011 08:28:22 -0600 From: Michael Larabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Sergey Matveychuk References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9F546.6060503@freebsd.org> <4EE9F7D2.4050607@phoronix.com> <4EEA0388.7010605@FreeBSD.org> In-Reply-To: <4EEA0388.7010605@FreeBSD.org> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: FreeBSD Stable Mailing List , Current FreeBSD , Stefan Esser , Michael Ross , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 14:28:26 -0000 On 12/15/2011 08:26 AM, Sergey Matveychuk wrote: > 15.12.2011 17:36, Michael Larabel пишет: >> On 12/15/2011 07:25 AM, Stefan Esser wrote: >>> Am 15.12.2011 11:10, schrieb Michael Larabel: >>>> No, the same hardware was used for each OS. >>>> >>>> In terms of the software, the stock software stack for each OS was >>>> used. >>> Just curious: Why did you choose ZFS on FreeBSD, while UFS2 (with >>> journaling enabled) should be an obvious choice since it is more >>> similar >>> in concept to ext4 and since that is what most FreeBSD users will use >>> with FreeBSD? >> >> I was running some ZFS vs. UFS tests as well and this happened to have >> ZFS on when I was running some other tests. >> > > Can we look at the tests? > My opinion is ZFS without tuning is much slower than UFS2. > http://www.phoronix.com/scan.php?page=news_item&px=MTAyNjg From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 14:28:36 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9DDA0106564A; Thu, 15 Dec 2011 14:28:36 +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 25D788FC18; Thu, 15 Dec 2011 14:28:34 +0000 (UTC) Received: from [192.168.100.59] (varna2.digsys.bg [193.68.0.70]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBFDwgXO002173 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NO); Thu, 15 Dec 2011 15:58:48 +0200 (EET) (envelope-from daniel@digsys.bg) Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: text/plain; charset=windows-1252 From: Daniel Kalchev In-Reply-To: <20111215134853.GA24753@icarus.home.lan> Date: Thu, 15 Dec 2011 15:58:44 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <0C72D682-CF5E-42D6-91F3-FEF1AB02F5D6@digsys.bg> References: <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <20111215134853.GA24753@icarus.home.lan> To: Jeremy Chadwick X-Mailer: Apple Mail (2.1251.1) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Adrian Chadd , "Samuel J. Greear" , Current FreeBSD , FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, "O. Hartmann" Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 14:28:36 -0000 On Dec 15, 2011, at 3:48 PM, Jeremy Chadwick wrote: [=85] > That said: thrown out, data ignored, done. >=20 > Now what? Where are we? We're right back where we were a day or two > ago; meaning no closer to solving the dilemma reported by users and > SCHED_ULE. Heck, we're not even sure if there is an issue, other than > some folks confirming that SCHED_4BSD performs better for them (that's > what started this whole thread), and there are at least a couple which > have stated this. But, are any of these benchmarks really engaging the 4BSD/ULE scheduler = differences? Most such benchmarks are run on a system with no other load = whatsoever and in no way represent real world experience. What is more, I believe in such benchmarks "the system feels sluggish" = is not measured at all. Even if it is measured, if in such case the = benchmark finishes "better" - that is, faster, or say, makes the system = freeze for the user for the duration of the test -- it will be = considered "win", because the benchmark suite ran faster on that = particular system -- whereas a system which ran the benchmark fast, = provided good interactive response etc would be considered "loser". I think it is not good idea to hijack this thread, but instead focusing = on the other SCHED_ULE bashing thread to define an reasonable benchmark = or a set of benchmarks rather -- so that many would run it and provide = feedback. Daniel= From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 14:28:38 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id B64011065672; Thu, 15 Dec 2011 14:28:38 +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 3B34E8FC08; Thu, 15 Dec 2011 14:28:37 +0000 (UTC) Received: from [192.168.100.59] (varna2.digsys.bg [193.68.0.70]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBFDpWq6002143 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NO); Thu, 15 Dec 2011 15:51:41 +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: <4EE9F546.6060503@freebsd.org> Date: Thu, 15 Dec 2011 15:51:33 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9F546.6060503@freebsd.org> To: Stefan Esser X-Mailer: Apple Mail (2.1251.1) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Michael Larabel , FreeBSD Stable Mailing List , Current FreeBSD , Michael Ross , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 14:28:38 -0000 On Dec 15, 2011, at 3:25 PM, Stefan Esser wrote: > Am 15.12.2011 11:10, schrieb Michael Larabel: >> No, the same hardware was used for each OS. >>=20 >> In terms of the software, the stock software stack for each OS was = used. >=20 > Just curious: Why did you choose ZFS on FreeBSD, while UFS2 (with > journaling enabled) should be an obvious choice since it is more = similar > in concept to ext4 and since that is what most FreeBSD users will use > with FreeBSD? Or perhaps, since it is "server" Linux distribution, use ZFS on Linux as = well. With identical tuning on both Linux and FreeBSD. Having the same = FS used by both OS will help make the comparison more sensible for FS = I/O. Daniel= From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 15:04:27 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6CA23106566C; Thu, 15 Dec 2011 15:04:27 +0000 (UTC) (envelope-from c.kworr@gmail.com) Received: from mail-ey0-f182.google.com (mail-ey0-f182.google.com [209.85.215.182]) by mx1.freebsd.org (Postfix) with ESMTP id 7E0558FC1A; Thu, 15 Dec 2011 15:04:26 +0000 (UTC) Received: by eaaf13 with SMTP id f13so2846321eaa.13 for ; Thu, 15 Dec 2011 07:04:25 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=message-id:date:from:user-agent:mime-version:to:cc:subject :references:in-reply-to:content-type:content-transfer-encoding; bh=MwE4PWmmZsIrl3Fv2tOOByGa4iu4zNYVZ+pfk7K/CbQ=; b=WEPBi2oUCm0WMb3/rGnGlDFgZ6oMJAoS6jfGmZDV2uJWn+fiP+AeUG7zYHXRWMkv+a fThzvtxH7VuuhFW1S6pihiYXbW8GoAd8h4yMJaSEwk5LVceVG+DSHOMXSuYpCaJPFzF4 EijjxPSKUZ49lumVSGr7w4tAHs62WzyZHpTVc= Received: by 10.205.122.133 with SMTP id gg5mr1158106bkc.65.1323959852122; Thu, 15 Dec 2011 06:37:32 -0800 (PST) Received: from green.tandem.local (utwig.xim.bz. [91.216.237.46]) by mx.google.com with ESMTPS id j9sm14858864bkd.2.2011.12.15.06.37.29 (version=SSLv3 cipher=OTHER); Thu, 15 Dec 2011 06:37:30 -0800 (PST) Message-ID: <4EEA0627.3000409@gmail.com> Date: Thu, 15 Dec 2011 16:37:27 +0200 From: Volodymyr Kostyrko User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111111 Thunderbird/8.0 MIME-Version: 1.0 To: Jeremy Chadwick References: <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <20111215134853.GA24753@icarus.home.lan> In-Reply-To: <20111215134853.GA24753@icarus.home.lan> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Adrian Chadd , "Samuel J. Greear" , Current FreeBSD , FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, "O. Hartmann" Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 15:04:27 -0000 15.12.2011 15:48, Jeremy Chadwick wrote: > I'm getting to the point where I'm considering formulating a private > mail to Jeff Roberson, requesting that he be aware of the discussion > that's happening (not that he necessarily follow or read it), and that > based on what I can tell we're at a roadblock -- nobody so far is > absolutely certain how to "benchmark" and compare ULE vs. 4BSD in > multiple ways, so that those of us involved here can run such utilities > and provide the data somewhere central for devs to review. I only > mention this because so far I haven't seen anyone really say "okay, this > is what we should be using for these kinds of tests". Yay nature of the > beast. I'll try to summarize and propose a test scenario. I don't know whether this helps or not. We should have two different task types for this one. The first would be Super Affine tasks. They should use few to none syscalls, use medium math, have low memory footprint. No syscalls means this tasks will never stop for memory/disk or other activity so each time the queue is looked upon this task will be ready to run. Medium math means this shouldn't be just a simple big loop so that processor will really compute something with this data. Low memory footprint means this task can reside with data on CPU L1 cache for eons. I'm not sure about branch prediction, should it be distorted or not... The other task type would be Worker. It doesn't matter what it does but it agressively uses syscalls like working with files/directories. There should be at least one SA-task per core and at least 10 (?) W-tasks per core. -- Sphinx of black quartz judge my vow. From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 17:49:00 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 51BC5106566C for ; Thu, 15 Dec 2011 17:49:00 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta04.westchester.pa.mail.comcast.net (qmta04.westchester.pa.mail.comcast.net [76.96.62.40]) by mx1.freebsd.org (Postfix) with ESMTP id AEA348FC14 for ; Thu, 15 Dec 2011 17:48:59 +0000 (UTC) Received: from omta22.westchester.pa.mail.comcast.net ([76.96.62.73]) by qmta04.westchester.pa.mail.comcast.net with comcast id 9UzZ1i00C1ap0As54VozbY; Thu, 15 Dec 2011 17:48:59 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta22.westchester.pa.mail.comcast.net with comcast id 9Voy1i01K1t3BNj3iVoydW; Thu, 15 Dec 2011 17:48:59 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id 2B4DD102C19; Thu, 15 Dec 2011 09:48:57 -0800 (PST) Date: Thu, 15 Dec 2011 09:48:57 -0800 From: Jeremy Chadwick To: Attilio Rao Message-ID: <20111215174857.GA28551@icarus.home.lan> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <20111213073615.GA69641@icarus.home.lan> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: "O. Hartmann" , Current FreeBSD , freebsd-stable@freebsd.org, freebsd-performance@freebsd.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 17:49:00 -0000 On Thu, Dec 15, 2011 at 05:26:27PM +0100, Attilio Rao wrote: > 2011/12/13 Jeremy Chadwick : > > On Mon, Dec 12, 2011 at 02:47:57PM +0100, O. Hartmann wrote: > >> > Not fully right, boinc defaults to run on idprio 31 so this isn't an > >> > issue. And yes, there are cases where SCHED_ULE shows much better > >> > performance then SCHED_4BSD. ??[...] > >> > >> Do we have any proof at hand for such cases where SCHED_ULE performs > >> much better than SCHED_4BSD? Whenever the subject comes up, it is > >> mentioned, that SCHED_ULE has better performance on boxes with a ncpu > > >> 2. But in the end I see here contradictionary statements. People > >> complain about poor performance (especially in scientific environments), > >> and other give contra not being the case. > >> > >> Within our department, we developed a highly scalable code for planetary > >> science purposes on imagery. It utilizes present GPUs via OpenCL if > >> present. Otherwise it grabs as many cores as it can. > >> By the end of this year I'll get a new desktop box based on Intels new > >> Sandy Bridge-E architecture with plenty of memory. If the colleague who > >> developed the code is willing performing some benchmarks on the same > >> hardware platform, we'll benchmark bot FreeBSD 9.0/10.0 and the most > >> recent Suse. For FreeBSD I intent also to look for performance with both > >> different schedulers available. > > > > This is in no way shape or form the same kind of benchmark as what > > you're planning to do, but I thought I'd throw it out there for folks to > > take in as they see fit. > > > > I know folks were focused mainly on buildworld. > > > > 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). > > > > -- > > | Jeremy Chadwick ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ??jdc at parodius.com | > > | Parodius Networking ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? ?? http://www.parodius.com/ | > > | UNIX Systems Administrator ?? ?? ?? ?? ?? ?? ?? ?? ?? Mountain View, CA, US | > > | Making life hard for others since 1977. ?? ?? ?? ?? ?? ?? ?? PGP 4BD6C0CB | > > > > > > sched_ule > > =========== > > - time make -j2 buildworld > > ??1689.831u 229.328s 18:46.20 170.4% 6566+2051k 432+4264io 4565pf+0w > > - time make -j2 buildkernel > > ??640.542u 87.737s 9:01.38 134.5% 6490+1920k 134+5968io 0pf+0w > > > > > > sched_4bsd > > ============ > > - time make -j2 buildworld > > ??1662.793u 206.908s 17:12.02 181.1% 6578+2054k 23750+4271io 6451pf+0w > > - time make -j2 buildkernel > > ??638.717u 76.146s 8:34.90 138.8% 6530+1927k 6415+5903io 0pf+0w > > > > > > software > > ========== > > * sched_ule test: ??FreeBSD 8.2-STABLE, Thu Dec ??1 04:37:29 PST 2011 > > * sched_4bsd test: FreeBSD 8.2-STABLE, Mon Dec 12 22:42:54 PST 2011 > > Hi Jeremy, > thanks for the time you spent on this. > > However, I wanted to ask/let you note 3 things: > 1) Did you use 2 different code base for the test? (one updated on > December 1 and another one on December 12) No; src-all (/usr/src on this system) was not updated between December 1st and December 12th PST. I do believe I updated it today (15th PST). I can/will obviously hold off so that we have a consistent code base for comparing numbers between schedulers during buildworld and/or buildkernel. > 2) Please note that you should have repeated this test several times > (basically until you don't get a standard deviation which is > acceptable with ministat) and report the ministat output This is the first time I have heard of ministat(1). I'm pretty sure I see what it's for and how it applies to this situation, but boy that man page could use some clarification (I have 3 people looking at this thing right now trying to figure out what means what in the graph :-) ). Anyway, graph or not, I see the point. Regarding multiple tests: yup, you're absolutely right, the only way to do it would be to run a sequence of tests repeatedly (probably 10 per scheduler). Reboots and rm -fr /usr/obj/* would be required after each test too, to guarantee empty kernel caches (of all types) consistently every time. What I posted was supposed to give people just a "general idea" if there was any gigantic difference between the two, and there really isn't. But, as others have stated (and you below), buildworld may not be an effective way to "benchmark" what we're trying to test. Hence me wondering exactly what would make for a good test. Example: 1. Run + background some program that "beats on things" (I really don't know what; creation/deletion of threads? CPU benchmark? bonnie++?), with output going to /dev/null. 2. Run + background "time make -j2 buildworld" with output going to /dev/null 3. Record/save output from "time". 4. rm -fr /usr/obj && shutdown -r now 5. Repeat all steps ~10 times 6. Adjust kernel configuration file to use other scheduler 7. Repeat steps 1-5. What I'm trying to figure out is what #1 and #2 should be in the above example. > 3) The difference is less than 2% which I suspect is really > statistically unuseful/the same Understood. > I'm not really even surprised ULE is not faster than 4BSD in this case > because usually buildworld/buildkernel tests are driven for the vast > majority by I/O overhead rather than scheduler capacity. It would be > more interesting to analyze how buildworld does while another type of > workload is going on. Yup, agreed/understood, hence me trying to find out what would classify as a good stress test for all of this. I have a testbed system in my garage which I could set up to literally do all of this in a loop, meaning automate the entire above process and just let it go, writing stderr from time to a file (which wouldn't skew the results at all). Let me know what #1 and #2 above, re: "the workloads", should be and I'll be happy to set it up. -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Thu Dec 15 21:48:03 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 189551065673; Thu, 15 Dec 2011 21:48:03 +0000 (UTC) (envelope-from kob6558@gmail.com) Received: from mail-ww0-f50.google.com (mail-ww0-f50.google.com [74.125.82.50]) by mx1.freebsd.org (Postfix) with ESMTP id 6763B8FC22; Thu, 15 Dec 2011 21:48:02 +0000 (UTC) Received: by wgbdr11 with SMTP id dr11so4721837wgb.31 for ; Thu, 15 Dec 2011 13:48:01 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=01rUC02AA1IBImtEMcYSDqr1FhgQzKU+JGgR5l659IE=; b=mPbuaR7qYL9qQqflmhEG/FOaQEfmuj02b98bHd+SanqMl7dERFG5KaTYVMQkAfsKKC e9OvIZ9LOWmPEN83dZkwSRZvOCAyuriuV1wOtiGP0CSMe4UoPSY9hhbEcSBUuUaCQu5O 0RbaaZ6XLpaZFEyiHTZGLh6JB77EHRvg/zljI= MIME-Version: 1.0 Received: by 10.180.95.136 with SMTP id dk8mr3940463wib.11.1323984306922; Thu, 15 Dec 2011 13:25:06 -0800 (PST) Received: by 10.223.158.129 with HTTP; Thu, 15 Dec 2011 13:25:06 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EE9C79B.7080607@phoronix.com> <4EE9F546.6060503@freebsd.org> <4EEA3556.7030105@zedat.fu-berlin.de> Date: Thu, 15 Dec 2011 13:25:06 -0800 Message-ID: From: Kevin Oberman To: Chris Rees Content-Type: text/plain; charset=ISO-8859-1 X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Michael Larabel , FreeBSD Stable Mailing List , Current FreeBSD , Daniel Kalchev , Michael Ross , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 15 Dec 2011 21:48:03 -0000 On Thu, Dec 15, 2011 at 10:46 AM, Chris Rees wrote: > On 15 December 2011 17:58, O. Hartmann wrote: >> Since ZFS in Linux can only be achieved via FUSE (ad far as I know), it >> is legitimate to compare ZFS and ext4. It would be much more competetive >> to compare Linux BTRFS and FreeBSD ZFS. >> > > > Er... does ext4 guarantee data integrity? > > You're not comparing like with like; please do some research on the > point of ZFS before asserting that they're fair comparisons. > > A fair(er) comparison could be ext4 with UFS+soft-updates. Wouldn't UFS+SUJ be the closest atch? -- R. Kevin Oberman, Network Engineer E-mail: kob6558@gmail.com From owner-freebsd-performance@FreeBSD.ORG Fri Dec 16 10:54:29 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C4474106564A; Fri, 16 Dec 2011 10:54:29 +0000 (UTC) (envelope-from dnebdal@gmail.com) Received: from mail-iy0-f182.google.com (mail-iy0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 7A37A8FC12; Fri, 16 Dec 2011 10:54:29 +0000 (UTC) Received: by iadj38 with SMTP id j38so68691iad.13 for ; Fri, 16 Dec 2011 02:54:29 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=1u0F4g9CC7lFBI3qpLktZSXpm+PHNOHRsPym8ToIw+Y=; b=UhZujmfmHS8bB/tnv+8mJix1OwDzCq3yZn7NNgoe0Od+bmLfHHTEm0FKhI13+tt2s3 UE597qNb7lLMGinYFElLqJQrCvewJtLSAh2Cz3WG6+92FmhqY3sXVO66YDDUjaQyyIgL PLNc6T42yXIk4W2qRrt5PYwy9HsAbE4vk4rnw= MIME-Version: 1.0 Received: by 10.50.12.161 with SMTP id z1mr7622571igb.85.1324031450026; Fri, 16 Dec 2011 02:30:50 -0800 (PST) Received: by 10.231.211.78 with HTTP; Fri, 16 Dec 2011 02:30:49 -0800 (PST) In-Reply-To: <4EEA5F5C.8080503@sentex.net> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213230441.GB42285@stack.nl> <4ee7e2d3.0a3c640a.4617.4a33SMTPIN_ADDED@mx.google.com> <4EE8D607.1000504@sentex.net> <4EEA227E.7080704@sentex.net> <4EEA25BB.7040706@sentex.net> <4EEA5F5C.8080503@sentex.net> Date: Fri, 16 Dec 2011 11:30:49 +0100 Message-ID: From: Daniel Nebdal To: Mike Tancsa Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: freebsd-performance@freebsd.org, Current FreeBSD Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Dec 2011 10:54:29 -0000 On Thu, Dec 15, 2011 at 9:58 PM, Mike Tancsa wrote: > On 12/15/2011 11:56 AM, Attilio Rao wrote: >> So, as very first thing, can you try the following: >> - Same codebase, etc. etc. >> - Make the test 4 times, discard the first and ministat for the other 3 >> - Reboot >> - Change the steal_thresh value >> - Make the test 4 times, discard the first and ministat for the other 3 >> >> Then report discarded values and the ministated one and we will have >> more informations I guess >> (also, I don't think devfs contention should play a role here, thus >> nevermind about it for now). > > > Results and data at > > http://www.tancsa.com/ule-bsd.html > > =A0 =A0 =A0 =A0---Mike > I took the liberty of re-plotting this as one boxplot per test-type, in the hope of getting a better overview. R script included. Beware the y-ranges. (To re-plot with a specific y range, add e.g. "ylim=3Dc(0,35)" to the boxplot() calls.) http://nebdal.net/sched/plot.html --=20 Daniel Nebdal Dep. of genetics, Oslo University Hospital From owner-freebsd-performance@FreeBSD.ORG Fri Dec 16 13:08:04 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4E0BD1065670 for ; Fri, 16 Dec 2011 13:08:04 +0000 (UTC) (envelope-from se@freebsd.org) Received: from nm25.bullet.mail.sp2.yahoo.com (nm25.bullet.mail.sp2.yahoo.com [98.139.91.95]) by mx1.freebsd.org (Postfix) with SMTP id 238088FC17 for ; Fri, 16 Dec 2011 13:08:03 +0000 (UTC) Received: from [98.139.91.65] by nm25.bullet.mail.sp2.yahoo.com with NNFMP; 16 Dec 2011 13:08:03 -0000 Received: from [208.71.42.194] by tm5.bullet.mail.sp2.yahoo.com with NNFMP; 16 Dec 2011 13:08:03 -0000 Received: from [127.0.0.1] by smtp205.mail.gq1.yahoo.com with NNFMP; 16 Dec 2011 13:08:03 -0000 X-Yahoo-Newman-Id: 652125.75823.bm@smtp205.mail.gq1.yahoo.com X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: Cu40vcsVM1kJrvHsrx71G96hiB690PcmeMkTDiHI9oBRkqt YWQJaFGRuJPY_TmwKWgyr7BGneCUFJfTRWT5iARHmc7ipc3nV8AdrgUR6vMF 0_kZwnzdRuhsmVfiVpdbXwhjVTNtG1RIFXPfs.cKU1t.gSbYV_9iwkz9pIWd IyvnUhhhOzaeIR1NSHXaPLRHZlM56AkBCfixeJsZQv0ftPmgFdUCitG1dzob x0n836_d7U3mCZQCH9oqFmwwjVIXbvJZ11uzhOZMo2poGINkNcjXRSSDZ6WZ KzltOPyargb9EWBqH9VhESRphb4ZVOV209e2NI1lY9x1tYLt2J3XeXz0dofn hgdaFsTQGBIFmyQFIOexA2.4FSL8wzJ7pRguDO1USB0ub2c9r8Dn_oceFLya KKlwUheSvUcU2 X-Yahoo-SMTP: iDf2N9.swBDAhYEh7VHfpgq0lnq. Received: from [192.168.119.20] (se@81.173.157.6 with plain) by smtp205.mail.gq1.yahoo.com with SMTP; 16 Dec 2011 05:08:03 -0800 PST Message-ID: <4EEB42B1.1000506@freebsd.org> Date: Fri, 16 Dec 2011 14:08:01 +0100 From: Stefan Esser User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: "O. Hartmann" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EEAE8DF.40303@rewt.org.uk> <4EEAEDE1.50604@zedat.fu-berlin.de> In-Reply-To: <4EEAEDE1.50604@zedat.fu-berlin.de> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Joe Holden , FreeBSD Stable Mailing List , Current FreeBSD , Arnaud Lacombe , freebsd-performance@freebsd.org, Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Dec 2011 13:08:04 -0000 Am 16.12.2011 08:06, schrieb O. Hartmann: > For the underlying OS, as far as I know, the compiler hasn't as much > impact as on userland software since autovectorization and other neat > things are not used during system build. > > From my experience using gcc 4.2 or 4.4/4.5 does not have an impact > beyond 3% when SSE isn't explicetly enforced. Well, but the compute intensive tests showed performance variance of a few percents only, IIRC. The big differences were in the parts that heavily depend on file system and buffer cache concepts (i.e. the low limit on dirty buffers in FreeBSD, which is very beneficial in real world situations; do you remember the first few releases of SunOS-4, which heavily suffered in interactive performance due to a naive unified buffer cache VM system that did not limit the amount of dirty buffers? It caused interactive shells to be swapped out within seconds on systems with background jobs writing to disk). > More interesting is the performance gain due to the architecture. I > think it would be very easy for M. Larabel to repeat this benchmark with > a "bleeding edge" Ubuntu or Suse as well. And since FreeBSD 9.0 can be > compiled with CLANG, it should be possible to compare both also with > "bleeding edge" compilers, say FreeBSD 9/CLANG, Ubuntu 12/gcc 4.6.2. Clang may be considered "bleeding edge", but in quite a different way than gcc-4.6.2. While the latter can look back on 2 decades of development, clang is still in a state where feature completeness (and bug-to-bug compatibility with GCC ;-) is much more important than performance. there is much promise of powerful optimizations becoming available in clang once it is mature, but just now expect GCC 4.6.2 to deliver 5% to 10% higher performance than clang. But as stated before: To exclude compiler dependencies just run the Linux binaries on FreeBSD. There is slight emulation overhead and Glibc is not particularly optimized for FreeBSD, but this will still provide more useful results. And the tests should be selected to represent reasonable real-world scenarios. Server programs tested on otherwise idle systems and running for just a few seconds (not reaching equilibrium during the majority of the test period) are not representative at all (again: if your goal is to compare server performance). Regards, STefan From owner-freebsd-performance@FreeBSD.ORG Fri Dec 16 17:16:41 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 161701065675; Fri, 16 Dec 2011 17:16:41 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id D7B278FC1D; Fri, 16 Dec 2011 17:16:40 +0000 (UTC) Received: from mobile-166-205-138-224.mycingular.net ([166.205.138.224] helo=www.palm.com) by phx1.phoronix.com with esmtpa (Exim 4.69) (envelope-from ) id 1RbbOg-0006dP-AI; Fri, 16 Dec 2011 11:16:39 -0600 Date: Fri, 16 Dec 2011 09:16:36 -0800 From: To: "Adrian Chadd" , "Stefan Esser" In-Reply-To: X-Mailer: Palm webOS X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Message-Id: <20111216171641.161701065675@hub.freebsd.org> X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Joe Holden , FreeBSD Stable Mailing List , Michael Larabel , Current FreeBSD , Arnaud Lacombe , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 16 Dec 2011 17:16:41 -0000 Thanks. My request for the person documenting the tunings also runs = the benchmark to ensure expected behaviour. The installation, execut= ion and comparison against the benchmarks in the article is fairly simple.<= br> Note that some tuning may not be relevant or recommended (ie: some o= f the fs benchmarks are sensitive to barriers and other synchronous operati= ons). I'd recommend bowing out of a benchmark with a 'we're going to = be slower since the default configuration is this way for the following rea= son' if this is the case. Thanks 'someone'. Matthew Dec 16, 2011 8:46 AM,= Adrian Chadd wrote: Can someone please write up a nice, concise blog post somewhere=0D= outlining all of this?=0D =0D Extra bonus points if it's a blog t= hat is picked up by=0D blogs.freebsdish.org and/or some of the other BSD= sites.=0D =0D Guys/girls/fuzzy things - this is 2011; people look at= shiny blog=0D sites with graphs rather than mailing lists. Sorry, we lo= st that=0D battle. :)=0D =0D =0D =0D Adrian=0D __________= _____________________________________=0D freebsd-performance@freebsd.org= mailing list=0D http://lists.freebsd.org/mailman/listinfo/freebsd-perfo= rmance=0D To unsubscribe, send any mail to "freebsd-performance-unsubscr= ibe@freebsd.org"=0D From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 10:24:01 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: by hub.freebsd.org (Postfix, from userid 1233) id 389D41065670; Sun, 18 Dec 2011 10:24:01 +0000 (UTC) Date: Sun, 18 Dec 2011 10:24:01 +0000 From: Alexander Best To: Andrey Chernov , Ian Smith , Bruce Cran , Ivan Klymenko , Doug Barton , "O. Hartmann" , Current FreeBSD , freebsd-stable@FreeBSD.ORG, freebsd-performance@FreeBSD.ORG Message-ID: <20111218102401.GA42627@freebsd.org> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20111218075241.GA45367@vniz.net> X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 10:24:01 -0000 On Sun Dec 18 11, Andrey Chernov wrote: > On Sun, Dec 18, 2011 at 05:51:47PM +1100, Ian Smith wrote: > > On Sun, 18 Dec 2011 02:37:52 +0000, Bruce Cran wrote: > > > On 13/12/2011 09:00, Andrey Chernov wrote: > > > > I observe ULE interactivity slowness even on single core machine (Pentium > > > > 4) in very visible places, like 'ps ax' output stucks in the middle by ~1 > > > > second. When I switch back to SHED_4BSD, all slowness is gone. > > > > > > I'm also seeing problems with ULE on a dual-socket quad-core Xeon machine > > > with 16 logical CPUs. If I run "tar xf somefile.tar" and "make -j16 > > > buildworld" then logging into another console can take several seconds. > > > Sometimes even the "Password:" prompt can take a couple of seconds to appear > > > after typing my username. > > > > I'd resigned myself to expecting this sort of behaviour as 'normal' on > > my single core 1133MHz PIII-M. As a reproducable data point, running > > 'dd if=/dev/random of=/dev/null' in one konsole, specifically to heat > > the CPU while testing my manual fan control script, hogs it up pretty > > much while regularly running the script below in another konsole to > > check values - which often gets stuck half way, occasionally pausing > > _twice_ before finishing. Switching back to the first konsole (on > > another desktop) to kill the dd can also take a couple/few seconds. > > This issue not about slow machine under load, because the same > slow machine under exact the same load, but with SCHED_4BSD is very fast > to response interactively. > > I think we should not misinterpret interactivity with speed. I see no big > speed (i.e. compilation time) differences, switching schedulers, but see > big _interactivity_ difference. ULE in general tends to underestimate > interactive processes in favour of background ones. It perhaps helps to > compilation, but looks like slowpoke OS from the interactive user > experience. +1 i've also experienced issues with ULE and performed several tests to compare it to the historical 4BSD scheduler. the difference between the two does *not* seem to be speed (at least not a huge difference), but interactivity. one of the tests i performed was the following ttyv0: untar a *huge* (+10G) archive ttyv1: after ~ 30 seconds of untaring do 'ls -la $direcory', where directory contains a lot of files. i used "direcory = /var/db/portsnap", because that directory contains 23117 files on my machine. measuring 'ls -la $direcory' via time(1) revealed that SCHED_ULE takes > 15 seconds, whereas SCHED_4BSD only takes ~ 3-5 seconds. i think the issue is io. io operations usually get a high priority, because statistics have shown that - unlike computational tasks - io intensive tasks only run for a small fraction of time and then exit: read data -> change data -> writeback data. so SCHED_ULE might take these statistics too literaly and gives tasks like bsdtar(1) (in my case) too many ressources, so other tasks which require io are struggling to get some ressources assigned to them (ls(1) in my case). of course SCHED_4BSD isn't perfect, too. try using it and run the stress2 testsuite. your whole system will grind to a halt. mouse input drops below 1 HZ. even after killing all the stress2 tests, it will take a few minutes after the system becomes snappy again. cheers. alex > > -- > http://ache.vniz.net/ From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 10:26:00 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: by hub.freebsd.org (Postfix, from userid 1233) id B25331065679; Sun, 18 Dec 2011 10:26:00 +0000 (UTC) Date: Sun, 18 Dec 2011 10:26:00 +0000 From: Alexander Best To: Andrey Chernov , Ian Smith , Bruce Cran , Ivan Klymenko , Doug Barton , "O. Hartmann" , Current FreeBSD , freebsd-stable@FreeBSD.ORG, freebsd-performance@FreeBSD.ORG Message-ID: <20111218102600.GA44118@freebsd.org> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20111218102401.GA42627@freebsd.org> X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 10:26:00 -0000 On Sun Dec 18 11, Alexander Best wrote: > On Sun Dec 18 11, Andrey Chernov wrote: > > On Sun, Dec 18, 2011 at 05:51:47PM +1100, Ian Smith wrote: > > > On Sun, 18 Dec 2011 02:37:52 +0000, Bruce Cran wrote: > > > > On 13/12/2011 09:00, Andrey Chernov wrote: > > > > > I observe ULE interactivity slowness even on single core machine (Pentium > > > > > 4) in very visible places, like 'ps ax' output stucks in the middle by ~1 > > > > > second. When I switch back to SHED_4BSD, all slowness is gone. > > > > > > > > I'm also seeing problems with ULE on a dual-socket quad-core Xeon machine > > > > with 16 logical CPUs. If I run "tar xf somefile.tar" and "make -j16 > > > > buildworld" then logging into another console can take several seconds. > > > > Sometimes even the "Password:" prompt can take a couple of seconds to appear > > > > after typing my username. > > > > > > I'd resigned myself to expecting this sort of behaviour as 'normal' on > > > my single core 1133MHz PIII-M. As a reproducable data point, running > > > 'dd if=/dev/random of=/dev/null' in one konsole, specifically to heat > > > the CPU while testing my manual fan control script, hogs it up pretty > > > much while regularly running the script below in another konsole to > > > check values - which often gets stuck half way, occasionally pausing > > > _twice_ before finishing. Switching back to the first konsole (on > > > another desktop) to kill the dd can also take a couple/few seconds. > > > > This issue not about slow machine under load, because the same > > slow machine under exact the same load, but with SCHED_4BSD is very fast > > to response interactively. > > > > I think we should not misinterpret interactivity with speed. I see no big > > speed (i.e. compilation time) differences, switching schedulers, but see > > big _interactivity_ difference. ULE in general tends to underestimate > > interactive processes in favour of background ones. It perhaps helps to > > compilation, but looks like slowpoke OS from the interactive user > > experience. > > +1 > > i've also experienced issues with ULE and performed several tests to compare > it to the historical 4BSD scheduler. the difference between the two does *not* > seem to be speed (at least not a huge difference), but interactivity. > > one of the tests i performed was the following > > ttyv0: untar a *huge* (+10G) archive > ttyv1: after ~ 30 seconds of untaring do 'ls -la $direcory', where directory > contains a lot of files. i used "direcory = /var/db/portsnap", because s/portsnap/portsnap\/files/ > that directory contains 23117 files on my machine. > > measuring 'ls -la $direcory' via time(1) revealed that SCHED_ULE takes > 15 > seconds, whereas SCHED_4BSD only takes ~ 3-5 seconds. i think the issue is io. > io operations usually get a high priority, because statistics have shown that > - unlike computational tasks - io intensive tasks only run for a small fraction > of time and then exit: read data -> change data -> writeback data. > > so SCHED_ULE might take these statistics too literaly and gives tasks like > bsdtar(1) (in my case) too many ressources, so other tasks which require io are > struggling to get some ressources assigned to them (ls(1) in my case). > > of course SCHED_4BSD isn't perfect, too. try using it and run the stress2 > testsuite. your whole system will grind to a halt. mouse input drops below > 1 HZ. even after killing all the stress2 tests, it will take a few minutes > after the system becomes snappy again. > > cheers. > alex > > > > > -- > > http://ache.vniz.net/ From owner-freebsd-performance@FreeBSD.ORG Sun Dec 18 10:34:41 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 652C6106564A; Sun, 18 Dec 2011 10:34:41 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 9BEF08FC13; Sun, 18 Dec 2011 10:34:40 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so5897013vcb.13 for ; Sun, 18 Dec 2011 02:34:39 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=s6kIoTrilkDgvCqa7CBeAusmCWmQmTPCl4RVMTG7W7o=; b=odf2/KQtLGeZG11305gEP1KiG7+ubW+oPsc0+7Eh8JLQguv73H4Ua8edlUNJ1tn3Ls hdqo8DlYC7pwZkaRQP3wBMZf+fswsbnnmZ0+DEwryKtpV3YdRC0aQLf6dR9SSXKf4uFk cVdOKApp/s6YE6A3yN8lV+o80IFCotsTmKyKA= MIME-Version: 1.0 Received: by 10.220.151.204 with SMTP id d12mr7411703vcw.40.1324204479840; Sun, 18 Dec 2011 02:34:39 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.26.50 with HTTP; Sun, 18 Dec 2011 02:34:39 -0800 (PST) In-Reply-To: <20111218102600.GA44118@freebsd.org> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost.> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> Date: Sun, 18 Dec 2011 02:34:39 -0800 X-Google-Sender-Auth: uHpK_GNrw2hgPHGTKxPMp-CpkzM Message-ID: From: Adrian Chadd To: Alexander Best Content-Type: text/plain; charset=ISO-8859-1 X-Mailman-Approved-At: Sun, 18 Dec 2011 22:30:34 +0000 Cc: Bruce Cran , Ivan Klymenko , Doug Barton , Andrey Chernov , Ian Smith , "O. Hartmann" , Current FreeBSD , freebsd-stable@freebsd.org, freebsd-performance@freebsd.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 18 Dec 2011 10:34:41 -0000 The trouble is that there's lots of anecdotal evidence, but noone's really gone digging deep into _their_ example of why it's broken. The developers who know this stuff don't see anything wrong. That hints to me it may be something a little more creepy - as an example, the interplay between netisr/swi/taskqueue/callbacks and such. It may be that something is being starved that isn't obviously obvious. It's just a stab in the dark, but it sounds somewhat plausible based on what I've seen ULE do in my network throughput hacking. I applaud reppie for trying to make it as easy as possible for people to use KTR to provide scheduler traces for him to go digging with, so please, if you have these issues and you can absolutely reproduce them, please follow his instructions and work with him to get him what he needs. Adrian (wow, lots of personal pronouns packed into one sentence. It must be sleep time.) From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 08:27:25 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 91256106566C; Mon, 19 Dec 2011 08:27:25 +0000 (UTC) (envelope-from lev@FreeBSD.org) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id 251198FC13; Mon, 19 Dec 2011 08:27:25 +0000 (UTC) Received: from lion.home.serebryakov.spb.ru (unknown [IPv6:2001:470:923f:1:2831:a229:70d2:ba0b]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPA id 099D14AC1C; Mon, 19 Dec 2011 12:27:22 +0400 (MSK) Date: Mon, 19 Dec 2011 12:27:21 +0400 From: Lev Serebryakov Organization: FreeBSD X-Priority: 3 (Normal) Message-ID: <6140271.20111219122721@serebryakov.spb.ru> To: "Samuel J. Greear" In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=windows-1251 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Mon, 19 Dec 2011 11:07:51 +0000 Cc: Adrian Chadd , FreeBSD Stable Mailing List , Current FreeBSD , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: lev@FreeBSD.org List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 08:27:25 -0000 Hello, Samuel. You wrote 15 =E4=E5=EA=E0=E1=F0=FF 2011 =E3., 16:32:47: > Other benchmarks in the Phoronix suite and their representations are > similarly flawed, _ALL_ of these results should be ignored and no time > should be wasted by any FreeBSD committer further evaluating this > garbage. (Yes, I have been down this rabbit hole). Here is one problem: we have choice from three items: (1) Make FreeBSD looks good on benchmarks by "fixing" FreeBSD (2) Make FreeBSD looks good on benchmarks by "fixing" Phoronix (communication with them, convincing, that they benchamrks are unfare / meaningless, ets) (3) Lose [potential] userbase. You know, that these benchmarks are bad. I know. But potential (and even some current!) user doesn't. And it seems, that these benchmarks become popular over Internet. --=20 // Black Lion AKA Lev Serebryakov From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 09:44:13 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 904F0106566B; Mon, 19 Dec 2011 09:44:13 +0000 (UTC) (envelope-from lev@FreeBSD.org) Received: from onlyone.friendlyhosting.spb.ru (onlyone.friendlyhosting.spb.ru [IPv6:2a01:4f8:131:60a2::2]) by mx1.freebsd.org (Postfix) with ESMTP id 2191A8FC16; Mon, 19 Dec 2011 09:44:13 +0000 (UTC) Received: from lion.home.serebryakov.spb.ru (unknown [IPv6:2001:470:923f:1:2831:a229:70d2:ba0b]) (Authenticated sender: lev@serebryakov.spb.ru) by onlyone.friendlyhosting.spb.ru (Postfix) with ESMTPA id 0E0B94AC1C; Mon, 19 Dec 2011 13:44:10 +0400 (MSK) Date: Mon, 19 Dec 2011 13:44:09 +0400 From: Lev Serebryakov Organization: FreeBSD X-Priority: 3 (Normal) Message-ID: <1902268932.20111219134409@serebryakov.spb.ru> To: Adrian Chadd In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EEAE8DF.40303@rewt.org.uk> <4EEAEDE1.50604@zedat.fu-berlin.de> <4EEB42B1.1000506@freebsd.org> MIME-Version: 1.0 Content-Type: text/plain; charset=windows-1251 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Mon, 19 Dec 2011 11:53:28 +0000 Cc: Joe Holden , FreeBSD Stable Mailing List , Current FreeBSD , Stefan Esser , Arnaud Lacombe , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: lev@FreeBSD.org List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 09:44:13 -0000 Hello, Adrian. You wrote 16 =E4=E5=EA=E0=E1=F0=FF 2011 =E3., 20:43:27: > Guys/girls/fuzzy things - this is 2011; people look at shiny blog > sites with graphs rather than mailing lists. Sorry, we lost that > battle. :) My thoughts exactly. --=20 // Black Lion AKA Lev Serebryakov From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 10:43:21 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 143A1106564A; Mon, 19 Dec 2011 10:43:21 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id B2A8A8FC14; Mon, 19 Dec 2011 10:43:20 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Rcagh-0006Da-77>; Mon, 19 Dec 2011 11:43:19 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Rcagh-0005tu-3r>; Mon, 19 Dec 2011 11:43:19 +0100 Message-ID: <4EEF1541.3020009@mail.zedat.fu-berlin.de> Date: Mon, 19 Dec 2011 11:43:13 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: lev@FreeBSD.org References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> In-Reply-To: <6140271.20111219122721@serebryakov.spb.ru> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="------------enig42E820DE89A492B418570B73" X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Mon, 19 Dec 2011 11:53:40 +0000 Cc: Adrian Chadd , FreeBSD Stable Mailing List , Current FreeBSD , "Samuel J. Greear" , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 10:43:21 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig42E820DE89A492B418570B73 Content-Type: text/plain; charset=windows-1251 Content-Transfer-Encoding: quoted-printable On 12/19/11 09:27, Lev Serebryakov wrote: > Hello, Samuel. > You wrote 15 =E4=E5=EA=E0=E1=F0=FF 2011 =E3., 16:32:47: >=20 >> Other benchmarks in the Phoronix suite and their representations are >> similarly flawed, _ALL_ of these results should be ignored and no time= >> should be wasted by any FreeBSD committer further evaluating this >> garbage. (Yes, I have been down this rabbit hole). > Here is one problem: we have choice from three items: >=20 > (1) Make FreeBSD looks good on benchmarks by "fixing" FreeBSD >=20 > (2) Make FreeBSD looks good on benchmarks by "fixing" Phoronix > (communication with them, convincing, that they benchamrks are unfare > / meaningless, ets) >=20 > (3) Lose [potential] userbase. >=20 > You know, that these benchmarks are bad. I know. But potential (and > even some current!) user doesn't. And it seems, that these benchmarks > become popular over Internet. >=20 +1 It is not about a faky way to let a specific OS look good by any means. I'M afraid of (3), which also implies pushing more towards beeing meaningless and not anymore a alternative with a unique, remarkable criteria to be choosen as __the__ operating system of the first choice for several purposes. By the way, how such a development could look alaike is very clear when it comes to GPGPU/HPC, highly related to the availability of proper graphics card drivers, X11 development and the necessary libraries, APIs and even compilers. None of those "professionals" out here, none of those pushing the eyewhitness of bad performance into very deep-insight-talks about what could cause the problem has obviously ever negotiated with people of the "upper floor" when it comes to the choice of the OS. Within my department, the *BSD aren't even considered an option, even if they would perform best for the specified purpose (which, I regeret, is a shrinking basis now since also Linux will have ZFS). Sometimes I feel like Don Quixote, fighting against windmills. Sorry having brought up this thread and I beg for pardon for putting another scrtach into the autoerotic world of the "core". --------------enig42E820DE89A492B418570B73 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iF4EAREIAAYFAk7vFUcACgkQU6Ni+wtCKv9T5QD/SOTCNVyyf6NlJowS3L0ui56j xOjYEv9qTcg9rDKxwZYA/1i6XhGlfyysh26mCTKtLsRPIA/qoBmszBE6DHj2BVnm =kznr -----END PGP SIGNATURE----- --------------enig42E820DE89A492B418570B73-- From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 11:49:19 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5A55B1065675; Mon, 19 Dec 2011 11:49:19 +0000 (UTC) (envelope-from sjg@evilcode.net) Received: from mail-qy0-f182.google.com (mail-qy0-f182.google.com [209.85.216.182]) by mx1.freebsd.org (Postfix) with ESMTP id B249D8FC08; Mon, 19 Dec 2011 11:49:18 +0000 (UTC) Received: by qcse13 with SMTP id e13so4457735qcs.13 for ; Mon, 19 Dec 2011 03:49:18 -0800 (PST) MIME-Version: 1.0 Received: by 10.229.106.230 with SMTP id y38mr5306405qco.83.1324295357936; Mon, 19 Dec 2011 03:49:17 -0800 (PST) Received: by 10.229.6.142 with HTTP; Mon, 19 Dec 2011 03:49:17 -0800 (PST) In-Reply-To: <6140271.20111219122721@serebryakov.spb.ru> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> Date: Mon, 19 Dec 2011 04:49:17 -0700 Message-ID: From: "Samuel J. Greear" To: lev@freebsd.org Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Mon, 19 Dec 2011 12:09:41 +0000 Cc: Adrian Chadd , FreeBSD Stable Mailing List , Current FreeBSD , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 11:49:19 -0000 2011/12/19 Lev Serebryakov : > Hello, Samuel. > You wrote 15 =D0=B4=D0=B5=D0=BA=D0=B0=D0=B1=D1=80=D1=8F 2011 =D0=B3., 16:= 32:47: > >> Other benchmarks in the Phoronix suite and their representations are >> similarly flawed, _ALL_ of these results should be ignored and no time >> should be wasted by any FreeBSD committer further evaluating this >> garbage. (Yes, I have been down this rabbit hole). > =C2=A0Here is one problem: we have choice from three items: > > (1) Make FreeBSD looks good on benchmarks by "fixing" FreeBSD > > (2) Make FreeBSD looks good on benchmarks by "fixing" Phoronix > (communication with them, convincing, that they benchamrks are unfare > / meaningless, ets) > > (3) Lose [potential] userbase. > > =C2=A0You know, that these benchmarks are bad. I know. But potential (and > =C2=A0even some current!) user doesn't. And it seems, that these benchmar= ks > =C2=A0become popular over Internet. > > -- > // Black Lion AKA Lev Serebryakov > Here is where you completely derail the train, let me paste again what I said before. ... Take the first test as an example, Blogbench read. This doesn't raise any red flags, right? At least not until you realize that Blogbench isn't a read test, it's a read/write test. So what they have done here is run a read/write test and then thrown away the write results for both platforms and reported only the read results. If you dig down into the actual results, http://openbenchmarking.org/result/1112113-AR-ORACLELIN37 -- you will see two Blogbench numbers, one for read and another for write. These were both taken from the same Blogbench run, so FreeBSD optimizes writes over reads, that's probably a good thing for your data but a bad thing when someone totally misrepresents benchmark results. ... FreeBSD actually does _BETTER_ (subjectively) in this test than the Linux system when you look at what is really going on. FreeBSD is favoring writes, which is _GOOD_. FreeBSD does not need to be fixed, the benchmarks need to be fixed to represent reality rather than throwing half of the results in the trash. To be quite frank, "fixing" FreeBSD to look good on this benchmark will make it a worse real-world OS. But you guys go ahead and foot-shoot over these ridiculous benchmarks all you want. Sam From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 13:19:13 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 119E1106564A; Mon, 19 Dec 2011 13:19:13 +0000 (UTC) (envelope-from sergey.dyatko@gmail.com) Received: from mail-we0-f182.google.com (mail-we0-f182.google.com [74.125.82.182]) by mx1.freebsd.org (Postfix) with ESMTP id 38F658FC18; Mon, 19 Dec 2011 13:19:11 +0000 (UTC) Received: by werb13 with SMTP id b13so2325770wer.13 for ; Mon, 19 Dec 2011 05:19:11 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=date:from:to:cc:subject:message-id:in-reply-to:references:x-mailer :mime-version:content-type:content-transfer-encoding; bh=lls6y80Nd/RuyUl6N7wAstGd8BdDDfkZAUHkGUZDaiM=; b=rfn+yCIoiZBb40tS4uP2KC09leFO1/FHWdYd5FyXthtdJDUJ7CBLYkf4GfUkNFhMuR odqOPlbX4Hcuaa0oci9BqN8BG64nCRdi5L3UOd+r31wwq+DcgMDQYDO54b2CbWEHb9RE WNE7qrKPfv+/5x0dNcBEYvrMCSX5O7rnPH2eE= Received: by 10.216.137.28 with SMTP id x28mr6959899wei.0.1324299054008; Mon, 19 Dec 2011 04:50:54 -0800 (PST) Received: from laptop (m-s.agava.net. [195.222.84.203]) by mx.google.com with ESMTPS id 28sm25596278wby.3.2011.12.19.04.50.51 (version=SSLv3 cipher=OTHER); Mon, 19 Dec 2011 04:50:52 -0800 (PST) Date: Mon, 19 Dec 2011 15:51:05 +0300 From: "Sergey V. Dyatko" To: Andreas Nilsson Message-ID: <20111219155105.5209cc2a@laptop> In-Reply-To: <-4802855903238902044@unknownmsgid> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> <-4802855903238902044@unknownmsgid> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: Adrian Chadd , "lev@freebsd.org" , "Samuel J. Greear" , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 13:19:13 -0000 On Mon, 19 Dec 2011 13:21:35 +0100 Andreas Nilsson wrote: [skipped] guys, sorry, but... can you choose just _one_ ML and spam it ? performance@, for example. p.s. does anyone trust results from Phoronix, except completely idiots? -- wbr, tiger From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 12:43:35 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 90F9C1065670; Mon, 19 Dec 2011 12:43:35 +0000 (UTC) (envelope-from andrnils@gmail.com) Received: from mail-ey0-f182.google.com (mail-ey0-f182.google.com [209.85.215.182]) by mx1.freebsd.org (Postfix) with ESMTP id 76E908FC12; Mon, 19 Dec 2011 12:43:34 +0000 (UTC) Received: by eaaf13 with SMTP id f13so6629679eaa.13 for ; Mon, 19 Dec 2011 04:43:33 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=references:in-reply-to:mime-version:from:date:message-id:subject:to :cc:content-type:content-transfer-encoding; bh=FQVOCcpkzlD7NzWddQVT3iYX1aJO/J5QVY5rRxYEaxY=; b=evT7zSp1kNTjCvTgiS9RujfehmeSMY2HcIifI0CFV8kxtBgRQVm8bcF3UQl1HhxwSU XCsVRud5+KaswrU6a2wIXHdkChfYxGEOPv36te5Bh/vA9oskmN3gtZaE7tArQYKN5W4g 2JyM6W8oJBwr9qPcHuutAiNmX3tXu7OalIFXU= Received: by 10.204.145.86 with SMTP id c22mr1307688bkv.61.1324297303797; Mon, 19 Dec 2011 04:21:43 -0800 (PST) References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> In-Reply-To: Mime-Version: 1.0 (1.0) From: Andreas Nilsson Date: Mon, 19 Dec 2011 13:21:35 +0100 Message-ID: <-4802855903238902044@unknownmsgid> To: "Samuel J. Greear" Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Mon, 19 Dec 2011 13:41:44 +0000 Cc: Adrian Chadd , "lev@freebsd.org" , FreeBSD Stable Mailing List , Current FreeBSD , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 12:43:35 -0000 On 19 dec 2011, at 12:50, "Samuel J. Greear" wrote: > 2011/12/19 Lev Serebryakov : >> Hello, Samuel. >> You wrote 15 =D0=B4=D0=B5=D0=BA=D0=B0=D0=B1=D1=80=D1=8F 2011 =D0=B3., 16= :32:47: >> >>> Other benchmarks in the Phoronix suite and their representations are >>> similarly flawed, _ALL_ of these results should be ignored and no time >>> should be wasted by any FreeBSD committer further evaluating this >>> garbage. (Yes, I have been down this rabbit hole). >> Here is one problem: we have choice from three items: >> >> (1) Make FreeBSD looks good on benchmarks by "fixing" FreeBSD >> >> (2) Make FreeBSD looks good on benchmarks by "fixing" Phoronix >> (communication with them, convincing, that they benchamrks are unfare >> / meaningless, ets) >> >> (3) Lose [potential] userbase. >> >> You know, that these benchmarks are bad. I know. But potential (and >> even some current!) user doesn't. And it seems, that these benchmarks >> become popular over Internet. >> >> -- >> // Black Lion AKA Lev Serebryakov >> > > Here is where you completely derail the train, let me paste again what > I said before. > > ... > Take the first test as an example, Blogbench read. This doesn't raise > any red flags, right? At least not until you realize that Blogbench > isn't a read test, it's a read/write test. So what they have done here > is run a read/write test and then thrown away the write results for > both platforms and reported only the read results. If you dig down > into the actual results, > http://openbenchmarking.org/result/1112113-AR-ORACLELIN37 -- you will > see two Blogbench numbers, one for read and another for write. These > were both taken from the same Blogbench run, so FreeBSD optimizes > writes over reads, that's probably a good thing for your data but a > bad thing when someone totally misrepresents benchmark results. > ... > > FreeBSD actually does _BETTER_ (subjectively) in this test than the > Linux system when you look at what is really going on. FreeBSD is > favoring writes, which is _GOOD_. FreeBSD does not need to be fixed, > the benchmarks need to be fixed to represent reality rather than > throwing half of the results in the trash. To be quite frank, "fixing" > FreeBSD to look good on this benchmark will make it a worse real-world > OS. But you guys go ahead and foot-shoot over these ridiculous > benchmarks all you want. > > Sam > I seem to remember that before ULE people were fleeing to Linux as the os to run apache on since 4BSD didn't scale all too well. That may have changed over time though. However ULE could perhaps be made aware technologies like turbo-boost, ie with few threads higher performance might be gained by utilizing all virtual cores on a physical core before spreading tasks to too different cores. Just my speculations though :) Regards Andreas Nilsson From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 13:40:21 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 10E271065783; Mon, 19 Dec 2011 13:40:21 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id A510F8FC13; Mon, 19 Dec 2011 13:40:20 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RcdRy-0005wV-Vs>; Mon, 19 Dec 2011 14:40:19 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RcdRy-00011A-Sa>; Mon, 19 Dec 2011 14:40:18 +0100 Message-ID: <4EEF3EBD.5070804@mail.zedat.fu-berlin.de> Date: Mon, 19 Dec 2011 14:40:13 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: Andreas Nilsson References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> <-4802855903238902044@unknownmsgid> In-Reply-To: <-4802855903238902044@unknownmsgid> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="------------enig29BC4489A3A49561FC71552C" X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Mon, 19 Dec 2011 13:42:16 +0000 Cc: Adrian Chadd , "lev@freebsd.org" , FreeBSD Stable Mailing List , Current FreeBSD , "Samuel J. Greear" , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 13:40:21 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig29BC4489A3A49561FC71552C Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 12/19/11 13:21, Andreas Nilsson wrote: > On 19 dec 2011, at 12:50, "Samuel J. Greear" wrote: >=20 >> 2011/12/19 Lev Serebryakov : >>> Hello, Samuel. >>> You wrote 15 =D0=B4=D0=B5=D0=BA=D0=B0=D0=B1=D1=80=D1=8F 2011 =D0=B3.,= 16:32:47: >>> >>>> Other benchmarks in the Phoronix suite and their representations are= >>>> similarly flawed, _ALL_ of these results should be ignored and no ti= me >>>> should be wasted by any FreeBSD committer further evaluating this >>>> garbage. (Yes, I have been down this rabbit hole). >>> Here is one problem: we have choice from three items: >>> >>> (1) Make FreeBSD looks good on benchmarks by "fixing" FreeBSD >>> >>> (2) Make FreeBSD looks good on benchmarks by "fixing" Phoronix >>> (communication with them, convincing, that they benchamrks are unfare= >>> / meaningless, ets) >>> >>> (3) Lose [potential] userbase. >>> >>> You know, that these benchmarks are bad. I know. But potential (and >>> even some current!) user doesn't. And it seems, that these benchmark= s >>> become popular over Internet. >>> >>> -- >>> // Black Lion AKA Lev Serebryakov >>> >> >> Here is where you completely derail the train, let me paste again what= >> I said before. >> >> ... >> Take the first test as an example, Blogbench read. This doesn't raise >> any red flags, right? At least not until you realize that Blogbench >> isn't a read test, it's a read/write test. So what they have done here= >> is run a read/write test and then thrown away the write results for >> both platforms and reported only the read results. If you dig down >> into the actual results, >> http://openbenchmarking.org/result/1112113-AR-ORACLELIN37 -- you will >> see two Blogbench numbers, one for read and another for write. These >> were both taken from the same Blogbench run, so FreeBSD optimizes >> writes over reads, that's probably a good thing for your data but a >> bad thing when someone totally misrepresents benchmark results. >> ... >> >> FreeBSD actually does _BETTER_ (subjectively) in this test than the >> Linux system when you look at what is really going on. FreeBSD is >> favoring writes, which is _GOOD_. FreeBSD does not need to be fixed, >> the benchmarks need to be fixed to represent reality rather than >> throwing half of the results in the trash. To be quite frank, "fixing"= >> FreeBSD to look good on this benchmark will make it a worse real-world= >> OS. But you guys go ahead and foot-shoot over these ridiculous >> benchmarks all you want. >> >> Sam >> >=20 > I seem to remember that before ULE people were fleeing to Linux as the > os to run apache on since 4BSD didn't scale all too well. That may > have changed over time though. >=20 > However ULE could perhaps be made aware technologies like turbo-boost, > ie with few threads higher performance might be gained by utilizing > all virtual cores on a physical core before spreading tasks to too > different cores. >=20 > Just my speculations though :) >=20 > Regards > Andreas Nilsson Such a scheduling stratey is definitely necessary on AMDs new "Bulldozer" architecture, which seems to be very pitty about threads locked on the same module. Microsoft just offered a patch for Windows 7 to implant such a "Bulldozer" awarenes but they withdraw the patch as invalid two days after the release. The seults seem to favour FPU performance over integer performance. As Samuel Greear wrote, FreeBSD looks not that bad in some of the benchmarks but there are obviosly issues, at least the fact that Phoronix/openbenchmark.org are the only sites offering benchmarks at all.= People outside the FreeBSD realm looking for opportunities, what do you think they will look first after? Phoronix/Openbenchmark.org made the first step and they seem to make FreeBSD look bad (in my opinion), whether righteous or not. Compared to several subjective impressions I have in our heterogeneous environment at the lab, Linux on the same hardware looks in several aspects much bett= er. Oliver --------------enig29BC4489A3A49561FC71552C Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iF4EAREIAAYFAk7vPsIACgkQU6Ni+wtCKv9F6gD+L6Yl43PugtrH2aCjeNsAAURl UlEQkfMGOI2jl0hz1sAA/2kbm5jV1Gg1LCzkX4CurY8Q7fMkNnNVpONHIyW0wI3Q =a3fR -----END PGP SIGNATURE----- --------------enig29BC4489A3A49561FC71552C-- From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 13:39:49 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5C957106566C; Mon, 19 Dec 2011 13:39:49 +0000 (UTC) (envelope-from yerenkow@gmail.com) Received: from mail-gx0-f182.google.com (mail-gx0-f182.google.com [209.85.161.182]) by mx1.freebsd.org (Postfix) with ESMTP id F1F388FC0C; Mon, 19 Dec 2011 13:39:48 +0000 (UTC) Received: by ggnp1 with SMTP id p1so5855996ggn.13 for ; Mon, 19 Dec 2011 05:39:48 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=3lafZdW7FjQwsg/ddhWPav/+PadBzHpHigeVEwEYI50=; b=S7xgKsi5Y4gAvXSK00qaNwcVLkjUVxbQFSSrGtPSxzDWHrJVb1XQU4HtyQmEfBgy++ SVs1eb7xSV30VxDf6+TN78KtA6l75KSyzEv2BtoePCcMgWhMX7vc0iRZLp219AcdfTmI UdWfIueepxrteTZf4Dukc98KCmh0SYHDQ01A8= MIME-Version: 1.0 Received: by 10.182.112.9 with SMTP id im9mr2072693obb.74.1324300615141; Mon, 19 Dec 2011 05:16:55 -0800 (PST) Received: by 10.182.150.70 with HTTP; Mon, 19 Dec 2011 05:16:55 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> Date: Mon, 19 Dec 2011 15:16:55 +0200 Message-ID: From: Alexander Yerenkow To: Edho Arief X-Mailman-Approved-At: Mon, 19 Dec 2011 13:51:17 +0000 Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 13:39:49 -0000 IMHO, no offence, as always. As were told, Phoronix used "default" setup, not tuned. So? Is average user will tune it after setup? No, he'll get same defaults, and would expect same performance as in tests, and he probably get it. The problem of FreeBSD is not it's default settings, some kind of very-safe defaults really should be there. But problem really is lacking of choosing them (defaults) during install, for average users. For example, few checkboxes with common sysctl tuning would be perfect, even if they would be marked as "Experimental", or not recommended. I'm thinking it's better way to make something in one place (like in installer) rather than require make almost same actions in many (hundreds of thousands?... more?...) places (end-users forced to read mail-lists/handbooks/forums over and over for same solutions). Simple example - many connections for PostgreSQL is not available on FreeBSD out-of-box. Just google "postgresql freebsd max connection" and you'll see how many there bikesheds requested and same solutions posted again and again :) FreeBSD currently have very obscure, closed community. To get in touch, you need to subscribe to several mail lists, constantly read them, I've just found recently (my shame of course) in mail list that there is service ( pub.allbsd.org) which constantly building current versions. This is great, but at homepage of freebsd.org there is no word about it :) I hope we all do something good about this, and things will going to change. -- Regards, Alexander Yerenkow From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 16:47:44 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 23E6B1065670 for ; Mon, 19 Dec 2011 16:47:44 +0000 (UTC) (envelope-from bruce@cran.org.uk) Received: from muon.cran.org.uk (muon.cran.org.uk [IPv6:2a01:348:0:15:5d59:5c40:0:1]) by mx1.freebsd.org (Postfix) with ESMTP id 9F2558FC14 for ; Mon, 19 Dec 2011 16:47:43 +0000 (UTC) Received: from muon.cran.org.uk (localhost [127.0.0.1]) by muon.cran.org.uk (Postfix) with ESMTP id 24FDCE6217; Mon, 19 Dec 2011 16:47:42 +0000 (GMT) DKIM-Signature: v=1; a=rsa-sha1; c=relaxed; d=cran.org.uk; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; s=mail; bh=2WxkJRkHHuth CZH4M/0L0fesbA4=; b=jGxUc4xw9U51x82Y7XE+h2MY0idOjDY43WRESQ1Y7N1d UwY8wjGtEYteydrkg3MQaYbIsoNTAJ6qYUmz/2vZRfqa0IjtqQZmKGNk9y7Vf0eA vXWErF6qGcGsiSyCpsjSeBakN3ZNKk4+wuSdYMEUdSEqo290os7ykpVohfDETU0= DomainKey-Signature: a=rsa-sha1; c=nofws; d=cran.org.uk; h=message-id :date:from:mime-version:to:cc:subject:references:in-reply-to :content-type:content-transfer-encoding; q=dns; s=mail; b=T3d8tH FMlZ//fm/HvKnGzeqZWq4dX33ZO6zhPiajACTkeZU32af95qkyYcB2FweUCXEGSJ ap829znpvcBkaTzJgd11Nd6aNAiEE9QUgCsOAA4Ao0DtgWQrfx01IlZMZmGZzSni O0wdYJTGkzkWNEFGF3fRFNV2W8WDXXYldUsPI= Received: from [192.168.1.68] (188-220-36-32.zone11.bethere.co.uk [188.220.36.32]) (using TLSv1 with cipher DHE-RSA-CAMELLIA256-SHA (256/256 bits)) (No client certificate requested) by muon.cran.org.uk (Postfix) with ESMTPSA id EA04EE6214; Mon, 19 Dec 2011 16:47:41 +0000 (GMT) Message-ID: <4EEF6AAB.6040803@cran.org.uk> Date: Mon, 19 Dec 2011 16:47:39 +0000 From: Bruce Cran User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Alexander Yerenkow References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-performance@freebsd.org, Edho Arief Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 16:47:44 -0000 [removed freebsd-current and freebsd-stable] On 19/12/2011 13:16, Alexander Yerenkow wrote: > For example, few checkboxes with common sysctl tuning would be perfect, > even if they would be marked as "Experimental", or not recommended. > I'm thinking it's better way to make something in one place (like in > installer) rather than require make almost same actions in many (hundreds > of thousands?... more?...) places (end-users forced to read > mail-lists/handbooks/forums over and over for same solutions). > Simple example - many connections for PostgreSQL is not available on > FreeBSD out-of-box. Just google "postgresql freebsd max connection" and > you'll see how many there bikesheds requested and same solutions posted > again and again :) This is what openSUSE does - it's possible to zoom through the installer choosing the defaults, but on the final page before installation you can tweak everything from the location of the bootloader to sysctl values. I know this has been tried before, but I wonder if we need a project to build a new installer that can do this, perhaps funded through the FreeBSD Foundation? -- Bruce Cran From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 16:50:56 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id BBE84106566C for ; Mon, 19 Dec 2011 16:50:56 +0000 (UTC) (envelope-from nwhitehorn@freebsd.org) Received: from agogare.doit.wisc.edu (agogare.doit.wisc.edu [144.92.197.211]) by mx1.freebsd.org (Postfix) with ESMTP id 89BCE8FC17 for ; Mon, 19 Dec 2011 16:50:56 +0000 (UTC) MIME-version: 1.0 Content-transfer-encoding: 7BIT Content-type: text/plain; CHARSET=US-ASCII; format=flowed Received: from avs-daemon.smtpauth2.wiscmail.wisc.edu by smtpauth2.wiscmail.wisc.edu (Sun Java(tm) System Messaging Server 7u2-7.05 32bit (built Jul 30 2009)) id <0LWG00M0KK0UBF00@smtpauth2.wiscmail.wisc.edu>; Mon, 19 Dec 2011 09:50:54 -0600 (CST) Received: from comporellon.tachypleus.net ([unknown] [76.210.77.223]) by smtpauth2.wiscmail.wisc.edu (Sun Java(tm) System Messaging Server 7u2-7.05 32bit (built Jul 30 2009)) with ESMTPSA id <0LWG00GLOK0RRM10@smtpauth2.wiscmail.wisc.edu>; Mon, 19 Dec 2011 09:50:51 -0600 (CST) Date: Mon, 19 Dec 2011 09:50:50 -0600 From: Nathan Whitehorn In-reply-to: To: freebsd-current@freebsd.org, freebsd-performance@freebsd.org Message-id: <4EEF5D5A.5050700@freebsd.org> X-Spam-Report: AuthenticatedSender=yes, SenderIP=76.210.77.223 X-Spam-PmxInfo: Server=avs-14, Version=5.6.1.2065439, Antispam-Engine: 2.7.2.376379, Antispam-Data: 2011.12.19.154214, SenderIP=76.210.77.223 References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111113 Thunderbird/8.0 X-Mailman-Approved-At: Mon, 19 Dec 2011 17:07:20 +0000 Cc: Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 16:50:56 -0000 On 12/18/11 04:34, Adrian Chadd wrote: > The trouble is that there's lots of anecdotal evidence, but noone's > really gone digging deep into _their_ example of why it's broken. The > developers who know this stuff don't see anything wrong. That hints to > me it may be something a little more creepy - as an example, the > interplay between netisr/swi/taskqueue/callbacks and such. It may be > that something is being starved that isn't obviously obvious. It's > just a stab in the dark, but it sounds somewhat plausible based on > what I've seen ULE do in my network throughput hacking. > > I applaud reppie for trying to make it as easy as possible for people > to use KTR to provide scheduler traces for him to go digging with, so > please, if you have these issues and you can absolutely reproduce > them, please follow his instructions and work with him to get him what > he needs. > The thing I've seen is that ULE is substantially more enthusiastic about migrating processes between cores than 4BSD. Often, this is a good thing, but can increase the rate of cache misses, hurting performance for cache-bound processes (I see this particularly in HPC-type scientific workloads). It might be interesting to add some kind of tunable here. Another more interesting and slightly longer-term possibility if someone wants a project would be to integrate scheduling decisions with hwpmc counters, to accumulate statistics on cache hits at each context switch and preferentially keep processes with a high hits/misses ratio on the same thread/cache domain relative to processes with a low one. -Nathan P.S. The other thing that could be very interesting from a research and scheduling standpoint would be to integrate heterogeneous SMP support into the operating system, with a FreeBSD-4 "Application Processor" syscall model. We seem to be going down the road where GPGPU computing has MMUs, timer interrupts, IPIs, etc. (the next AMD Fusions, IBM Cell), as well as potential systems with both x86 and ARM cores. This is something that no operating system currently supports well, and would be a place for BSD to shine. If anyone has a free graduate student... From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 18:00:33 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5893C106564A for ; Mon, 19 Dec 2011 18:00:33 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-tul01m020-f182.google.com (mail-tul01m020-f182.google.com [209.85.214.182]) by mx1.freebsd.org (Postfix) with ESMTP id 187958FC14 for ; Mon, 19 Dec 2011 18:00:32 +0000 (UTC) Received: by obbwd18 with SMTP id wd18so2830567obb.13 for ; Mon, 19 Dec 2011 10:00:32 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=0zvjS9FtSjqYgFSk1SUX7I20w4O9+fjp8OMXFOx1Etw=; b=LPBLvvr4V2I/9SayI/A75KnRzNdNxQDWjNUW9WjSaJpWgCyYGqNZDjLe/PEU+4Drzn UFJ3688spP1eK/Dom4I0lR+bsxFZEM18hzFQX7+qetOQsbf2tLug2k/wpvn0Q0xmTIsw VOGRZ+XVWg3MfKXfm6SuVXdQt8cMp9f1WAa3Y= MIME-Version: 1.0 Received: by 10.182.225.66 with SMTP id ri2mr10667924obc.26.1324316296544; Mon, 19 Dec 2011 09:38:16 -0800 (PST) Received: by 10.182.62.227 with HTTP; Mon, 19 Dec 2011 09:38:15 -0800 (PST) In-Reply-To: <4EEF6AAB.6040803@cran.org.uk> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> <4EEF6AAB.6040803@cran.org.uk> Date: Mon, 19 Dec 2011 09:38:15 -0800 Message-ID: From: Garrett Cooper To: freebsd-performance@freebsd.org Content-Type: text/plain; charset=ISO-8859-1 Cc: matthew@phrononix.com Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 18:00:33 -0000 My personal thoughts on all of the complaints that FreeBSD isn't fast enough and the Phoronix benchmarks aren't representative of true FreeBSD performance. Disclaimer: I don't know if the Phoronix benchmarks do tuning out of the box or not on Linux, so if they do, please correct me Matthew. The ultimate problem from my perspective is multifold: - There's an unknown -- seemingly unquantifiable -- SCHED_ULE scheduler performance issue that people are trying to root cause. ZFS: - Out of the box requires extensive tuning in order to get reasonable performance if you're doing something intensive on the machine, depending on what features you enable as well (hint: don't ever use dedup if you want performance). - FreeBSD's ZFS assumes that it owns all of the hardware except in certain low memory scenarios (VMs) from what I've seen. - It's also hardware hungry (RAM, SSD or better L2ARC and ZIL, etc), unlike certain filesystems like ext*, and UFS SU+J. Depending on what operations you perform (asynch/synch writes, etc), throwing hardware at the problem will fix things. In general: - FreeBSD is currently 'tuned' for the L.C.D. compute machine, which means my Soekris box (if I had one) or an AMD/Intel 48+ core machine can run FreeBSD out of the box with GENERIC (ex: `cpu I486_CPU', etc'). - GENERIC's also full of a bunch of drivers and options that are potentially useless for standard users depending on my machine and what I'm trying to achieve (ex: `device fdc', `makeoptions DEBUG=-g', `options FLOWTABLE', etc). - Some of the default tuning parameters don't work for compute intensive or interactive scenarios, and in many cases they're mutually exclusive (kern.sched.preempt_thresh comes to mind). - Our timecounter mechanism has been noted as slow compared to Linux because of its precision (clock_gettime and friends), which also affects other dependent syscalls if I'm not mistaken (epoll, select, etc?) which are used extensively in some tests and applications. IMHO we should have a less precise timecounter on by default (if it's good enough for the system and the user doesn't see an issue, it should be good enough for the masses). - There are a lot of other fancy features in Linux that help performance that don't exist on FreeBSD (ex: a true tickless kernel, better NUMA architecture support, etc). And the list goes on and on. The point is that while some of the suggestions have been good on how to write good benchmarks (someone suggested a medium math and a worker benchmark set of tests, which I think was on the right track), a lot of the shouting on the list has been missing the key point based on Matthew's statement a while back about using *untuned* FreeBSD in his benchmarks: - In order to use FreeBSD [well] on more recent hardware, I need to tune the OS in order for it to perform reasonably close to what Linux performs at. My personal suggestion based on personal observations to Matthew: - Don't touch ZFS unless you have the hardware to make it go faster, i.e. at least an enterprise SSD for your ZIL and L2ARC, and at least 12GB of RAM. It's slow otherwise if you slam the box, compared to UFS SU+J. - If you run X11 on the box you need to set an rtprio for Xorg, but I really advise not using X11 in your benchmarks because it introduces noise in the benchmarks -- in part because the featuresets between Linux and FreeBSD as far as what's enabled and how things are coded up can differ a *lot* (ex: many developers code things up with inotify, not kqueues or even libevent, and can sprinkle little architecture specific #ifdef's around the code), but also because interaction at some level with the syscalls differs enough on a micro scale that it can affect the macro picture. Thanks, -Garrett From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 20:36:42 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E3AF61065672 for ; Mon, 19 Dec 2011 20:36:42 +0000 (UTC) (envelope-from nec556@retena.com) Received: from resmaa12.ono.com (smtp12.ono.com [62.42.230.20]) by mx1.freebsd.org (Postfix) with ESMTP id 77CD98FC08 for ; Mon, 19 Dec 2011 20:36:42 +0000 (UTC) Received: from GogPortatil.retena.com (95.22.232.16) by resmaa12.ono.com (8.5.113) (authenticated as nec556@retena.com) id 4EE6D4BA0014B834 for freebsd-performance@freebsd.org; Mon, 19 Dec 2011 21:36:40 +0100 Message-ID: <4EE6D4BA0014B834@> (added by postmaster@resmaa12.ono.com) X-Mailer: QUALCOMM Windows Eudora Version 7.1.0.9 Date: Mon, 19 Dec 2011 21:36:47 +0100 To: freebsd-performance@freebsd.org From: Eduardo Morras Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Antivirus: AVG for E-mail 10.0.1415 [2108/4090] Subject: Re: PostgreSQL user experience: FreeBSD (ZFS) vs OpenIndiana (ZFS) vs Linux (EXT4) X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 20:36:43 -0000 At 14:26 17/12/2011, you wrote: >Hi everyone, > >I would like to share some of our expreience with PostgreSQL on FreeBSD. >It has been a while ago since we had to stop using FreeBSD for our >customer's PostgreSQL servers. > >PostgreSQL (8.4 and 9.0) was demonstrating slow performance under heavy >loads and one day I decided to compare it to other alternatives on the >very same system (one 8-core with 16GB RAM, another 12-core with 48GB >RAM). With ZFS it was extremely slow and with UFS the speed was >acceptable (still 10-20% slower) if not under high load. Our databases >have a size from several gigabytes to tens of gigabytes. > >A single real-world query on a idle system was noticeably slower on a >FreeBSD system than on the other systems (ZFS and UFS). We compared the >EXPLAIN ANALYZE output and the performance penalty was almost equally >spread on all items. With rising loads, PostgreSQL processes remain a >long time in "semwait" and "msgwait" states and the "top" output shows a >high system load on FreeBSD. > >I have also tried different tunings, compilers and optimizations, but >with that I was able to gain only 5-10% better results. > >The result of a pgbench run by one of my customers on a 12-core system >with 48GB RAM is here (FreeBSD ZFS vs OpenIndiana (ZFS) vs Linux (EXT4): >http://www.vx.sk/benchmarks/postgresql/pgbench_20110630.ods > >So our decision so far is the following: >- if we are building a PostgreSQL server for heavy loads, we prefer >Solaris/OpenIndiana (ZFS or UFS) or Linux (EXT4) to FreeBSD (ZFS or UFS) >- if we want to use PostgreSQL on FreeBSD, we prefer UFS to ZFS > >P.S: Our webservers still run FreeBSD and e.g. OpenIndiana (Solaris) >performed much worse in our high load real-world web application. What FreeBSD tunings have you used in tests? Have you set kern.ipc.shm_use_phys=1? Have you tuned the FreeBSD semaphores? Them increased more than 5-10% on my server, i increased clients from 25 (with saturation problems) to 40 (without problems). About UFS/ZFS, i prefer UFS, it has less memory/cpu footprint that can use for more postgresql cache and tps. >-- >Martin Matuska >FreeBSD committer >http://blog.vx.sk From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 21:33:45 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: by hub.freebsd.org (Postfix, from userid 1233) id 6B4AF106566B; Mon, 19 Dec 2011 21:33:45 +0000 (UTC) Date: Mon, 19 Dec 2011 21:33:45 +0000 From: Alexander Best To: Nathan Whitehorn Message-ID: <20111219213345.GA64578@freebsd.org> References: <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> <4EEF5CC1.7020709@freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EEF5CC1.7020709@freebsd.org> X-Mailman-Approved-At: Mon, 19 Dec 2011 21:50:58 +0000 Cc: Bruce Cran , Ivan Klymenko , Adrian Chadd , Doug Barton , freebsd-stable@freebsd.org, Ian Smith , "O. Hartmann" , Current FreeBSD , freebsd-performance@freebsd.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 21:33:45 -0000 On Mon Dec 19 11, Nathan Whitehorn wrote: > On 12/18/11 04:34, Adrian Chadd wrote: > >The trouble is that there's lots of anecdotal evidence, but noone's > >really gone digging deep into _their_ example of why it's broken. The > >developers who know this stuff don't see anything wrong. That hints to > >me it may be something a little more creepy - as an example, the > >interplay between netisr/swi/taskqueue/callbacks and such. It may be > >that something is being starved that isn't obviously obvious. It's > >just a stab in the dark, but it sounds somewhat plausible based on > >what I've seen ULE do in my network throughput hacking. > > > >I applaud reppie for trying to make it as easy as possible for people > >to use KTR to provide scheduler traces for him to go digging with, so > >please, if you have these issues and you can absolutely reproduce > >them, please follow his instructions and work with him to get him what > >he needs. > > The thing I've seen is that ULE is substantially more enthusiastic about > migrating processes between cores than 4BSD. Often, this is a good > thing, but can increase the rate of cache misses, hurting performance > for cache-bound processes (I see this particularly in HPC-type > scientific workloads). It might be interesting to add some kind of > tunable here. does r228718 have any impact regarding this behaviour? cheers. alex > > Another more interesting and slightly longer-term possibility if someone > wants a project would be to integrate scheduling decisions with hwpmc > counters, to accumulate statistics on cache hits at each context switch > and preferentially keep processes with a high hits/misses ratio on the > same thread/cache domain relative to processes with a low one. > -Nathan > > P.S. The other thing that could be very interesting from a research and > scheduling standpoint would be to integrate heterogeneous SMP support > into the operating system, with a FreeBSD-4 "Application Processor" > syscall model. We seem to be going down the road where GPGPU computing > has MMUs, timer interrupts, IPIs, etc. (the next AMD Fusions, IBM Cell). > This is something that no operating system currently supports well, and > would be a place for BSD to shine. If anyone has a free graduate student... From owner-freebsd-performance@FreeBSD.ORG Mon Dec 19 21:34:42 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 71759106567C; Mon, 19 Dec 2011 21:34:42 +0000 (UTC) (envelope-from avg@FreeBSD.org) Received: from citadel.icyb.net.ua (citadel.icyb.net.ua [212.40.38.140]) by mx1.freebsd.org (Postfix) with ESMTP id 849AF8FC19; Mon, 19 Dec 2011 21:34:41 +0000 (UTC) Received: from porto.starpoint.kiev.ua (porto-e.starpoint.kiev.ua [212.40.38.100]) by citadel.icyb.net.ua (8.8.8p3/ICyb-2.3exp) with ESMTP id XAA13903; Mon, 19 Dec 2011 23:22:42 +0200 (EET) (envelope-from avg@FreeBSD.org) Received: from localhost ([127.0.0.1]) by porto.starpoint.kiev.ua with esmtp (Exim 4.34 (FreeBSD)) id 1RckfS-000GLT-HD; Mon, 19 Dec 2011 23:22:42 +0200 Message-ID: <4EEFAB20.4070300@FreeBSD.org> Date: Mon, 19 Dec 2011 23:22:40 +0200 From: Andriy Gapon User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111206 Thunderbird/8.0 MIME-Version: 1.0 To: Nathan Whitehorn References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> <4EEF5D5A.5050700@freebsd.org> In-Reply-To: <4EEF5D5A.5050700@freebsd.org> X-Enigmail-Version: undefined Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Mon, 19 Dec 2011 21:51:09 +0000 Cc: freebsd-performance@FreeBSD.org, freebsd-current@FreeBSD.org Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 19 Dec 2011 21:34:42 -0000 on 19/12/2011 17:50 Nathan Whitehorn said the following: > The thing I've seen is that ULE is substantially more enthusiastic about > migrating processes between cores than 4BSD. Hmm, this seems to be contrary to my theoretical expectations. I thought that with 4BSD all threads that were not in one of the following categories: - temporary pinned - bound to cpu in kernel via sched_bind - belong to a cpu set which a strict subset of a total set were placed onto a common queue that was shared by all cpus. And as such I expected them to get picked up by the cpus semi-randomly. In other words, I thought that it was ULE that took into account cpu/cache affinities while 4BSD was deliberately entirely ignorant of those details. -- Andriy Gapon From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:42:33 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AB2CF1065676; Tue, 20 Dec 2011 09:42:33 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-yx0-f182.google.com (mail-yx0-f182.google.com [209.85.213.182]) by mx1.freebsd.org (Postfix) with ESMTP id 470508FC1B; Tue, 20 Dec 2011 09:42:32 +0000 (UTC) Received: by yenl9 with SMTP id l9so4698412yen.13 for ; Tue, 20 Dec 2011 01:42:32 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=subject:mime-version:content-type:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to:x-mailer; bh=kVd8UBTZMv7IHwY6VOwz8O9ZZkkAnvhEJYsyHGg7Gw8=; b=rxjC/xC7pVllkHy/Dz3hhG0JYGh/0YXi2gWwjW++U0XZ03zmJFfvH0/cxX0/QvdyE1 se1tmo3gADIAy7Min460houA3KPAtTrbmaZHlf1GcWEvkkq3evzCa8JW2t1Dcxmpenj4 HR+W38EhbBCgp3/tv87gqANxsO7MaqG/y57Ag= Received: by 10.236.201.137 with SMTP id b9mr1991915yho.124.1324374152574; Tue, 20 Dec 2011 01:42:32 -0800 (PST) Received: from starr-wireless.local (c-24-6-49-154.hsd1.ca.comcast.net. [24.6.49.154]) by mx.google.com with ESMTPS id n5sm2321003yhk.1.2011.12.20.01.42.27 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 20 Dec 2011 01:42:31 -0800 (PST) Mime-Version: 1.0 (Apple Message framework v1084) Content-Type: text/plain; charset=us-ascii From: Garrett Cooper In-Reply-To: Date: Tue, 20 Dec 2011 01:42:20 -0800 Content-Transfer-Encoding: quoted-printable Message-Id: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> To: Christer Solskogen X-Mailer: Apple Mail (2.1084) Cc: Edho Arief , freebsd-performance@freebsd.org, Alexander Yerenkow , FreeBSD Stable Mailing List , Current FreeBSD Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:42:33 -0000 On Dec 20, 2011, at 1:01 AM, Christer Solskogen wrote: > On Mon, Dec 19, 2011 at 2:16 PM, Alexander Yerenkow = wrote: >> FreeBSD currently have very obscure, closed community. To get in = touch, you >> need to subscribe to several mail lists, constantly read them, I've = just >> found recently (my shame of course) in mail list that there is = service ( >> pub.allbsd.org) which constantly building current versions. This is = great, >> but at homepage of freebsd.org there is no word about it :) >=20 > That's because it's not official. Do you take the risk? Would a > multi-milion-dollar company do that? > For your private server, sure it's probably fine. But how do you know > that those files are not contaminated? > (That being said, the purpose of that service is good. And the files > there a most probably 100% fine. But if it's not official... then..) As long as I have reliable checksums that match the what the upstream = source says is the real thing, it doesn't practically matter where I get = my images from. -Garrett= From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:55:37 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6D7881065672; Tue, 20 Dec 2011 09:55:37 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-gy0-f182.google.com (mail-gy0-f182.google.com [209.85.160.182]) by mx1.freebsd.org (Postfix) with ESMTP id E8FE58FC1A; Tue, 20 Dec 2011 09:55:36 +0000 (UTC) Received: by ghrr16 with SMTP id r16so941401ghr.13 for ; Tue, 20 Dec 2011 01:55:36 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=subject:mime-version:content-type:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to:x-mailer; bh=MDysFyqsbkr7dTfBbRyLi93e+kOxXhoDK8XikFwcsuw=; b=weev6e8nHr19Ba5tb2NpTCt1YkeMK7K7ikWTq2c5gcqiM3jNyr5/3W+CZRKrhWvWQ7 uvODo6d7Lv3xmHXM9iSOBErvHWqyWJEIOhg0IgLBWOl9zt5cg3HP6wN2Ei3NImOZ2nRz NDKr9U2qgnCICg7W+iORdF4PnaYX8EwN/nIq8= Received: by 10.236.175.72 with SMTP id y48mr2291729yhl.17.1324374936200; Tue, 20 Dec 2011 01:55:36 -0800 (PST) Received: from starr-wireless.local (c-24-6-49-154.hsd1.ca.comcast.net. [24.6.49.154]) by mx.google.com with ESMTPS id m38sm3707595anq.16.2011.12.20.01.55.34 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 20 Dec 2011 01:55:35 -0800 (PST) Mime-Version: 1.0 (Apple Message framework v1084) Content-Type: text/plain; charset=us-ascii From: Garrett Cooper In-Reply-To: Date: Tue, 20 Dec 2011 01:55:32 -0800 Content-Transfer-Encoding: quoted-printable Message-Id: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> To: Christer Solskogen X-Mailer: Apple Mail (2.1084) Cc: Edho Arief , freebsd-performance@freebsd.org, Alexander Yerenkow , FreeBSD Stable Mailing List , Current FreeBSD Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:55:37 -0000 On Dec 20, 2011, at 1:51 AM, Christer Solskogen wrote: > On Tue, Dec 20, 2011 at 10:42 AM, Garrett Cooper = wrote: >>=20 >> As long as I have reliable checksums that match the what the upstream = source says is the real thing, it doesn't practically matter where I get = my images from. >=20 > Checksums compared to what? How would you know what the correct > checksums for OpenBSD-current is, if it's not built by Theo? Release engineering for FreeBSD produces SHA256 checksums for = all official releases. AFAIK though they're only in the announcement = emails and not stored anywhere else. I can't speak for OpenBSD's release process. Thanks, -Garrett= From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:30:00 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CEE73106564A; Tue, 20 Dec 2011 09:30:00 +0000 (UTC) (envelope-from gljennjohn@googlemail.com) Received: from mail-ee0-f54.google.com (mail-ee0-f54.google.com [74.125.83.54]) by mx1.freebsd.org (Postfix) with ESMTP id D4B4F8FC12; Tue, 20 Dec 2011 09:29:59 +0000 (UTC) Received: by eekc50 with SMTP id c50so7341739eek.13 for ; Tue, 20 Dec 2011 01:29:58 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=date:from:to:cc:subject:message-id:in-reply-to:references:reply-to :x-mailer:mime-version:content-type:content-transfer-encoding; bh=3t0Usdm1HKG61fuGPfVDA7MaB10LmXBKnzyAXpm8tLM=; b=aX8WXLG6TU6LcTtrr/I7te38dqJ/+x13hm9cw0NAYC/Tz+Mo0DdPw38cQIqRZ7iRmW 1UwDfYKEmGLMhppPLoKTTSsff98w8nPjpLJAluO65sAaFrH3OYS3Bdx0CPqKHxvdceZd /YY0LHJvGVFue/+vkENeK7rCla9R52h1z+f7o= Received: by 10.213.110.6 with SMTP id l6mr344419ebp.71.1324373398491; Tue, 20 Dec 2011 01:29:58 -0800 (PST) Received: from ernst.jennejohn.org (p578E26BF.dip.t-dialin.net. [87.142.38.191]) by mx.google.com with ESMTPS id s16sm4547200eef.2.2011.12.20.01.29.56 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 20 Dec 2011 01:29:57 -0800 (PST) Date: Tue, 20 Dec 2011 10:29:55 +0100 From: Gary Jennejohn To: Andriy Gapon Message-ID: <20111220102955.068bb756@ernst.jennejohn.org> In-Reply-To: <4EEFAB20.4070300@FreeBSD.org> References: <4EE1EAFE.3070408@m5p.com> <4EE22421.9060707@gmail.com> <4EE6060D.5060201@mail.zedat.fu-berlin.de> <4EE69C5A.3090005@FreeBSD.org> <20111213104048.40f3e3de@nonamehost> <20111213090051.GA3339@vniz.net> <4EED5200.20302@cran.org.uk> <20111218164924.L64681@sola.nimnet.asn.au> <20111218075241.GA45367@vniz.net> <20111218102401.GA42627@freebsd.org> <20111218102600.GA44118@freebsd.org> <4EEF5D5A.5050700@freebsd.org> <4EEFAB20.4070300@FreeBSD.org> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd10.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Tue, 20 Dec 2011 12:39:17 +0000 Cc: freebsd-performance@FreeBSD.org, freebsd-current@FreeBSD.org, Nathan Whitehorn Subject: Re: SCHED_ULE should not be the default X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: gljennjohn@googlemail.com List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:30:00 -0000 On Mon, 19 Dec 2011 23:22:40 +0200 Andriy Gapon wrote: > on 19/12/2011 17:50 Nathan Whitehorn said the following: > > The thing I've seen is that ULE is substantially more enthusiastic about > > migrating processes between cores than 4BSD. > > Hmm, this seems to be contrary to my theoretical expectations. I thought that > with 4BSD all threads that were not in one of the following categories: > - temporary pinned > - bound to cpu in kernel via sched_bind > - belong to a cpu set which a strict subset of a total set > were placed onto a common queue that was shared by all cpus. And as such I > expected them to get picked up by the cpus semi-randomly. > > In other words, I thought that it was ULE that took into account cpu/cache > affinities while 4BSD was deliberately entirely ignorant of those details. > I have a 6-core AMD CPU running FreeeBSD 10.0 and SCHED_4BSD. I've noticed with large ports builds which are not MAKE_JOBS_SAFE that the compile load migrates between the cores pretty quickly, but I haven't compared it to ULE. -- Gary Jennejohn From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:32:19 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 71516106566C; Tue, 20 Dec 2011 09:32:19 +0000 (UTC) (envelope-from christer.solskogen@gmail.com) Received: from mail-wi0-f182.google.com (mail-wi0-f182.google.com [209.85.212.182]) by mx1.freebsd.org (Postfix) with ESMTP id 941FA8FC13; Tue, 20 Dec 2011 09:32:18 +0000 (UTC) Received: by wibhr1 with SMTP id hr1so2567919wib.13 for ; Tue, 20 Dec 2011 01:32:17 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; bh=yuWdyf7Fw56Lo6gbnvRnGyn2QVHW7uYejRRUOH85lzY=; b=LUraSKFBVdU3/BgtIgOqc2qBE0ooMQUByClekkZAy/QLElhNiJFqfL0kmYi0hZvgSA Xs3/xZrj/6qZwsJtmKCzDt7JoOIA1IIJUHOXKIZrCGsGbiy/Ft+O/ZsFMpNaBfRKeZLU y2qlpPSin5+RJcg6oROYFqj1ro8ocKV5f6pSE= Received: by 10.180.19.138 with SMTP id f10mr3389515wie.3.1324371697282; Tue, 20 Dec 2011 01:01:37 -0800 (PST) MIME-Version: 1.0 Received: by 10.227.57.82 with HTTP; Tue, 20 Dec 2011 01:01:16 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> From: Christer Solskogen Date: Tue, 20 Dec 2011 10:01:16 +0100 Message-ID: To: Alexander Yerenkow Content-Type: text/plain; charset=UTF-8 X-Mailman-Approved-At: Tue, 20 Dec 2011 12:39:50 +0000 Cc: FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, Current FreeBSD , Edho Arief Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:32:19 -0000 On Mon, Dec 19, 2011 at 2:16 PM, Alexander Yerenkow wrote: > FreeBSD currently have very obscure, closed community. To get in touch, you > need to subscribe to several mail lists, constantly read them, I've just > found recently (my shame of course) in mail list that there is service ( > pub.allbsd.org) which constantly building current versions. This is great, > but at homepage of freebsd.org there is no word about it :) That's because it's not official. Do you take the risk? Would a multi-milion-dollar company do that? For your private server, sure it's probably fine. But how do you know that those files are not contaminated? (That being said, the purpose of that service is good. And the files there a most probably 100% fine. But if it's not official... then..) -- chs, if there is only one candiate, there is one one choice! From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:51:41 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id EE631106566B; Tue, 20 Dec 2011 09:51:41 +0000 (UTC) (envelope-from christer.solskogen@gmail.com) Received: from mail-wi0-f182.google.com (mail-wi0-f182.google.com [209.85.212.182]) by mx1.freebsd.org (Postfix) with ESMTP id 2B0258FC12; Tue, 20 Dec 2011 09:51:40 +0000 (UTC) Received: by wibhr1 with SMTP id hr1so2581487wib.13 for ; Tue, 20 Dec 2011 01:51:40 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type; bh=eZXzKbhJ/aJknufgoUTuGgSuDXqIapHqOQEL7vQhu4k=; b=j4u6NEKLCDEzdH9jBfkKHZsqJUCIJxJVxh2TOHVK67tNhTyXyRG1/VebqEzTm30iXO 8QPEHxCxHDfiqOr/8iruMylRUKZexA6K5PoHekfmSaGj+hbhBKQMbmyen6dT5QacLOwQ rLGs7ItwAbRn1ZcH/qyG7noESUMQplM9Fth04= Received: by 10.180.19.138 with SMTP id f10mr3861498wie.3.1324374700162; Tue, 20 Dec 2011 01:51:40 -0800 (PST) MIME-Version: 1.0 Received: by 10.227.57.82 with HTTP; Tue, 20 Dec 2011 01:51:19 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> From: Christer Solskogen Date: Tue, 20 Dec 2011 10:51:19 +0100 Message-ID: To: Garrett Cooper Content-Type: text/plain; charset=UTF-8 X-Mailman-Approved-At: Tue, 20 Dec 2011 12:40:13 +0000 Cc: Edho Arief , freebsd-performance@freebsd.org, Alexander Yerenkow , FreeBSD Stable Mailing List , Current FreeBSD Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:51:42 -0000 On Tue, Dec 20, 2011 at 10:42 AM, Garrett Cooper wrote: > > As long as I have reliable checksums that match the what the upstream source says is the real thing, it doesn't practically matter where I get my images from. Checksums compared to what? How would you know what the correct checksums for OpenBSD-current is, if it's not built by Theo? -- chs, From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 09:59:38 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F04BB106567D; Tue, 20 Dec 2011 09:59:38 +0000 (UTC) (envelope-from christer.solskogen@gmail.com) Received: from mail-ww0-f50.google.com (mail-ww0-f50.google.com [74.125.82.50]) by mx1.freebsd.org (Postfix) with ESMTP id 19AB08FC20; Tue, 20 Dec 2011 09:59:37 +0000 (UTC) Received: by wgbdr11 with SMTP id dr11so12100655wgb.31 for ; Tue, 20 Dec 2011 01:59:37 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:from:date:message-id:subject:to :cc:content-type:content-transfer-encoding; bh=z4QhDsp0VyZDq+EW4mX25buZmYwLO4eSaoxVxI5K1r0=; b=EpMfDVYoxb4NH/nMwyJyGMhLUZFg9uCOyqQqJTG81ohO5zGML0ZLEYgiJ62gvPCknF L7J+nSiVZvn/+44QBOfX73HeudXQnsynQtl57XXvqM9Ys6MWX+vQOO0/CNklucbfVL/X KZYNQG6Y2L9DRqxuos7ViV2XCyL7REDP8QuPc= Received: by 10.216.136.231 with SMTP id w81mr788584wei.3.1324375177146; Tue, 20 Dec 2011 01:59:37 -0800 (PST) MIME-Version: 1.0 Received: by 10.227.57.82 with HTTP; Tue, 20 Dec 2011 01:59:15 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> From: Christer Solskogen Date: Tue, 20 Dec 2011 10:59:15 +0100 Message-ID: To: Garrett Cooper Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-Mailman-Approved-At: Tue, 20 Dec 2011 12:40:34 +0000 Cc: Edho Arief , freebsd-performance@freebsd.org, Alexander Yerenkow , FreeBSD Stable Mailing List , Current FreeBSD Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 09:59:39 -0000 On Tue, Dec 20, 2011 at 10:55 AM, Garrett Cooper wrote= : > =C2=A0 =C2=A0 =C2=A0 =C2=A0Release engineering for FreeBSD produces SHA25= 6 checksums for all official releases. AFAIK though they're only in the ann= ouncement emails and not stored anywhere else. > =C2=A0 =C2=A0 =C2=A0 =C2=A0I can't speak for OpenBSD's release process. > Thanks, So why do you want to download from a non-official site then? What do you gain with that? --=20 chs, From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 10:46:05 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 487951065677 for ; Tue, 20 Dec 2011 10:46:05 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id E40B08FC14 for ; Tue, 20 Dec 2011 10:46:04 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RcxCt-0005eD-Ia>; Tue, 20 Dec 2011 11:46:03 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RcxCt-0007wS-FM>; Tue, 20 Dec 2011 11:46:03 +0100 Message-ID: <4EF06765.5050107@mail.zedat.fu-berlin.de> Date: Tue, 20 Dec 2011 11:45:57 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: Christer Solskogen References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="------------enig4F73BAF636BD69D68BDE37C4" X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Tue, 20 Dec 2011 12:40:59 +0000 Cc: freebsd-performance@freebsd.org, Alexander Yerenkow , Edho Arief Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 10:46:05 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig4F73BAF636BD69D68BDE37C4 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 12/20/11 10:01, Christer Solskogen wrote: > On Mon, Dec 19, 2011 at 2:16 PM, Alexander Yerenkow wrote: >> FreeBSD currently have very obscure, closed community. To get in touch= , you >> need to subscribe to several mail lists, constantly read them, I've ju= st >> found recently (my shame of course) in mail list that there is service= ( >> pub.allbsd.org) which constantly building current versions. This is gr= eat, >> but at homepage of freebsd.org there is no word about it :) >=20 > That's because it's not official. Do you take the risk? Would a > multi-milion-dollar company do that? > For your private server, sure it's probably fine. But how do you know > that those files are not contaminated? > (That being said, the purpose of that service is good. And the files > there a most probably 100% fine. But if it's not official... then..) >=20 Well, then, FreeBSD is with priority for multi-million-euro companies? No one knows whether those companies like Suse or similar are not undermined by the US agencies or those from Telaviv. What about Microsoft and its funny Zero-Day bugs? Do you trust that company, which does not give any insight in its code? This shit is even more widespread in governments, agencies and defence than "real" traitors. Even a multi-million-what-so-ever has to decide on their own what to get, where to get it from and this is obviously not argument NOT giving such valuable informations the community at hand like pub.allbsd.org. For years outdated stuff from a Period when freeBSD 4.X outperformed the Linux crap is sometimes still present on the FreeBSD pages (luckily, those has gone after a load of discussion). --------------enig4F73BAF636BD69D68BDE37C4 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/ iF4EAREIAAYFAk7wZ2sACgkQU6Ni+wtCKv+PmwEApd9VrRs07X5JK2gjrWXzAhC5 kjmT4HnIIDMOCYA1l7IBAI8RpHQMZrCMWz2vblYmNEE5jRxqXeRwgPbI00wQUkLC =kFov -----END PGP SIGNATURE----- --------------enig4F73BAF636BD69D68BDE37C4-- From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 19:44:38 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AB14E106566C for ; Tue, 20 Dec 2011 19:44:38 +0000 (UTC) (envelope-from sodynet1@gmail.com) Received: from mail-iy0-f182.google.com (mail-iy0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 6233E8FC14 for ; Tue, 20 Dec 2011 19:44:38 +0000 (UTC) Received: by iadj38 with SMTP id j38so10004765iad.13 for ; Tue, 20 Dec 2011 11:44:37 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type; bh=Pwp3RmjVFJ7KAY3SAUtiXlqMvhqD3WQgHQkphcjhKgM=; b=l4Lp708Qd0heGxylsr7ob3lIOxJGRz45OQyIdPxbYlk/SuMeymfd9x8VOqT9pCN1dU Gu12VBUqbLqPtuL/e3FXOHbFDODEDcCu7UIL0kmj6//aZaFJFswSssOWjWY2G8luasag q39uuYzZLt8/tjYFpGETdJooIS7D1CLVtiB+E= MIME-Version: 1.0 Received: by 10.43.65.79 with SMTP id xl15mr3093825icb.6.1324408547912; Tue, 20 Dec 2011 11:15:47 -0800 (PST) Received: by 10.231.41.206 with HTTP; Tue, 20 Dec 2011 11:15:47 -0800 (PST) In-Reply-To: <4EF06765.5050107@mail.zedat.fu-berlin.de> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <6140271.20111219122721@serebryakov.spb.ru> <4EF06765.5050107@mail.zedat.fu-berlin.de> Date: Tue, 20 Dec 2011 21:15:47 +0200 Message-ID: From: Sami Halabi To: "O. Hartmann" Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Christer Solskogen , freebsd-performance@freebsd.org, Alexander Yerenkow , Edho Arief Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 19:44:38 -0000 Hi, I'm not sure i trust allbsd.org, such as their site has last updated at 2005. Sami On Tue, Dec 20, 2011 at 12:45 PM, O. Hartmann < ohartman@mail.zedat.fu-berlin.de> wrote: > On 12/20/11 10:01, Christer Solskogen wrote: > > On Mon, Dec 19, 2011 at 2:16 PM, Alexander Yerenkow > wrote: > >> FreeBSD currently have very obscure, closed community. To get in touch, > you > >> need to subscribe to several mail lists, constantly read them, I've just > >> found recently (my shame of course) in mail list that there is service ( > >> pub.allbsd.org) which constantly building current versions. This is > great, > >> but at homepage of freebsd.org there is no word about it :) > > > > That's because it's not official. Do you take the risk? Would a > > multi-milion-dollar company do that? > > For your private server, sure it's probably fine. But how do you know > > that those files are not contaminated? > > (That being said, the purpose of that service is good. And the files > > there a most probably 100% fine. But if it's not official... then..) > > > > Well, then, FreeBSD is with priority for multi-million-euro companies? > > No one knows whether those companies like Suse or similar are not > undermined by the US agencies or those from Telaviv. What about > Microsoft and its funny Zero-Day bugs? Do you trust that company, which > does not give any insight in its code? This shit is even more widespread > in governments, agencies and defence than "real" traitors. > > Even a multi-million-what-so-ever has to decide on their own what to > get, where to get it from and this is obviously not argument NOT giving > such valuable informations the community at hand like pub.allbsd.org. > > For years outdated stuff from a Period when freeBSD 4.X outperformed the > Linux crap is sometimes still present on the FreeBSD pages (luckily, > those has gone after a load of discussion). > > -- Sami Halabi Information Systems Engineer NMS Projects Expert From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 20:48:14 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0D4EC106564A; Tue, 20 Dec 2011 20:48:14 +0000 (UTC) (envelope-from mozolevsky@gmail.com) Received: from mail-pw0-f54.google.com (mail-pw0-f54.google.com [209.85.160.54]) by mx1.freebsd.org (Postfix) with ESMTP id BFA2C8FC1A; Tue, 20 Dec 2011 20:48:13 +0000 (UTC) Received: by pbcc3 with SMTP id c3so5312078pbc.13 for ; Tue, 20 Dec 2011 12:48:13 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:from:date :x-google-sender-auth:message-id:subject:to:cc:content-type; bh=/CaEm1Px9Ljrz2CxJ7e4Ko5mcSwakpZcL4rqV3nij4w=; b=WUGe0HQf5q8d5HsXXUv7p7CZiDfulGL/J15RyvgOb+XcguAgWqrHEPNkyE5k9vk+rJ PYyA6UmVhYcuyVD2nC1OFMj9IdocI0SZCEb/HEUTdt5Ex7YBDOfnu1k2pSBnJg48KMGn J4XcYq6WKyd+BnYlYWruu3OSFmtNVrpRGjjPg= Received: by 10.68.74.98 with SMTP id s2mr5591159pbv.46.1324412493178; Tue, 20 Dec 2011 12:21:33 -0800 (PST) MIME-Version: 1.0 Sender: mozolevsky@gmail.com Received: by 10.68.51.133 with HTTP; Tue, 20 Dec 2011 12:20:52 -0800 (PST) In-Reply-To: <4EE9A2A0.80607@zedat.fu-berlin.de> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> From: Igor Mozolevsky Date: Tue, 20 Dec 2011 20:20:52 +0000 X-Google-Sender-Auth: sq1TBiXB5HA-vy4_GqUuXWzzqyM Message-ID: To: "O. Hartmann" Content-Type: text/plain; charset=UTF-8 X-Mailman-Approved-At: Tue, 20 Dec 2011 21:00:43 +0000 Cc: freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 20:48:14 -0000 Interestingly, while people seem to be (arguably rightly) focused on criticising Phoronix's benchmarking, nobody has offered an alternative benchmark; and while (again, arguably rightly) it is important to benchmark real world performance, equally, nobody has offered any numbers in relation to, for example, HTTP or SMTP, or any other "real world"-application torture tests done on the aforementioned two platforms... IMO, this just goes to show that "doing is hard" and "criticising is much easier" (yes, I am aware of the irony involved in making this statement, but someone has to!) Cheers, Igor M :-) From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 21:39:24 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 60458106566B; Tue, 20 Dec 2011 21:39:24 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 02F7F8FC17; Tue, 20 Dec 2011 21:39:23 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Rd7P8-0003XO-F9>; Tue, 20 Dec 2011 22:39:22 +0100 Received: from e178016253.adsl.alicedsl.de ([85.178.16.253] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Rd7P8-0004Ye-9D>; Tue, 20 Dec 2011 22:39:22 +0100 Message-ID: <4EF10088.1010409@zedat.fu-berlin.de> Date: Tue, 20 Dec 2011 22:39:20 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: Igor Mozolevsky References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig8C1553888582332653719232" X-Originating-IP: 85.178.16.253 Cc: freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 21:39:24 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig8C1553888582332653719232 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 12/20/11 21:20, Igor Mozolevsky wrote: > Interestingly, while people seem to be (arguably rightly) focused on > criticising Phoronix's benchmarking, nobody has offered an alternative > benchmark; and while (again, arguably rightly) it is important to > benchmark real world performance, equally, nobody has offered any > numbers in relation to, for example, HTTP or SMTP, or any other "real > world"-application torture tests done on the aforementioned two > platforms... IMO, this just goes to show that "doing is hard" and > "criticising is much easier" (yes, I am aware of the irony involved in > making this statement, but someone has to!) >=20 >=20 > Cheers, > Igor M :-) Unfortunately, M. Larabel is the only one who's performing benchmarks on FreeBSD, comparing its performance to the Linux-opponents. Adn indeed, there is a lot of criticism, but no alternative. I said unfortunately - not offensive - since Larabel and Phoronix are sadly the only ones who do actually such bechmarking. It would be much more nicer and kind to support those people. Well, in January/February we get new hardware. One box is supposed to do number crunching via 12 cores and a TESLA GPU. My colleague is developing a high parallelized peice of software for satellite data transformation. The software package is CPU bound, partially GPU, but massively memory hungry (96 to 128 GB RAM is needed). What I can offer is, since I will also work on that machine and I've free hand to administer, in the spare time of doing my PhD, installing FreeBSD 9.0/10.0 besides SuSe Linux and looking forward having one ZFS data storage drive for homes, so both systems can perform on a most recent ZFS. I'm new to Linux, not a BSD guru, nor I'm a professional programmer/developer. My skills are sufficient for the daily scientific work. So, without pressure, I'm willing to perform some HPC benchmarks under advice if the day comes and those interested in bare numbers of FreeBSD vs. Linux performance with a real-world-scientific application. I would appreciate to see some of the developers and/or FreeBSD hackers to help Phoronix setting up a proper testenvironment instead of bashing M. Larabel and his fellows. Regards, Oliver --------------enig8C1553888582332653719232 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO8QCJAAoJEOgBcD7A/5N8EoQIAMj9hcl5dL2gB5V7lkebJIWI hrxXPCISgYoRq3nLa/YbH+Ub532VB4t6ftfI+C6UE5/3/NBFujnI9My5bV9Xnys6 +yUbzdxY7t9SRujf8rhg8JpwwgUySwhMa4v9pnefUML9Pi+fN2U35ZjDCWFbFlpS IRfcsueq4OgKr9PWa06eeZmlbp2AYoKsnlV+bM1TvI4pDAvpqgHkzci526h/TzAc gbPhw+Wjn/JvH7ZWxKnF3pG8U+zAuOSI0g7JC6wy59O71UJEpEiEVwAvmv/dFDgx 61GvOy0cZ/zLMkN0ag7D8Zy/1byNnaIa7Rli42bJV8Ho3SRp7joYrBryf2L3J2Q= =6hh+ -----END PGP SIGNATURE----- --------------enig8C1553888582332653719232-- From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 21:45:54 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C8AC21065670; Tue, 20 Dec 2011 21:45:54 +0000 (UTC) (envelope-from sjg@evilcode.net) Received: from mail-qy0-f182.google.com (mail-qy0-f182.google.com [209.85.216.182]) by mx1.freebsd.org (Postfix) with ESMTP id 5863C8FC19; Tue, 20 Dec 2011 21:45:54 +0000 (UTC) Received: by qcse13 with SMTP id e13so5904734qcs.13 for ; Tue, 20 Dec 2011 13:45:53 -0800 (PST) MIME-Version: 1.0 Received: by 10.224.205.134 with SMTP id fq6mr5166209qab.99.1324417553722; Tue, 20 Dec 2011 13:45:53 -0800 (PST) Received: by 10.229.6.142 with HTTP; Tue, 20 Dec 2011 13:45:53 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> Date: Tue, 20 Dec 2011 14:45:53 -0700 Message-ID: From: "Samuel J. Greear" To: Igor Mozolevsky X-Mailman-Approved-At: Tue, 20 Dec 2011 22:13:03 +0000 Content-Type: text/plain; charset=ISO-8859-1 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, Current FreeBSD , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 21:45:55 -0000 http://www.osnews.com/story/25334/DragonFly_BSD_MP_Performance_Significantly_Improved PostgreSQL tests, see the linked PDF for #'s on FreeBSD, DragonFly, Linux and Solaris. Steps to reproduce these benchmarks provided. Sam On Tue, Dec 20, 2011 at 1:20 PM, Igor Mozolevsky wrote: > Interestingly, while people seem to be (arguably rightly) focused on > criticising Phoronix's benchmarking, nobody has offered an alternative > benchmark; and while (again, arguably rightly) it is important to > benchmark real world performance, equally, nobody has offered any > numbers in relation to, for example, HTTP or SMTP, or any other "real > world"-application torture tests done on the aforementioned two > platforms... IMO, this just goes to show that "doing is hard" and > "criticising is much easier" (yes, I am aware of the irony involved in > making this statement, but someone has to!) > > > Cheers, > Igor M :-) > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" > From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 22:54:26 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id DFA5A106566B; Tue, 20 Dec 2011 22:54:26 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 81BE08FC08; Tue, 20 Dec 2011 22:54:26 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Rd8Zl-0002HE-1k>; Tue, 20 Dec 2011 23:54:25 +0100 Received: from e178016253.adsl.alicedsl.de ([85.178.16.253] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Rd8Zk-0008C4-Pd>; Tue, 20 Dec 2011 23:54:25 +0100 Message-ID: <4EF1121F.9010209@zedat.fu-berlin.de> Date: Tue, 20 Dec 2011 23:54:23 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: "Samuel J. Greear" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigB1D490B63A11258175672D7F" X-Originating-IP: 85.178.16.253 Cc: freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 22:54:27 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigB1D490B63A11258175672D7F Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/20/11 22:45, Samuel J. Greear wrote: > http://www.osnews.com/story/25334/DragonFly_BSD_MP_Performance_Signific= antly_Improved >=20 > PostgreSQL tests, see the linked PDF for #'s on FreeBSD, DragonFly, Lin= ux > and Solaris. Steps to reproduce these benchmarks provided. >=20 > Sam >=20 > On Tue, Dec 20, 2011 at 1:20 PM, Igor Mozolevsky wrote: >=20 >> Interestingly, while people seem to be (arguably rightly) focused on >> criticising Phoronix's benchmarking, nobody has offered an alternative= >> benchmark; and while (again, arguably rightly) it is important to >> benchmark real world performance, equally, nobody has offered any >> numbers in relation to, for example, HTTP or SMTP, or any other "real >> world"-application torture tests done on the aforementioned two >> platforms... IMO, this just goes to show that "doing is hard" and >> "criticising is much easier" (yes, I am aware of the irony involved in= >> making this statement, but someone has to!) >> >> >> Cheers, >> Igor M :-) >> _______________________________________________ >> freebsd-current@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-current >> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.= org" >> Thanks for those numbers. Impressive how Matthew Dillon's project jumps forward now. And it is still impressive to see that the picture is still in the right place when it comes to a comparison to Linux. Also, OpenIndiana shows an impressive performance. But this is only one suite of testing. Scientific Linux is supposed to give the best performance for scientifi purposes, i.e. for longhaul calculations, much numerical stuff. It outperforms in a typical server application FreeBSd, were "FreeBSD shoulkd have the power to serve". Is the postgresql benchmark the only way to benchmark? Well, this inspires me to gather together all the benchmarks someone could find. There were lots of compalins about FreeBSD's poor performance with BIND - once a domain of FreeBSD. Network performance seems also to be an issue if it comes to scalability. It would be nice to see what portion of the raw CPU/GPU power the OS (FreeBSD, Linux ...) delivers to scientific applications. I only know some kind of benchmarks, BYTE UNIX benchmark, LINPACK test =2E.. Does someone know a site to look for a couple of benchmarks to test= a) memory system b) scalability (apart from pgbench) c) network performance/throughput/network scalability d) portion of CPU performance the system delivers for numerical applications to the user apart from the system's own consumption e) disk I/O performance and scalability it would also be nice to discuss some nice settings and performance tunings for FreeBSD for several scenarios. I guess, starting developing benchmarking test scenarios for several purposes would lead faster to real numbers and non polemic than weird discussions ... --------------enigB1D490B63A11258175672D7F Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO8RIfAAoJEOgBcD7A/5N8dhQIANomh6qezYWsQVSYv3QYaLQR /ooQAaxCODCdunq3ZGmDl41YH3UTUvmOTpUoxTgSCeiycMRQW74DGm7mYHDb72hY 6PaxU2c5Ehh9bFT7TUsolZFHY0xHysHcQCpu9tqoj5hvuXAAZG6SO7PUxTDDyjAc VgWGaX3iYF0W3H1dNqYz4970Z1E1Zhb4X2rFvWkpPYEqinvNbwsz3YImeLCCVNVL r+nru3JMwwnu1XUSd7InYySbQFGW42YQ5hXwvc84NzbCR+pMGL3LYh9QIaZMlVtQ vgFjvMOSPWLCjJepq5jrMg7EiYUIRnTqVHDOJe4WgXxPzuzQq+s7UaMwEcabtWU= =8iuY -----END PGP SIGNATURE----- --------------enigB1D490B63A11258175672D7F-- From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 23:33:49 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 780C71065670; Tue, 20 Dec 2011 23:33:49 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 3AEA18FC12; Tue, 20 Dec 2011 23:33:48 +0000 (UTC) Received: from palm-64-28-152-131.palm.com ([64.28.152.131] helo=LT740055CZ0L1.palm1.palmone.com) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1Rd9Bq-000144-UL; Tue, 20 Dec 2011 17:33:46 -0600 Message-ID: <4EF11B57.7090007@phoronix.com> Date: Tue, 20 Dec 2011 15:33:43 -0800 From: Matthew Tippett User-Agent: Mozilla/5.0 (X11; Linux i686; rv:9.0) Gecko/20111214 Thunderbird/9.0 MIME-Version: 1.0 To: "O. Hartmann" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> In-Reply-To: <4EF1121F.9010209@zedat.fu-berlin.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Cc: FreeBSD Stable Mailing List , Current FreeBSD , Igor Mozolevsky , "Samuel J. Greear" , freebsd-performance@freebsd.org, Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 23:33:49 -0000 Bottom post this time to follow Oliver :). On 12/20/2011 02:54 PM, O. Hartmann wrote: > On 12/20/11 22:45, Samuel J. Greear wrote: >> http://www.osnews.com/story/25334/DragonFly_BSD_MP_Performance_Significantly_Improved >> >> PostgreSQL tests, see the linked PDF for #'s on FreeBSD, DragonFly, Linux >> and Solaris. Steps to reproduce these benchmarks provided. >> >> Sam There are still possible issues with those benchmarks. The Xeon has known problems scaling from 6 to 12 cores (well enabling the hyperthreading), so you may find that some platforms are penalized in performance if HT is turned on. See the scaling that Phoronix has done in http://openbenchmarking.org/result/1112166-AR-1112153AR03 Most systems are good with scaling on real cores, the hyperthreading (and for that matter the Bulldozer thread affinity) can really break performance. Different platforms have different behaviours. Benchmarking is a mucky business.. Note that the benchmarks with Phoronix test suite are repeatable, once installed, you can just run "./phoronix-test-suite benchmark 1112113-AR-ORACLELIN37" to repeat (as close as the system allows) the benchmarks that started this thread. >> Is the postgresql benchmark the only way to benchmark? pgbench is already included in the Phoronix Test Suite (at least 9.0.1 TPC-B benchmark. >> >> Well, this inspires me to gather together all the benchmarks someone >> could find. There were lots of compalins about FreeBSD's poor >> performance with BIND - once a domain of FreeBSD. Network performance >> seems also to be an issue if it comes to scalability. >> It would be nice to see what portion of the raw CPU/GPU power the OS >> (FreeBSD, Linux ...) delivers to scientific applications. >> >> I only know some kind of benchmarks, BYTE UNIX benchmark, LINPACK test >> ... Does someone know a site to look for a couple of benchmarks to test >> >> a) memory system >> b) scalability (apart from pgbench) >> c) network performance/throughput/network scalability >> d) portion of CPU performance the system delivers for numerical >> applications to the user apart from the system's own consumption >> e) disk I/O performance and scalability The majority of these benchmarks are already in Phoronix Test Suite. There is monitoring capability (temp, load, CPU states, etc). The question is the mapping from system attribute to benchmark, as well as determine what the ambigious terms mean (scaling can mean on increasing workloads, as memory is increased, as cpus are increased). >> >> it would also be nice to discuss some nice settings and performance >> tunings for FreeBSD for several scenarios. I guess, starting developing >> benchmarking test scenarios for several purposes would lead faster to >> real numbers and non polemic than weird discussions ... >> This is what Michael and I are wanting to see. Adrian Chadd has offerered to help facilitate within the FreeBSD community. As mentioned before, what I'd like to see is 1) Recommendations for more rounded benchmarks from the FreeBSD perspective 2) Tuning guide documented somewhere within the community 3) Comparative results based on the communities testing. All concrete, and all achievable. Regards, Matthew From owner-freebsd-performance@FreeBSD.ORG Tue Dec 20 23:29:29 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 446F2106566C for ; Tue, 20 Dec 2011 23:29:29 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta05.westchester.pa.mail.comcast.net (qmta05.westchester.pa.mail.comcast.net [76.96.62.48]) by mx1.freebsd.org (Postfix) with ESMTP id D617A8FC14 for ; Tue, 20 Dec 2011 23:29:28 +0000 (UTC) Received: from omta17.westchester.pa.mail.comcast.net ([76.96.62.89]) by qmta05.westchester.pa.mail.comcast.net with comcast id BbAy1i0031vXlb855bVUkV; Tue, 20 Dec 2011 23:29:28 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta17.westchester.pa.mail.comcast.net with comcast id BbVT1i00c1t3BNj3dbVTkp; Tue, 20 Dec 2011 23:29:28 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id DAF21102C19; Tue, 20 Dec 2011 15:29:25 -0800 (PST) Date: Tue, 20 Dec 2011 15:29:25 -0800 From: Jeremy Chadwick To: "O. Hartmann" Message-ID: <20111220232925.GA55953@icarus.home.lan> References: <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EF1121F.9010209@zedat.fu-berlin.de> User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Tue, 20 Dec 2011 23:38:26 +0000 Cc: FreeBSD Stable Mailing List , freebsd-performance@freebsd.org, Current FreeBSD , "Samuel J. Greear" , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 20 Dec 2011 23:29:29 -0000 On Tue, Dec 20, 2011 at 11:54:23PM +0100, O. Hartmann wrote: > On 12/20/11 22:45, Samuel J. Greear wrote: > > http://www.osnews.com/story/25334/DragonFly_BSD_MP_Performance_Significantly_Improved > > > > PostgreSQL tests, see the linked PDF for #'s on FreeBSD, DragonFly, Linux > > and Solaris. Steps to reproduce these benchmarks provided. > > > > Sam > > > > On Tue, Dec 20, 2011 at 1:20 PM, Igor Mozolevsky wrote: > > > >> Interestingly, while people seem to be (arguably rightly) focused on > >> criticising Phoronix's benchmarking, nobody has offered an alternative > >> benchmark; and while (again, arguably rightly) it is important to > >> benchmark real world performance, equally, nobody has offered any > >> numbers in relation to, for example, HTTP or SMTP, or any other "real > >> world"-application torture tests done on the aforementioned two > >> platforms... IMO, this just goes to show that "doing is hard" and > >> "criticising is much easier" (yes, I am aware of the irony involved in > >> making this statement, but someone has to!) > >> > >> > >> Cheers, > >> Igor M :-) > >> _______________________________________________ > >> freebsd-current@freebsd.org mailing list > >> http://lists.freebsd.org/mailman/listinfo/freebsd-current > >> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" > >> > > Thanks for those numbers. > Impressive how Matthew Dillon's project jumps forward now. And it is > still impressive to see that the picture is still in the right place > when it comes to a comparison to Linux. > Also, OpenIndiana shows an impressive performance. Preface to my long post below: The things being discussed here are benchmarks, as in "how much work can you get out of Thing". This is VERY DIFFERENT from testing interactivity in a scheduler, which is more of a test that says "when Thing X is executed while heavier-Thing Y is also being executed, how much interaction is lost in Thing X". The reason people notice this when using Xorg is because it's visual, in an environment where responsiveness is absolutely mandatory above all else. Nobody is going to put up with a system where during a buildworld they go to move a window or click a mouse button or type a key and find that the window doesn't move, the mouse click is lost, or the key typed has gone into the bit bucket -- or, that those things are SEVERELY delayed, to the point where interactivity is crap. I just want to make that clear to folks. This immense thread has been with regards to the latter -- bad interactivity/responsiveness on a system which was undergoing load that SHOULD be distributed "more evenly" across the system *while* keeping interactivity/responsiveness high. Historically nice/renice has been used for this task, but that was when kernels were a little less complex and I/O subsystems were less complex. Remember: we've now got schedulers for each type of thing, and who gets what priority? You get my point I'm sure. So remember: this was to discuss that aspect, with regards to ULE vs. 4BSD schedulers. Now, back to the benchmarks: This also interested me: * Linux system crashed http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00008.html * OpenIndiana system crashed same way as Linux system http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00017.html I cannot help but wonder if the Linux and OpenIndiana installations were more stressful on the hardware -- getting more out of the system, maybe resulting in increased power/load, which in turn resulted in the systems locking up (shoddy PSU, unstable mainboard, MCH problems, etc.). My point is that Francois states these things in such a way to imply that "DragonflyBSD was more stable", when in fact I happen to wonder the opposite point -- that is to say, Linux and OpenIndiana were trying to use the hardware more-so than DragonflyBSD, thus tickled what may be a hardware-level problem. > But this is only one suite of testing. Scientific Linux is supposed to > give the best performance for scientifi purposes, i.e. for longhaul > calculations, much numerical stuff. It outperforms in a typical server > application FreeBSd, were "FreeBSD shoulkd have the power to serve". > > Is the postgresql benchmark the only way to benchmark? I sure hope not. But you know what's equally as interesting? This: http://people.freebsd.org/~kris/scaling/ Specifically circa 2008: http://people.freebsd.org/~kris/scaling/4cpu-pgsql.png http://people.freebsd.org/~kris/scaling/pgsql-16cpu-2.png http://people.freebsd.org/~kris/scaling/pgsql-16cpu.png Now, I don't know if what was used in those ("pgsql sysbench") was the same thing as "pg_bench" in the DragonflyBSD tests, but if so, the numbers are different to a point that is preposterous. There's also this: http://people.freebsd.org/~kris/scaling/pgsql-ncpu.png Now, compare those numbers to the TPS numbers shown here: http://dl.wolfpond.org/Pg-benchmarks.pdf So um... yeah. Now, if someone here is going to say "well, what was tested by Kris was FreeBSD 7.0, while what was tested by Francois was FreeBSD 9.0, and there have been improvements", then I ask that someone show me where the improvements are that would exhibit a 4-8x performance increase in some cases. This rambling of mine is the same rambling I posted earlier in this thread. There needs to be a consistent, standardised way of testing this stuff. Every system tested tuned the exact same way, software configured the same way, absolutely no quirks applied, etc.. Otherwise we end up with "mixed results" as shown above. Much to the disapproval of others, the Phoronix test suite is supposed to be that "standard". Meaning, it's a suite you're supposed to be able to install and thus ensures that, aside from compiler used and any system tests, that the same code is being used regardless of what system and OS it's on. Have I ever used it? No. And it's important that I admit that up front, because being honest is necessary. > Well, this inspires me to gather together all the benchmarks someone > could find. There were lots of compalins about FreeBSD's poor > performance with BIND - once a domain of FreeBSD. Network performance > seems also to be an issue if it comes to scalability. > It would be nice to see what portion of the raw CPU/GPU power the OS > (FreeBSD, Linux ...) delivers to scientific applications. Kris Kenneway's "BIND benchmark" that was released a long time ago touched base on this. Remember: these plots show nothing other than number of queries per second correlated with number of DNS server threads (since BIND does have a 1:1 thread-to-CPU creation ratio): http://people.freebsd.org/~kris/scaling/bind-pt.png http://people.freebsd.org/~kris/scaling/bind-pt-2.png http://people.freebsd.org/~kris/scaling/bind-pt-gige.png > I only know some kind of benchmarks, BYTE UNIX benchmark, LINPACK test > ... Does someone know a site to look for a couple of benchmarks to test > > a) memory system > b) scalability (apart from pgbench) > c) network performance/throughput/network scalability > d) portion of CPU performance the system delivers for numerical > applications to the user apart from the system's own consumption > e) disk I/O performance and scalability > > it would also be nice to discuss some nice settings and performance > tunings for FreeBSD for several scenarios. I guess, starting developing > benchmarking test scenarios for several purposes would lead faster to > real numbers and non polemic than weird discussions ... All I wish is that we had some kind of "test suite" of our own, maybe as a port, maybe in the base system, which could really help with all of this. Something consistent. Now I'm switching back to discussing interactivity/responsiveness tests: Attilio Rao did comment in this thread to me, giving me some test methodologies for testing interactivity during two types of simultaneous loads -- but one involves dnetc, which I imagine means I'd need to get familiar with that whole thing. http://lists.freebsd.org/pipermail/freebsd-stable/2011-December/064936.html I haven't responded to his post yet (this thread is so long and tedious that I'm having serious problems following it + remembering all the details -- am I the only one who feels daunted by this? God I hope not), but his insights are, as always, beneficial, but also overwhelming. Furthermore, I do not have 16-core or 24-core systems to test on -- I have single-CPU, quad-core and dual-core systems to test on. I am a firm believer these are going to make up the majority of the FreeBSD userbase (desktop and server environments). Extreme hardware (e.g. quad CPU with 12 cores per CPU) can be tested too, but let's at least pick a demographic to start with. Again: the FreeBSD users and administrative community want to help. All of us do. We just need to know exactly what we should be doing to test, and what exactly we're testing for. I'll be blunt while choosing to play the Idiot Admin for a moment: I'd be much happier if someone had a tarball of shell scripts and things which could be used to test these things. Lots of things need to be kept in mind, such as if someone is running the "client" test on the same box as the "server" test, and things like "the test data is written to a local filesystem, with echo/printf statements constantly flushed" (great, now we're causing I/O load on top of our tests!), which to me means we should probably be using something like mdconfig(8) to create a temporary filesystem to store logs/data results. The KTR stuff Atillio and many others have requested, I think, will be the most beneficial way to get the developers the data they need. I had no idea about it until I found out that KTR was something completely different than ktrace. I still haven't found the time to do all of this, BTW, and for that I apologise. The reason has to do with time at work + personal desire to do it. When I get a daunting task, I tend to get... well, not depressed, but "scared" of the massive undertaking since it involves lots of recurring tests, reboots, etc. -- hours of work -- and if I get that wrong, it's wasted effort (thus wasted developer time). I want to get it right. :-) -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 00:28:08 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 239181065670; Wed, 21 Dec 2011 00:28:08 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 8E64C8FC0C; Wed, 21 Dec 2011 00:28:07 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RdA2Q-0002E4-Ou>; Wed, 21 Dec 2011 01:28:06 +0100 Received: from e178016253.adsl.alicedsl.de ([85.178.16.253] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RdA2Q-0003rz-DI>; Wed, 21 Dec 2011 01:28:06 +0100 Message-ID: <4EF12815.2090805@zedat.fu-berlin.de> Date: Wed, 21 Dec 2011 01:28:05 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111109 Thunderbird/8.0 MIME-Version: 1.0 To: Jeremy Chadwick References: <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <20111220232925.GA55953@icarus.home.lan> In-Reply-To: <20111220232925.GA55953@icarus.home.lan> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig3B0CE417BCECAA1895E10BDC" X-Originating-IP: 85.178.16.253 Cc: "Samuel J. Greear" , freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 00:28:08 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig3B0CE417BCECAA1895E10BDC Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/21/11 00:29, Jeremy Chadwick wrote: > On Tue, Dec 20, 2011 at 11:54:23PM +0100, O. Hartmann wrote: >> On 12/20/11 22:45, Samuel J. Greear wrote: >>> http://www.osnews.com/story/25334/DragonFly_BSD_MP_Performance_Signif= icantly_Improved >>> >>> PostgreSQL tests, see the linked PDF for #'s on FreeBSD, DragonFly, L= inux >>> and Solaris. Steps to reproduce these benchmarks provided. >>> >>> Sam >>> >>> On Tue, Dec 20, 2011 at 1:20 PM, Igor Mozolevsky wrote: >>> >>>> Interestingly, while people seem to be (arguably rightly) focused on= >>>> criticising Phoronix's benchmarking, nobody has offered an alternati= ve >>>> benchmark; and while (again, arguably rightly) it is important to >>>> benchmark real world performance, equally, nobody has offered any >>>> numbers in relation to, for example, HTTP or SMTP, or any other "rea= l >>>> world"-application torture tests done on the aforementioned two >>>> platforms... IMO, this just goes to show that "doing is hard" and >>>> "criticising is much easier" (yes, I am aware of the irony involved = in >>>> making this statement, but someone has to!) >>>> >>>> >>>> Cheers, >>>> Igor M :-) >>>> _______________________________________________ >>>> freebsd-current@freebsd.org mailing list >>>> http://lists.freebsd.org/mailman/listinfo/freebsd-current >>>> To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebs= d.org" >>>> >> >> Thanks for those numbers. >> Impressive how Matthew Dillon's project jumps forward now. And it is >> still impressive to see that the picture is still in the right place >> when it comes to a comparison to Linux. >> Also, OpenIndiana shows an impressive performance. >=20 > Preface to my long post below: >=20 > The things being discussed here are benchmarks, as in "how much work > can you get out of Thing". This is VERY DIFFERENT from testing > interactivity in a scheduler, which is more of a test that says "when > Thing X is executed while heavier-Thing Y is also being executed, how > much interaction is lost in Thing X". >=20 > The reason people notice this when using Xorg is because it's visual, > in an environment where responsiveness is absolutely mandatory above al= l > else. Nobody is going to put up with a system where during a buildworl= d > they go to move a window or click a mouse button or type a key and find= > that the window doesn't move, the mouse click is lost, or the key typed= > has gone into the bit bucket -- or, that those things are SEVERELY > delayed, to the point where interactivity is crap. I whitnessed sticky, jumpy and non-responsive-for seconds FreeBSD servers (serving homes, NFS/SAMBA and PostgreSQL database (small)). Those "seconds" where enough to cut a ssh line. Not funny. Network traffic droped significantly. X/Desktop makes the problem visible, indeed. But not seeing it does not mean it isn't there. This might be the reason why FreeBSD is so much behind when it comes to X= ? >=20 > I just want to make that clear to folks. This immense thread has been > with regards to the latter -- bad interactivity/responsiveness on a > system which was undergoing load that SHOULD be distributed "more > evenly" across the system *while* keeping interactivity/responsiveness > high. Historically nice/renice has been used for this task, but that > was when kernels were a little less complex and I/O subsystems were les= s > complex. Remember: we've now got schedulers for each type of thing, > and who gets what priority? You get my point I'm sure. >=20 > So remember: this was to discuss that aspect, with regards to ULE vs. > 4BSD schedulers. >=20 > Now, back to the benchmarks: >=20 > This also interested me: >=20 > * Linux system crashed > http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00008.html= >=20 > * OpenIndiana system crashed same way as Linux system > http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00017.html= >=20 > I cannot help but wonder if the Linux and OpenIndiana installations wer= e > more stressful on the hardware -- getting more out of the system, maybe= > resulting in increased power/load, which in turn resulted in the system= s > locking up (shoddy PSU, unstable mainboard, MCH problems, etc.). Is FreeBSD supposed to run on dumpyard equipment? In former times, freeBSD was used on high value hardware, not the decomissioned crap with shoddy PSUs or whatsoever. If I need a server, I care about quality hardware as I do for my lab's box and my own box at home. I expect a "server garde" hardware to act like that and I expect the operating system to get the maximum out of that hardware. Otherwise it is not worth one shot. >=20 > My point is that Francois states these things in such a way to imply > that "DragonflyBSD was more stable", when in fact I happen to wonder th= e > opposite point -- that is to say, Linux and OpenIndiana were trying to > use the hardware more-so than DragonflyBSD, thus tickled what may be a > hardware-level problem. >=20 >> But this is only one suite of testing. Scientific Linux is supposed to= >> give the best performance for scientifi purposes, i.e. for longhaul >> calculations, much numerical stuff. It outperforms in a typical server= >> application FreeBSd, were "FreeBSD shoulkd have the power to serve". >> >> Is the postgresql benchmark the only way to benchmark? >=20 > I sure hope not. But you know what's equally as interesting? This: >=20 > http://people.freebsd.org/~kris/scaling/ >=20 > Specifically circa 2008: >=20 > http://people.freebsd.org/~kris/scaling/4cpu-pgsql.png > http://people.freebsd.org/~kris/scaling/pgsql-16cpu-2.png > http://people.freebsd.org/~kris/scaling/pgsql-16cpu.png >=20 > Now, I don't know if what was used in those ("pgsql sysbench") was the > same thing as "pg_bench" in the DragonflyBSD tests, but if so, the > numbers are different to a point that is preposterous. >=20 > There's also this: >=20 > http://people.freebsd.org/~kris/scaling/pgsql-ncpu.png >=20 > Now, compare those numbers to the TPS numbers shown here: >=20 > http://dl.wolfpond.org/Pg-benchmarks.pdf >=20 > So um... yeah. Now, if someone here is going to say "well, what > was tested by Kris was FreeBSD 7.0, while what was tested by Francois > was FreeBSD 9.0, and there have been improvements", then I ask that > someone show me where the improvements are that would exhibit a 4-8x > performance increase in some cases. >=20 > This rambling of mine is the same rambling I posted earlier in this > thread. There needs to be a consistent, standardised way of testing > this stuff. Every system tested tuned the exact same way, software > configured the same way, absolutely no quirks applied, etc.. Otherwise= > we end up with "mixed results" as shown above. Didn't got M. Larabel at Phoronix this half the way, except the ZFS fault= ? >=20 > Much to the disapproval of others, the Phoronix test suite is supposed > to be that "standard". Meaning, it's a suite you're supposed to be abl= e > to install and thus ensures that, aside from compiler used and any > system tests, that the same code is being used regardless of what syste= m > and OS it's on. Have I ever used it? No. And it's important that I > admit that up front, because being honest is necessary. >=20 >> Well, this inspires me to gather together all the benchmarks someone >> could find. There were lots of compalins about FreeBSD's poor >> performance with BIND - once a domain of FreeBSD. Network performance >> seems also to be an issue if it comes to scalability. >> It would be nice to see what portion of the raw CPU/GPU power the OS >> (FreeBSD, Linux ...) delivers to scientific applications. >=20 > Kris Kenneway's "BIND benchmark" that was released a long time ago > touched base on this. Remember: these plots show nothing other than > number of queries per second correlated with number of DNS server > threads (since BIND does have a 1:1 thread-to-CPU creation ratio): >=20 > http://people.freebsd.org/~kris/scaling/bind-pt.png > http://people.freebsd.org/~kris/scaling/bind-pt-2.png > http://people.freebsd.org/~kris/scaling/bind-pt-gige.png >=20 >> I only know some kind of benchmarks, BYTE UNIX benchmark, LINPACK test= >> ... Does someone know a site to look for a couple of benchmarks to tes= t >> >> a) memory system >> b) scalability (apart from pgbench) >> c) network performance/throughput/network scalability >> d) portion of CPU performance the system delivers for numerical >> applications to the user apart from the system's own consumption >> e) disk I/O performance and scalability >> >> it would also be nice to discuss some nice settings and performance >> tunings for FreeBSD for several scenarios. I guess, starting developin= g >> benchmarking test scenarios for several purposes would lead faster to >> real numbers and non polemic than weird discussions ... >=20 > All I wish is that we had some kind of "test suite" of our own, maybe a= s > a port, maybe in the base system, which could really help with all of > this. Something consistent. Why not supporting those guys at Phoronix? If we start with "our own", then we end up as you described above - not comparable, different numbers on different platforms, no normalization possible. >=20 > Now I'm switching back to discussing interactivity/responsiveness tests= : >=20 > Attilio Rao did comment in this thread to me, giving me some test > methodologies for testing interactivity during two types of simultaneou= s > loads -- but one involves dnetc, which I imagine means I'd need to get > familiar with that whole thing. >=20 > http://lists.freebsd.org/pipermail/freebsd-stable/2011-December/064936.= html >=20 > I haven't responded to his post yet (this thread is so long and tedious= > that I'm having serious problems following it + remembering all the > details -- am I the only one who feels daunted by this? God I hope > not), but his insights are, as always, beneficial, but also > overwhelming. Furthermore, I do not have 16-core or 24-core systems > to test on -- I have single-CPU, quad-core and dual-core systems to tes= t > on. I am a firm believer these are going to make up the majority of th= e > FreeBSD userbase (desktop and server environments). Extreme hardware (= e.g. > quad CPU with 12 cores per CPU) can be tested too, but let's at least > pick a demographic to start with. >=20 > Again: the FreeBSD users and administrative community want to help. Al= l > of us do. We just need to know exactly what we should be doing to test= , > and what exactly we're testing for. I'll be blunt while choosing to > play the Idiot Admin for a moment: I'd be much happier if someone had a= > tarball of shell scripts and things which could be used to test these > things. Lots of things need to be kept in mind, such as if someone is > running the "client" test on the same box as the "server" test, and > things like "the test data is written to a local filesystem, with > echo/printf statements constantly flushed" (great, now we're causing I/= O > load on top of our tests!), which to me means we should probably be > using something like mdconfig(8) to create a temporary filesystem to > store logs/data results. >=20 > The KTR stuff Atillio and many others have requested, I think, will be > the most beneficial way to get the developers the data they need. I ha= d > no idea about it until I found out that KTR was something completely > different than ktrace. >=20 > I still haven't found the time to do all of this, BTW, and for that I > apologise. The reason has to do with time at work + personal desire to= > do it. When I get a daunting task, I tend to get... well, not > depressed, but "scared" of the massive undertaking since it involves > lots of recurring tests, reboots, etc. -- hours of work -- and if I get= > that wrong, it's wasted effort (thus wasted developer time). I want to= > get it right. :-) >=20 --------------enig3B0CE417BCECAA1895E10BDC Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO8SgVAAoJEOgBcD7A/5N8hgIH/3OXj5P3KAZ7bAx0Xdcg93EP qU1qvXqmbf/H4QCYxWIEk7NG+TT5MoTIoRN9393F1n1+nkn8QRjU27NLqnPwFsbx cRk8VWQXtJ58DImkfHnAhmuScfScPrS5u5CDRs5LXS7cPT9r6NPZ6uyNr6qcEA7i Y5urmT8RLtPMZIcJRJx4i8BU0Wg314QxfH2AiOjiiS8vbIcXk3gYB+2C7VnPM2Le nvo2OYPW5T3t6KSwW/T2ikXSTNgKqy6YL9hX6Q/xZOvG/ZvXS/QkVNmnKuUgroqU A28ILznYmqnACfXrV4yzJAb04SrzxxCN8BgOwOs/zdzzzuQximfETIDNn44GYpY= =rq59 -----END PGP SIGNATURE----- --------------enig3B0CE417BCECAA1895E10BDC-- From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 01:18:14 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6F6B2106566B; Wed, 21 Dec 2011 01:18:14 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 3263C8FC13; Wed, 21 Dec 2011 01:18:13 +0000 (UTC) Received: from palm-64-28-152-131.palm.com ([64.28.152.131] helo=LT740055CZ0L1.palm1.palmone.com) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1RdAot-0007Xv-N9; Tue, 20 Dec 2011 19:18:11 -0600 Message-ID: <4EF133D0.4050800@phoronix.com> Date: Tue, 20 Dec 2011 17:18:08 -0800 From: Matthew Tippett User-Agent: Mozilla/5.0 (X11; Linux i686; rv:9.0) Gecko/20111214 Thunderbird/9.0 MIME-Version: 1.0 To: "O. Hartmann" References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF10088.1010409@zedat.fu-berlin.de> In-Reply-To: <4EF10088.1010409@zedat.fu-berlin.de> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Cc: freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , Jeremy Chadwick , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 01:18:14 -0000 For such a system, the greatest immediate value would be to attempt to reproduce the benchmarks in question. Install PTS from www.phoronix-test-suite.com or freshports.org. Run the benchmark against those used in the article phoronix-test-suite benchmark 1112113-AR-ORACLELIN37 You will be asked to push the comparison up to openbenchmarking at the end. Matthew On 12/20/2011 01:39 PM, O. Hartmann wrote: > On 12/20/11 21:20, Igor Mozolevsky wrote: >> Interestingly, while people seem to be (arguably rightly) focused on >> criticising Phoronix's benchmarking, nobody has offered an alternative >> benchmark; and while (again, arguably rightly) it is important to >> benchmark real world performance, equally, nobody has offered any >> numbers in relation to, for example, HTTP or SMTP, or any other "real >> world"-application torture tests done on the aforementioned two >> platforms... IMO, this just goes to show that "doing is hard" and >> "criticising is much easier" (yes, I am aware of the irony involved in >> making this statement, but someone has to!) >> >> >> Cheers, >> Igor M :-) > Unfortunately, M. Larabel is the only one who's performing benchmarks on > FreeBSD, comparing its performance to the Linux-opponents. Adn indeed, > there is a lot of criticism, but no alternative. > I said unfortunately - not offensive - since Larabel and Phoronix are > sadly the only ones who do actually such bechmarking. > > It would be much more nicer and kind to support those people. > > Well, in January/February we get new hardware. One box is supposed to do > number crunching via 12 cores and a TESLA GPU. My colleague is > developing a high parallelized peice of software for satellite data > transformation. The software package is CPU bound, partially GPU, but > massively memory hungry (96 to 128 GB RAM is needed). > What I can offer is, since I will also work on that machine and I've > free hand to administer, in the spare time of doing my PhD, installing > FreeBSD 9.0/10.0 besides SuSe Linux and looking forward having one ZFS > data storage drive for homes, so both systems can perform on a most > recent ZFS. I'm new to Linux, not a BSD guru, nor I'm a professional > programmer/developer. My skills are sufficient for the daily scientific > work. So, without pressure, I'm willing to perform some HPC benchmarks > under advice if the day comes and those interested in bare numbers of > FreeBSD vs. Linux performance with a real-world-scientific application. > > I would appreciate to see some of the developers and/or FreeBSD hackers > to help Phoronix setting up a proper testenvironment instead of bashing > M. Larabel and his fellows. > > Regards, > Oliver > From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 01:29:31 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 29EA01065675; Wed, 21 Dec 2011 01:29:31 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 992F88FC13; Wed, 21 Dec 2011 01:29:30 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so9273525vcb.13 for ; Tue, 20 Dec 2011 17:29:29 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=uiHoaCecTy8i62ljEyDn8TNea/c6xahUxa/A1fPBeb8=; b=Pzqnx0y4tN2mVFfGo8rcVLAmixoHR43lvNtAchgG9UNe85vmr3QyydHPk94wcKAioF 0jQgWZ7uYvYfOk3KxQ6DzFXzKcAC6VHaL1F4RX94LCRuNSvmQ2VySZRbDGvqAVwuLEph QJ3m2D6h7ZlDla07+qPflASsqkV+8ZJMLdHE4= MIME-Version: 1.0 Received: by 10.220.232.10 with SMTP id js10mr3491829vcb.2.1324430969838; Tue, 20 Dec 2011 17:29:29 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.158.104 with HTTP; Tue, 20 Dec 2011 17:29:29 -0800 (PST) In-Reply-To: <4EF133D0.4050800@phoronix.com> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF10088.1010409@zedat.fu-berlin.de> <4EF133D0.4050800@phoronix.com> Date: Tue, 20 Dec 2011 17:29:29 -0800 X-Google-Sender-Auth: 62l0R5YMedc4zy-sUOAXdflMBKE Message-ID: From: Adrian Chadd To: Matthew Tippett Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: FreeBSD Stable Mailing List , Current FreeBSD , Igor Mozolevsky , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 01:29:31 -0000 Is there a specific version of the test suite that should be used, to compare against the published results? Adrian On 20 December 2011 17:18, Matthew Tippett wrote: > For such a system, the greatest immediate value would be to attempt to > reproduce the benchmarks in question. > > Install PTS from www.phoronix-test-suite.com or freshports.org. > > Run the benchmark against those used in the article > > =A0 =A0phoronix-test-suite benchmark 1112113-AR-ORACLELIN37 > > You will be asked to push the comparison up to openbenchmarking at the en= d. > > Matthew > > > On 12/20/2011 01:39 PM, O. Hartmann wrote: >> >> On 12/20/11 21:20, Igor Mozolevsky wrote: >>> >>> Interestingly, while people seem to be (arguably rightly) focused on >>> criticising Phoronix's benchmarking, nobody has offered an alternative >>> benchmark; and while (again, arguably rightly) it is important to >>> benchmark real world performance, equally, nobody has offered any >>> numbers in relation to, for example, HTTP or SMTP, or any other "real >>> world"-application torture tests done on the aforementioned two >>> platforms... IMO, this just goes to show that "doing is hard" and >>> "criticising is much easier" (yes, I am aware of the irony involved in >>> making this statement, but someone has to!) >>> >>> >>> Cheers, >>> Igor M :-) >> >> Unfortunately, M. Larabel is the only one who's performing benchmarks on >> FreeBSD, comparing its performance to the Linux-opponents. Adn indeed, >> there is a lot of criticism, but no alternative. >> I said unfortunately - not offensive - since Larabel and Phoronix are >> sadly the only ones who do actually such bechmarking. >> >> It would be much more nicer and kind to support those people. >> >> Well, in January/February we get new hardware. One box is supposed to do >> number crunching via 12 cores and a TESLA GPU. My colleague is >> developing a high parallelized peice of software for satellite data >> transformation. The software package is CPU bound, partially GPU, but >> massively memory hungry (96 to 128 GB RAM is needed). >> What I can offer is, since I will also work on that machine and I've >> free hand to administer, in the spare time of doing my PhD, installing >> FreeBSD 9.0/10.0 besides SuSe Linux and looking forward having one ZFS >> data storage drive for homes, so both systems can perform on a most >> recent ZFS. I'm new to Linux, not a BSD guru, nor I'm a professional >> programmer/developer. My skills are sufficient for the daily scientific >> work. So, without pressure, I'm willing to perform some HPC benchmarks >> under advice if the day comes and those interested in bare numbers of >> FreeBSD vs. Linux performance with a real-world-scientific application. >> >> I would appreciate to see some of the developers and/or FreeBSD hackers >> to help Phoronix setting up a proper testenvironment instead of bashing >> M. Larabel and his fellows. >> >> Regards, >> Oliver >> > > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 01:37:33 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id BDE8E106566B; Wed, 21 Dec 2011 01:37:33 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 888C58FC14; Wed, 21 Dec 2011 01:37:33 +0000 (UTC) Received: from mobile-166-205-136-198.mycingular.net ([166.205.136.198] helo=www.palm.com) by phx1.phoronix.com with esmtpa (Exim 4.69) (envelope-from ) id 1RdB7b-0007Hu-W1; Tue, 20 Dec 2011 19:37:32 -0600 Date: Tue, 20 Dec 2011 17:37:29 -0800 From: To: "Adrian Chadd" In-Reply-To: X-Mailer: Palm webOS X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Message-Id: <20111221013733.BDE8E106566B@hub.freebsd.org> Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: FreeBSD Stable Mailing List , Current FreeBSD , Igor Mozolevsky , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 01:37:33 -0000 The benchmarks themselves are versioned. So in general most of the av= ailable versions of PTS itself should be fine. PTS can be considered = an execution shell that doesn't affect the benchmark itself. Note th= at you'll download a pile of the benchmarks, build and install them. = Then you run about 49 individual steps. Matthew -- Sent from my HP Pre3 _________________________________________________________________ On Dec 20, 2011 5:30 PM, Adrian Chadd = ; wrote: Is there a specific version of the test suite that = should be used, to=0D compare against the published results?=0D =0D=0D Adrian=0D =0D On 20 December 2011 17:18, Matthew Tippett <= ;matthew@phoronix.com> wrote:=0D > For such a system, the greatest= immediate value would be to attempt to=0D > reproduce the benchmarks= in question.=0D >=0D > Install PTS from www.phoronix-test-suit= e.com or freshports.org.=0D >=0D > Run the benchmark against th= ose used in the article=0D >=0D > =C2=A0 =C2=A0phoronix-test-su= ite benchmark 1112113-AR-ORACLELIN37=0D >=0D > You will be aske= d to push the comparison up to openbenchmarking at the end.=0D >=0D> Matthew=0D >=0D >=0D > On 12/20/2011 01:39 PM, O. = Hartmann wrote:=0D >>=0D >> On 12/20/11 21:20, Igor Mozol= evsky wrote:=0D >>>=0D >>> Interestingly, while peo= ple seem to be (arguably rightly) focused on=0D >>> criticising= Phoronix's benchmarking, nobody has offered an alternative=0D >>&= gt; benchmark; and while (again, arguably rightly) it is important to=0D >>> benchmark real world performance, equally, nobody has offered= any=0D >>> numbers in relation to, for example, HTTP or SMTP, = or any other "real=0D >>> world"-application torture tests done= on the aforementioned two=0D >>> platforms... IMO, this just g= oes to show that "doing is hard" and=0D >>> "criticising is muc= h easier" (yes, I am aware of the irony involved in=0D >>> maki= ng this statement, but someone has to!)=0D >>>=0D >>&g= t;=0D >>> Cheers,=0D >>> Igor M :-)=0D >>= =0D >> Unfortunately, M. Larabel is the only one who's performing = benchmarks on=0D >> FreeBSD, comparing its performance to the Linu= x-opponents. Adn indeed,=0D >> there is a lot of criticism, but no= alternative.=0D >> I said unfortunately - not offensive - since L= arabel and Phoronix are=0D >> sadly the only ones who do actually = such bechmarking.=0D >>=0D >> It would be much more nicer= and kind to support those people.=0D >>=0D >> Well, in J= anuary/February we get new hardware. One box is supposed to do=0D >&g= t; number crunching via 12 cores and a TESLA GPU. My colleague is=0D >= ;> developing a high parallelized peice of software for satellite data= =0D >> transformation. The software package is CPU bound, partiall= y GPU, but=0D >> massively memory hungry (96 to 128 GB RAM is need= ed).=0D >> What I can offer is, since I will also work on that mac= hine and I've=0D >> free hand to administer, in the spare time of = doing my PhD, installing=0D >> FreeBSD 9.0/10.0 besides SuSe Linux= and looking forward having one ZFS=0D >> data storage drive for h= omes, so both systems can perform on a most=0D >> recent ZFS. I'm = new to Linux, not a BSD guru, nor I'm a professional=0D >> program= mer/developer. My skills are sufficient for the daily scientific=0D >= > work. So, without pressure, I'm willing to perform some HPC benchmarks= =0D >> under advice if the day comes and those interested in bare = numbers of=0D >> FreeBSD vs. Linux performance with a real-world-s= cientific application.=0D >>=0D >> I would appreciate to = see some of the developers and/or FreeBSD hackers=0D >> to help Ph= oronix setting up a proper testenvironment instead of bashing=0D >>= ; M. Larabel and his fellows.=0D >>=0D >> Regards,=0D = >> Oliver=0D >>=0D >=0D > ______________________= _________________________=0D > freebsd-stable@freebsd.org mailing lis= t=0D > http://lists.freebsd.org/mailman/listinfo/freebsd-stable=0D > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.= org"=0D _______________________________________________=0D freebsd-pe= rformance@freebsd.org mailing list=0D http://lists.freebsd.org/mailman/l= istinfo/freebsd-performance=0D To unsubscribe, send any mail to "freebsd= -performance-unsubscribe@freebsd.org"=0D From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 01:38:33 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 45152106564A; Wed, 21 Dec 2011 01:38:33 +0000 (UTC) (envelope-from michael.larabel@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 0EC348FC2A; Wed, 21 Dec 2011 01:38:32 +0000 (UTC) Received: from c-98-193-96-120.hsd1.il.comcast.net ([98.193.96.120] helo=[172.16.93.133]) by phx1.phoronix.com with esmtpsa (TLSv1:AES256-SHA:256) (Exim 4.69) (envelope-from ) id 1RdB8a-0007JA-Gg; Tue, 20 Dec 2011 19:38:32 -0600 Message-ID: <4EF13895.9060307@phoronix.com> Date: Tue, 20 Dec 2011 19:38:29 -0600 From: Michael Larabel User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Adrian Chadd References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF10088.1010409@zedat.fu-berlin.de> <4EF133D0.4050800@phoronix.com> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com X-Mailman-Approved-At: Wed, 21 Dec 2011 01:43:43 +0000 Cc: FreeBSD Stable Mailing List , Matthew Tippett , Current FreeBSD , Igor Mozolevsky , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 01:38:33 -0000 Any version is fine that's PTS 3.0 or newer in terms of being compatible, since the test profiles are versioned separately and automatically fetched to match the result file. However, I'd recommended the newest (PTS 3.6) as it contains the best FreeBSD support at present in terms of hardware/software information parsing (for the automated table), etc. Michael On 12/20/2011 07:29 PM, Adrian Chadd wrote: > Is there a specific version of the test suite that should be used, to > compare against the published results? > > > Adrian > > On 20 December 2011 17:18, Matthew Tippett wrote: >> For such a system, the greatest immediate value would be to attempt to >> reproduce the benchmarks in question. >> >> Install PTS from www.phoronix-test-suite.com or freshports.org. >> >> Run the benchmark against those used in the article >> >> phoronix-test-suite benchmark 1112113-AR-ORACLELIN37 >> >> You will be asked to push the comparison up to openbenchmarking at the end. >> >> Matthew >> >> >> On 12/20/2011 01:39 PM, O. Hartmann wrote: >>> On 12/20/11 21:20, Igor Mozolevsky wrote: >>>> Interestingly, while people seem to be (arguably rightly) focused on >>>> criticising Phoronix's benchmarking, nobody has offered an alternative >>>> benchmark; and while (again, arguably rightly) it is important to >>>> benchmark real world performance, equally, nobody has offered any >>>> numbers in relation to, for example, HTTP or SMTP, or any other "real >>>> world"-application torture tests done on the aforementioned two >>>> platforms... IMO, this just goes to show that "doing is hard" and >>>> "criticising is much easier" (yes, I am aware of the irony involved in >>>> making this statement, but someone has to!) >>>> >>>> >>>> Cheers, >>>> Igor M :-) >>> Unfortunately, M. Larabel is the only one who's performing benchmarks on >>> FreeBSD, comparing its performance to the Linux-opponents. Adn indeed, >>> there is a lot of criticism, but no alternative. >>> I said unfortunately - not offensive - since Larabel and Phoronix are >>> sadly the only ones who do actually such bechmarking. >>> >>> It would be much more nicer and kind to support those people. >>> >>> Well, in January/February we get new hardware. One box is supposed to do >>> number crunching via 12 cores and a TESLA GPU. My colleague is >>> developing a high parallelized peice of software for satellite data >>> transformation. The software package is CPU bound, partially GPU, but >>> massively memory hungry (96 to 128 GB RAM is needed). >>> What I can offer is, since I will also work on that machine and I've >>> free hand to administer, in the spare time of doing my PhD, installing >>> FreeBSD 9.0/10.0 besides SuSe Linux and looking forward having one ZFS >>> data storage drive for homes, so both systems can perform on a most >>> recent ZFS. I'm new to Linux, not a BSD guru, nor I'm a professional >>> programmer/developer. My skills are sufficient for the daily scientific >>> work. So, without pressure, I'm willing to perform some HPC benchmarks >>> under advice if the day comes and those interested in bare numbers of >>> FreeBSD vs. Linux performance with a real-world-scientific application. >>> >>> I would appreciate to see some of the developers and/or FreeBSD hackers >>> to help Phoronix setting up a proper testenvironment instead of bashing >>> M. Larabel and his fellows. >>> >>> Regards, >>> Oliver >>> >> _______________________________________________ >> freebsd-stable@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-stable >> To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" > _______________________________________________ > freebsd-stable@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-stable > To unsubscribe, send any mail to "freebsd-stable-unsubscribe@freebsd.org" > From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 09:04:03 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 89244106564A for ; Wed, 21 Dec 2011 09:04:03 +0000 (UTC) (envelope-from ftigeot@wolfpond.org) Received: from sabik.zefyris.com (sabik.zefyris.com [IPv6:2001:7a8:bd07:2::254]) by mx1.freebsd.org (Postfix) with ESMTP id 032EB8FC13 for ; Wed, 21 Dec 2011 09:04:02 +0000 (UTC) Received: from sekishi.zefyris.com (sekishi.zefyris.com [IPv6:2001:7a8:bd07:2:219:d1ff:fe81:e03]) by sabik.zefyris.com (8.14.5/8.14.5) with ESMTP id pBL93wmI022217; Wed, 21 Dec 2011 10:03:58 +0100 (CET) Date: Wed, 21 Dec 2011 10:03:57 +0100 From: Francois Tigeot To: Jeremy Chadwick Message-ID: <20111221090357.GA982@sekishi.zefyris.com> References: <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <20111220232925.GA55953@icarus.home.lan> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20111220232925.GA55953@icarus.home.lan> User-Agent: Mutt/1.5.21 (2010-09-15) X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.7 (sabik.zefyris.com [IPv6:2001:7a8:bd07:2::254]); Wed, 21 Dec 2011 10:03:59 +0100 (CET) X-Mailman-Approved-At: Wed, 21 Dec 2011 12:11:25 +0000 Cc: "Samuel J. Greear" , freebsd-performance@freebsd.org, Current FreeBSD , FreeBSD Stable Mailing List , kernel@crater.dragonflybsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 09:04:03 -0000 On Tue, Dec 20, 2011 at 03:29:25PM -0800, Jeremy Chadwick wrote: > > This also interested me: > > * Linux system crashed > http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00008.html > > * OpenIndiana system crashed same way as Linux system > http://leaf.dragonflybsd.org/mailarchive/kernel/2011-11/msg00017.html > > I cannot help but wonder if the Linux and OpenIndiana installations were > more stressful on the hardware -- getting more out of the system, maybe > resulting in increased power/load, which in turn resulted in the systems > locking up (shoddy PSU, unstable mainboard, MCH problems, etc.). > > My point is that Francois states these things in such a way to imply > that "DragonflyBSD was more stable", Same thing can be said for FreeBSD, only Linux and OpenIndiana crashed reliably if I remember correctly. > when in fact I happen to wonder the > opposite point -- that is to say, Linux and OpenIndiana were trying to > use the hardware more-so than DragonflyBSD, thus tickled what may be a > hardware-level problem. I actually ran the benchmarks on two different machines with the same hardware -- brand new Supermicro boxes with ECC memory and no cut corners. Since then, I've found I could stop the Linux crashes by disabling some options in the BIOS setup: - advanced ACPI settings (don't remember exactly which ones) - and a new WHEA one. WHEA means Windows Hardware Error Architecture. For all I know, it may have been the only culprit but I didn't have time to verify if the machines also ran fine with only this option disabled. -- Francois Tigeot From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 13:15:05 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AEB2E106566B for ; Wed, 21 Dec 2011 13:15:05 +0000 (UTC) (envelope-from schulra@earlham.edu) Received: from chkenon.earlham.edu (chkenon.earlham.edu [159.28.1.87]) by mx1.freebsd.org (Postfix) with ESMTP id 60CD28FC12 for ; Wed, 21 Dec 2011 13:15:05 +0000 (UTC) X-ASG-Debug-ID: 1324473300-037b9f16aa170100001-3XdwJY Received: from tdream.lly.earlham.edu (tdream.lly.earlham.edu [159.28.7.241]) by chkenon.earlham.edu with ESMTP id W1o9txvtChYcnEbL; Wed, 21 Dec 2011 08:15:00 -0500 (EST) X-Barracuda-Envelope-From: schulra@earlham.edu X-Barracuda-Apparent-Source-IP: 159.28.7.241 Date: Wed, 21 Dec 2011 08:16:21 -0500 (EST) From: Randy Schultz X-X-Sender: schulra@tdream.lly.earlham.edu To: Matthew Tippett In-Reply-To: <4EF11B57.7090007@phoronix.com> X-ASG-Orig-Subj: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server Message-ID: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> User-Agent: Alpine 2.00 (BSF 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Barracuda-Connect: tdream.lly.earlham.edu[159.28.7.241] X-Barracuda-Start-Time: 1324473300 X-Barracuda-URL: http://159.28.1.87:8000/cgi-mod/mark.cgi X-Virus-Scanned: by bsmtpd at earlham.edu X-Barracuda-Spam-Score: 0.89 X-Barracuda-Spam-Status: No, SCORE=0.89 using global scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=1000.0 tests=SARE_ADLTSUB4 X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.83704 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.89 SARE_ADLTSUB4 Apparent spam seems to contain porn subject Cc: freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 13:15:05 -0000 On Tue, 20 Dec 2011, Matthew Tippett spaketh thusly: -}There are still possible issues with those benchmarks. The Xeon has known -}problems scaling from 6 to 12 cores (well enabling the hyperthreading), so you -}may find that some platforms are penalized in performance if HT is turned on. -}See the scaling that Phoronix has done in -} -}http://openbenchmarking.org/result/1112166-AR-1112153AR03 -} -}Most systems are good with scaling on real cores, the hyperthreading (and for -}that matter the Bulldozer thread affinity) can really break performance. -}Different platforms have different behaviours. Benchmarking is a mucky -}business.. This brings up a good point. While I don't have any hard #'s, I suspect the vast majority of SA's do not have/spend much time tweaking this and tuning that. Order the box, drop the OS on it, install needed bits and go. Saying "oh for app X you need to tune these sysctl's", while it may be entirely true, kinda throws things out the window. It seems that once one starts down that slippery slope, it merely becomes a game of how much time to you have to "tune 1 more thing". ;> I think Phoronix has the right idea of just grabbing a stock box and not looking into what needs to be tweaked for a specific app. -- Randy (schulra@earlham.edu) 765.983.1283 <*> nosce te ipsum From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 13:28:16 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A38D81065670 for ; Wed, 21 Dec 2011 13:28:16 +0000 (UTC) (envelope-from tevans.uk@googlemail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 254EA8FC13 for ; Wed, 21 Dec 2011 13:28:15 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so9985350vcb.13 for ; Wed, 21 Dec 2011 05:28:15 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=googlemail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=bjYohqK6GPXcePTcBDs2VJshagtqgaLkkh4KYs6XzbQ=; b=DNlQ2Rj46qSKq/VUpPJSuoWk+kUox8TS45mAMOTGypeS+OGF8ubWyyGnN7ezSuE9li IFzx9hbdBk16B2czHjuk62zDTaq6Y088oCI9DsUvGn9eG0H1qTY6jZHwDHYLGVh3YwNy 3ZyoN2kO+06mj/7XnKdFpXglxI1Cqm2YcEtIQ= MIME-Version: 1.0 Received: by 10.220.66.70 with SMTP id m6mr4254367vci.57.1324474093738; Wed, 21 Dec 2011 05:28:13 -0800 (PST) Received: by 10.52.162.202 with HTTP; Wed, 21 Dec 2011 05:28:13 -0800 (PST) In-Reply-To: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> Date: Wed, 21 Dec 2011 13:28:13 +0000 Message-ID: From: Tom Evans To: Randy Schultz Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-performance@freebsd.org, Matthew Tippett Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 13:28:16 -0000 On Wed, Dec 21, 2011 at 1:16 PM, Randy Schultz wrote: > On Tue, 20 Dec 2011, Matthew Tippett spaketh thusly: > > -}There are still possible issues with those benchmarks. =C2=A0The Xeon h= as known > -}problems scaling from 6 to 12 cores (well enabling the hyperthreading),= so you > -}may find that some platforms are penalized in performance if HT is turn= ed on. > -}See the scaling that Phoronix has done in > -} > -}http://openbenchmarking.org/result/1112166-AR-1112153AR03 > -} > -}Most systems are good with scaling on real cores, the hyperthreading (a= nd for > -}that matter the Bulldozer thread affinity) can really break performance= . > -}Different platforms have different behaviours. =C2=A0Benchmarking is a = mucky > -}business.. > > This brings up a good point. =C2=A0While I don't have any hard #'s, I sus= pect the > vast majority of SA's do not have/spend much time tweaking this and tunin= g that. > Order the box, drop the OS on it, install needed bits and go. =C2=A0Sayin= g "oh for > app X you need to tune these sysctl's", while it may be entirely true, ki= nda > throws things out the window. =C2=A0It seems that once one starts down th= at slippery > slope, it merely becomes a game of how much time to you have to "tune 1 m= ore > thing". =C2=A0;> =C2=A0I think Phoronix has the right idea of just grabbi= ng a stock box > and not looking into what needs to be tweaked for a specific app. > I think that a good SA will at least consider how drives are arranged. We don't just slap ZFS on a single disk and expect magic to happen, we consider how write heavy a system will be and consider a dedicated ZIL, we consider what proportion of files will be re-read and how much application memory will be required and adjust ARC and L2ARC accordingly. Tuning and foresight are important. Cheers Tom From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 14:14:06 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id B0FBA106564A for ; Wed, 21 Dec 2011 14:14:06 +0000 (UTC) (envelope-from prvs=1336820bf7=killing@multiplay.co.uk) Received: from mail1.multiplay.co.uk (mail1.multiplay.co.uk [85.236.96.23]) by mx1.freebsd.org (Postfix) with ESMTP id 188A98FC17 for ; Wed, 21 Dec 2011 14:14:05 +0000 (UTC) X-MDAV-Processed: mail1.multiplay.co.uk, Wed, 21 Dec 2011 14:03:32 +0000 X-Spam-Processed: mail1.multiplay.co.uk, Wed, 21 Dec 2011 14:03:32 +0000 X-Spam-Checker-Version: SpamAssassin 3.2.5 (2008-06-10) on mail1.multiplay.co.uk X-Spam-Level: X-Spam-Status: No, score=-5.0 required=6.0 tests=USER_IN_WHITELIST shortcircuit=ham autolearn=disabled version=3.2.5 Received: from r2d2 ([188.220.16.49]) by mail1.multiplay.co.uk (mail1.multiplay.co.uk [85.236.96.23]) (MDaemon PRO v10.0.4) with ESMTP id md50017222112.msg for ; Wed, 21 Dec 2011 14:03:31 +0000 X-MDRemoteIP: 188.220.16.49 X-Return-Path: prvs=1336820bf7=killing@multiplay.co.uk X-Envelope-From: killing@multiplay.co.uk X-MDaemon-Deliver-To: freebsd-performance@freebsd.org Message-ID: <25E425F57A7348808EA5E89670F8F337@multiplay.co.uk> From: "Steven Hartland" To: "Tom Evans" , "Randy Schultz" References: <4EE1EAFE.3070408@m5p.com><4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com><4EE933C6.4020209@zedat.fu-berlin.de><20111215024249.GA13557@icarus.home.lan><4EE9A2A0.80607@zedat.fu-berlin.de><4EF1121F.9010209@zedat.fu-berlin.de><4EF11B57.7090007@phoronix.com> Date: Wed, 21 Dec 2011 14:04:04 -0000 MIME-Version: 1.0 Content-Type: text/plain; format=flowed; charset="UTF-8"; reply-type=original Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 6.00.2900.5931 X-MimeOLE: Produced By Microsoft MimeOLE V6.00.2900.6157 Cc: freebsd-performance@freebsd.org, Matthew Tippett Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 14:14:06 -0000 ----- Original Message ----- From: "Tom Evans" > I think that a good SA will at least consider how drives are arranged. > We don't just slap ZFS on a single disk and expect magic to happen, we > consider how write heavy a system will be and consider a dedicated > ZIL, we consider what proportion of files will be re-read and how much > application memory will be required and adjust ARC and L2ARC > accordingly. Tuning and foresight are important. With the additional features and easy of management when using ZFS vs. UFS I know which one we choose even on single disk machines with no L2ARC. Its all very well people saying but if you tune this or tune that it would be much better, but where is the information on how to do this in various scenarios? If we want people to do that the information needs to be easily available and currently that's not the case, if an admin have a network related issue they will search for the solution and apply the fix, for db's the same but that's very time consuming and very error prone. The idea of some default profiles which take into account the amount of memory on the machine + user answered questions as to the roll to create a sensible install default is a great idea. Regards Steve ================================================ This e.mail is private and confidential between Multiplay (UK) Ltd. and the person or entity to whom it is addressed. In the event of misdirection, the recipient is prohibited from using, copying, printing or otherwise disseminating it or any information contained in it. In the event of misdirection, illegible or incomplete transmission please telephone +44 845 868 1337 or return the E.mail to postmaster@multiplay.co.uk. From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 14:19:41 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 100841065673 for ; Wed, 21 Dec 2011 14:19:41 +0000 (UTC) (envelope-from schulra@earlham.edu) Received: from chkenon.earlham.edu (chkenon.earlham.edu [159.28.1.87]) by mx1.freebsd.org (Postfix) with ESMTP id B09FD8FC1B for ; Wed, 21 Dec 2011 14:19:40 +0000 (UTC) X-ASG-Debug-ID: 1324477177-037b9f16aa1707e0001-3XdwJY Received: from tdream.lly.earlham.edu (tdream.lly.earlham.edu [159.28.7.241]) by chkenon.earlham.edu with ESMTP id ZVlfb3N6eiBaM7Jk; Wed, 21 Dec 2011 09:19:37 -0500 (EST) X-Barracuda-Envelope-From: schulra@earlham.edu X-Barracuda-Apparent-Source-IP: 159.28.7.241 Date: Wed, 21 Dec 2011 09:20:59 -0500 (EST) From: Randy Schultz X-X-Sender: schulra@tdream.lly.earlham.edu To: Tom Evans In-Reply-To: X-ASG-Orig-Subj: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server Message-ID: References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> User-Agent: Alpine 2.00 (BSF 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-Barracuda-Connect: tdream.lly.earlham.edu[159.28.7.241] X-Barracuda-Start-Time: 1324477177 X-Barracuda-URL: http://159.28.1.87:8000/cgi-mod/mark.cgi X-Virus-Scanned: by bsmtpd at earlham.edu X-Barracuda-Spam-Score: 0.89 X-Barracuda-Spam-Status: No, SCORE=0.89 using global scores of TAG_LEVEL=1000.0 QUARANTINE_LEVEL=1000.0 KILL_LEVEL=1000.0 tests=SARE_ADLTSUB4 X-Barracuda-Spam-Report: Code version 3.2, rules version 3.2.2.83708 Rule breakdown below pts rule name description ---- ---------------------- -------------------------------------------------- 0.89 SARE_ADLTSUB4 Apparent spam seems to contain porn subject Cc: freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 14:19:41 -0000 On Wed, 21 Dec 2011, Tom Evans spaketh thusly: -} -}I think that a good SA will at least consider how drives are arranged. -}We don't just slap ZFS on a single disk and expect magic to happen, we -}consider how write heavy a system will be and consider a dedicated -}ZIL, we consider what proportion of files will be re-read and how much -}application memory will be required and adjust ARC and L2ARC -}accordingly. Tuning and foresight are important. I agree whole-heartedly. I guess I wasn't clear. I wasn't trying to say most SA's never tune, only that from watching other SA's over the years, little tuning is done. IOW, while certainly some tune and play, I suspect that few build up a system then try it with and without hyperthreading, test how big the kern.ipc.shmmax needs to be or if tuning the inflight bits has any effect. Heh, I'ld do this all day long if I could. ;> I love tweaking and tuning, digging into docs and seeing if I can eke a little bit more out of the box. Hmmm, I wonder if the reason base benchmarks like Phoronix have become important is because not a lot of SA's spend a lot of time tuning... Or perhaps they just use it as a starting point. However my main point is that saying something needs to be tuned to get more, or a "proper", speed seems like a slippery slope. "There's always 1 more thing to try." (TM) ;> This then bring up the importance of something previously mentioned - what ever you do, try it yourself in your environment. Do whatever amount of tuning you do (or don't do) and try it. In our environment, fbsd stomps linux for a mail relay. OTOH linux's iSCSI initiator stomps fbsd's. Heh, what would be really cool even if only from an academic perspective would be to take a stock install of OS's, benchmark an app, then tune the them to the max and re-run the tests to see the difference. /me eyes the student SA's... ;> -- Randy (schulra@earlham.edu) 765.983.1283 <*> nosce te ipsum From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 15:45:01 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 62432106564A for ; Wed, 21 Dec 2011 15:45:01 +0000 (UTC) (envelope-from erik@cederstrand.dk) Received: from csmtp2.one.com (csmtp2.one.com [91.198.169.22]) by mx1.freebsd.org (Postfix) with ESMTP id 14CA68FC0C for ; Wed, 21 Dec 2011 15:45:00 +0000 (UTC) Received: from [192.168.187.69] (unknown [87.54.33.251]) by csmtp2.one.com (Postfix) with ESMTPA id 36A20307653D; Wed, 21 Dec 2011 15:29:21 +0000 (UTC) Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: text/plain; charset=us-ascii From: Erik Cederstrand In-Reply-To: Date: Wed, 21 Dec 2011 16:29:20 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <77FBE722-2CAC-49A5-B0D2-4BBE33DDBCE5@cederstrand.dk> References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> To: Randy Schultz X-Mailer: Apple Mail (2.1251.1) Cc: Tom Evans , freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 15:45:01 -0000 Den 21/12/2011 kl. 15.20 skrev Randy Schultz: > I agree whole-heartedly. I guess I wasn't clear. I wasn't trying to = say most > SA's never tune, only that from watching other SA's over the years, = little > tuning is done. As a casual SA, I often find I'm fumbling around in the dark to find out = if my server is running optimally. I can check CPU and memory usage, but = finding out if I could get my server to perform better by fiddling with = block sizes or any number of sysctls is daunting. Who knows, maybe my = batch jobs can complete 50% faster, or my CPU load can go from 20% to = 10%? I really like the mysqltuner script for MySQL in this regard because it = contains all the hard-earned experience of others and actually manages = to suggest useful values for the configuration file for me to adjust. It = would be great if there was something similar for FreeBSD that could = suggest things like "hey, you are getting interrupt storms on em0, might = want to check up on that" or "the block size on ada0 is insane for the = current I/O load" or "on this particular hardware, try setting sysctls = xxx and yyy to NNN instead" or "process 12345 is doing 1 billion system = calls/sec, doesn't seem right". Something like taking the suggestions = from = http://serverfault.com/questions/64356/freebsd-performance-tuning-sysctls-= loader-conf-kernel and trying to guess from my specific setup which = knobs might apply, and possibly which values. I'm perfectly aware that this is not a substitution for actually = thinking, profiling and benchmarking, but at least I'll have a place to = start. Erik= From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 16:45:28 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 40A1E106566B for ; Wed, 21 Dec 2011 16:45:28 +0000 (UTC) (envelope-from vince@unsane.co.uk) Received: from unsane.co.uk (unsane-pt.tunnel.tserv5.lon1.ipv6.he.net [IPv6:2001:470:1f08:110::2]) by mx1.freebsd.org (Postfix) with ESMTP id A73538FC16 for ; Wed, 21 Dec 2011 16:45:27 +0000 (UTC) Received: from vhoffman-macbooklocal.local ([10.10.10.20]) (authenticated bits=0) by unsane.co.uk (8.14.4/8.14.4) with ESMTP id pBLGjJsA029016 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Wed, 21 Dec 2011 16:45:20 GMT (envelope-from vince@unsane.co.uk) Message-ID: <4EF20D1F.3080507@unsane.co.uk> Date: Wed, 21 Dec 2011 16:45:19 +0000 From: Vincent Hoffman User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Erik Cederstrand References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> <77FBE722-2CAC-49A5-B0D2-4BBE33DDBCE5@cederstrand.dk> In-Reply-To: <77FBE722-2CAC-49A5-B0D2-4BBE33DDBCE5@cederstrand.dk> X-Enigmail-Version: 1.3.4 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: Tom Evans , freebsd-performance@freebsd.org, Randy Schultz Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 16:45:28 -0000 On 21/12/2011 15:29, Erik Cederstrand wrote: > Den 21/12/2011 kl. 15.20 skrev Randy Schultz: > >> I agree whole-heartedly. I guess I wasn't clear. I wasn't trying to say most >> SA's never tune, only that from watching other SA's over the years, little >> tuning is done. > As a casual SA, I often find I'm fumbling around in the dark to find out if my server is running optimally. I can check CPU and memory usage, but finding out if I could get my server to perform better by fiddling with block sizes or any number of sysctls is daunting. Who knows, maybe my batch jobs can complete 50% faster, or my CPU load can go from 20% to 10%? > > I really like the mysqltuner script for MySQL in this regard because it contains all the hard-earned experience of others and actually manages to suggest useful values for the configuration file for me to adjust. It would be great if there was something similar for FreeBSD that could suggest things like "hey, you are getting interrupt storms on em0, might want to check up on that" or "the block size on ada0 is insane for the current I/O load" or "on this particular hardware, try setting sysctls xxx and yyy to NNN instead" or "process 12345 is doing 1 billion system calls/sec, doesn't seem right". Something like taking the suggestions from http://serverfault.com/questions/64356/freebsd-performance-tuning-sysctls-loader-conf-kernel and trying to guess from my specific setup which knobs might apply, and possibly which values. > > I'm perfectly aware that this is not a substitution for actually thinking, profiling and benchmarking, but at least I'll have a place to start. I agree that something like mysqltuner would be great, although its such a wide area to cover a single utility probably would not be practical. A good start would be updating the tuning(7) man page. Its been a while since I read it but the first paragraph regarding partition sizes is most definitely out of date. Time to reread it followed by groff_man(7) i guess ;) Vince > Erik_______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 16:55:25 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id E23DF106566C for ; Wed, 21 Dec 2011 16:55:24 +0000 (UTC) (envelope-from vince@unsane.co.uk) Received: from unsane.co.uk (unsane-pt.tunnel.tserv5.lon1.ipv6.he.net [IPv6:2001:470:1f08:110::2]) by mx1.freebsd.org (Postfix) with ESMTP id 4FF4B8FC14 for ; Wed, 21 Dec 2011 16:55:24 +0000 (UTC) Received: from vhoffman-macbooklocal.local ([10.10.10.20]) (authenticated bits=0) by unsane.co.uk (8.14.4/8.14.4) with ESMTP id pBLGtM5v029427 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO) for ; Wed, 21 Dec 2011 16:55:23 GMT (envelope-from vince@unsane.co.uk) Message-ID: <4EF20F7A.6010101@unsane.co.uk> Date: Wed, 21 Dec 2011 16:55:22 +0000 From: Vincent Hoffman User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: freebsd-performance@freebsd.org References: <4EE1EAFE.3070408@m5p.com> <4EE2AE64.9060802@m5p.com> <4EE88343.2050302@m5p.com> <4EE933C6.4020209@zedat.fu-berlin.de> <20111215024249.GA13557@icarus.home.lan> <4EE9A2A0.80607@zedat.fu-berlin.de> <4EF1121F.9010209@zedat.fu-berlin.de> <4EF11B57.7090007@phoronix.com> <77FBE722-2CAC-49A5-B0D2-4BBE33DDBCE5@cederstrand.dk> <4EF20D1F.3080507@unsane.co.uk> In-Reply-To: <4EF20D1F.3080507@unsane.co.uk> X-Enigmail-Version: 1.3.4 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 16:55:25 -0000 On 21/12/2011 16:45, Vincent Hoffman wrote: > On 21/12/2011 15:29, Erik Cederstrand wrote: >> Den 21/12/2011 kl. 15.20 skrev Randy Schultz: >> >>> I agree whole-heartedly. I guess I wasn't clear. I wasn't trying to say most >>> SA's never tune, only that from watching other SA's over the years, little >>> tuning is done. >> As a casual SA, I often find I'm fumbling around in the dark to find out if my server is running optimally. I can check CPU and memory usage, but finding out if I could get my server to perform better by fiddling with block sizes or any number of sysctls is daunting. Who knows, maybe my batch jobs can complete 50% faster, or my CPU load can go from 20% to 10%? >> >> I really like the mysqltuner script for MySQL in this regard because it contains all the hard-earned experience of others and actually manages to suggest useful values for the configuration file for me to adjust. It would be great if there was something similar for FreeBSD that could suggest things like "hey, you are getting interrupt storms on em0, might want to check up on that" or "the block size on ada0 is insane for the current I/O load" or "on this particular hardware, try setting sysctls xxx and yyy to NNN instead" or "process 12345 is doing 1 billion system calls/sec, doesn't seem right". Something like taking the suggestions from http://serverfault.com/questions/64356/freebsd-performance-tuning-sysctls-loader-conf-kernel and trying to guess from my specific setup which knobs might apply, and possibly which values. >> >> I'm perfectly aware that this is not a substitution for actually thinking, profiling and benchmarking, but at least I'll have a place to start. > I agree that something like mysqltuner would be great, although its such > a wide area to cover a single utility probably would not be practical. > A good start would be updating the tuning(7) man page. Its been a while > since I read it but the first paragraph regarding partition sizes is > most definitely out of date. > Time to reread it followed by groff_man(7) i guess ;) http://people.*freebsd*.org/~kris/scaling/*Help*_*my*_*system_is_slow*.pdf is also a good read, again written a few years ago so parts may be outdated. Vince > > Vince >> Erik_______________________________________________ >> freebsd-performance@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-performance >> To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 18:54:49 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 8BC58106564A for ; Wed, 21 Dec 2011 18:54:49 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id 0F4B38FC16 for ; Wed, 21 Dec 2011 18:54:48 +0000 (UTC) Received: from outgoing.leidinger.net (p4FC4361F.dip.t-dialin.net [79.196.54.31]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id C0D6C84400D; Wed, 21 Dec 2011 19:49:28 +0100 (CET) Received: from localhost (unknown [85.94.224.19]) by outgoing.leidinger.net (Postfix) with ESMTPSA id 1047C50F2; Wed, 21 Dec 2011 19:49:24 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=Leidinger.net; s=outgoing-alex; t=1324493366; bh=UpNk2LDb3gn/pxm4FGwY5wCyiIKDCrIxMtLKMo+qO6Y=; h=Date:Subject:Message-ID:From:To:Cc:MIME-Version:Content-Type; b=MBt8uzMz/QxZzHf6KLJBl5l0vQYyID1wmS5JbvYIUTVFYfvR5vRbEHIVHlrq6L8ZX HDi5DOukYDvygDxieYekproYNUoufjhZdeAurKlsrL+gbRWTKvKbsCugjCtywnxo8X iUnG1qQEIm8eUe9QQ/qQi1+dNAdpGf6HbDoy7QCINvUhPIIQLG/HPnQs7ZXWKf51G9 TikE0swV0a50WfzXcTMdMs15rOWq/fyTpZ1c2TBLfoNxBLx4vCh3iHrdyASIhqVhor 3JtJTNkkYu5oqa5ziyK3y7xQZ5HqkML5D5CuMZSsJofXHe7C6quvPHP5PSVJ8InoBe 2nu4jmRtT0wVA== Date: Wed, 21 Dec 2011 19:48:32 +0100 Message-ID: Importance: normal From: Alexander Leidinger To: erik@cederstrand.dk, schulra@earlham.edu MIME-Version: 1.0 X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: C0D6C84400D.A4BE8 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=1.478, required 6, autolearn=disabled, ALL_TRUSTED -1.00, DKIM_SIGNED 0.10, DKIM_VALID -0.10, DKIM_VALID_AU -0.10, HTML_MESSAGE 0.00, SARE_ADLTSUB4 2.50, TW_QL 0.08) X-EBL-MailScanner-SpamScore: s X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1325098169.6959@u5RiX2ZZl1BGx05i+q9WFw X-EBL-Spam-Status: No Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: base64 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: tevans.uk@googlemail.com, freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 18:54:49 -0000 SGksCgpmZWVsIGZyZWUgdG8gYWRkIGFuIGVudHJ5IHRvIHRoZSBpZGVhcyBsaXN0IGluIHRoZSB3 aWtpLCBpdCBpcyBwcm9taW5lbnRseSBsaW5rZWQgaW4gdGhlIHRvcCBjdXJyZW50IGxpbmtzIHNl Y3Rpb24uIElmIHlvdSBkb24ndCBoYXZlIGFjY2VzcyBhbmQgZG9uJ3Qgd2FudCB0byByZWdpc3Rl ciwganVzdCBwcm92aWRlIGEgbmljZSB0ZXh0IGluIHRoZSBzdHlsZSBvZiB0aGUgaWRlYXMgcGFn ZSBhbmQgc29tZW9uZSBjYW4gYWRkIGl0LgoKQW5kIHJlbGF0ZWQgdG8gdGhlIHN1YmplY3Q6IHdh c24ndCBpdCB5b3Ugd2hvIGRldmVsb3BlZCB0aGUgYXV0b21hdGljIGJlbmNobWFya2luZyBzdHVm Zj8gSWYgeWVzLCB3aHkgbm90IG1ha2UgaXQgYXZhaWxhYmxlPyBJZiB5b3UgZG9uJ3QgaGF2ZSBo ZSByZXNvdXJjZXMsIEkgb2ZmZXIgbXkgaGVscCB0byBtYWtlIGl0IGF2YWlsYWJsZSBzb21ld2hl cmUuCgpCeWUsCkFsZXhhbmRlci4KCi0tIApTZW5kIHZpYSBhbiBBbmRyb2lkIGRldmljZSwgcGxl YXNlIGZvcmdpdmUgYnJldml0eSBhbmQgdHlwb2dyYXBoaWMgYW5kIHNwZWxsaW5nIGVycm9ycy7C oEVyaWsgQ2VkZXJzdHJhbmQgPGVyaWtAY2VkZXJzdHJhbmQuZGs+IGhhdCBnZXNjaHJpZWJlbjoK RGVuIDIxLzEyLzIwMTEga2wuIDE1LjIwIHNrcmV2IFJhbmR5IFNjaHVsdHo6Cgo+IEkgYWdyZWUg d2hvbGUtaGVhcnRlZGx5LsKgIEkgZ3Vlc3MgSSB3YXNuJ3QgY2xlYXIuwqAgSSB3YXNuJ3QgdHJ5 aW5nIHRvIHNheSBtb3N0Cj4gU0EncyBuZXZlciB0dW5lLCBvbmx5IHRoYXQgZnJvbSB3YXRjaGlu ZyBvdGhlciBTQSdzIG92ZXIgdGhlIHllYXJzLCBsaXR0bGUKPiB0dW5pbmcgaXMgZG9uZS4KCkFz IGEgY2FzdWFsIFNBLCBJIG9mdGVuIGZpbmQgSSdtIGZ1bWJsaW5nIGFyb3VuZCBpbiB0aGUgZGFy ayB0byBmaW5kIG91dCBpZiBteSBzZXJ2ZXIgaXMgcnVubmluZyBvcHRpbWFsbHkuIEkgY2FuIGNo ZWNrIENQVSBhbmQgbWVtb3J5IHVzYWdlLCBidXQgZmluZGluZyBvdXQgaWYgSSBjb3VsZCBnZXQg bXkgc2VydmVyIHRvIHBlcmZvcm0gYmV0dGVyIGJ5IGZpZGRsaW5nIHdpdGggYmxvY2sgc2l6ZXMg b3IgYW55IG51bWJlciBvZiBzeXNjdGxzIGlzIGRhdW50aW5nLiBXaG8ga25vd3MsIG1heWJlIG15 IGJhdGNoIGpvYnMgY2FuIGNvbXBsZXRlIDUwJSBmYXN0ZXIsIG9yIG15IENQVSBsb2FkIGNhbiBn byBmcm9tIDIwJSB0byAxMCU/CgpJIHJlYWxseSBsaWtlIHRoZSBteXNxbHR1bmVyIHNjcmlwdCBm b3IgTXlTUUwgaW4gdGhpcyByZWdhcmQgYmVjYXVzZSBpdCBjb250YWlucyBhbGwgdGhlIGhhcmQt ZWFybmVkIGV4cGVyaWVuY2Ugb2Ygb3RoZXJzIGFuZCBhY3R1YWxseSBtYW5hZ2VzIHRvIHN1Z2dl c3QgdXNlZnVsIHZhbHVlcyBmb3IgdGhlIGNvbmZpZ3VyYXRpb24gZmlsZSBmb3IgbWUgdG8gYWRq dXN0LiBJdCB3b3VsZCBiZSBncmVhdCBpZiB0aGVyZSB3YXMgc29tZXRoaW5nIHNpbWlsYXIgZm9y IEZyZWVCU0QgdGhhdCBjb3VsZCBzdWdnZXN0IHRoaW5ncyBsaWtlICJoZXksIHlvdSBhcmUgZ2V0 dGluZyBpbnRlcnJ1cHQgc3Rvcm1zIG9uIGVtMCwgbWlnaHQgd2FudCB0byBjaGVjayB1cCBvbiB0 aGF0IiBvciAidGhlIGJsb2NrIHNpemUgb24gYWRhMCBpcyBpbnNhbmUgZm9yIHRoZSBjdXJyZW50 IEkvTyBsb2FkIiBvciAib24gdGhpcyBwYXJ0aWN1bGFyIGhhcmR3YXJlLCB0cnkgc2V0dGluZyBz eXNjdGxzIHh4eCBhbmQgeXl5IHRvIE5OTiBpbnN0ZWFkIiBvciAicHJvY2VzcyAxMjM0NSBpcyBk b2luZyAxIGJpbGxpb24gc3lzdGVtIGNhbGxzL3NlYywgZG9lc24ndCBzZWVtIHJpZ2h0Ii4gU29t ZXRoaW5nIGxpa2UgdGFraW5nIHRoZSBzdWdnZXN0aW9ucyBmcm9tIGh0dHA6Ly9zZXJ2ZXJmYXVs dC5jb20vcXVlc3Rpb25zLzY0MzU2L2ZyZWVic2QtcGVyZm9ybWFuY2UtdHVuaW5nLXN5c2N0bHMt bG9hZGVyLWNvbmYta2VybmVsIGFuZCB0cnlpbmcgdG8gZ3Vlc3MgZnJvbSBteSBzcGVjaWZpYyBz ZXR1cCB3aGljaCBrbm9icyBtaWdodCBhcHBseSwgYW5kIHBvc3NpYmx5IHdoaWNoIHZhbHVlcy4K CkknbSBwZXJmZWN0bHkgYXdhcmUgdGhhdCB0aGlzIGlzIG5vdCBhIHN1YnN0aXR1dGlvbiBmb3Ig YWN0dWFsbHkgdGhpbmtpbmcsIHByb2ZpbGluZyBhbmQgYmVuY2htYXJraW5nLCBidXQgYXQgbGVh c3QgSSdsbCBoYXZlIGEgcGxhY2UgdG8gc3RhcnQuCgpFcmlrX19fX19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX18KZnJlZWJzZC1wZXJmb3JtYW5jZUBmcmVlYnNkLm9y ZyBtYWlsaW5nIGxpc3QKaHR0cDovL2xpc3RzLmZyZWVic2Qub3JnL21haWxtYW4vbGlzdGluZm8v ZnJlZWJzZC1wZXJmb3JtYW5jZQpUbyB1bnN1YnNjcmliZSwgc2VuZCBhbnkgbWFpbCB0byAiZnJl ZWJzZC1wZXJmb3JtYW5jZS11bnN1YnNjcmliZUBmcmVlYnNkLm9yZyIKCg== From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 18:56:38 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0A184106564A for ; Wed, 21 Dec 2011 18:56:38 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id 841458FC08 for ; Wed, 21 Dec 2011 18:56:37 +0000 (UTC) Received: from outgoing.leidinger.net (p4FC4361F.dip.t-dialin.net [79.196.54.31]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id A856C84400D; Wed, 21 Dec 2011 19:56:20 +0100 (CET) Received: from localhost (unknown [85.94.224.19]) by outgoing.leidinger.net (Postfix) with ESMTPSA id 48A0650F4; Wed, 21 Dec 2011 19:56:16 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=Leidinger.net; s=outgoing-alex; t=1324493777; bh=Ypynza7JgeuHB7WN0bOZJWn0xHg8fZu7CVs8rbEE5SU=; h=Date:Subject:Message-ID:From:To:Cc:MIME-Version:Content-Type; b=BlnlSV0zUGkQBMW90qNlnD4x88FAHT0u2KBDSmf+fpo054t3n0uO8Dy0JazbADJLl Tq1rOMsyKegnLq3lWQuTN4bFLu9PEkdmjDQ5GH0WfSjdxfDOt3oMZLTMOZ6fJ5UyrB +yDscw57ZpH2IBgG3B7ClGfIOuBWUw3EvVEzM/69sNG2LO9xUFwO2TJv5fXeVQbiPI ZIdW+yp5qXbf4lm2AM/GL4RMNPZatXmiFlEZECo1hoBNe7dDtsOvTqRx2RTt4yOYwi AQ+LL0xiCNU01ruXgYTGTRZobmMctlQRRTsELl3ctkIrCcwnkqWMsYOajEqZABha5a p3W+boMAkfRRQ== Date: Wed, 21 Dec 2011 19:55:25 +0100 Message-ID: Importance: normal From: Alexander Leidinger To: vince@unsane.co.uk, erik@cederstrand.dk MIME-Version: 1.0 X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: A856C84400D.A3F39 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=1.478, required 6, autolearn=disabled, ALL_TRUSTED -1.00, DKIM_SIGNED 0.10, DKIM_VALID -0.10, DKIM_VALID_AU -0.10, HTML_MESSAGE 0.00, SARE_ADLTSUB4 2.50, TW_QL 0.08) X-EBL-MailScanner-SpamScore: s X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1325098584.73036@+nl2o9POP+xbbqwYBTXE0A X-EBL-Spam-Status: No Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: base64 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: tevans.uk@googlemail.com, freebsd-performance@freebsd.org, schulra@earlham.edu Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 18:56:38 -0000 SGksCgpJIHN1Z2dlc3QgdG8gYWRkIHRoZSBjb250ZW50IHRvIHRoZSB3aWtpLCBpbXByb3ZlIGl0 ICh0b2dldGhlciB3aXRoIG90aGVyIHBlb3BsZSkgwqBhbmQgdGhlbiDCoHRvIGZpeCB0aGUgbWFu LXBhZ2Ugd2l0aCB0aGUgcmVzdWx0LgoKSWYgeW91IHdhbnQgd3JpdGUgYWNjZXNzIHRvIHRoZSB3 aWtpIGp1c3QgcmVnaXN0ZXIgd2l0aCBGaXJzdG5hbWVMYXN0bmFtZSBhbmQgdGVsbCBtZSBvciBh bnkgb3RoZXIgRnJlZUJTRCBjb21pdHRlciB3aXRoIHdpa2kgYWNjZXNzIGFib3V0IGl0IHNvIHRo YXQgd2UgY2FuIGhhbmQgb3V0IHdyaXRlIGFjY2Vzcy4KCkJ5ZSwKQWxleGFuZGVyLgoKLS0gClNl bmQgdmlhIGFuIEFuZHJvaWQgZGV2aWNlLCBwbGVhc2UgZm9yZ2l2ZSBicmV2aXR5IGFuZCB0eXBv Z3JhcGhpYyBhbmQgc3BlbGxpbmcgZXJyb3JzLsKgVmluY2VudCBIb2ZmbWFuIDx2aW5jZUB1bnNh bmUuY28udWs+IGhhdCBnZXNjaHJpZWJlbjpPbiAyMS8xMi8yMDExIDE1OjI5LCBFcmlrIENlZGVy c3RyYW5kIHdyb3RlOgo+IERlbiAyMS8xMi8yMDExIGtsLiAxNS4yMCBza3JldiBSYW5keSBTY2h1 bHR6Ogo+Cj4+IEkgYWdyZWUgd2hvbGUtaGVhcnRlZGx5LsKgIEkgZ3Vlc3MgSSB3YXNuJ3QgY2xl YXIuwqAgSSB3YXNuJ3QgdHJ5aW5nIHRvIHNheSBtb3N0Cj4+IFNBJ3MgbmV2ZXIgdHVuZSwgb25s eSB0aGF0IGZyb20gd2F0Y2hpbmcgb3RoZXIgU0EncyBvdmVyIHRoZSB5ZWFycywgbGl0dGxlCj4+ IHR1bmluZyBpcyBkb25lLgo+IEFzIGEgY2FzdWFsIFNBLCBJIG9mdGVuIGZpbmQgSSdtIGZ1bWJs aW5nIGFyb3VuZCBpbiB0aGUgZGFyayB0byBmaW5kIG91dCBpZiBteSBzZXJ2ZXIgaXMgcnVubmlu ZyBvcHRpbWFsbHkuIEkgY2FuIGNoZWNrIENQVSBhbmQgbWVtb3J5IHVzYWdlLCBidXQgZmluZGlu ZyBvdXQgaWYgSSBjb3VsZCBnZXQgbXkgc2VydmVyIHRvIHBlcmZvcm0gYmV0dGVyIGJ5IGZpZGRs aW5nIHdpdGggYmxvY2sgc2l6ZXMgb3IgYW55IG51bWJlciBvZiBzeXNjdGxzIGlzIGRhdW50aW5n LiBXaG8ga25vd3MsIG1heWJlIG15IGJhdGNoIGpvYnMgY2FuIGNvbXBsZXRlIDUwJSBmYXN0ZXIs IG9yIG15IENQVSBsb2FkIGNhbiBnbyBmcm9tIDIwJSB0byAxMCU/Cj4KPiBJIHJlYWxseSBsaWtl IHRoZSBteXNxbHR1bmVyIHNjcmlwdCBmb3IgTXlTUUwgaW4gdGhpcyByZWdhcmQgYmVjYXVzZSBp dCBjb250YWlucyBhbGwgdGhlIGhhcmQtZWFybmVkIGV4cGVyaWVuY2Ugb2Ygb3RoZXJzIGFuZCBh Y3R1YWxseSBtYW5hZ2VzIHRvIHN1Z2dlc3QgdXNlZnVsIHZhbHVlcyBmb3IgdGhlIGNvbmZpZ3Vy YXRpb24gZmlsZSBmb3IgbWUgdG8gYWRqdXN0LiBJdCB3b3VsZCBiZSBncmVhdCBpZiB0aGVyZSB3 YXMgc29tZXRoaW5nIHNpbWlsYXIgZm9yIEZyZWVCU0QgdGhhdCBjb3VsZCBzdWdnZXN0IHRoaW5n cyBsaWtlICJoZXksIHlvdSBhcmUgZ2V0dGluZyBpbnRlcnJ1cHQgc3Rvcm1zIG9uIGVtMCwgbWln aHQgd2FudCB0byBjaGVjayB1cCBvbiB0aGF0IiBvciAidGhlIGJsb2NrIHNpemUgb24gYWRhMCBp cyBpbnNhbmUgZm9yIHRoZSBjdXJyZW50IEkvTyBsb2FkIiBvciAib24gdGhpcyBwYXJ0aWN1bGFy IGhhcmR3YXJlLCB0cnkgc2V0dGluZyBzeXNjdGxzIHh4eCBhbmQgeXl5IHRvIE5OTiBpbnN0ZWFk IiBvciAicHJvY2VzcyAxMjM0NSBpcyBkb2luZyAxIGJpbGxpb24gc3lzdGVtIGNhbGxzL3NlYywg ZG9lc24ndCBzZWVtIHJpZ2h0Ii4gU29tZXRoaW5nIGxpa2UgdGFraW5nIHRoZSBzdWdnZXN0aW9u cyBmcm9tIGh0dHA6Ly9zZXJ2ZXJmYXVsdC5jb20vcXVlc3Rpb25zLzY0MzU2L2ZyZWVic2QtcGVy Zm9ybWFuY2UtdHVuaW5nLXN5c2N0bHMtbG9hZGVyLWNvbmYta2VybmVsIGFuZCB0cnlpbmcgdG8g Z3Vlc3MgZnJvbSBteSBzcGVjaWZpYyBzZXR1cCB3aGljaCBrbm9icyBtaWdodCBhcHBseSwgYW5k IHBvc3NpYmx5IHdoaWNoIHZhbHVlcy4KPgo+IEknbSBwZXJmZWN0bHkgYXdhcmUgdGhhdCB0aGlz IGlzIG5vdCBhIHN1YnN0aXR1dGlvbiBmb3IgYWN0dWFsbHkgdGhpbmtpbmcsIHByb2ZpbGluZyBh bmQgYmVuY2htYXJraW5nLCBidXQgYXQgbGVhc3QgSSdsbCBoYXZlIGEgcGxhY2UgdG8gc3RhcnQu CkkgYWdyZWUgdGhhdCBzb21ldGhpbmcgbGlrZSBteXNxbHR1bmVyIHdvdWxkIGJlIGdyZWF0LCBh bHRob3VnaCBpdHMgc3VjaAphIHdpZGUgYXJlYSB0byBjb3ZlciBhIHNpbmdsZSB1dGlsaXR5IHBy b2JhYmx5IHdvdWxkIG5vdCBiZSBwcmFjdGljYWwuCkEgZ29vZCBzdGFydCB3b3VsZCBiZSB1cGRh dGluZyB0aGUgdHVuaW5nKDcpIG1hbiBwYWdlLiBJdHMgYmVlbiBhIHdoaWxlCnNpbmNlIEkgcmVh ZCBpdCBidXQgdGhlIGZpcnN0IHBhcmFncmFwaCByZWdhcmRpbmcgcGFydGl0aW9uIHNpemVzIGlz Cm1vc3QgZGVmaW5pdGVseSBvdXQgb2YgZGF0ZS4KVGltZSB0byByZXJlYWQgaXQgZm9sbG93ZWQg YnkgZ3JvZmZfbWFuKDcpIGkgZ3Vlc3MgOykKClZpbmNlCj4gRXJpa19fX19fX19fX19fX19fX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fCj4gZnJlZWJzZC1wZXJmb3JtYW5jZUBmcmVl YnNkLm9yZyBtYWlsaW5nIGxpc3QKPiBodHRwOi8vbGlzdHMuZnJlZWJzZC5vcmcvbWFpbG1hbi9s aXN0aW5mby9mcmVlYnNkLXBlcmZvcm1hbmNlCj4gVG8gdW5zdWJzY3JpYmUsIHNlbmQgYW55IG1h aWwgdG8gImZyZWVic2QtcGVyZm9ybWFuY2UtdW5zdWJzY3JpYmVAZnJlZWJzZC5vcmciCgpfX19f X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fXwpmcmVlYnNkLXBlcmZv cm1hbmNlQGZyZWVic2Qub3JnIG1haWxpbmcgbGlzdApodHRwOi8vbGlzdHMuZnJlZWJzZC5vcmcv bWFpbG1hbi9saXN0aW5mby9mcmVlYnNkLXBlcmZvcm1hbmNlClRvIHVuc3Vic2NyaWJlLCBzZW5k IGFueSBtYWlsIHRvICJmcmVlYnNkLXBlcmZvcm1hbmNlLXVuc3Vic2NyaWJlQGZyZWVic2Qub3Jn IgoK From owner-freebsd-performance@FreeBSD.ORG Wed Dec 21 18:59:50 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5C71B1065675; Wed, 21 Dec 2011 18:59:50 +0000 (UTC) (envelope-from alexander@leidinger.net) Received: from mail.ebusiness-leidinger.de (mail.ebusiness-leidinger.de [217.11.53.44]) by mx1.freebsd.org (Postfix) with ESMTP id B61A68FC0A; Wed, 21 Dec 2011 18:59:49 +0000 (UTC) Received: from outgoing.leidinger.net (p4FC4361F.dip.t-dialin.net [79.196.54.31]) by mail.ebusiness-leidinger.de (Postfix) with ESMTPSA id 55F0784403D; Wed, 21 Dec 2011 19:42:52 +0100 (CET) Received: from localhost (unknown [85.94.224.19]) by outgoing.leidinger.net (Postfix) with ESMTPSA id 1A97150F0; Wed, 21 Dec 2011 19:42:47 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=simple/simple; d=Leidinger.net; s=outgoing-alex; t=1324492969; bh=4atfPkeMSYP08jaQLeAsPAUzgPt9uduUQPdLguW35so=; h=Date:Subject:Message-ID:From:To:Cc:MIME-Version:Content-Type; b=nH/sPQat45+bMi41Grr+whSe0zk9MYPI+Ll4LEdACUMlwClXSa8DcdA2hPERD4z2y 0S5DEw4U9f4QcQjlJIqMqiQ0NcArnUysiOuN7DYc3D4GRUGXm3le6KbAUCI1Tzm2Dx y7mKFl9myH4tqNpZGF9hSSjM+SMTOVSeqT92s2NEnPd1/C7prjFLOtw3FTe+5EKZbc 2r220/+haMijMZtSW0MrOgyy+ofjLndWQtg6BMpmj83Ph49Ly0srfCLMB48TaZCYTx M8Ir833nE+lq+2aGSfqILCngLUbl5EwDoYM7sSsj4xJW7wwWibfIElbPVnsaecMZGv rReuxxLek/sOA== Date: Wed, 21 Dec 2011 19:41:47 +0100 Message-ID: Importance: normal From: Alexander Leidinger To: ohartman@zedat.fu-berlin.de, igor@hybrid-lab.co.uk MIME-Version: 1.0 X-EBL-MailScanner-Information: Please contact the ISP for more information X-EBL-MailScanner-ID: 55F0784403D.A2C06 X-EBL-MailScanner: Found to be clean X-EBL-MailScanner-SpamCheck: not spam, spamhaus-ZEN, SpamAssassin (not cached, score=1.401, required 6, autolearn=disabled, ALL_TRUSTED -1.00, DKIM_SIGNED 0.10, DKIM_VALID -0.10, DKIM_VALID_AU -0.10, HTML_MESSAGE 0.00, SARE_ADLTSUB4 2.50) X-EBL-MailScanner-SpamScore: s X-EBL-MailScanner-From: alexander@leidinger.net X-EBL-MailScanner-Watermark: 1325097773.95682@UAS4O1xQyDoZUisA6ZeAIw X-EBL-Spam-Status: No Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: base64 X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, freebsd-stable@freebsd.org, freebsd@jdc.parodius.com Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 21 Dec 2011 18:59:50 -0000 SGksCgp3aGlsZSB0aGUgZGlzY3Vzc2lvbiBjb250aW51ZWQgaGVyZSwgc29tZSB3b3JrIHN0YXJ0 ZWQgYXQgc29tZSBvdGhlciBwbGFjZS4gTm93Li4uIGluIGNhc2Ugc29tZW9uZSBoZXJlIGlzIHdp bGxpbmcgdG8gaGVscCBpbnN0ZWFkIG9mIHRhbGtpbmcsIGZlZWwgZnJlZSB0byBnbyB0byBodHRw Oi8vd2lraS5mcmVlYnNkLm9yZy9CZW5jaG1hcmtBZHZpY2UgYW5kIGhhdmUgYSBsb29rIHdoYXQg Y2FuIGJlIGltcHJvdmVkLiBUaGUgcGFnZSBpcyBmYXIgZnJvbSBwZXJmZWN0IGFuZCBuZWVkcyBz b21lIGFkZGl0aW9uYWwgcGVvcGxlIHdoaWNoIGFyZSB3aWxsaW5nIHRvIGltcHJvdmUgaXQuCgpU aGlzIGlzIG9ubHkgcGFydCBvZiB0aGUgcHJvYmxlbS4gQSB0dW5pbmcgcGFnZSBpbiB0aGUgd2lr aSAtIHdoaWNoIGNvdWxkIGJlIHJlZmVyZW5jZWQgZnJvbSB0aGUgYmVuY2htYXJrIHBhZ2UgLSB3 b3VsZCBiZSBncmVhdCB0b28uIEFueSB2b2x1bnRlZXJzPyBBIGZpcnN0IHN0ZXAgd291bGQgYmUg dG8gdGFrZSBoZSB0dW5pbmctbWFuLXBhZ2UgYW5kIHdpa2lmeSBpdC4gT3RoZXIgdHVuaW5nIHNv dXJjZXMgYXJlIHdlbGNvbWUgdG9vLgoKRXZlcnkgRnJlZUJTRCBkZXYgd2l0aCBhIHdpa2kgYWNj b3VudCBjYW4gaGFuZCBvdXQgd3JpdGUgYWNjZXNzIHRvIHRoZSB3aWtpLiBUaGUgYmVuY2htYXJr IHBhZ2UgZ2l2ZXMgY29udHJpYnV0b3ItYWNjZXNzLiBJZiBzb21lb25lIHdhbnRzIHdyaXRlIGFj Y2VzcyBjcmVhdGUgYSBGaXJzdG5hbWVMYXN0bmFtZSBhY2NvdW50IGFuZCBhc2sgaGVyZSBmb3Ig Y29udHJpYnV0b3ItYWNjZXNzLgoKRG9uJ3Qgd29ycnkgaWYgeW91IHRoaW5rIHlvdXIgZW5nbGlz aCBpcyBub3QgZ29vZCBlbm91Z2gsIGV2ZW4gc29tZSBvbmUtd29yZCBub3RlcyBjYW4gaGVscCAo YW5kIF9teV8gZW5nbGlzaCBnb3QgYWxyZWFkeSBjb3JyZWN0ZWQgYnkgb3RoZXIgcGVvcGxlIG9u IHRoZSBiZW5jaG1hcmsgcGFnZSkuCgpCeWUsCkFsZXhhbmRlci4KCi0tIApTZW5kIHZpYSBhbiBB bmRyb2lkIGRldmljZSwgcGxlYXNlIGZvcmdpdmUgYnJldml0eSBhbmQgdHlwb2dyYXBoaWMgYW5k IHNwZWxsaW5nIGVycm9ycy7CoCJPLiBIYXJ0bWFubiIgPG9oYXJ0bWFuQHplZGF0LmZ1LWJlcmxp bi5kZT4gaGF0IGdlc2NocmllYmVuOk9uIDEyLzIwLzExIDIxOjIwLCBJZ29yIE1vem9sZXZza3kg d3JvdGU6Cj4gSW50ZXJlc3RpbmdseSwgd2hpbGUgcGVvcGxlIHNlZW0gdG8gYmUgKGFyZ3VhYmx5 IHJpZ2h0bHkpIGZvY3VzZWQgb24KPiBjcml0aWNpc2luZyBQaG9yb25peCdzIGJlbmNobWFya2lu Zywgbm9ib2R5IGhhcyBvZmZlcmVkIGFuIGFsdGVybmF0aXZlCj4gYmVuY2htYXJrOyBhbmQgd2hp bGUgKGFnYWluLCBhcmd1YWJseSByaWdodGx5KSBpdCBpcyBpbXBvcnRhbnQgdG8KPiBiZW5jaG1h cmsgcmVhbCB3b3JsZCBwZXJmb3JtYW5jZSwgZXF1YWxseSwgbm9ib2R5IGhhcyBvZmZlcmVkIGFu eQo+IG51bWJlcnMgaW4gcmVsYXRpb24gdG8sIGZvciBleGFtcGxlLCBIVFRQIG9yIFNNVFAsIG9y IGFueSBvdGhlciAicmVhbAo+IHdvcmxkIi1hcHBsaWNhdGlvbiB0b3J0dXJlIHRlc3RzIGRvbmUg b24gdGhlIGFmb3JlbWVudGlvbmVkIHR3bwo+IHBsYXRmb3Jtcy4uLiBJTU8sIHRoaXMganVzdCBn b2VzIHRvIHNob3cgdGhhdCAiZG9pbmcgaXMgaGFyZCIgYW5kCj4gImNyaXRpY2lzaW5nIGlzIG11 Y2ggZWFzaWVyIiAoeWVzLCBJIGFtIGF3YXJlIG9mIHRoZSBpcm9ueSBpbnZvbHZlZCBpbgo+IG1h a2luZyB0aGlzIHN0YXRlbWVudCwgYnV0IHNvbWVvbmUgaGFzIHRvISkKPiAKPiAKPiBDaGVlcnMs Cj4gSWdvciBNIDotKQoKVW5mb3J0dW5hdGVseSwgTS4gTGFyYWJlbCBpcyB0aGUgb25seSBvbmUg d2hvJ3MgcGVyZm9ybWluZyBiZW5jaG1hcmtzIG9uCkZyZWVCU0QsIGNvbXBhcmluZyBpdHMgcGVy Zm9ybWFuY2UgdG8gdGhlIExpbnV4LW9wcG9uZW50cy4gQWRuIGluZGVlZCwKdGhlcmUgaXMgYSBs b3Qgb2YgY3JpdGljaXNtLCBidXQgbm8gYWx0ZXJuYXRpdmUuCkkgc2FpZCB1bmZvcnR1bmF0ZWx5 IC0gbm90IG9mZmVuc2l2ZSAtIHNpbmNlIExhcmFiZWwgYW5kIFBob3Jvbml4IGFyZQpzYWRseSB0 aGUgb25seSBvbmVzIHdobyBkbyBhY3R1YWxseSBzdWNoIGJlY2htYXJraW5nLgoKSXQgd291bGQg YmUgbXVjaCBtb3JlIG5pY2VyIGFuZCBraW5kIHRvIHN1cHBvcnQgdGhvc2UgcGVvcGxlLgoKV2Vs bCwgaW4gSmFudWFyeS9GZWJydWFyeSB3ZSBnZXQgbmV3IGhhcmR3YXJlLiBPbmUgYm94IGlzIHN1 cHBvc2VkIHRvIGRvCm51bWJlciBjcnVuY2hpbmcgdmlhIDEyIGNvcmVzIGFuZCBhIFRFU0xBIEdQ VS4gTXkgY29sbGVhZ3VlIGlzCmRldmVsb3BpbmcgYSBoaWdoIHBhcmFsbGVsaXplZCBwZWljZSBv ZiBzb2Z0d2FyZSBmb3Igc2F0ZWxsaXRlIGRhdGEKdHJhbnNmb3JtYXRpb24uIFRoZSBzb2Z0d2Fy ZSBwYWNrYWdlIGlzIENQVSBib3VuZCwgcGFydGlhbGx5IEdQVSwgYnV0Cm1hc3NpdmVseSBtZW1v cnkgaHVuZ3J5ICg5NiB0byAxMjggR0IgUkFNIGlzIG5lZWRlZCkuCldoYXQgSSBjYW4gb2ZmZXIg aXMsIHNpbmNlIEkgd2lsbCBhbHNvIHdvcmsgb24gdGhhdCBtYWNoaW5lIGFuZCBJJ3ZlCmZyZWUg aGFuZCB0byBhZG1pbmlzdGVyLCBpbiB0aGUgc3BhcmUgdGltZSBvZiBkb2luZyBteSBQaEQsIGlu c3RhbGxpbmcKRnJlZUJTRCA5LjAvMTAuMCBiZXNpZGVzIFN1U2UgTGludXggYW5kIGxvb2tpbmcg Zm9yd2FyZCBoYXZpbmcgb25lIFpGUwpkYXRhIHN0b3JhZ2UgZHJpdmUgZm9yIGhvbWVzLCBzbyBi b3RoIHN5c3RlbXMgY2FuIHBlcmZvcm0gb24gYSBtb3N0CnJlY2VudCBaRlMuIEknbSBuZXcgdG8g TGludXgsIG5vdCBhIEJTRCBndXJ1LCBub3IgSSdtIGEgcHJvZmVzc2lvbmFsCnByb2dyYW1tZXIv ZGV2ZWxvcGVyLiBNeSBza2lsbHMgYXJlIHN1ZmZpY2llbnQgZm9yIHRoZSBkYWlseSBzY2llbnRp ZmljCndvcmsuIFNvLCB3aXRob3V0IHByZXNzdXJlLCBJJ20gd2lsbGluZyB0byBwZXJmb3JtIHNv bWUgSFBDIGJlbmNobWFya3MKdW5kZXIgYWR2aWNlIGlmIHRoZSBkYXkgY29tZXMgYW5kIHRob3Nl IGludGVyZXN0ZWQgaW4gYmFyZSBudW1iZXJzIG9mCkZyZWVCU0QgdnMuIExpbnV4IHBlcmZvcm1h bmNlIHdpdGggYSByZWFsLXdvcmxkLXNjaWVudGlmaWMgYXBwbGljYXRpb24uCgpJIHdvdWxkIGFw cHJlY2lhdGUgdG8gc2VlIHNvbWUgb2YgdGhlIGRldmVsb3BlcnMgYW5kL29yIEZyZWVCU0QgaGFj a2Vycwp0byBoZWxwIFBob3Jvbml4IHNldHRpbmcgdXAgYSBwcm9wZXIgdGVzdGVudmlyb25tZW50 IGluc3RlYWQgb2YgYmFzaGluZwpNLiBMYXJhYmVsIGFuZCBoaXMgZmVsbG93cy4KClJlZ2FyZHMs Ck9saXZlcgoK From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 11:21:05 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 22F47106566B for ; Thu, 22 Dec 2011 11:21:05 +0000 (UTC) (envelope-from erik@cederstrand.dk) Received: from csmtp3.one.com (csmtp3.one.com [91.198.169.23]) by mx1.freebsd.org (Postfix) with ESMTP id D9DBE8FC0A for ; Thu, 22 Dec 2011 11:21:04 +0000 (UTC) Received: from [10.10.10.10] (unknown [217.157.7.216]) by csmtp3.one.com (Postfix) with ESMTPA id 3F4D824110B7; Thu, 22 Dec 2011 11:21:03 +0000 (UTC) Mime-Version: 1.0 (Apple Message framework v1251.1) Content-Type: text/plain; charset=us-ascii From: Erik Cederstrand In-Reply-To: Date: Thu, 22 Dec 2011 12:21:04 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <001CED31-FDD0-4CB1-B972-2F2344EEB9D3@cederstrand.dk> References: To: Alexander Leidinger X-Mailer: Apple Mail (2.1251.1) Cc: freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 11:21:05 -0000 Den 21/12/2011 kl. 19.48 skrev Alexander Leidinger: > And related to the subject: wasn't it you who developed the automatic = benchmarking stuff? If yes, why not make it available? If you don't have = he resources, I offer my help to make it available somewhere. Yes, that's me. I'm mostly out of time right now, but I'd like to offer = help if someone wants to pick up the project. For those who haven't heard about it, it's a system designed = specifically to track performance of FreeBSD over time by comparing = revisions of FreeBSD, everything else being equal. It consists of a = tinderbox-like build script for a build server, a script to install = FreeBSD and run benchmarks on at least one slave, and a database-backed = website to aggregate and visualize results. The framework does work as-is, but it really needs to be updated: = convert the scripts to use the SVN repo instead of CVS, improve = visualization and search on the web fronted, and improve the = benchmarking script so it's easier to extend. I don't have hardware = available to run the benchmarks, but I think there's hardware available = in the FreeBSD cluster. Here's a link to the source code: http://dev.affect-it.dk/tracker.tgz And to my thesis describing how it works: = http://dev.affect-it.dk/tracker.pdf Just send me a mail if you're interested. Thanks, Erik= From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 16:56:15 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id C44BE1065670 for ; Thu, 22 Dec 2011 16:56:15 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 725688FC12 for ; Thu, 22 Dec 2011 16:56:15 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so11892939vcb.13 for ; Thu, 22 Dec 2011 08:56:14 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type :content-transfer-encoding; bh=e4iEXhzdB0KzlMO98g4IAMghNi2fXywam6/1QL50a+E=; b=BbJ+ARbiHrHXak/lbvBYfVSQhgLJlcWafojtIjueu9jOO0O5sFY8f1jl9BxpxB388U iJ9oZT7iIafFBCwDoGxBys2TueHnkkbHA/CZZ8+IzbRSOsHWht9PCio4CFczx9JHQWww JRufZ0XjBQnmdP95kQL+1Pjs0Jy9abp8ycSS8= MIME-Version: 1.0 Received: by 10.220.153.134 with SMTP id k6mr7434485vcw.23.1324572974869; Thu, 22 Dec 2011 08:56:14 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.36.5 with HTTP; Thu, 22 Dec 2011 08:56:13 -0800 (PST) In-Reply-To: <001CED31-FDD0-4CB1-B972-2F2344EEB9D3@cederstrand.dk> References: <001CED31-FDD0-4CB1-B972-2F2344EEB9D3@cederstrand.dk> Date: Thu, 22 Dec 2011 08:56:13 -0800 X-Google-Sender-Auth: wweQgQUy99CdEuzFFuMBD2UkcBE Message-ID: From: Adrian Chadd To: Erik Cederstrand Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: Alexander Leidinger , freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 16:56:15 -0000 Guys, girls, fuzzy creatures, This is by far the best example of a constructive email in this entire thre= ad. If people would like to help, Erik here is exactly the kind of person with exactly the kind of software that needs a hand. I think enough philosophizing has been done - now we have questions that need answering; theories that need testing. And that requires, you know, coding. :) The best thing right now would be for *BSD people to pick up the Phronix test suite, try to compile/run it, and provide feedback. Do your own benchmarks on your own hardware and report back the results. That's how we fix the "benchmarking problem." We don't fix it by armchair philosophy, we fix it by getting our hands dirty. :) 2c, Adrian On 22 December 2011 03:21, Erik Cederstrand wrote: > Den 21/12/2011 kl. 19.48 skrev Alexander Leidinger: > >> And related to the subject: wasn't it you who developed the automatic be= nchmarking stuff? If yes, why not make it available? If you don't have he r= esources, I offer my help to make it available somewhere. > > Yes, that's me. I'm mostly out of time right now, but I'd like to offer h= elp if someone wants to pick up the project. > > For those who haven't heard about it, it's a system designed specifically= to track performance of FreeBSD over time by comparing revisions of FreeBS= D, everything else being equal. It consists of a tinderbox-like build scrip= t for a build server, a script to install FreeBSD and run benchmarks on at = least one slave, and a database-backed website to aggregate and visualize r= esults. > > The framework does work as-is, but it really needs to be updated: convert= the scripts to use the SVN repo instead of CVS, improve visualization and = search on the web fronted, and improve the benchmarking script so it's easi= er to extend. I don't have hardware available to run the benchmarks, but I = think there's hardware available in the FreeBSD cluster. > > Here's a link to the source code: http://dev.affect-it.dk/tracker.tgz > And to my thesis describing how it works: http://dev.affect-it.dk/tracker= .pdf > > Just send me a mail if you're interested. > > Thanks, > Erik_______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to "freebsd-performance-unsubscribe@freebsd= .org" From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 18:00:20 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6D422106566B; Thu, 22 Dec 2011 18:00:20 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id 276398FC14; Thu, 22 Dec 2011 18:00:19 +0000 (UTC) Received: from mobile-198-228-212-238.mycingular.net ([198.228.212.238] helo=www.palm.com) by phx1.phoronix.com with esmtpa (Exim 4.69) (envelope-from ) id 1RdmwD-00088y-TX; Thu, 22 Dec 2011 12:00:18 -0600 Date: Thu, 22 Dec 2011 10:00:19 -0800 From: To: "Adrian Chadd" In-Reply-To: X-Mailer: Palm webOS X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Message-Id: <20111222180020.6D422106566B@hub.freebsd.org> Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Alexander Leidinger , freebsd-performance@freebsd.org, Erik Cederstrand Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Matthew Tippett List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 18:00:20 -0000 =0A =0A =0A =0A =0A Let me suggest an alternative. =0A = =0A Within the Phoronix Test Suite ecosystem, we have a continious=0A = integration/validation system called Phoromatic=0A ([1]http://www.phoromatic.c= om/). We have a brief theory of operation=0A on it captured=0A= =0A [2]https://docs.google.com/present/view?id=3Dds439pg_42hpg57m86=0A . = You can see a Linux oriented tracker available at=0A [3]http://ph= oromatic.com/kernel-tracker.php (the nice graphs are when=0A you sel= ect 180 days and the ION 330 systems). We've re-assigned the=0A sy= stems to other projects so it is no longer being updated, but it=0A serv= ed our purposes. =0A =0A This system will allow you to just de= dicate a machine to be=0A updateable and pick up the directions for whic= h test to be run. The=0A FreeBSD project (or contributors) would m= aintain the slave or test=0A machines. The test suite would be sel= ected and managed by the=0A FreeBSD project or contributors. The g= lue code to emit triggers=0A (possibly SVN, git or other submission, or = even just daily) and the=0A scripts to update the systems would also be = maintained by the=0A FreeBSD community. =0A =0A Phoronix Me= dia would be happy to host it on Phoromatic.com (we've=0A played with ho= sted with project branding) and provide the data store=0A and the analyt= ics. We'd also be willing to make enhancements to=0A support the F= reeBSD project. =0A =0A This should solve the "I don't have ti= me to maintain a automated=0A test infrastructure". You don't need= to, just write the glue=0A scripts, and dedicate a couple of machines.&= nbsp; I believe FreeBSD=0A vendors like ixSystems may be able to support= this effort with a=0A dedicated machine. You can have as many mac= hines as you like=0A demonstrating AMD/Intel/32/64/large mem/low mem,etc= =2E =0A =0A The comments around interactivi= ty can also be measured to some=0A extent. We have the model of a = "monitor". This can be configured=0A to determine jitter around a = number of system variables and to=0A possibly inject actions to measure = impacts. =0A =0A We're more than happy to work with you guys, = and are willing to help=0A do a lot of the infrastructure and automation= lifting. =0A =0A Regards, =0A =0A Matthew =0A= =0A =0A =0A On 12/22/11 8:56 AM, Adrian Chadd wrot= e:=0A =0A Guys, gir= ls, fuzzy creatures,=0A=0AThis is by far the best example of a constructive= email in this entire thread.=0A=0AIf people would like to help, Erik here = is exactly the kind of person=0Awith exactly the kind of software that need= s a hand.=0A=0AI think enough philosophizing has been done - now we have qu= estions=0Athat need answering; theories that need testing. And that require= s,=0Ayou know, coding. :)=0A=0AThe best thing right now would be for *BSD p= eople to pick up the=0APhronix test suite, try to compile/run it, and provi= de feedback. Do=0Ayour own benchmarks on your own hardware and report back = the results.=0AThat's how we fix the "benchmarking problem." We don't fix i= t by=0Aarmchair philosophy, we fix it by getting our hands dirty. :)=0A=0A2= c,=0A=0A=0AAdrian=0A=0A=0AOn 22 December 2011 03:21, Erik Cederstrand [4] wrote:=0A =0A = =0A Den 21/12/2011 kl. 19.48 skrev Alexander Leidinge= r:=0A=0A =0A =0A And related to the subject: wasn't it you who developed the automatic= benchmarking stuff? If yes, why not make it available? If you don't have h= e resources, I offer my help to make it available somewhere.=0A =0A = =0A Yes, that's me. I'm mostly out = of time right now, but I'd like to offer help if someone wants to pick up t= he project.=0A=0AFor those who haven't heard about it, it's a system design= ed specifically to track performance of FreeBSD over time by comparing revi= sions of FreeBSD, everything else being equal. It consists of a tinderbox-l= ike build script for a build server, a script to install FreeBSD and run be= nchmarks on at least one slave, and a database-backed website to aggregate = and visualize results.=0A=0AThe framework does work as-is, but it really ne= eds to be updated: convert the scripts to use the SVN repo instead of CVS, = improve visualization and search on the web fronted, and improve the benchm= arking script so it's easier to extend. I don't have hardware available to = run the benchmarks, but I think there's hardware available in the FreeBSD c= luster.=0A=0AHere's a link to the source code: [5]http://dev.affect-it.dk= /tracker.tgz=0AAnd to my thesis describing how it works: [6]http://de= v.affect-it.dk/tracker.pdf=0A=0AJust send me a mail if you're intereste= d.=0A=0AThanks,=0AErik_______________________________________________=0A[7]free bsd-performance@freebsd.org mailing list=0A[8]http://lists.freebsd.org/mailman/ listinfo/freebsd-performanc= e=0ATo unsubscribe, send any mail to [9]"freebsd-perfo= rmance-unsubscribe@freebsd.org"=0A =0A =0A = _______________________________________________=0A[10]freebsd-performance@freeb sd.org mailing list=0A[11]http://lists.freebsd.org/mailman/listinfo/freebsd-per formance= =0ATo unsubscribe, send any mail to [12]"freebsd-performanc= e-unsubscribe@freebsd.org"=0A =0A =0A =0A = =0A=0A=20 References 1. 3D"http://www.phoromatic.com/" 2. 3D"https://docs.google.com/present/view?id=3Dds439pg_42hpg57m86= 3. 3D"http://phoromatic.com/kernel-tracker.php" 4. 3D"mailto:erik@cederstrand.dk" 5. 3D"http://dev.affect-it.dk/tracker.tgz" 6. 3D"http://dev.affect-it.dk/tracker.pdf" 7. 3D"mailto:freebsd-performance@freeb= 8. 3D"http://lists.freebsd.org/mailman/listinfo/freebs= 9. 3D"mailto:freebsd-performance-unsubscribe@freebsd.org" 10. 3D"mailto:freebsd-performance@freebsd.or= 11. 3D"http://lists.freebsd.org/mailman/listinfo/freebsd-per= 12. =3D"mailto:freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 18:49:56 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 036E61065670; Thu, 22 Dec 2011 18:49:56 +0000 (UTC) (envelope-from matthew@phoronix.com) Received: from phx1.phoronix.com (173.192.77.202-static.reverse.softlayer.com [173.192.77.202]) by mx1.freebsd.org (Postfix) with ESMTP id C0E268FC16; Thu, 22 Dec 2011 18:49:55 +0000 (UTC) Received: from palm-64-28-152-140.palm.com ([64.28.152.140] helo=MBP123456.local) by phx1.phoronix.com with esmtpa (Exim 4.69) (envelope-from ) id 1Rdni3-0004XY-M4; Thu, 22 Dec 2011 12:49:43 -0600 Message-ID: <4EF37BBC.3070404@phoronix.com> Date: Thu, 22 Dec 2011 10:49:32 -0800 From: Matthew Tippett User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:7.0.1) Gecko/20110929 Thunderbird/7.0.1 MIME-Version: 1.0 To: Adrian Chadd References: <001CED31-FDD0-4CB1-B972-2F2344EEB9D3@cederstrand.dk> In-Reply-To: X-AntiAbuse: This header was added to track abuse, please include it with any abuse report X-AntiAbuse: Primary Hostname - phx1.phoronix.com X-AntiAbuse: Original Domain - freebsd.org X-AntiAbuse: Originator/Caller UID/GID - [47 12] / [47 12] X-AntiAbuse: Sender Address Domain - phoronix.com Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Alexander Leidinger , freebsd-performance@freebsd.org, Erik Cederstrand Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 18:49:56 -0000 (Resending - hopefully without horrific escaping somewhere upstream). Let me suggest an alternative. Within the Phoronix Test Suite ecosystem, we have a continious integration/validation system called Phoromatic (http://www.phoromatic.com/). We have a brief theory of operation on it captured https://docs.google.com/present/view?id=ds439pg_42hpg57m86 . You can see a Linux oriented tracker available at http://phoromatic.com/kernel-tracker.php (the nice graphs are when you select 180 days and the ION 330 systems). We've re-assigned the systems to other projects so it is no longer being updated, but it served our purposes. This system will allow you to just dedicate a machine to be updateable and pick up the directions for which test to be run. The FreeBSD project (or contributors) would maintain the slave or test machines. The test suite would be selected and managed by the FreeBSD project or contributors. The glue code to emit triggers (possibly SVN, git or other submission, or even just daily) and the scripts to update the systems would also be maintained by the FreeBSD community. Phoronix Media would be happy to host it on Phoromatic.com (we've played with hosted with project branding) and provide the data store and the analytics. We'd also be willing to make enhancements to support the FreeBSD project. This should solve the "I don't have time to maintain a automated test infrastructure". You don't need to, just write the glue scripts, and dedicate a couple of machines. I believe FreeBSD vendors like ixSystems may be able to support this effort with a dedicated machine. You can have as many machines as you like demonstrating AMD/Intel/32/64/large mem/low mem,etc. The comments around interactivity can also be measured to some extent. We have the model of a "monitor". This can be configured to determine jitter around a number of system variables and to possibly inject actions to measure impacts. We're more than happy to work with you guys, and are willing to help do a lot of the infrastructure and automation lifting. Regards, Matthew On 12/22/11 8:56 AM, Adrian Chadd wrote: > Guys, girls, fuzzy creatures, > > This is by far the best example of a constructive email in this entire thread. > > If people would like to help, Erik here is exactly the kind of person > with exactly the kind of software that needs a hand. > > I think enough philosophizing has been done - now we have questions > that need answering; theories that need testing. And that requires, > you know, coding. :) > > The best thing right now would be for *BSD people to pick up the > Phronix test suite, try to compile/run it, and provide feedback. Do > your own benchmarks on your own hardware and report back the results. > That's how we fix the "benchmarking problem." We don't fix it by > armchair philosophy, we fix it by getting our hands dirty. :) > > 2c, > > > Adrian > > > On 22 December 2011 03:21, Erik Cederstrand wrote: >> Den 21/12/2011 kl. 19.48 skrev Alexander Leidinger: >> >>> And related to the subject: wasn't it you who developed the automatic benchmarking stuff? If yes, why not make it available? If you don't have he resources, I offer my help to make it available somewhere. >> Yes, that's me. I'm mostly out of time right now, but I'd like to offer help if someone wants to pick up the project. >> >> For those who haven't heard about it, it's a system designed specifically to track performance of FreeBSD over time by comparing revisions of FreeBSD, everything else being equal. It consists of a tinderbox-like build script for a build server, a script to install FreeBSD and run benchmarks on at least one slave, and a database-backed website to aggregate and visualize results. >> >> The framework does work as-is, but it really needs to be updated: convert the scripts to use the SVN repo instead of CVS, improve visualization and search on the web fronted, and improve the benchmarking script so it's easier to extend. I don't have hardware available to run the benchmarks, but I think there's hardware available in the FreeBSD cluster. >> >> Here's a link to the source code:http://dev.affect-it.dk/tracker.tgz >> And to my thesis describing how it works:http://dev.affect-it.dk/tracker.pdf >> >> Just send me a mail if you're interested. >> >> Thanks, >> Erik_______________________________________________ >> freebsd-performance@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-performance >> To unsubscribe, send any mail to"freebsd-performance-unsubscribe@freebsd.org" > _______________________________________________ > freebsd-performance@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-performance > To unsubscribe, send any mail to"freebsd-performance-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 23:44:19 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 38C1A106564A; Thu, 22 Dec 2011 23:44:19 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id E011A8FC0C; Thu, 22 Dec 2011 23:44:18 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RdsJ5-000468-V0>; Fri, 23 Dec 2011 00:44:16 +0100 Received: from e178027232.adsl.alicedsl.de ([85.178.27.232] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RdsJ5-0003tb-Q0>; Fri, 23 Dec 2011 00:44:15 +0100 Message-ID: <4EF3C0CE.5040802@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 00:44:14 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Alexander Leidinger References: In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig363DC61A08FC2B64410B086C" X-Originating-IP: 85.178.27.232 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, freebsd-stable@freebsd.org, freebsd@jdc.parodius.com, igor@hybrid-lab.co.uk Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 23:44:19 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig363DC61A08FC2B64410B086C Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/21/11 19:41, Alexander Leidinger wrote: > Hi, >=20 > while the discussion continued here, some work started at some other pl= ace. Now... in case someone here is willing to help instead of talking, f= eel free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look= what can be improved. The page is far from perfect and needs some additi= onal people which are willing to improve it. >=20 > This is only part of the problem. A tuning page in the wiki - which cou= ld be referenced from the benchmark page - would be great too. Any volunt= eers? A first step would be to take he tuning-man-page and wikify it. Oth= er tuning sources are welcome too. >=20 > Every FreeBSD dev with a wiki account can hand out write access to the = wiki. The benchmark page gives contributor-access. If someone wants write= access create a FirstnameLastname account and ask here for contributor-a= ccess. >=20 > Don't worry if you think your english is not good enough, even some one= -word notes can help (and _my_ english got already corrected by other peo= ple on the benchmark page). >=20 > Bye, > Alexander. >=20 >=20 >=20 >=20 Nice to see movement ;-) But there seems something unclear: man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in /etc/make.conf. The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. What's right and what's wrong now? Oliver --------------enig363DC61A08FC2B64410B086C Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO88DOAAoJEOgBcD7A/5N8fsMIAJqxov2X2KfdyjzSXd89kYdD w/JFgI4xZCVaStAHWTyHm7UJh+cQvaZBqGtKiBooTdiLcbhwOck7YgQ9WL8piCS/ CBvjHZC7xPUSIywIvVA7uGf9i3Lbxq/TuoO9+Qk9AOfKtZswn6hATMtlNMyw0OC6 bJBp0rGa7MHsFQ020z5tomRqfU2ANdu3GrrLpge9rTOUCZ+ieq7GGrWEwlTFiDAM bd7NCiWyjgBtsjLBYsS0mjhE6aNW5i1fyT74AzNEyNn5BTWSTg0QPyNS0VXUTdec lNsCQxFbmmX17tPjCBiCACKn99sYQ8PTDq49F5ksj57Ku9LzIQZLaXa7kRpVB9I= =ikbF -----END PGP SIGNATURE----- --------------enig363DC61A08FC2B64410B086C-- From owner-freebsd-performance@FreeBSD.ORG Thu Dec 22 23:58:50 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 91FDF1065673 for ; Thu, 22 Dec 2011 23:58:50 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta12.westchester.pa.mail.comcast.net (qmta12.westchester.pa.mail.comcast.net [76.96.59.227]) by mx1.freebsd.org (Postfix) with ESMTP id 090208FC18 for ; Thu, 22 Dec 2011 23:58:49 +0000 (UTC) Received: from omta21.westchester.pa.mail.comcast.net ([76.96.62.72]) by qmta12.westchester.pa.mail.comcast.net with comcast id CPaH1i0091ZXKqc5CPyq92; Thu, 22 Dec 2011 23:58:50 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta21.westchester.pa.mail.comcast.net with comcast id CPyo1i0151t3BNj3hPyocH; Thu, 22 Dec 2011 23:58:50 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id E5F55102C19; Thu, 22 Dec 2011 15:58:46 -0800 (PST) Date: Thu, 22 Dec 2011 15:58:46 -0800 From: Jeremy Chadwick To: "O. Hartmann" Message-ID: <20111222235846.GA6071@icarus.home.lan> References: <4EF3C0CE.5040802@zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EF3C0CE.5040802@zedat.fu-berlin.de> User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Fri, 23 Dec 2011 00:02:51 +0000 Cc: Alexander Leidinger , freebsd-performance@freebsd.org, freebsd-current@freebsd.org, freebsd-stable@freebsd.org, igor@hybrid-lab.co.uk Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 22 Dec 2011 23:58:50 -0000 On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: > On 12/21/11 19:41, Alexander Leidinger wrote: > > Hi, > > > > while the discussion continued here, some work started at some other place. Now... in case someone here is willing to help instead of talking, feel free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look what can be improved. The page is far from perfect and needs some additional people which are willing to improve it. > > > > This is only part of the problem. A tuning page in the wiki - which could be referenced from the benchmark page - would be great too. Any volunteers? A first step would be to take he tuning-man-page and wikify it. Other tuning sources are welcome too. > > > > Every FreeBSD dev with a wiki account can hand out write access to the wiki. The benchmark page gives contributor-access. If someone wants write access create a FirstnameLastname account and ask here for contributor-access. > > > > Don't worry if you think your english is not good enough, even some one-word notes can help (and _my_ english got already corrected by other people on the benchmark page). > > > > Bye, > > Alexander. > > > > > > > > > > Nice to see movement ;-) > > But there seems something unclear: > > man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in > /etc/make.conf. > The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. > > What's right and what's wrong now? I can say with certainty that this value belongs in /etc/make.conf (on RELENG_8 and earlier at least). src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, so, this is definitely a make.conf variable. -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 01:05:41 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 28A6E106566C; Fri, 23 Dec 2011 01:05:41 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 685D08FC0A; Fri, 23 Dec 2011 01:05:40 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RdtZr-0002Yw-Ld>; Fri, 23 Dec 2011 02:05:39 +0100 Received: from e178027232.adsl.alicedsl.de ([85.178.27.232] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RdtZr-0007Fs-Dr>; Fri, 23 Dec 2011 02:05:39 +0100 Message-ID: <4EF3D3E2.9000403@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 02:05:38 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Johan Hendriks References: <4EF25468.9040204@gmail.com> <4EF2D814.1090805@freebsd.org> <4EF2F210.6080009@gmail.com> In-Reply-To: <4EF2F210.6080009@gmail.com> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigA2AB74508AC85FFC0BBAD257" X-Originating-IP: 85.178.27.232 Cc: freebsd-performance@freebsd.org, Stefan Esser , FreeBSD Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 01:05:41 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigA2AB74508AC85FFC0BBAD257 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/22/11 10:02, Johan Hendriks wrote: > Stefan Esser schreef: >> Am 21.12.2011 22:49, schrieb Johan Hendriks: >>> Nice page, but one thing i do not get is the following. >>> >>> [quote] >>> If you compare FreeBSD / GCC 4.2.1 against, for example, Ubuntu / GCC= >>> 4.7 then the results are unlikely to tell you anything meaningful abo= ut >>> FreeBSD vs Ubuntu. >>> [/quote] >>> >>> That is a little strange in my opinion. >>> It tells me that FreeBSD falls more and more behind on Linux. >>> The reason is or could be that FreeBSD cannot or will not include GCC= >>> 4.7 and that FreeBSD will not be on par with Linux anymore. >>> To compare it with Formula1 cars. >>> If Mercedes decide to use the engine from 2 seasons back (the engine >>> version 4.2.1) in there 2012 car, and Ferrari uses there new Engine >>> (version 4.7). >>> Can we not compare them anymore because of the decission from Mercede= s >>> to use the old engine? >>> No we just say, if you want to win a race, get the Ferrari. >>> >>> It is the reallity, FreeBSD uses 4.2.1 as there compiler!!! >> As has been pointed out by others, FreeBSD ships with gcc-4.2.1 (with >> some local modifications and fixes) as the system compiler. >=20 >>> If you tune up FreeBSD to use the GCC 4.7 compiler, or downgrade linu= x >>> to 4.2.1, then that will tell me nothing about FreeBSD vs Linux. >> The gcc version distributed with FreeBSD was chosen for license reason= s, >> not for technical reasons. If you are OK with installing a GPLv3 >> licensed compiler on your systems, then just do it and take advantage = of >> the improved code generated by it. > It does not matter what the decission is to use the old compiler, it is= > a fact that the base comes with 4.2.x > Does that mean we can not compare/benchmark against other distributions= > because they use GPLv3 stuff. > No, i want to know where standard released FreeBSD stands against > standard released Linux distributions. > If you compare benchmark userland applictions, then it is fair to use > the latest compiler for the userland software also on FreeBSD. > But what if the ports tree defaults to LLVM, then again we want to know= > what FreeBSD does against a Linux distribution. > Why because that is what most of us will be using...!! Who ever tried to use gcc 4.6 to compile the base system knows that it is no eays task and it isn't so easy to simply change the compiler! This is also true for a lot of ports. If it is so easy to use a more modern compiler as some of the statements made here would suggest, then I would expect a dedicated chapter in the handbook! In such a case, every systems administrator trying to make a long-term decission what operating system might be the base for the future, does not need to be an enthusiastic of either BSD or Linux to understand how to tweak - fanboys, developers or enthusiasts have already choosen, apart from any rational or reason. What matters are advantages which can be approved. Downlad the DVD, install the OS, do some adjustments regarding to some pages of the manual, choose a propper set of applicable software to benchmark, compile, benchmark the system. Phoronix did so. Well, it's hard for me to find the chapter in the handbook which describes the performance tuning of SCHED_ULE and its sysctl tweaks, someone may call me stupid and point me to the page, please ... >=20 > If we start to compile all the ports with gcc 4.7 to be on par in > comparising and benchmarking, why spend all the time getting LLVM as th= e > default compiler for ports also? > Why not take that effort into making the WHOLE ports tree to compile > with GCC4.7? >=20 > Reason, because FreeBSD goes the LLVM route. That is a decission FreeBS= D > is making! Yes, and it is legitime to question that and bring pro and contra for that decission. But since "FreeBSD" is obviously a small club of people sitting like a duck on eggs (and, by the way, not their own genuine invented eggs, more or less reingeneered eggs), those decissions get more obscure than they seem to be anyway. > And that choise will be the FreeBSD that is used in comparising and > benchmarks on the net , not the utterly overcopiled and tuned FreeBSD > against stock Ubuntu or whatever Linux distribution. >=20 > If it is a good or bad choice! That we will see in the > comparising/benchmarks we will be seeing when that time comes. >=20 > Same goes for the scheduler! and all the other subsystems FreeBSD has > choosen, that makes FreeBSD. >=20 =2E.. sometimes the underdog has to pick up what's left ... >> >>> I my opinion, you benchmark the latest release of Linux, FreeBSD, >>> Solaris, Windows and whatever OS you want to compare! >> As you probably know, Linux is just the kernel and the distributions a= dd >> user space programs, including a compiler. You can easily create a >> "FreeBSD distribution" with more advanced compiler and use or even sel= l >> it. But the FreeBSD project was cautious to not heavily depend on a >> GPLv3 compiler (for reasons openly discussed at the time this decision= >> was made). > I know Linux is a kernel, re read Linux as Linux Distribution! > Yes you can use a more advanced compiler on FreeBSD, BUT you can do tha= t > on Linux also ,so where do you stop? > Are you going to spend a month to compare a fullly tuned up FreeBSD > system against a Linux distribution? > No because the users will not spend months tuning and recompile there > servers. > They use the FreeBSD version that comes with the CD! > And that we want to compare/benchmark against a Linux distribution. When it comes to the question what to benchmark, what would you suggest? Only the Linux kernel, so called LINUX and a couple of self selected, self compiled, probably seld optimized GNU userland tools? At the end I pick up a distribution as it comes from the "vendor", pick up some informations about tweaks for several target workloads and start benchmarking. >=20 >>> You want to benchmark the release and not a tuned version against a >>> standard version. >>> And that in general are the versions most of us users will use. >> If you compare operating systems from a technical point of view, then >> you'll be interested in relative performance of algorithms and methods= >> chosen. This is best achieved by using the same compiler for each of t= he >> candidates. >> >> If you compare performance from a user point of view, you are correct >> that performance delivered out of the box (without complicated tuning)= >> may be, what counts for most users. But those users that depend on bes= t >> performance e.g. for a FreeBSD based embedded product or a data center= , >> may tune the system, including compilation with a newer compiler than >> the system default. >> >>> And what if in the future LLVM gets on par with Linux, is it stil fai= r >>> to compare FreeBSD with Linux? >> You can always compare anything with whatever you like (even apples wi= th >> oranges), but you need to be aware of what you compare and what your >> goals are, to be able to draw reasonable conclusions. >> >> If you want to test out of the box performance, then test with system >> compilers (or just those binaries delivered with the system). >> >> If you want to test for code efficiency or scalability, then use the >> same compilers for each system under test to remove differences >> introduced by the compilers (which are an external component not >> developed by the FreeBSD people). >> >>> Or do we say, well we are on par, but it is not fair, yes we used the= >>> latest releases, but you can not blame Linux because they are still >>> using GCC. >> Depends on what you want or need to measure ... > I am mainly talking about the out of the box comparison, because that i= s > what most sites will do when doing a benchmark. > they want to know if the the all new version of FreeBSD can compete wit= h > the latest release of Ubuntu. > That are the benchmarks you will see on the net. And this is the right way to do. The only way. I start my project now. I got funding now. I have a time contraint to keep to fullfill my scientific work, say, a PhD or a project. I need to look into the future, I need to make decissions for a long haul development. So, I pick up the OSs of my choice and benchmark them as they are. All right, if there is a chapter in the handbook explaining how to tune towards a specific expected workload, much better, so do so =2E.. If this is not the way it is, please correct me! >=20 >=20 >>> No what we will see then are haleluja blogs that FreeBSD is on par wi= th >>> Linux. >> Such blog messages are not common in the FreeBSD community. FreeBSD us= ed >> to have big technical and performance advantages when Linux was young,= >> but even then, there was technical discussion between camps (and many >> concepts were implemented in Linux based on BSD examples; I have taken= >> part in such discussions myself, some 15 to 20 years back). > Well not quite, i remember the mysql on SCHED_ULE reports, and they > where quit haleluja about the whole thing. > Not wrong at all, we are all human and like to compete and even more > like to be on top in what we do. >=20 >=20 >>> For me peformance is not a show stopper, and for the most of us i thi= nk >>> it is not. >>> FreeBSD for me is a clean system that does the job perfect and has a >>> very helpful community. >> Well, this are valid aspects, too, and very hard to with benchmarks ;-= ) >> >> Regards, STefan > I am not saying FreeBSD is bad and is not performing, i just do not > understand why FreeBSD is doing all these things to look good. > Again, most comparisings/benchmarks will be stock *BSD vs a stock Linux= > distribution. > If we want to look good, FreeBSD must make sure there released version > gets on par! > We all know FreeBSD is quite conservative with its default settings. > Maybe we need to set some default settings less conservative. > But i do not know if that is good just for the numbers! >=20 > Regards, > Johan oh --------------enigA2AB74508AC85FFC0BBAD257 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO89PiAAoJEOgBcD7A/5N8hNcIAJatBurrv4Hjl/pyaGSP+wlV v2OjnU5nAL9ahjoC3xqZZ3BAvSGxN2XpFozE5LS4TEQQaPNs7Uy4DBRk3h4Zgc7Z YiVt7wJQouX9Lps7H+5d3sPV7XXqbYJjA304bwWeRoHMjE/gqjmM55eLi3h1Cs0I toHrQf6EV0IOeOqObguBcDdANX4tA1VVZPO0Y48bCC1wSsJvUlt8qw9OOPbUUKGR BFsW6Aqc587vVG+sW1GkKXKShiBfjkVl0sogmxqCSvTesQYkmlRaeN/h2swEzIhK DQm3M4+unIxypCmX9VcgMbtnlywr0JE+7+P8wzl/ftE9M02W3adPftwbDdbsih4= =Q9m2 -----END PGP SIGNATURE----- --------------enigA2AB74508AC85FFC0BBAD257-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 01:17:03 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6FA3F106564A; Fri, 23 Dec 2011 01:17:03 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 2190C8FC12; Fri, 23 Dec 2011 01:17:03 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Rdtkr-0003VQ-6t>; Fri, 23 Dec 2011 02:17:01 +0100 Received: from e178027232.adsl.alicedsl.de ([85.178.27.232] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Rdtkr-0007gX-1Q>; Fri, 23 Dec 2011 02:17:01 +0100 Message-ID: <4EF3D68C.2060803@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 02:17:00 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Igor Mozolevsky References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enigAF289CA4D0C93747BA1C84E1" X-Originating-IP: 85.178.27.232 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Daniel Kalchev Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 01:17:03 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enigAF289CA4D0C93747BA1C84E1 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable On 12/22/11 10:56, Igor Mozolevsky wrote: > On 22 December 2011 05:54, Daniel Kalchev wrote: [...] >> Any 'benchmark' has a goal. You first define the goal and then measure= how >> different contenders achieve it. Reaching the goal may have several >> measurable metrics, that you will use to later declare the winner in e= ach. >> Besides, you need to define a baseline and be aware of what theoretica= l >> max/min values are possible. >=20 > Treating a benchmark as a binary win/lose is rather naive, it's not a > competition, and (I hope) no serious person ever does that. A proper > benchmark shows true strength and weaknesses so than a well-informed > intelligent decision can be taken by an individual according to that > individual's needs. The caveat, of course, is making your methodology > clear and methods repeatable! >=20 >=20 > Cheers, >=20 > -- Benchmarks also could lead developers to look into more details of the weak points of their OS, if they're open for that. Therefore, benchmarks are very useful. But not if any real fault of the OS is excused by a faulty becnhmarking. I remember that the worse threaded I/O performance of FreeBSD has been long discussed as a bad benchmarks schematics. Or even look at the thread regarding to SCHED_ULE. Why has a user, experiencing really worse performance with SCHED_ULE, in a nearly scientific manner some engineer the fault? I'd expect the developer or care-taking engineer taking care in a more user friendly manner. If a benchmark reveals some severe weak points in FreeBSD and I have to read about obscure tweaks of non documented sysctl, then this OS would be a no-go if I was a manager to make decissions. And yes, i know, FreeBSD is an free and open project. But I also know that this free and open project does not rely only on "volonteers". A volunteers do not expect funding or payment. So, even freeBSD is dependend on some finacial basis and such a basis has to be taken care of= =2E --------------enigAF289CA4D0C93747BA1C84E1 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO89aMAAoJEOgBcD7A/5N8crUIAMyz/7q/VOujbdrUZrfa9MqN mZv95SkaWn9nBFOxL5FRVbrPgqg8Ys4D82JPsNQwdZbQD+rtGSm1wwQmRsSKu+cZ j4IfOyiLMnNC5e3hWYwjtaVow2QKQjmL9NaQzb3UHe+snD6i8nB/DAwC2jhduhN+ wPXJM61uNV6oaShc7+dOnc+wOz9Q6oDqtXFTZVdalVZkKi8CqEEP428FcH2N1lp2 X2bcPBFi9eOkzyuHk/F4weKMCFFzq13r+7nuz9Dqndc7adbvl08WMoxClP3Foe99 jMA0I8VbRXtdLeoXVlaCqa1+jobCbJFO5Dsu8NM5JdNi2IMa71KTjY1HGyBs4oQ= =UdvK -----END PGP SIGNATURE----- --------------enigAF289CA4D0C93747BA1C84E1-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 01:31:06 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6D43B1065675; Fri, 23 Dec 2011 01:31:06 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 206F18FC17; Fri, 23 Dec 2011 01:31:05 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1RdtyT-0004ah-5b>; Fri, 23 Dec 2011 02:31:05 +0100 Received: from e178027232.adsl.alicedsl.de ([85.178.27.232] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1RdtyT-0008GR-0C>; Fri, 23 Dec 2011 02:31:05 +0100 Message-ID: <4EF3D9D7.5010907@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 02:31:03 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Adrian Chadd References: <001CED31-FDD0-4CB1-B972-2F2344EEB9D3@cederstrand.dk> In-Reply-To: X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig67F64EE14A43A4461166E561" X-Originating-IP: 85.178.27.232 Cc: Alexander Leidinger , freebsd-performance@freebsd.org, Erik Cederstrand Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 01:31:06 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig67F64EE14A43A4461166E561 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/22/11 17:56, Adrian Chadd wrote: > Guys, girls, fuzzy creatures, >=20 > This is by far the best example of a constructive email in this entire = thread. Agreed! >=20 > If people would like to help, Erik here is exactly the kind of person > with exactly the kind of software that needs a hand. >=20 > I think enough philosophizing has been done - now we have questions > that need answering; theories that need testing. And that requires, > you know, coding. :) Many thanks for that piece of software. And many thanks to Erik for the thesis as well. >=20 > The best thing right now would be for *BSD people to pick up the > Phronix test suite, try to compile/run it, and provide feedback. Do > your own benchmarks on your own hardware and report back the results. > That's how we fix the "benchmarking problem." We don't fix it by > armchair philosophy, we fix it by getting our hands dirty. :) :-) >=20 > 2c, >=20 >=20 > Adrian >=20 >=20 > On 22 December 2011 03:21, Erik Cederstrand wrote= : >> Den 21/12/2011 kl. 19.48 skrev Alexander Leidinger: >> >>> And related to the subject: wasn't it you who developed the automatic= benchmarking stuff? If yes, why not make it available? If you don't have= he resources, I offer my help to make it available somewhere. >> >> Yes, that's me. I'm mostly out of time right now, but I'd like to offe= r help if someone wants to pick up the project. >> >> For those who haven't heard about it, it's a system designed specifica= lly to track performance of FreeBSD over time by comparing revisions of F= reeBSD, everything else being equal. It consists of a tinderbox-like buil= d script for a build server, a script to install FreeBSD and run benchmar= ks on at least one slave, and a database-backed website to aggregate and = visualize results. >> >> The framework does work as-is, but it really needs to be updated: conv= ert the scripts to use the SVN repo instead of CVS, improve visualization= and search on the web fronted, and improve the benchmarking script so it= 's easier to extend. I don't have hardware available to run the benchmark= s, but I think there's hardware available in the FreeBSD cluster. >> >> Here's a link to the source code: http://dev.affect-it.dk/tracker.tgz >> And to my thesis describing how it works: http://dev.affect-it.dk/trac= ker.pdf >> >> Just send me a mail if you're interested. >> >> Thanks, >> Erik_______________________________________________ >> freebsd-performance@freebsd.org mailing list >> http://lists.freebsd.org/mailman/listinfo/freebsd-performance >> To unsubscribe, send any mail to "freebsd-performance-unsubscribe@free= bsd.org" > _______________________________________________ --------------enig67F64EE14A43A4461166E561 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO89nXAAoJEOgBcD7A/5N8XZsIAIZ/K7IBO87qbjhuwQ/oAXzZ Gn5mI/Djv2bteW4trvGRHoB1xg9rG81tXU2ONgOhVRvTgEFd2pXDNU1Fr0llF/5N raVPBr4d7+WprNBykYhdYdj/XrNHLZL8PrAz5y1R8tr29xpxzJaB8O5dRWS7rv4u VB/JVLFdqs7y8POY3TrGpuQmIWSJAXYjjOSHLQ1JjmFf3/DfRV3qqD70298G5+Pi bzVZgqDuDMdKpj8pe+1Wt2cCaWKsDO7owlEJuUu5765IuhGZqSUdtlv8nnP5C5Sp 5wgGq/E1m/FWYbF/zLFXtNBUuYnydZAF/6gloCrd3E1RP+93fHeaU7HDp1n4dxA= =Sv+f -----END PGP SIGNATURE----- --------------enig67F64EE14A43A4461166E561-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 02:56:32 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F03DC106564A; Fri, 23 Dec 2011 02:56:31 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-iy0-f182.google.com (mail-iy0-f182.google.com [209.85.210.182]) by mx1.freebsd.org (Postfix) with ESMTP id 9572C8FC0A; Fri, 23 Dec 2011 02:56:31 +0000 (UTC) Received: by iadj38 with SMTP id j38so16048658iad.13 for ; Thu, 22 Dec 2011 18:56:31 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=references:in-reply-to:mime-version:content-transfer-encoding :content-type:message-id:cc:x-mailer:from:subject:date:to; bh=C7U0E5PPsXEkzu6WcR6qQiAumZ0/fligcBBPx+q5vbI=; b=Y9k2MSZvPbLQDnA/bCDeEwk1xJG5A4DfHyTUGCHHLgYw1KT1hjcVBQinR8OBDvF1s2 QUK7mVuhaELk+i1bB5xR4/Fuo/oo0cVZ7GalqLM9pgb9c8O7nL8JJBOIeufhjqY2Pg5d Lc332WMvE8mayCPh3fwMSUx34dj3XjoYxZ9qU= Received: by 10.50.170.35 with SMTP id aj3mr11595295igc.2.1324608991063; Thu, 22 Dec 2011 18:56:31 -0800 (PST) Received: from [10.75.41.133] (mobile-166-205-136-165.mycingular.net. [166.205.136.165]) by mx.google.com with ESMTPS id gf6sm38973155igb.1.2011.12.22.18.56.25 (version=TLSv1/SSLv3 cipher=OTHER); Thu, 22 Dec 2011 18:56:30 -0800 (PST) References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> In-Reply-To: <20111222235846.GA6071@icarus.home.lan> Mime-Version: 1.0 (1.0) Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=us-ascii Message-Id: <9706CBFC-9A69-4365-8883-FF45BDFDC108@gmail.com> X-Mailer: iPhone Mail (9A405) From: Garrett Cooper Date: Thu, 22 Dec 2011 18:56:17 -0800 To: Jeremy Chadwick Cc: "freebsd-stable@freebsd.org" , "freebsd-current@freebsd.org" , "igor@hybrid-lab.co.uk" , Alexander Leidinger , "freebsd-performance@freebsd.org" , "O. Hartmann" Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 02:56:32 -0000 On Dec 22, 2011, at 3:58 PM, Jeremy Chadwick wrot= e: > On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: >> On 12/21/11 19:41, Alexander Leidinger wrote: >>> Hi, >>>=20 >>> while the discussion continued here, some work started at some other pla= ce. Now... in case someone here is willing to help instead of talking, feel f= ree to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look what ca= n be improved. The page is far from perfect and needs some additional people= which are willing to improve it. >>>=20 >>> This is only part of the problem. A tuning page in the wiki - which coul= d be referenced from the benchmark page - would be great too. Any volunteers= ? A first step would be to take he tuning-man-page and wikify it. Other tuni= ng sources are welcome too. >>>=20 >>> Every FreeBSD dev with a wiki account can hand out write access to the w= iki. The benchmark page gives contributor-access. If someone wants write acc= ess create a FirstnameLastname account and ask here for contributor-access. >>>=20 >>> Don't worry if you think your english is not good enough, even some one-= word notes can help (and _my_ english got already corrected by other people o= n the benchmark page). >>>=20 >>> Bye, >>> Alexander. >>>=20 >>>=20 >>>=20 >>>=20 >>=20 >> Nice to see movement ;-) >>=20 >> But there seems something unclear: >>=20 >> man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in >> /etc/make.conf. >> The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. >>=20 >> What's right and what's wrong now? >=20 > I can say with certainty that this value belongs in /etc/make.conf > (on RELENG_8 and earlier at least). >=20 > src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, > so, this is definitely a make.conf variable. Take the advice in tuning(7) with a grain of salt because a number of sugges= tions are really outdated. I know because I filed a PR last night after I sa= w how out of synch some of the defaults it claimed were with reality on 9.x+= . And I know other suggestions in the manpage are dated as well ;/. Thanks, -Garrett= From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 10:38:25 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1222E106566C; Fri, 23 Dec 2011 10:38:25 +0000 (UTC) (envelope-from vince@unsane.co.uk) Received: from unsane.co.uk (unsane-pt.tunnel.tserv5.lon1.ipv6.he.net [IPv6:2001:470:1f08:110::2]) by mx1.freebsd.org (Postfix) with ESMTP id 829018FC18; Fri, 23 Dec 2011 10:38:24 +0000 (UTC) Received: from vhoffman-macbooklocal.local ([10.10.10.20]) (authenticated bits=0) by unsane.co.uk (8.14.4/8.14.4) with ESMTP id pBNAcKPR056271 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Fri, 23 Dec 2011 10:38:20 GMT (envelope-from vince@unsane.co.uk) Message-ID: <4EF45A1B.1050505@unsane.co.uk> Date: Fri, 23 Dec 2011 10:38:19 +0000 From: Vincent Hoffman User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Garrett Cooper References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> <9706CBFC-9A69-4365-8883-FF45BDFDC108@gmail.com> In-Reply-To: <9706CBFC-9A69-4365-8883-FF45BDFDC108@gmail.com> X-Enigmail-Version: 1.3.4 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "freebsd-stable@freebsd.org" , "freebsd-current@freebsd.org" , "igor@hybrid-lab.co.uk" , Alexander Leidinger , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 10:38:25 -0000 On 23/12/2011 02:56, Garrett Cooper wrote: > On Dec 22, 2011, at 3:58 PM, Jeremy Chadwick wrote: > >> On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: >>> On 12/21/11 19:41, Alexander Leidinger wrote: >>>> Hi, >>>> >>>> while the discussion continued here, some work started at some other place. Now... in case someone here is willing to help instead of talking, feel free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look what can be improved. The page is far from perfect and needs some additional people which are willing to improve it. >>>> >>>> This is only part of the problem. A tuning page in the wiki - which could be referenced from the benchmark page - would be great too. Any volunteers? A first step would be to take he tuning-man-page and wikify it. Other tuning sources are welcome too. >>>> >>>> Every FreeBSD dev with a wiki account can hand out write access to the wiki. The benchmark page gives contributor-access. If someone wants write access create a FirstnameLastname account and ask here for contributor-access. >>>> >>>> Don't worry if you think your english is not good enough, even some one-word notes can help (and _my_ english got already corrected by other people on the benchmark page). >>>> >>>> Bye, >>>> Alexander. >>>> >>>> >>>> >>>> >>> Nice to see movement ;-) >>> >>> But there seems something unclear: >>> >>> man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in >>> /etc/make.conf. >>> The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. >>> >>> What's right and what's wrong now? >> I can say with certainty that this value belongs in /etc/make.conf >> (on RELENG_8 and earlier at least). >> >> src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, >> so, this is definitely a make.conf variable. > Take the advice in tuning(7) with a grain of salt because a number of suggestions are really outdated. I know because I filed a PR last night after I saw how out of synch some of the defaults it claimed were with reality on 9.x+. And I know other suggestions in the manpage are dated as well ;/. There is a wiki page http://wiki.freebsd.org/SystemTuning which is currently more or less tuning(7) with some annotations, the idea being to sort out whats outdated/invalid with an aim of rewriting tuning(7) to be more accurate and useful. I'll grab any info in your pr thats not up there already to keep it updated if thats ok. Vince > Thanks, > -Garrett_______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 07:13:56 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 719EF106564A for ; Fri, 23 Dec 2011 07:13:56 +0000 (UTC) (envelope-from martin@sugioarto.com) Received: from mailserv.regfish.com (mailserv.regfish.com [79.140.61.33]) by mx1.freebsd.org (Postfix) with ESMTP id B83D48FC19 for ; Fri, 23 Dec 2011 07:13:54 +0000 (UTC) Received: (qmail 4306 invoked from network); 23 Dec 2011 06:47:13 -0000 Received: from pd9ec02b0.dip0.t-ipconnect.de (HELO yuni.sugioarto.com) (46959-0001@[217.236.2.176]) (envelope-sender ) by mailserv.regfish.com (qmail-ldap-1.03) with SMTP for ; 23 Dec 2011 06:47:13 -0000 Received: from zelda.sugioarto.com (zelda.sugioarto.com [192.168.0.12]) by yuni.sugioarto.com (Postfix) with ESMTP id 066EF1BAC57; Fri, 23 Dec 2011 07:47:11 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=sugioarto.com; s=mail; t=1324622832; bh=cQB+8TKO5vLCqciaHHbSVsfp1qERUqnQUj35oShp5MA=; h=Date:From:To:Cc:Subject:Message-ID:In-Reply-To:References: Mime-Version:Content-Type; b=NsXkMgj/FwSHvW7Zag1prmzup3/cNJkEdKfWgeG8sxHaBEb7AHuo8Pw+JdO2Qp0qM eAnyed3nDwMYL/JjKAbMHK+hwLQqDvb0fB8+VdaYY+jrvQu3x5Wrz6v7qpWEapD+8D hcGXjc0dz4vKpDTngsCoZ4v8umwS5njZdQ6GDURQ= Date: Fri, 23 Dec 2011 07:47:06 +0100 From: Martin Sugioarto To: "O. Hartmann" Message-ID: <20111223074706.1afe4d26@zelda.sugioarto.com> In-Reply-To: <4EF3D68C.2060803@zedat.fu-berlin.de> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> X-Mailer: Claws Mail 3.7.10 (GTK+ 2.24.6; amd64-portbld-freebsd9.0) Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/jRZwjGURFyHlrz8lFS52Y/6"; protocol="application/pgp-signature" X-Mailman-Approved-At: Fri, 23 Dec 2011 12:09:16 +0000 Cc: Daniel, freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky , Kalchev Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 07:13:56 -0000 --Sig_/jRZwjGURFyHlrz8lFS52Y/6 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Am Fri, 23 Dec 2011 02:17:00 +0100 schrieb "O. Hartmann" : > Benchmarks also could lead developers to look into more details of the > weak points of their OS, if they're open for that. Therefore, > benchmarks are very useful. But not if any real fault of the OS is > excused by a faulty becnhmarking. Hi, it is important for the project to be known and I think that the benchmarks made by Phoronix help FreeBSD to gain popularity, even they look bad sometimes. Furthermore, to make a benchmark is a lot of work and the results are useful, because at the end someone will look at it and will try to improve the results. Thank you for investing your time. I remember that I've made some tests with different platforms i386 vs amd64 with simple tools like "openssl speed" some time ago and got some bad results for amd64 that no one cared to explain. These bad results weren't reflected on Linux that I tested later for comparison. And most people have a weird attitude to think that the tester measures wrong instead of taking a look at it. They forget that as a FreeBSD user you would rather see FreeBSD win over Linux. I've seen that Phoronix made various benchmarks about FreeBSD compared to Linux and I can tell you that _subjectively_ the benchmarks reflect what I always thought about FreeBSD. I simply _know_ that FreeBSD is worse in concurrency behavior, I know that it has I/O trouble, I know that it is mostly faster emulating 3D games than Linux runs them natively. I knew this already _before_ you published the benchmark about the 3D performance. I cannot see any evil intentions in these benchmarks. All I can see is the wrong attitude _here_. If anyone thinks that Phoronix makes bad benchmarks, they should do these benchmarks by themselves and publish the results. As long as no one tries, Phoronix stays the best reference for me and for everyone else. And don't forget, benchmarks can never be objective enough and someone will always be mad about the results. Especially, when you present them a "versus battle". A further thing is that I cannot understand the people here sometimes. I would like that the -RELEASE versions of FreeBSD perform well without any further optimizations. When the distribution does not compile with the latest compiler it's simply a bug. Why should one try to penalize the other distribution and downgrade their binaries? When FreeBSD has a bad default setup, there must be a reason for that. Tell me this reason and show me that it's justified in form of some other benchmark. -- Martin --Sig_/jRZwjGURFyHlrz8lFS52Y/6 Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) iQIcBAEBAgAGBQJO9CPvAAoJEF8wvLx/5p/7AscP/36ttnZiUG518fD7APAPwH7d 5h1i23jL29L5eF2XECnjk6sqXX8VasM85186oFSQGiOmCPgTNIU32ke/zhpzm3AN wRffG6SwQEfJWz/jxdbTu0plLchBsIzVtxArLfqVgc9MVsxcyp8+PPGolBESWN27 xQrTasf8G8JZB/HbXIrrins/8h+DWOfUn5yTO5OFmYst5H0Iziy9MhKFh/EqvBXn Lj/2V2Gf0qy9ISDXc6lxHdlZmtANP/0QTSuEBovm/5qZAMoOUSKyUlxd6W+XRfKV S1O1BMp3XL9rZOj9kevgNPKUTKy56Asga1Gpo17iAJP7/9TLnpIndrWOnBWi4dgc bHYUHeyOesdNFc5Wx3bIKtwZWFn8alN5wNK4MveTN02k4KmDkB8Kdu1XzW7guKXj TdrK3vRiqZKIf979knEeUvlE/0jhyew6epEawTqa/u3mt5Of+tAWTnMJkF231+K2 iq3ud0FHRGle0AEEKT77KVvh4LS/kpbWy6EEITKNLg2BCh8LWdQOGHc+BBh7IWhz HS154BQs8F27zTuqh7PWWv4iqG9qr7QltNDldtDYEZGw+Vwe5hyFJ7myqaYXQoF8 98U8xwnToL1yqhLwmiPwTWXSYZAGqgdwPqD5xpcC+WAyUJs+fbi4qsTxD5vBPWqn OyTMoFHe1G+9V1/2upYZ =jyvu -----END PGP SIGNATURE----- --Sig_/jRZwjGURFyHlrz8lFS52Y/6-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 09:07:22 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id F2E5A106566B; Fri, 23 Dec 2011 09:07:22 +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 740418FC18; Fri, 23 Dec 2011 09:07:21 +0000 (UTC) Received: from dcave.digsys.bg (dcave.digsys.bg [192.92.129.5]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBN977WM046266 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Fri, 23 Dec 2011 11:07:13 +0200 (EET) (envelope-from daniel@digsys.bg) Message-ID: <4EF444BB.9090400@digsys.bg> Date: Fri, 23 Dec 2011 11:07:07 +0200 From: Daniel Kalchev User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: "O. Hartmann" References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> In-Reply-To: <4EF3D68C.2060803@zedat.fu-berlin.de> Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Fri, 23 Dec 2011 12:27:21 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 09:07:23 -0000 On 23.12.11 03:17, O. Hartmann wrote: > Or even look at the thread regarding to SCHED_ULE. Why has a user, > experiencing really worse performance with SCHED_ULE, in a nearly > scientific manner some engineer the fault? I'd expect the developer or > care-taking engineer taking care in a more user friendly manner. You remember that those developers are not paid to do what they do? You remember that nobody has sold you this OS and promised support in whatever form? Still, this issue is discussed publicly and experiments are being made, I guess also new code is being experimented. If you are interested in the outcome, just follow the discussion. If you can help with something and you are willing, please do. There will be good solution to the SCHED_ULE shortcomings. FreeBSD is unique group of people, who all sit on their eggs, be it eggs they themselves produced, or they inherited one way or another. These people include all the developers and most of the system administrators and users of FreeBSD. There is no "they" and "us". If your preference for the OS is different, you might feel more comfortable in choosing another OS, probably a commercial OS with support from the vendor. > If a benchmark reveals some severe weak points in FreeBSD and I have > to read about obscure tweaks of non documented sysctl, then this OS > would be a no-go if I was a manager to make decissions. Luckily, managers do not care about knobs or how difficult it is for the system administrator to achieve specific goal. All they care is the bottom line in general and in short therm the goals they have set. No sane manager will care about benchmarks, as long as he gets what he wants. Back, to the Phoronix benchmarks. There has already been communication. Phoronix were given advices on how to better do some things on FreeBSD (which will make the quality of their benchmarks better and therefore more trusted). Phoronix has made their updated test suite available to FreeBSD users (that include developers) to try on their own hardware. By the way, it is in /usr/ports/benchmarks/phoronix-test-suite. Linux and FreeBSD are not enemies, they both solve the same problems with different means. Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 09:18:13 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9F14C1065673; Fri, 23 Dec 2011 09:18:13 +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 047828FC13; Fri, 23 Dec 2011 09:18:12 +0000 (UTC) Received: from dcave.digsys.bg (dcave.digsys.bg [192.92.129.5]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBN9I31R046333 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Fri, 23 Dec 2011 11:18:09 +0200 (EET) (envelope-from daniel@digsys.bg) Message-ID: <4EF4474B.3050203@digsys.bg> Date: Fri, 23 Dec 2011 11:18:03 +0200 From: Daniel Kalchev User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Martin Sugioarto References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> In-Reply-To: <20111223074706.1afe4d26@zelda.sugioarto.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Fri, 23 Dec 2011 12:27:32 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, "O. Hartmann" , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 09:18:13 -0000 On 23.12.11 08:47, Martin Sugioarto wrote: > A further thing is that I cannot understand the people here sometimes. > I would like that the -RELEASE versions of FreeBSD perform well > without any further optimizations. The -RELEASE things is just a freeze (or, let's say tested freeze) of the corresponding branch at some time. It is the code available and tested at that time. Thus, it is safe to say that FreeBSD 8.0-RELEASE is much worse than FreeBSD RELENG_8 (still 8.2 at the moment), because years have passed between both code bases, lots of bugs have been discovered and fixed and new technologies have been integrated. Especially in this line, the compiler has changed from 4.2.1 to 4.2.2. > When the distribution does not compile with the latest compiler it's > simply a bug. FreeBSD is not a distribution. It also compiles with the latest compiler - LLVM. :) I find it amusing, that people want everything compiled with GCC 4.7, which is still very much developing, therefore highly unstable and (probably) full of bugs. > Why should one try to penalize the other distribution and downgrade > their binaries? Many suggested that the Linux binaries be run via the FreeBSD Linux emulation. Unchanged. There is one problem here though, the emulation is still 32 bit. > When FreeBSD has a bad default setup, there must be a reason for that. > Tell me this reason and show me that it's justified in form of some > other benchmark. FreeBSD has safe default. It is supposed to work out of the box on whatever hardware you put it. As much as it has drives for that hardware, of course. Once you have working installation, you may tweak it all the way you wish. If your installation is pre-optimized, chances are it will crash all the time on you and there will be no easy way for you to fix, short of installing another "distribution". Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 10:48:42 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 2B82A1065672; Fri, 23 Dec 2011 10:48:42 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id C36368FC1B; Fri, 23 Dec 2011 10:48:38 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Re2g1-0005Kp-J0>; Fri, 23 Dec 2011 11:48:37 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Re2g1-0007XM-Gu>; Fri, 23 Dec 2011 11:48:37 +0100 Message-ID: <4EF45C85.9010709@mail.zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 11:48:37 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Martin Sugioarto References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> In-Reply-To: <20111223074706.1afe4d26@zelda.sugioarto.com> X-Enigmail-Version: undefined Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Fri, 23 Dec 2011 12:27:50 +0000 Cc: freebsd-current@freebsd.org, Igor Mozolevsky , Kalchev , freebsd-performance@freebsd.org, "O. Hartmann" , Daniel@FreeBSD.ORG Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 10:48:42 -0000 On 12/23/11 07:47, Martin Sugioarto wrote: > Am Fri, 23 Dec 2011 02:17:00 +0100 > schrieb "O. Hartmann" : > >> Benchmarks also could lead developers to look into more details of the >> weak points of their OS, if they're open for that. Therefore, >> benchmarks are very useful. But not if any real fault of the OS is >> excused by a faulty becnhmarking. > > Hi, > > it is important for the project to be known and I think that the > benchmarks made by Phoronix help FreeBSD to gain popularity, even they > look bad sometimes. > > Furthermore, to make a benchmark is a lot of work and the results are > useful, because at the end someone will look at it and will try to > improve the results. Thank you for investing your time. > > I remember that I've made some tests with different platforms i386 vs > amd64 with simple tools like "openssl speed" some time ago and got some > bad results for amd64 that no one cared to explain. These bad results > weren't reflected on Linux that I tested later for comparison. And most > people have a weird attitude to think that the tester measures wrong > instead of taking a look at it. They forget that as a FreeBSD user you > would rather see FreeBSD win over Linux. > > I've seen that Phoronix made various benchmarks about FreeBSD compared > to Linux and I can tell you that _subjectively_ the benchmarks reflect > what I always thought about FreeBSD. I simply _know_ that FreeBSD is > worse in concurrency behavior, I know that it has I/O trouble, I know > that it is mostly faster emulating 3D games than Linux runs them > natively. I knew this already _before_ you published the benchmark > about the 3D performance. > > I cannot see any evil intentions in these benchmarks. All I can see is > the wrong attitude _here_. If anyone thinks that Phoronix makes bad > benchmarks, they should do these benchmarks by themselves and publish > the results. As long as no one tries, Phoronix stays the best reference > for me and for everyone else. There IS NO EVIL INTENTION, except, hypothetical, the benchmarker is of the age were he is called a "beardless". But: In many articles, there is a very distinguished and underlined emphasizing of Linux that makes me feeling people have their Linux-glasses on. Linux is not UNIX! And if today someone tells me about the Linux-graphical subsystem X11, I turn green in my face ... X11 was, in former days, a development made on UNIX and is adopted by Linux. Ok, we all know that, most of all ... And the aspect of reference: I agree. They do something and this thread arose while they did. > > And don't forget, benchmarks can never be objective enough and someone > will always be mad about the results. Especially, when you present them > a "versus battle". > > A further thing is that I cannot understand the people here sometimes. > I would like that the -RELEASE versions of FreeBSD perform well without > any further optimizations. When the distribution does not compile with > the latest compiler it's simply a bug. Why should one try to penalize > the other distribution and downgrade their binaries? When FreeBSD has a > bad default setup, there must be a reason for that. Tell me this reason > and show me that it's justified in form of some other benchmark. Well, look at the mailing list. FreeBSD is handled via this list since we are spread around the globe and even the developers are spread worldwide. But when it comes to detecting worse performnce and someone isn't capable of giving a detailed insight and mostly scientific way of investigating the fault he experienced, the discussion, if it starts, get drowned by allegations like "bad testing", worse optimizations blabla. Look at Steve Kargls problem. He investigated a SCHED_ULE problem in a way that is far beyond enough! He gave tests, insights of his setup, bad performance compared to SCHED_4BSD and what happend? We are still stuck with this problem and more and more people realise, that FreeBSD does have somewhere a problem and this seems to be a nasty problem not easy to find or investigate. But look at how Steve has been silenced in the past ... Benchmarks, especially published ones, reveal those pits and soemone could look into it. Another problem is this very elite-feeling closed club. Once you managed it getting into the club of committers or core team members, you'll probably fight for your seat ... I dont propose for that socialists crap Linux people tend to be like, overcrowded townhalls full of important people with non-consense opinions. The other extreme end of this spectrum. I can not change this. And I do not know whether there is a real way-in-the-middle. But I follow the illusion that if people can see what benchmarks reveal, they start thinking and if the facts are starting to give a heavy load load on those rejecting the facts, they migght change their opinion or get hopefully replaced by more openminded people. A Vision. Oliver From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 11:01:35 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 17E8F106566C; Fri, 23 Dec 2011 11:01:35 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id AD1DE8FC08; Fri, 23 Dec 2011 11:01:34 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Re2sX-0007R5-V1>; Fri, 23 Dec 2011 12:01:34 +0100 Received: from telesto.geoinf.fu-berlin.de ([130.133.86.198]) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Re2sX-0008Fa-Sy>; Fri, 23 Dec 2011 12:01:33 +0100 Message-ID: <4EF45F8D.9030404@mail.zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 12:01:33 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Daniel Kalchev References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <4EF444BB.9090400@digsys.bg> In-Reply-To: <4EF444BB.9090400@digsys.bg> X-Enigmail-Version: undefined Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Originating-IP: 130.133.86.198 X-Mailman-Approved-At: Fri, 23 Dec 2011 12:28:04 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 11:01:35 -0000 On 12/23/11 10:07, Daniel Kalchev wrote: > > > On 23.12.11 03:17, O. Hartmann wrote: >> Or even look at the thread regarding to SCHED_ULE. Why has a user, >> experiencing really worse performance with SCHED_ULE, in a nearly >> scientific manner some engineer the fault? I'd expect the developer or >> care-taking engineer taking care in a more user friendly manner. > > You remember that those developers are not paid to do what they do? > You remember that nobody has sold you this OS and promised support in > whatever form? Well, as far as I know, the FreeBSD project is funding people doing a certain work! So, the implied opposit, FreeBSD is developed "free" isn't true. > > Still, this issue is discussed publicly and experiments are being made, > I guess also new code is being experimented. > If you are interested in the outcome, just follow the discussion. If you > can help with something and you are willing, please do. There will be > good solution to the SCHED_ULE shortcomings. > > FreeBSD is unique group of people, who all sit on their eggs, be it eggs > they themselves produced, or they inherited one way or another. These > people include all the developers and most of the system administrators > and users of FreeBSD. There is no "they" and "us". What I am in this terminology? I can hardly write some scientific code for my science, I'm able to patch software a bit, that has been developed only for Linux these days (ISIS3 from the USGS, for instance, but I do not dare to publish the crap of port I produced since it is not "professional"). I'm with FreeBSD now since 1996/97. I'm still with the system, although I desperately need scientific grade compilers or GPGPU support. So, even if Linux offers me a really much more convenient way to do my work, I stayed with FreeBSD since there is no real alternative in terms of cleaness of the system. I have also to administer an Ubuntu and Suse server and I feel not amused by this script hell that covers the real system just to get kiddies or Windows-Admins into the "admin-position". And, I dare to put some critics herein! Since I see that FreeBSD is "free", why not trying to make it better and more towards perfect? > > If your preference for the OS is different, you might feel more > comfortable in choosing another OS, probably a commercial OS with > support from the vendor. This is nonesense, you know that, regarding to my case. > >> If a benchmark reveals some severe weak points in FreeBSD and I have >> to read about obscure tweaks of non documented sysctl, then this OS >> would be a no-go if I was a manager to make decissions. > > Luckily, managers do not care about knobs or how difficult it is for the > system administrator to achieve specific goal. All they care is the > bottom line in general and in short therm the goals they have set. No > sane manager will care about benchmarks, as long as he gets what he wants. Well, in real world and beyond this armchair polemics, managers at last do the decissions. Those people dropping math, physics, with no glue to how things work in nature get a degree in law, business and whatsowever and then decide. In my eyes, those are enemies of every development and progress, but this is polemics, too. I faced this many times and it is hard to convince those people not taking care of knobs. But as an admin myself, I need to know about knobs and if essential knobs are not documented, than there is a potential gone for the OS in question. Look at FreeBSD and the problem of how well sysctls and their working are documented. It needs to be fixed. > > Back, to the Phoronix benchmarks. There has already been communication. > Phoronix were given advices on how to better do some things on FreeBSD > (which will make the quality of their benchmarks better and therefore > more trusted). Phoronix has made their updated test suite available to > FreeBSD users (that include developers) to try on their own hardware. By > the way, it is in /usr/ports/benchmarks/phoronix-test-suite. Yes, everyone interseted in this thread and communicating is aware of that fact. > > Linux and FreeBSD are not enemies, they both solve the same problems > with different means. > > Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 11:38:32 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A6C601065670; Fri, 23 Dec 2011 11:38:32 +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 21D838FC17; Fri, 23 Dec 2011 11:38:31 +0000 (UTC) Received: from dcave.digsys.bg (dcave.digsys.bg [192.92.129.5]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBNBcHOV047229 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Fri, 23 Dec 2011 13:38:24 +0200 (EET) (envelope-from daniel@digsys.bg) Message-ID: <4EF46829.6010508@digsys.bg> Date: Fri, 23 Dec 2011 13:38:17 +0200 From: Daniel Kalchev User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: "O. Hartmann" References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF45C85.9010709@mail.zedat.fu-berlin.de> In-Reply-To: <4EF45C85.9010709@mail.zedat.fu-berlin.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Fri, 23 Dec 2011 12:28:12 +0000 Cc: Martin Sugioarto , freebsd-current@FreeBSD.ORG, Igor Mozolevsky , freebsd-performance@FreeBSD.ORG, "O. Hartmann" , Daniel@FreeBSD.ORG Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 11:38:32 -0000 On 23.12.11 12:48, O. Hartmann wrote: > Look at Steve Kargls problem. He investigated a SCHED_ULE problem in a > way that is far beyond enough! He gave tests, insights of his setup, > bad performance compared to SCHED_4BSD and what happend? We are still > stuck with this problem and more and more people realise, that FreeBSD > does have somewhere a problem and this seems to be a nasty problem not > easy to find or investigate. This has made me to realize, that I was having a problem with SCHED_ULE that I was not aware of until now. WOW! :) Every scheduler has some problem, some fail here some fail there. I am confident, that the case that Steve Kargls has reported will be resolved. > Another problem is this very elite-feeling closed club. Once you > managed it getting into the club of committers or core team members, > you'll probably fight for your seat ... I dont propose for that > socialists crap Linux people tend to be like, [..] You never heard of the "People's Republic of Berkeley"? :) As for commiter access, this sort of comments trigger the system administrator in me. I have seen enough people, who for the lack of other excuses always use "but I don't have enough RIGHTS!". I am evil, I know.... > But I follow the illusion that if people can see what benchmarks > reveal, they start thinking and if the facts are starting to give a > heavy load load on those rejecting the facts, they migght change their > opinion or get hopefully replaced by more openminded people. Here is now it works: If you see an problem and have a solution: go fix it. Many will be grateful. If you can't fix it, but have an idea how to fix it, share it. May will be grateful. If you can't fix it and don't have any idea, just say "there is a problem" and stop there. There are many, many, many like you who just hold their breath. We all learn, every day. Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 11:44:24 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: by hub.freebsd.org (Postfix, from userid 1233) id B83091065670; Fri, 23 Dec 2011 11:44:24 +0000 (UTC) Date: Fri, 23 Dec 2011 11:44:24 +0000 From: Alexander Best To: Daniel Kalchev Message-ID: <20111223114424.GA60815@freebsd.org> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF4474B.3050203@digsys.bg> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EF4474B.3050203@digsys.bg> X-Mailman-Approved-At: Fri, 23 Dec 2011 12:28:23 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, "O. Hartmann" , Martin Sugioarto , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 11:44:24 -0000 On Fri Dec 23 11, Daniel Kalchev wrote: > > > On 23.12.11 08:47, Martin Sugioarto wrote: > >A further thing is that I cannot understand the people here sometimes. > >I would like that the -RELEASE versions of FreeBSD perform well > >without any further optimizations. > > The -RELEASE things is just a freeze (or, let's say tested freeze) of > the corresponding branch at some time. It is the code available and > tested at that time. > > Thus, it is safe to say that FreeBSD 8.0-RELEASE is much worse than > FreeBSD RELENG_8 (still 8.2 at the moment), because years have passed > between both code bases, lots of bugs have been discovered and fixed and > new technologies have been integrated. Especially in this line, the > compiler has changed from 4.2.1 to 4.2.2. > > >When the distribution does not compile with the latest compiler it's > >simply a bug. > > FreeBSD is not a distribution. It also compiles with the latest compiler > - LLVM. :) > > I find it amusing, that people want everything compiled with GCC 4.7, > which is still very much developing, therefore highly unstable and > (probably) full of bugs. > > >Why should one try to penalize the other distribution and downgrade > >their binaries? > > Many suggested that the Linux binaries be run via the FreeBSD Linux > emulation. Unchanged. > There is one problem here though, the emulation is still 32 bit. plus the current emulation layer is far from complete. a lot of stuff hasn't been implemented yet (meaning it's missing or implemented as dummy code). try running recent firefox linux binaries on freebsd. they will all crash almost instantly. cheers. alex > > >When FreeBSD has a bad default setup, there must be a reason for that. > >Tell me this reason and show me that it's justified in form of some > >other benchmark. > > FreeBSD has safe default. It is supposed to work out of the box on > whatever hardware you put it. As much as it has drives for that > hardware, of course. > Once you have working installation, you may tweak it all the way you wish. > > If your installation is pre-optimized, chances are it will crash all the > time on you and there will be no easy way for you to fix, short of > installing another "distribution". > > Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 14:20:59 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 71A3A106567A for ; Fri, 23 Dec 2011 14:20:59 +0000 (UTC) (envelope-from afmcc@btinternet.com) Received: from nm4-vm0.bt.bullet.mail.ird.yahoo.com (nm4-vm0.bt.bullet.mail.ird.yahoo.com [212.82.108.93]) by mx1.freebsd.org (Postfix) with SMTP id 8975E8FC14 for ; Fri, 23 Dec 2011 14:20:57 +0000 (UTC) Received: from [212.82.108.231] by nm4.bt.bullet.mail.ird.yahoo.com with NNFMP; 23 Dec 2011 14:20:57 -0000 Received: from [212.82.108.227] by tm4.bt.bullet.mail.ird.yahoo.com with NNFMP; 23 Dec 2011 14:20:57 -0000 Received: from [127.0.0.1] by omp1004.bt.mail.ird.yahoo.com with NNFMP; 23 Dec 2011 14:20:57 -0000 X-Yahoo-Newman-Id: 140851.58977.bm@omp1004.bt.mail.ird.yahoo.com Received: (qmail 40683 invoked from network); 23 Dec 2011 14:20:57 -0000 DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=btinternet.com; h=DKIM-Signature:X-Yahoo-Newman-Property:X-YMail-OSG:X-Yahoo-SMTP:Received:Date:From:To:Subject:Message-ID:In-Reply-To:References:X-Mailer:Mime-Version:Content-Type:Content-Transfer-Encoding; b=VCutrjVsoz5kEft1eR3w0l0NU3tS2UlM+D0FMzqt5jjrzdR05KJh502OS7+V+MJKOXyZCpOOyEFohhurTSe52JRCGG1vckHgQfUG2PasUrrfI9tNoR7sK75pzF/9iuxk5USa78735avkzSd2oZsJ2brb7cUeI7/kXgenDNHpnqo= ; DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=btinternet.com; s=s1024; t=1324650057; bh=xNrcVf3+jk2xFCPi30y8XhZMa00IyGjvIsLagXfVXpo=; h=X-Yahoo-Newman-Property:X-YMail-OSG:X-Yahoo-SMTP:Received:Date:From:To:Subject:Message-ID:In-Reply-To:References:X-Mailer:Mime-Version:Content-Type:Content-Transfer-Encoding; b=48tWzZpTonmQWDWf6T4t88VpfL9nVo/N3N+77vMNUTdtOO/4YkRpVJ0MJoFBEJ3nWTQlXMyGoxSLldaJ9DlzEI3FY+IbLWREKuO2sKrD7BxZCBzv6zGYUWJm5o7B3wmv8VCCbtJ7qTkhBuMPwahk+4Vw/4Pl2AisbOTWCR6SpVU= X-Yahoo-Newman-Property: ymail-3 X-YMail-OSG: sUVJvhQVM1mCI6g0Y2neN42cI4ofLvi1R3TqExutHSgyg9_ kwS22X3jZZH5W7wfvgkYyAeCXxSM6nMWojV6tttgp0QHbyIUmsXzPpE14mj2 tqGhc.3_EKfM_y2EkXjCb7vqt59bt5La4gD2c9T77Itn1foR6cwJiKqcpXGH 33_DA1FqhMcLVNzT93RXo1DpEem9MWXht6WRq_s0ir5tqEj5mpNTUSm82Oox l5gtMks2JPQfWCkLS03E2M_30up8WBWDmFkg.QG1_6phtOrzf02I88QRngYo zyyG55_eM13P6qlG.bWJkTqfK7tnA8q4dhGpCuH3pudkDlMXETHlAuZo99lR RGY1xUB8K2bETUO6HPlIn0MmfW3EoBDN9cEFuqExSjXHDaIx0AD53HtC7Hy6 7oQ-- X-Yahoo-SMTP: GbC5zv6swBDAJAX2wjERvjXPaCXFiJJLdMa.NuzRNApZ Received: from elena.home (afmcc@31.52.40.183 with login) by smtp827.mail.ird.yahoo.com with SMTP; 23 Dec 2011 06:20:56 -0800 PST Date: Fri, 23 Dec 2011 14:20:56 +0000 From: Tony McC To: freebsd-performance@freebsd.org Message-ID: <20111223142056.59d02cb4@elena.home> In-Reply-To: <4EF3D3E2.9000403@zedat.fu-berlin.de> References: <4EF25468.9040204@gmail.com> <4EF2D814.1090805@freebsd.org> <4EF2F210.6080009@gmail.com> <4EF3D3E2.9000403@zedat.fu-berlin.de> X-Mailer: Claws Mail 3.8.0 (GTK+ 2.24.6; amd64-portbld-freebsd9.0) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 14:20:59 -0000 On Fri, 23 Dec 2011 02:05:38 +0100 "O. Hartmann" wrote: > Yes, and it is legitime to question that and bring pro and contra for > that decission. But since "FreeBSD" is obviously a small club of > people sitting like a duck on eggs (and, by the way, not their own > genuine invented eggs, more or less reingeneered eggs), those > decissions get more obscure than they seem to be anyway. Dear OH, I am not sure why you feel the need to badmouth the FreeBSD community here. Genuinely puzzled. At first you seemed to be a user of FreeBSD who had a specific area to work where Linux seemed to promise better performance. But as the thread has gone on, your initial concerns seem to have dissolved into vague accusations and snide asides. I don't think that is going to help you, especially as it is very unclear now what helping you would even mean. Nevertheless, have a good Christmas and a productive New Year, whatever OS you use. Tony From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 14:47:48 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3984A1065672 for ; Fri, 23 Dec 2011 14:47:48 +0000 (UTC) (envelope-from martin@sugioarto.com) Received: from mailserv.regfish.com (mailserv.regfish.com [79.140.61.33]) by mx1.freebsd.org (Postfix) with ESMTP id 776DE8FC1B for ; Fri, 23 Dec 2011 14:47:45 +0000 (UTC) Received: (qmail 16114 invoked from network); 23 Dec 2011 14:47:44 -0000 Received: from pd9ec0d76.dip0.t-ipconnect.de (HELO yuni.sugioarto.com) (46959-0001@[217.236.13.118]) (envelope-sender ) by mailserv.regfish.com (qmail-ldap-1.03) with SMTP for ; 23 Dec 2011 14:47:44 -0000 Received: from zelda.sugioarto.com (zelda.sugioarto.com [192.168.0.12]) by yuni.sugioarto.com (Postfix) with ESMTP id DF6A31BAC55; Fri, 23 Dec 2011 15:47:41 +0100 (CET) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=sugioarto.com; s=mail; t=1324651662; bh=mFe3u5VorPV9E1SBudYtAdIa7JtOxWe1OwGFU1LzEDM=; h=Date:From:To:Cc:Subject:Message-ID:In-Reply-To:References: Mime-Version:Content-Type; b=OtZTgt9mxbvakGgfFoPI1jdk81n/E1iOmd42d1mGbquht/JMRblstxLGpQwGXp6k9 K2CD0H0KqSHuj1DAM3lZTj8Z67i4mnPswNNj2vur1xgOIz6HfOmCOeaDO/MK6Lhb7f SYprbxTwAy+Xa15CguEA5ElAxYLyFe4GmFrzZkow= Date: Fri, 23 Dec 2011 15:47:37 +0100 From: Martin Sugioarto To: Daniel Kalchev Message-ID: <20111223154737.4e5da6de@zelda.sugioarto.com> In-Reply-To: <4EF4474B.3050203@digsys.bg> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF4474B.3050203@digsys.bg> X-Mailer: Claws Mail 3.7.10 (GTK+ 2.24.6; amd64-portbld-freebsd9.0) Mime-Version: 1.0 Content-Type: multipart/signed; micalg=PGP-SHA1; boundary="Sig_/3wOr79UdKqdOz/Px5Xh3l2d"; protocol="application/pgp-signature" X-Mailman-Approved-At: Fri, 23 Dec 2011 15:02:47 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, "O. Hartmann" , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 14:47:48 -0000 --Sig_/3wOr79UdKqdOz/Px5Xh3l2d Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: quoted-printable Am Fri, 23 Dec 2011 11:18:03 +0200 schrieb Daniel Kalchev : > The -RELEASE things is just a freeze (or, let's say tested freeze) of=20 > the corresponding branch at some time. It is the code available and=20 > tested at that time. Hi Daniel, obviously performance is not a quality aspect, only stability. =20 > FreeBSD is not a distribution. It also compiles with the latest > compiler=20 > - LLVM. :) I thought that the "D" in FreeBSD stands for "distribution". Yes, it's ok that it compiles with LLVM. Does it also run faster in benchmarks? > I find it amusing, that people want everything compiled with GCC 4.7,=20 > which is still very much developing, therefore highly unstable and=20 > (probably) full of bugs. When you don't use the software don't complain that it is buggy, because you won't find the bugs. You cannot always tell the others to make everything perfect. I don't want to have everything compiled on $COMPILER. I want that there is a reasonable quality. And for me quality is not only stability, but also speed. > Many suggested that the Linux binaries be run via the FreeBSD Linux=20 > emulation. Unchanged. > There is one problem here though, the emulation is still 32 bit. I'm not talking about emulation. I don't use FreeBSD to run emulated binaries. I (any many people) want efficient servers and eventually desktops. You should not expect people to tune the system for speed, when it's clear that default setting does not make any sense. People will use default settings, because they trust developers that they thought about balanced stability, security and performance. > FreeBSD has safe default. This is what I am talking about. Don't complain that the benchmark does not show efficience. No one is interested in tuning FreeBSD just for a benchmark application. > It is supposed to work out of the box on=20 > whatever hardware you put it. As much as it has drives for that=20 > hardware, of course. > Once you have working installation, you may tweak it all the way you > wish. But if you don't tweak, you get a fair result in a benchmark. This is what you will see as a user of the system. These are the default settings, that means developers chose them as the BEST choice for the system. =20 > If your installation is pre-optimized, chances are it will crash all > the time on you and there will be no easy way for you to fix, short > of installing another "distribution". Sorry, no. If optimization makes bugs appear, there are bugs in the code (somewhere). And you will never find them when you hide them like this. You will also never see many advances in performance. -- Martin --Sig_/3wOr79UdKqdOz/Px5Xh3l2d Content-Type: application/pgp-signature; name=signature.asc Content-Disposition: attachment; filename=signature.asc -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.18 (FreeBSD) iQIcBAEBAgAGBQJO9JSMAAoJEF8wvLx/5p/7B70QAKjhEOblVtgDInsp7eHvvHWH FxrbRUjA+5XZywGs7qAbys2uEljX0CQ0Oe3s/pk56f0euyTyhQextYUnb9AiupG8 dPMz2e86oDhgeeIKJy2fNSZ3mh//7W1+JWU6VlaloExKNBIz/wXcMHiCI1gXtE0y opMGWIKHxyvcbrvWRI9fOyM6q7KZP1ygsbC/T3L7+jzr4SXOXVWHcOz35yh+tyBs XbUtZhu1EmkTNzpJOCmUfBm/bqY1RevNmMCOzBDsafB/opnJ9zqx5vagTmpxktfp G1e0V0pXoV22e3XDSAo0mMxR1pHqwegexdbUk2LZ9OnE/yz7NZhmjpSdjeoaE2fV 4o4LjAEaExkj2m96+neDDcbOh//2QJC76ijCIC0rA3Smjz+HPTlE0/o115S2mlCR MK0J6xWbTfQPl85kv9kZzJeGLQodjr6ttRgjXOQYLK1Lb2IZoqGAwrjv2qZj9r9h awosYg2tsMgsRQXNFV6/3oLpgPSamHCFoC4jlIA/7mLeemDS+EVcqUNf9h9JA9ey IgAG22RumA6XCPHyQ0TY+VtlJIJX0mdGk/5NWncPQKNHDr9ciWCogLFMPdIr8FE8 EPqTV6kk06FORReI6xNV/UVOZnKa2JfOazBiBdXPJwyJKgdN8eCAqNkZHAZC4Dd8 OoUoTI2t6q3+hYzc58rV =35Is -----END PGP SIGNATURE----- --Sig_/3wOr79UdKqdOz/Px5Xh3l2d-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 15:00:07 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 922F01065670; Fri, 23 Dec 2011 15:00:07 +0000 (UTC) (envelope-from jhb@freebsd.org) Received: from cyrus.watson.org (cyrus.watson.org [65.122.17.42]) by mx1.freebsd.org (Postfix) with ESMTP id 3D2D78FC14; Fri, 23 Dec 2011 15:00:07 +0000 (UTC) Received: from bigwig.baldwin.cx (bigwig.baldwin.cx [96.47.65.170]) by cyrus.watson.org (Postfix) with ESMTPSA id DF7EB46B09; Fri, 23 Dec 2011 10:00:06 -0500 (EST) Received: from jhbbsd.localnet (unknown [209.249.190.124]) by bigwig.baldwin.cx (Postfix) with ESMTPSA id 6ED65B955; Fri, 23 Dec 2011 10:00:06 -0500 (EST) From: John Baldwin To: freebsd-stable@freebsd.org Date: Fri, 23 Dec 2011 10:00:05 -0500 User-Agent: KMail/1.13.5 (FreeBSD/8.2-CBSD-20110714-p8; KDE/4.5.5; amd64; ; ) References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> In-Reply-To: <20111222235846.GA6071@icarus.home.lan> MIME-Version: 1.0 Content-Type: Text/Plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Message-Id: <201112231000.05712.jhb@freebsd.org> X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.7 (bigwig.baldwin.cx); Fri, 23 Dec 2011 10:00:06 -0500 (EST) X-Mailman-Approved-At: Fri, 23 Dec 2011 15:27:33 +0000 Cc: freebsd-current@freebsd.org, igor@hybrid-lab.co.uk, Alexander Leidinger , freebsd-performance@freebsd.org, "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 15:00:07 -0000 On Thursday, December 22, 2011 6:58:46 pm Jeremy Chadwick wrote: > On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: > > On 12/21/11 19:41, Alexander Leidinger wrote: > > > Hi, > > > > > > while the discussion continued here, some work started at some other place. Now... in case someone here is willing to help instead of talking, feel free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look what can be improved. The page is far from perfect and needs some additional people which are willing to improve it. > > > > > > This is only part of the problem. A tuning page in the wiki - which could be referenced from the benchmark page - would be great too. Any volunteers? A first step would be to take he tuning-man-page and wikify it. Other tuning sources are welcome too. > > > > > > Every FreeBSD dev with a wiki account can hand out write access to the wiki. The benchmark page gives contributor-access. If someone wants write access create a FirstnameLastname account and ask here for contributor-access. > > > > > > Don't worry if you think your english is not good enough, even some one- word notes can help (and _my_ english got already corrected by other people on the benchmark page). > > > > > > Bye, > > > Alexander. > > > > > > > > > > > > > > > > Nice to see movement ;-) > > > > But there seems something unclear: > > > > man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in > > /etc/make.conf. > > The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. > > > > What's right and what's wrong now? > > I can say with certainty that this value belongs in /etc/make.conf > (on RELENG_8 and earlier at least). > > src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, > so, this is definitely a make.conf variable. Eh, normal make variables can go in src.conf as well. They do not have to be listed in bsd.own.mk. World builds include /etc/src.conf whereas every make invocation includes /etc/make.conf via sys.mk. The only reason to use /etc/src.conf is to have a place to put variables only affect make buildworld / buildkernel but do not affect other make invocations. Also, MALLOC_PRODUCTION is generally enabled in a stable branch as part of making the stable branch, there should be no need to set it manually in a stable branch. -- John Baldwin From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 15:40:34 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 54AF710657C4; Fri, 23 Dec 2011 15:40:34 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id EA2238FC1E; Fri, 23 Dec 2011 15:40:33 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Re7EV-0000PZ-Dd>; Fri, 23 Dec 2011 16:40:31 +0100 Received: from e178023009.adsl.alicedsl.de ([85.178.23.9] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Re7EV-0005P1-73>; Fri, 23 Dec 2011 16:40:31 +0100 Message-ID: <4EF4A0E8.1050601@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 16:40:24 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Martin Sugioarto References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF4474B.3050203@digsys.bg> <20111223154737.4e5da6de@zelda.sugioarto.com> In-Reply-To: <20111223154737.4e5da6de@zelda.sugioarto.com> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig59B71D83F5A2078083DBFC0A" X-Originating-IP: 85.178.23.9 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky , Daniel Kalchev Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 15:40:34 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig59B71D83F5A2078083DBFC0A Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/23/11 15:47, Martin Sugioarto wrote: > Am Fri, 23 Dec 2011 11:18:03 +0200 > schrieb Daniel Kalchev : >=20 >> The -RELEASE things is just a freeze (or, let's say tested freeze) of = >> the corresponding branch at some time. It is the code available and=20 >> tested at that time. >=20 > Hi Daniel, >=20 > obviously performance is not a quality aspect, only stability. > =20 >> FreeBSD is not a distribution. It also compiles with the latest >> compiler=20 >> - LLVM. :) >=20 > I thought that the "D" in FreeBSD stands for "distribution". Yes, it's > ok that it compiles with LLVM. Does it also run faster in benchmarks? >=20 >> I find it amusing, that people want everything compiled with GCC 4.7, = >> which is still very much developing, therefore highly unstable and=20 >> (probably) full of bugs. >=20 > When you don't use the software don't complain that it is buggy, > because you won't find the bugs. You cannot always tell the others to > make everything perfect. As with GCC4.7, CLANG/LLVM is still considered "experimental" and definitely has some issues with CPU architectures beyond Core2. Personally, I compile everthing now with CLANG on FreeBSD 9.0/10.0 as far as I don't realise any conerns towards correctness and stability. Well, the GCC 4.7 came somewhere up and I picked it up, sorry. It is much easier to replace gcc 4.7 in this thread by 4.6.2, which is now considered stable and in production. And as some of the writers in this thread mentioned, the performance gain could be enormous since gcc 4.6 does support either core i7 architectures and its new facilities, the optimizer is aware of the core/uncore design an, maybe, of the three-folded cache levels. Is the legacy gcc 4.2 aware of that? I guess not, since it does not support architectures beyond Core2. I tried using gcc 4.6.2 from ports to compile world, but I failed. Simply replacing/setting CC, CXX and CPP isn't obviosuly enough. >=20 > I don't want to have everything compiled on $COMPILER. I want that > there is a reasonable quality. And for me quality is not only > stability, but also speed. Yes, agree. I think quality could inherit also a reasonable speed. Speed at all costs, even stability, is no option. Even for HPC systems, where jobs run uninetrupted for weeks or months (in our case). >=20 >> Many suggested that the Linux binaries be run via the FreeBSD Linux=20 >> emulation. Unchanged. >> There is one problem here though, the emulation is still 32 bit. With the usage of even 32bit Linux binaries you introduce all the mess you want to avoid by using FreeBSD. But it is very often recommended to use the so called Linuxulator. I'm happy to have this opportunity (I can not run FreeBSD binaries on some Ubuntu or Centos distros). But in some cases people of the FreeBSD community rely to much on this 32bit-limited option. I always prefer native BLOBs over emulated BLOBs. >=20 > I'm not talking about emulation. I don't use FreeBSD to run emulated > binaries. I (any many people) want efficient servers and eventually > desktops. You should not expect people to tune the system for speed, > when it's clear that default setting does not make any sense. People > will use default settings, because they trust developers that they > thought about balanced stability, security and performance. >=20 >> FreeBSD has safe default. >=20 > This is what I am talking about. Don't complain that the benchmark does= > not show efficience. No one is interested in tuning FreeBSD just for a > benchmark application. >=20 >> It is supposed to work out of the box on=20 >> whatever hardware you put it. As much as it has drives for that=20 >> hardware, of course. >> Once you have working installation, you may tweak it all the way you >> wish. >=20 > But if you don't tweak, you get a fair result in a benchmark. This is > what you will see as a user of the system. These are the default > settings, that means developers chose them as the BEST choice for the > system. Well, it is a very nice moce to have conservative settings to make FreeBSD stable for everyone intend to use it out of the box. But what I really miss is a certain, group of people dedicated to HPC and secure, stable tweak achieving that. The operating system is a nature and live. It is a balance of a limited resource. One can try to balance out every potential workload that can occur and the result is a very good allround syste, But in the server or HPC area, it might be necessary to push some parts in favor of some others. When computing, I do not need high USB performance, except a responsive keyboard. I/O and CPU performance is the main goal, but this seems the most difficult part. A file or network server, for instance, would balance more towards network I/O or delivering small data pieces instead of large streaming blocks of memory. I'm certain that the tweaks would differ for both scenarios. At home or at the desktop, the situation is more complicated, since people tend to use a lot of multimedia stuff and jumping audio is also not a very pleasant thing as stuck video. > =20 >> If your installation is pre-optimized, chances are it will crash all >> the time on you and there will be no easy way for you to fix, short >> of installing another "distribution". >=20 > Sorry, no. If optimization makes bugs appear, there are bugs in the > code (somewhere). And you will never find them when you hide them like > this. You will also never see many advances in performance. >=20 > -- > Martin Agree. Benchmarking could push a system towards its limits and reveal limits or bugs that make them crash. It is better to have them crash in a benchmark torture than in a data center delivering valuable data for business or in science, when the server crashes just before finishing a two month run due to some buffer problems ... oh --------------enig59B71D83F5A2078083DBFC0A Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO9KDuAAoJEOgBcD7A/5N8i5UH/A0PFxhgokV/43lyNvbCsp2M +rLcZVKwnC4y8/ZudlRmR5PqjRdrhFQiBxKOVR1nEjPjL84wZGvwGj6d5xTzJL4x KXEV4R67jbtXeQCyEWlZuXwIRDLyDP0IcKb7QTx2+eqtLNZPdgIN73UiYkQi/iS4 aJ285fa9nK9SU3s8IpRMK1FcbTsUE7B1lOFiDH0RUEgClq+eI+BVQ4DitQejoT1v 0OO7mK4IPAsdSlmEFc9NvBY3cQtTIii+lACpFzIPXuggLUV1OE4XOSEOCTF3XBkz fZNHf/OQTUpiUT7PG2B4vYaa6PlLG822TBETfIxmQyLw9o+LTU7aZ8oxzasUecE= =1D13 -----END PGP SIGNATURE----- --------------enig59B71D83F5A2078083DBFC0A-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 15:14:15 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A74E3106564A for ; Fri, 23 Dec 2011 15:14:15 +0000 (UTC) (envelope-from linimon@lonesome.com) Received: from mail.soaustin.net (pancho.soaustin.net [76.74.250.40]) by mx1.freebsd.org (Postfix) with ESMTP id 6D7BD8FC0A for ; Fri, 23 Dec 2011 15:14:15 +0000 (UTC) Received: by mail.soaustin.net (Postfix, from userid 502) id EEACC5619E; Fri, 23 Dec 2011 08:56:53 -0600 (CST) Date: Fri, 23 Dec 2011 08:56:53 -0600 From: Mark Linimon To: "O. Hartmann" Message-ID: <20111223145653.GA24107@lonesome.com> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <4EF444BB.9090400@digsys.bg> <4EF45F8D.9030404@mail.zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <4EF45F8D.9030404@mail.zedat.fu-berlin.de> User-Agent: Mutt/1.5.20 (2009-06-14) X-Mailman-Approved-At: Fri, 23 Dec 2011 15:48:59 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky , Daniel Kalchev Subject: FreeBSD funding [was: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1] Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 15:14:15 -0000 I have slightly reordered your email in my reply, in order to put the most important item last. On Fri, Dec 23, 2011 at 12:01:33PM +0100, O. Hartmann wrote: > I'm still with the system, although I desperately need scientific grade > compilers or GPGPU support. Your use-case, while valid, is clearly not the use-case that most of the committers working on FreeBSD face. But see below. > And, I dare to put some critics herein! Since I see that FreeBSD is > "free", why not trying to make it better and more towards perfect? Everyone wants the product to improve. The question is, what is achievable with the current committers? That's where you see the pushback and frustration from the current committers. > Look at FreeBSD and the problem of how well sysctls and their > working are documented. It needs to be fixed. There's no argument that some of the FreeBSD documentation is stale. We do, however, have one committer (eadler@) who has been trying to move the sysctl documentation forwards. Participation from the wider community is key. Although sending PRs does not guarantee things will get fixed, it's currently the best way that we have. > Well, as far as I know, the FreeBSD project is funding people doing a > certain work! So, the implied opposite, FreeBSD is developed "free" > isn't true. So here's the key point of your email IMHO, and the key misunderstanding. First, let me nit-pick the legalities. The FreeBSD Foundation (http://www.freebsdfoundation.org/) is a US non-profit that does fund some activities, and that's what I'll talk about here. "The FreeBSD Project" is the collective term for "all of the committers and developers" and is not an "entity" for US legal purposes. Second, the disclaimers: I am not a member of the FreeBSD Foundation Board of Directors, so I am not speaking for them. I have also directly benefited from Foundation funding (both travel, and via equipment they bought for portmgr), so am hardly unbiased. Now on to the gist of that matter. As a US non-profit, the Foundation is required to post its financial information to the public, and it does on its website: http://www.freebsdfoundation.org/documents/Budget2011.pdf You'll see here that the total budget for 2011 is $400k (USD). This, frankly, is miniscule. The largest line item for 2011 is $125k for project funding, which has gone towards 9 different projects (see http://www.freebsdfoundation.org/activities.shtml). For comparison, keep in mind that a commercial developers' salary in the US is upwards of $100k/yr. Even with this being a substantial increase from 2010's $83k, these numbers are tiny comared to "real-world" budgets. The projects that were sponsored were primarily networking-related, but also the GEM/KMS/DRI project, jails, the libc++ replacement, and clocks. I've listed those in the order that I think the most consumers of FreeBSD will be affected by. Note the absence of any work towards performance, schedulers, compilers, or numerical analysis. With a $125k budget, you're simply not going to see those on the list. The other notable line items are: hardware purchases (explicit disclaimer: portmgr has been one of the primary beneficiaries); conference sponsorship; conference travel; and salary for one employee to try to help coordinate all the above. Legal fees (things involving trademarking and licensing issues) takes up most of the remaining. I can't figure out the Linux Foundation's budget from their website, but I can tell immediately that their budget is a great many times more than $400k. Summary: on a fraction of the budget that Linux has available, we _nearly keep up_. I can't imagine what we could do with comparable funding. So, for everyone who thinks we are being "well funded", here's your reality check. And please note that the Foundation is in its year-end fund drive, too. Thanks for listening. mcl From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 15:22:57 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CC171106566B; Fri, 23 Dec 2011 15:22:57 +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 4F9518FC0C; Fri, 23 Dec 2011 15:22:57 +0000 (UTC) Received: from dcave.digsys.bg (dcave.digsys.bg [192.92.129.5]) (authenticated bits=0) by smtp-sofia.digsys.bg (8.14.4/8.14.4) with ESMTP id pBNFMl7O048645 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Fri, 23 Dec 2011 17:22:53 +0200 (EET) (envelope-from daniel@digsys.bg) Message-ID: <4EF49CC6.9050901@digsys.bg> Date: Fri, 23 Dec 2011 17:22:46 +0200 From: Daniel Kalchev User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:8.0) Gecko/20111110 Thunderbird/8.0 MIME-Version: 1.0 To: Martin Sugioarto References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF4474B.3050203@digsys.bg> <20111223154737.4e5da6de@zelda.sugioarto.com> In-Reply-To: <20111223154737.4e5da6de@zelda.sugioarto.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Fri, 23 Dec 2011 15:49:17 +0000 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, "O. Hartmann" , Igor Mozolevsky Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 15:22:57 -0000 On 23.12.11 16:47, Martin Sugioarto wrote: > I thought that the "D" in FreeBSD stands for "distribution". Yes, it's > ok that it compiles with LLVM. Does it also run faster in benchmarks? It does. From a language perspective. It is a "distribution", because at the times BSD was developed, it was not a complete operating system. It was supposed to be "added" to say AT&T System V to make it networking capable etc. The Linux people use the word "distribution" in a different context. > I don't want to have everything compiled on $COMPILER. I want that > there is a reasonable quality. And for me quality is not only > stability, but also speed. You can always have faster algorithm if it is not necessary to produce the right answer. > But if you don't tweak, you get a fair result in a benchmark. This is > what you will see as a user of the system. These are the default > settings, that means developers chose them as the BEST choice for the > system. Developers are not Gods. Developers have no clue on what system and for what purpose you will use the software. All they may do for you is to provide enough knobs for you to tune your system for your hardware/application and also make sure that the system scales, when you turn the knobs. Daniel From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 15:24:55 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 3FC0B1065670 for ; Fri, 23 Dec 2011 15:24:55 +0000 (UTC) (envelope-from jdc@koitsu.dyndns.org) Received: from qmta06.emeryville.ca.mail.comcast.net (qmta06.emeryville.ca.mail.comcast.net [76.96.30.56]) by mx1.freebsd.org (Postfix) with ESMTP id 22D208FC1C for ; Fri, 23 Dec 2011 15:24:54 +0000 (UTC) Received: from omta15.emeryville.ca.mail.comcast.net ([76.96.30.71]) by qmta06.emeryville.ca.mail.comcast.net with comcast id CeZt1i0041Y3wxoA6fQocS; Fri, 23 Dec 2011 15:24:48 +0000 Received: from koitsu.dyndns.org ([67.180.84.87]) by omta15.emeryville.ca.mail.comcast.net with comcast id Cfml1i0171t3BNj8bfmlmr; Fri, 23 Dec 2011 15:46:46 +0000 Received: by icarus.home.lan (Postfix, from userid 1000) id BC566102C19; Fri, 23 Dec 2011 07:24:52 -0800 (PST) Date: Fri, 23 Dec 2011 07:24:52 -0800 From: Jeremy Chadwick To: John Baldwin Message-ID: <20111223152452.GA21957@icarus.home.lan> References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> <201112231000.05712.jhb@freebsd.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <201112231000.05712.jhb@freebsd.org> User-Agent: Mutt/1.5.21 (2010-09-15) X-Mailman-Approved-At: Fri, 23 Dec 2011 15:49:29 +0000 Cc: freebsd-stable@freebsd.org, freebsd-current@freebsd.org, igor@hybrid-lab.co.uk, Alexander Leidinger , freebsd-performance@freebsd.org, "O. Hartmann" Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 15:24:55 -0000 On Fri, Dec 23, 2011 at 10:00:05AM -0500, John Baldwin wrote: > On Thursday, December 22, 2011 6:58:46 pm Jeremy Chadwick wrote: > > On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: > > > On 12/21/11 19:41, Alexander Leidinger wrote: > > > > Hi, > > > > > > > > while the discussion continued here, some work started at some other > place. Now... in case someone here is willing to help instead of talking, feel > free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look what can > be improved. The page is far from perfect and needs some additional people > which are willing to improve it. > > > > > > > > This is only part of the problem. A tuning page in the wiki - which > could be referenced from the benchmark page - would be great too. Any > volunteers? A first step would be to take he tuning-man-page and wikify it. > Other tuning sources are welcome too. > > > > > > > > Every FreeBSD dev with a wiki account can hand out write access to the > wiki. The benchmark page gives contributor-access. If someone wants write > access create a FirstnameLastname account and ask here for contributor-access. > > > > > > > > Don't worry if you think your english is not good enough, even some one- > word notes can help (and _my_ english got already corrected by other people on > the benchmark page). > > > > > > > > Bye, > > > > Alexander. > > > > > > > > > > > > > > > > > > > > > > Nice to see movement ;-) > > > > > > But there seems something unclear: > > > > > > man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in > > > /etc/make.conf. > > > The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. > > > > > > What's right and what's wrong now? > > > > I can say with certainty that this value belongs in /etc/make.conf > > (on RELENG_8 and earlier at least). > > > > src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, > > so, this is definitely a make.conf variable. > > Eh, normal make variables can go in src.conf as well. They do not have > to be listed in bsd.own.mk. World builds include /etc/src.conf whereas > every make invocation includes /etc/make.conf via sys.mk. The only reason > to use /etc/src.conf is to have a place to put variables only affect > make buildworld / buildkernel but do not affect other make invocations. I was always under the impression src.conf(5) variables had to be manually added to bsd.own.mk and similar bits (e.g. src/tools/build/options/WITH_xxx which is what's used to create the src.conf(5) man page), but upon your comment and manual investigation on my part, I found you're indeed right. Taken from bsd.own.mk: 107 .if !defined(_WITHOUT_SRCCONF) 108 SRCCONF?= /etc/src.conf 109 .if exists(${SRCCONF}) 110 .include "${SRCCONF}" 111 .endif 112 .endif As long as third-party software doesn't depend on MALLOC_PRODUCTION for something (I don't know why something would, but who knows; maybe there's a third-party malloc implementation which might?), then putting it in src.conf would be fine (src/lib/libc/stdlib files reference it). -- | Jeremy Chadwick jdc at parodius.com | | Parodius Networking http://www.parodius.com/ | | UNIX Systems Administrator Mountain View, CA, US | | Making life hard for others since 1977. PGP 4BD6C0CB | From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 17:26:43 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id A15CC10656AD; Fri, 23 Dec 2011 17:26:43 +0000 (UTC) (envelope-from ohartman@zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 41E138FC18; Fri, 23 Dec 2011 17:26:42 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1Re8tF-0003gF-Su>; Fri, 23 Dec 2011 18:26:41 +0100 Received: from e178023009.adsl.alicedsl.de ([85.178.23.9] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1Re8tF-00021A-NF>; Fri, 23 Dec 2011 18:26:41 +0100 Message-ID: <4EF4B9D1.8010900@zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 18:26:41 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Jeremy Chadwick References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> <201112231000.05712.jhb@freebsd.org> <20111223152452.GA21957@icarus.home.lan> In-Reply-To: <20111223152452.GA21957@icarus.home.lan> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig1502F529B2C0204E19EA4E4D" X-Originating-IP: 85.178.23.9 Cc: freebsd-stable@freebsd.org, John Baldwin , freebsd-current@freebsd.org, igor@hybrid-lab.co.uk, Alexander Leidinger , freebsd-performance@freebsd.org Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 17:26:43 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig1502F529B2C0204E19EA4E4D Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/23/11 16:24, Jeremy Chadwick wrote: > On Fri, Dec 23, 2011 at 10:00:05AM -0500, John Baldwin wrote: >> On Thursday, December 22, 2011 6:58:46 pm Jeremy Chadwick wrote: >>> On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: >>>> On 12/21/11 19:41, Alexander Leidinger wrote: >>>>> Hi, >>>>> >>>>> while the discussion continued here, some work started at some othe= r=20 >> place. Now... in case someone here is willing to help instead of talki= ng, feel=20 >> free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look = what can=20 >> be improved. The page is far from perfect and needs some additional pe= ople=20 >> which are willing to improve it. >>>>> >>>>> This is only part of the problem. A tuning page in the wiki - which= =20 >> could be referenced from the benchmark page - would be great too. Any = >> volunteers? A first step would be to take he tuning-man-page and wikif= y it.=20 >> Other tuning sources are welcome too. >>>>> >>>>> Every FreeBSD dev with a wiki account can hand out write access to = the=20 >> wiki. The benchmark page gives contributor-access. If someone wants wr= ite=20 >> access create a FirstnameLastname account and ask here for contributor= -access. >>>>> >>>>> Don't worry if you think your english is not good enough, even some= one- >> word notes can help (and _my_ english got already corrected by other p= eople on=20 >> the benchmark page). >>>>> >>>>> Bye, >>>>> Alexander. >>>>> >>>>> >>>>> >>>>> >>>> >>>> Nice to see movement ;-) >>>> >>>> But there seems something unclear: >>>> >>>> man make.conf(5) says, that MALLOC_PRODUCTION is a knob set in >>>> /etc/make.conf. >>>> The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. >>>> >>>> What's right and what's wrong now? >>> >>> I can say with certainty that this value belongs in /etc/make.conf >>> (on RELENG_8 and earlier at least). >>> >>> src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, >>> so, this is definitely a make.conf variable. >> >> Eh, normal make variables can go in src.conf as well. They do not hav= e >> to be listed in bsd.own.mk. World builds include /etc/src.conf wherea= s >> every make invocation includes /etc/make.conf via sys.mk. The only re= ason >> to use /etc/src.conf is to have a place to put variables only affect >> make buildworld / buildkernel but do not affect other make invocations= =2E >=20 > I was always under the impression src.conf(5) variables had to be > manually added to bsd.own.mk and similar bits (e.g. > src/tools/build/options/WITH_xxx which is what's used to create the > src.conf(5) man page), but upon your comment and manual investigation o= n > my part, I found you're indeed right. Taken from bsd.own.mk: >=20 > 107 .if !defined(_WITHOUT_SRCCONF) > 108 SRCCONF?=3D /etc/src.conf > 109 .if exists(${SRCCONF}) > 110 .include "${SRCCONF}" > 111 .endif > 112 .endif >=20 > As long as third-party software doesn't depend on MALLOC_PRODUCTION for= > something (I don't know why something would, but who knows; maybe > there's a third-party malloc implementation which might?), then putting= > it in src.conf would be fine (src/lib/libc/stdlib files reference it). >=20 Then the manpage should reflect this. man src.conf does not show up MALLOC_PRODUCTIOn, but man make.conf does. If the latter is right, then it should be worth mentioned that make.conf is incorporating src.conf. Just a suggestion. Regards, Oliver --------------enig1502F529B2C0204E19EA4E4D Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO9LnRAAoJEOgBcD7A/5N8jWkH/2vnf7syPz2Ody5yUBUIqBk8 6zLbCedWMEVT5Shv+Y9QI1Uc0ku5DieFK4kbFSkp5dpIwPz5FZyxq57bXvcB0lVs xGJJ+I6C9TySn58mGU46CR/qi2PWiX08aBtHerR6WOEKEhbeyw78Axf96KqhJmBG as04C9KmqFFrqRdLlMsttbj5FzJrJCbWXj0wTY1apFBbFYsxjNci7I1IOluIB5oM lcSX2Q1letuEHjf0snoMNW2CqszHxVuEOFEMPSCh09xLzuAMjv6a/4QN3ThqbaOZ MTf5G63H/LvlZRotYwalm+/LB21+8CYaYGlgwPXwLk+JlzRlbu1Ll6q9ElhIGI8= =UR3U -----END PGP SIGNATURE----- --------------enig1502F529B2C0204E19EA4E4D-- From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 18:58:18 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 949CE106564A; Fri, 23 Dec 2011 18:58:18 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vw0-f54.google.com (mail-vw0-f54.google.com [209.85.212.54]) by mx1.freebsd.org (Postfix) with ESMTP id 362BD8FC14; Fri, 23 Dec 2011 18:58:18 +0000 (UTC) Received: by vbbfr13 with SMTP id fr13so13360494vbb.13 for ; Fri, 23 Dec 2011 10:58:17 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=jdElovAiB5qt+8UhP+nHX0MFmqUm2lNEXxNyDKmJ8mE=; b=uoOZMo0leVeZb8ciFl3u+vu7OFukIk6BVGsRR4aajbXl85b10AVH6XcP5eP18cdg8B DuFaWS6moOB8S0ODqaDezuRhHH228bXqP6b30DuNkpKww47AeqGCc566s3xjvcC6/vuu hW90Xx6SnV3bv91ElA7gJCAW8ih6IBpCwOhps= MIME-Version: 1.0 Received: by 10.52.23.44 with SMTP id j12mr1978682vdf.117.1324666697608; Fri, 23 Dec 2011 10:58:17 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.36.5 with HTTP; Fri, 23 Dec 2011 10:58:17 -0800 (PST) In-Reply-To: <4EF45F8D.9030404@mail.zedat.fu-berlin.de> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <4EF444BB.9090400@digsys.bg> <4EF45F8D.9030404@mail.zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 10:58:17 -0800 X-Google-Sender-Auth: ONOZA9F9M6I5ZrXaguZ37Gp62lU Message-ID: From: Adrian Chadd To: "O. Hartmann" Content-Type: text/plain; charset=ISO-8859-1 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky , Daniel Kalchev Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 18:58:18 -0000 Hi, I think this thread has gone far, far off the rails. If you're able to provide some solid debugging or willing to put in the effort to provide said solid debugging, then great. The easier you can make it for someone to fix for you (whether they're a FreeBSD committer or otherwise) the more likely it'll be fixed. There's no-one notionally in charge and paid to look after the scheduler. This is the unfortunate truth. No amount of saying "but but people are paid to do this!" will fix that particular point. The way that 99% of FreeBSD work gets done is when someone (who is a committer or otherwise) gets angry at how something doesn't quite work for them, and they decide to go and do something about it. The only point where a committer needs be involved is when someone wants to push their code into "upstream" (to borrow a Linux-ism) FreeBSD. If you're able to setup KTR and drive it + schedgraph (just like Steve has) and run this on a workload that is _repeatedly_ broken for you, then you're immediately going to have a better chance at getting it fixed. Bonus points if you can run the same benchmark on 4BSD and ULE, reporting KTR + schedgraph traces for both. That is going to be _by far_ the most helpful thing anyone can do in this ridiculously overly-verbose thread. Come on guys/girls/fuzzy creatures, you want to fix the problem? Bitching about it won't help. Unless you're like me and have an interest in Linguistics and end up writing a "flame war to code" generator. Then we'll likely be fine. :) Adrian From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 19:00:26 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id CA493106568C; Fri, 23 Dec 2011 19:00:26 +0000 (UTC) (envelope-from adrian.chadd@gmail.com) Received: from mail-vx0-f182.google.com (mail-vx0-f182.google.com [209.85.220.182]) by mx1.freebsd.org (Postfix) with ESMTP id 49A6D8FC14; Fri, 23 Dec 2011 19:00:15 +0000 (UTC) Received: by vcbfk1 with SMTP id fk1so13269608vcb.13 for ; Fri, 23 Dec 2011 11:00:14 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:sender:in-reply-to:references:date :x-google-sender-auth:message-id:subject:from:to:cc:content-type; bh=pVNxq/sda4/ARnsIwaqQicIGf0cNN8ppmegJIqTTMao=; b=E/bJAlK33ESHR9+qif/dBAnNCt5ddqOq8AdiiLDxpdyzv3QwUitiECeL+q3Q7ygh7h ZswWn62WqZV1ob+Z+pqmsnYMONxEmnvii+zAuIPVlo8268F0VOOHHdr6TjjmCM9+3JqK k2NKpyhPL79mDQN+pgwpEU9BzEqPbgNmaGs6g= MIME-Version: 1.0 Received: by 10.220.149.193 with SMTP id u1mr9833148vcv.33.1324666814393; Fri, 23 Dec 2011 11:00:14 -0800 (PST) Sender: adrian.chadd@gmail.com Received: by 10.52.36.5 with HTTP; Fri, 23 Dec 2011 11:00:14 -0800 (PST) In-Reply-To: <4EF45F8D.9030404@mail.zedat.fu-berlin.de> References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <4EF444BB.9090400@digsys.bg> <4EF45F8D.9030404@mail.zedat.fu-berlin.de> Date: Fri, 23 Dec 2011 11:00:14 -0800 X-Google-Sender-Auth: 8FaQp-kjPH5nInbeXF--tPIiS50 Message-ID: From: Adrian Chadd To: "O. Hartmann" Content-Type: text/plain; charset=ISO-8859-1 Cc: freebsd-performance@freebsd.org, freebsd-current@freebsd.org, Igor Mozolevsky , Daniel Kalchev Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 19:00:26 -0000 Hi, I think this thread has gone far, far off the rails. If you're able to provide some solid debugging or willing to put in the effort to provide said solid debugging, then great. The easier you can make it for someone to fix for you (whether they're a FreeBSD committer or otherwise) the more likely it'll be fixed. There's no-one notionally in charge and paid to look after the scheduler. This is the unfortunate truth. No amount of saying "but but people are paid to do this!" will fix that particular point. The way that 99% of FreeBSD work gets done is when someone (who is a committer or otherwise) gets angry at how something doesn't quite work for them, and they decide to go and do something about it. The only point where a committer needs be involved is when someone wants to push their code into "upstream" (to borrow a Linux-ism) FreeBSD. If you're able to setup KTR and drive it + schedgraph (just like Steve has) and run this on a workload that is _repeatedly_ broken for you, then you're immediately going to have a better chance at getting it fixed. Bonus points if you can run the same benchmark on 4BSD and ULE, reporting KTR + schedgraph traces for both. That is going to be _by far_ the most helpful thing anyone can do in this ridiculously overly-verbose thread. Come on guys/girls/fuzzy creatr From owner-freebsd-performance@FreeBSD.ORG Fri Dec 23 20:23:29 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 1479C1065676; Fri, 23 Dec 2011 20:23:29 +0000 (UTC) (envelope-from yanegomi@gmail.com) Received: from mail-tul01m020-f182.google.com (mail-tul01m020-f182.google.com [209.85.214.182]) by mx1.freebsd.org (Postfix) with ESMTP id AFA358FC16; Fri, 23 Dec 2011 20:23:28 +0000 (UTC) Received: by obbwd18 with SMTP id wd18so8150718obb.13 for ; Fri, 23 Dec 2011 12:23:28 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=gamma; h=mime-version:in-reply-to:references:date:message-id:subject:from:to :cc:content-type:content-transfer-encoding; bh=Kf/ZXJWnVr9F2oe08cVEYJTbEa7jcwuO3NRfwYEot8k=; b=azgNLI9ss9WT4CGGhkjBlK9tCnMWtPX+DRCmM8/Mqf2K5P/+uUbIEKezatN0+uXQWR E8GXejMx6+PZQEsaSIG8Zeu5eyE580Xj82S3QRt0qCKV9dEsNIdnernQXeK0xMGuX94A Kem+wf6YwphwY0BfYl69DXcfkc2mjGv1PAOos= MIME-Version: 1.0 Received: by 10.182.225.66 with SMTP id ri2mr13927025obc.26.1324671808126; Fri, 23 Dec 2011 12:23:28 -0800 (PST) Received: by 10.182.62.227 with HTTP; Fri, 23 Dec 2011 12:23:27 -0800 (PST) In-Reply-To: <4EF45A1B.1050505@unsane.co.uk> References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> <9706CBFC-9A69-4365-8883-FF45BDFDC108@gmail.com> <4EF45A1B.1050505@unsane.co.uk> Date: Fri, 23 Dec 2011 12:23:27 -0800 Message-ID: From: Garrett Cooper To: Vincent Hoffman Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable Cc: "freebsd-stable@freebsd.org" , "freebsd-current@freebsd.org" , "igor@hybrid-lab.co.uk" , Alexander Leidinger , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 23 Dec 2011 20:23:29 -0000 On Fri, Dec 23, 2011 at 2:38 AM, Vincent Hoffman wrote= : > On 23/12/2011 02:56, Garrett Cooper wrote: >> On Dec 22, 2011, at 3:58 PM, Jeremy Chadwick = wrote: >> >>> On Fri, Dec 23, 2011 at 12:44:14AM +0100, O. Hartmann wrote: >>>> On 12/21/11 19:41, Alexander Leidinger wrote: >>>>> Hi, >>>>> >>>>> while the discussion continued here, some work started at some other = place. Now... in case someone here is willing to help instead of talking, f= eel free to go to http://wiki.freebsd.org/BenchmarkAdvice and have a look w= hat can be improved. The page is far from perfect and needs some additional= people which are willing to improve it. >>>>> >>>>> This is only part of the problem. A tuning page in the wiki - which c= ould be referenced from the benchmark page - would be great too. Any volunt= eers? A first step would be to take he tuning-man-page and wikify it. Other= tuning sources are welcome too. >>>>> >>>>> Every FreeBSD dev with a wiki account can hand out write access to th= e wiki. The benchmark page gives contributor-access. If someone wants write= access create a FirstnameLastname account and ask here for contributor-acc= ess. >>>>> >>>>> Don't worry if you think your english is not good enough, even some o= ne-word notes can help (and _my_ english got already corrected by other peo= ple on the benchmark page). >>>>> >>>>> Bye, >>>>> Alexander. >>>>> >>>>> >>>>> >>>>> >>>> Nice to see movement ;-) >>>> >>>> But there seems something unclear: >>>> >>>> man make.conf(5) says, that =A0MALLOC_PRODUCTION is a knob set in >>>> /etc/make.conf. >>>> The WiJi says, MALLOC_PRODUCTION is to be set in /etc/src.conf. >>>> >>>> What's right and what's wrong now? >>> I can say with certainty that this value belongs in /etc/make.conf >>> (on RELENG_8 and earlier at least). >>> >>> src/share/mk/bsd.own.mk has no framework for MK_MALLOC_PRODUCTION, >>> so, this is definitely a make.conf variable. >> Take the advice in tuning(7) with a grain of salt because a number of su= ggestions are really outdated. I know because I filed a PR last night after= I saw how out of synch some of the defaults it claimed were with reality o= n 9.x+. And I know other suggestions in the manpage are dated as well ;/. > There is a wiki page http://wiki.freebsd.org/SystemTuning which is > currently more or less tuning(7) with some annotations, the idea being > to sort out whats outdated/invalid with an aim of rewriting tuning(7) to > be more accurate and useful. I'll grab any info in your pr thats not up > there already to keep it updated if thats ok. Sure. Please take my suggestions (apart from the networking sysctls) with a grain of salt as I didn't look at the sourcecode for the filesystem ones (I was going off the top of my head and other emails I had seen passed around). I'll update the tuning 'wiki' with mention of the new networking defaults. If we want to make this manpage 'timeless', should we remove mention of defaults and go off basic guidelines (if you set this higher, you'll get better performance in scenario, X.Y.Z, etc)? Thanks! -Garrett From owner-freebsd-performance@FreeBSD.ORG Sat Dec 24 00:59:28 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 4B9901065670; Sat, 24 Dec 2011 00:59:28 +0000 (UTC) (envelope-from vince@unsane.co.uk) Received: from unsane.co.uk (unsane-pt.tunnel.tserv5.lon1.ipv6.he.net [IPv6:2001:470:1f08:110::2]) by mx1.freebsd.org (Postfix) with ESMTP id A85778FC0A; Sat, 24 Dec 2011 00:59:27 +0000 (UTC) Received: from vhoffman-macbooklocal.local ([10.10.10.20]) (authenticated bits=0) by unsane.co.uk (8.14.4/8.14.4) with ESMTP id pBO0xN07088483 (version=TLSv1/SSLv3 cipher=DHE-RSA-CAMELLIA256-SHA bits=256 verify=NO); Sat, 24 Dec 2011 00:59:24 GMT (envelope-from vince@unsane.co.uk) Message-ID: <4EF523EB.7060905@unsane.co.uk> Date: Sat, 24 Dec 2011 00:59:23 +0000 From: Vincent Hoffman User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:8.0) Gecko/20111105 Thunderbird/8.0 MIME-Version: 1.0 To: Garrett Cooper References: <4EF3C0CE.5040802@zedat.fu-berlin.de> <20111222235846.GA6071@icarus.home.lan> <9706CBFC-9A69-4365-8883-FF45BDFDC108@gmail.com> <4EF45A1B.1050505@unsane.co.uk> In-Reply-To: X-Enigmail-Version: 1.3.4 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "freebsd-stable@freebsd.org" , "freebsd-current@freebsd.org" , "igor@hybrid-lab.co.uk" , Alexander Leidinger , "freebsd-performance@freebsd.org" , "O. Hartmann" , Jeremy Chadwick Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 24 Dec 2011 00:59:28 -0000 On 23/12/2011 20:23, Garrett Cooper wrote: > On Fri, Dec 23, 2011 at 2:38 AM, Vincent Hoffman wrote: >> On 23/12/2011 02:56, Garrett Cooper wrote: >> There is a wiki page http://wiki.freebsd.org/SystemTuning which is >> currently more or less tuning(7) with some annotations, the idea being >> to sort out whats outdated/invalid with an aim of rewriting tuning(7) to >> be more accurate and useful. I'll grab any info in your pr thats not up >> there already to keep it updated if thats ok. > Sure. Please take my suggestions (apart from the networking > sysctls) with a grain of salt as I didn't look at the sourcecode for > the filesystem ones (I was going off the top of my head and other > emails I had seen passed around). > I'll update the tuning 'wiki' with mention of the new networking > defaults. If we want to make this manpage 'timeless', should we remove > mention of defaults and go off basic guidelines (if you set this > higher, you'll get better performance in scenario, X.Y.Z, etc)? > Thanks! > -Garrett Good point, for tuning the defaults are probably not so important as they are likely to change at some point (as the current man page will attest) so maybe its less important to document them. Happy Christmas (or holiday of your choice ;) to you all and I hope everyone has a good new year. Vince > _______________________________________________ > freebsd-current@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-current > To unsubscribe, send any mail to "freebsd-current-unsubscribe@freebsd.org" From owner-freebsd-performance@FreeBSD.ORG Sat Dec 24 14:49:04 2011 Return-Path: Delivered-To: freebsd-performance@FreeBSD.ORG Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id AB51E1065673; Sat, 24 Dec 2011 14:49:04 +0000 (UTC) (envelope-from ohartman@mail.zedat.fu-berlin.de) Received: from outpost1.zedat.fu-berlin.de (outpost1.zedat.fu-berlin.de [130.133.4.66]) by mx1.freebsd.org (Postfix) with ESMTP id 4FB438FC08; Sat, 24 Dec 2011 14:49:04 +0000 (UTC) Received: from inpost2.zedat.fu-berlin.de ([130.133.4.69]) by outpost1.zedat.fu-berlin.de (Exim 4.69) with esmtp (envelope-from ) id <1ReSuE-0003Zl-4H>; Sat, 24 Dec 2011 15:49:02 +0100 Received: from e178017174.adsl.alicedsl.de ([85.178.17.174] helo=thor.walstatt.dyndns.org) by inpost2.zedat.fu-berlin.de (Exim 4.69) with esmtpsa (envelope-from ) id <1ReSuD-0006C4-T1>; Sat, 24 Dec 2011 15:49:02 +0100 Message-ID: <4EF5E65C.3060405@mail.zedat.fu-berlin.de> Date: Sat, 24 Dec 2011 15:49:00 +0100 From: "O. Hartmann" User-Agent: Mozilla/5.0 (X11; FreeBSD amd64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Daniel Kalchev References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF45C85.9010709@mail.zedat.fu-berlin.de> <4EF46829.6010508@digsys.bg> In-Reply-To: <4EF46829.6010508@digsys.bg> X-Enigmail-Version: undefined Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="------------enig863C2B495A6AA626DD82D833" X-Originating-IP: 85.178.17.174 X-Mailman-Approved-At: Sat, 24 Dec 2011 15:01:29 +0000 Cc: Martin Sugioarto , freebsd-current@FreeBSD.ORG, Igor Mozolevsky , freebsd-performance@FreeBSD.ORG, "O. Hartmann" , Daniel@FreeBSD.ORG Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 24 Dec 2011 14:49:04 -0000 This is an OpenPGP/MIME signed message (RFC 2440 and 3156) --------------enig863C2B495A6AA626DD82D833 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable On 12/23/11 12:38, Daniel Kalchev wrote: >=20 >=20 > On 23.12.11 12:48, O. Hartmann wrote: >> Look at Steve Kargls problem. He investigated a SCHED_ULE problem in a= >> way that is far beyond enough! He gave tests, insights of his setup, >> bad performance compared to SCHED_4BSD and what happend? We are still >> stuck with this problem and more and more people realise, that FreeBSD= >> does have somewhere a problem and this seems to be a nasty problem not= >> easy to find or investigate. >=20 > This has made me to realize, that I was having a problem with SCHED_ULE= > that I was not aware of until now. WOW! :) >=20 > Every scheduler has some problem, some fail here some fail there. I am > confident, that the case that Steve Kargls has reported will be resolve= d. >=20 >> Another problem is this very elite-feeling closed club. Once you >> managed it getting into the club of committers or core team members, >> you'll probably fight for your seat ... I dont propose for that >> socialists crap Linux people tend to be like, > [..] >=20 > You never heard of the "People's Republic of Berkeley"? :) >=20 > As for commiter access, this sort of comments trigger the system > administrator in me. I have seen enough people, who for the lack of > other excuses always use "but I don't have enough RIGHTS!". I am evil, = I > know.... >=20 >> But I follow the illusion that if people can see what benchmarks >> reveal, they start thinking and if the facts are starting to give a >> heavy load load on those rejecting the facts, they migght change their= >> opinion or get hopefully replaced by more openminded people. >=20 > Here is now it works: >=20 > If you see an problem and have a solution: go fix it. Many will be > grateful. > If you can't fix it, but have an idea how to fix it, share it. May will= > be grateful. > If you can't fix it and don't have any idea, just say "there is a > problem" and stop there. There are many, many, many like you who just > hold their breath. >=20 > We all learn, every day. >=20 > Daniel Sorry, but your crap is simply breathtaking. oh --------------enig863C2B495A6AA626DD82D833 Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.11 (FreeBSD) iQEcBAEBAgAGBQJO9eZdAAoJEOgBcD7A/5N83ZwH/RTlnilxJOS4sBMpXduNFg/e LMRsokn+5zwp1EhqNg5HLPSJZbNq3DWm2IrutrPoRBOMAmUt2AYrxnxNu+9sSJwh r7Fvq+1i86sd+B28ngfmV3Xn+Kj7mB72gvxpUt1vlVGkb6viriBlwhG5tEUOwhS/ iSzcBQnEJbmjWnDOv2St1Up0ZV7jrLWW6n9ShUJnl7Nt76InhzQFGdB3YddUYWXX c0sqSzt7Y3y2DFFe5ZuRtyN/Xr2aAgEONhxnig10/ufh5gVWc/7DqGGUuY9zhwmF E6FQ7QPjSYq83aD9aKkKRD+nwenaX4gvsYCAyJUbpA5lIyrVcFk+UADIXC7JdJc= =q9EX -----END PGP SIGNATURE----- --------------enig863C2B495A6AA626DD82D833-- From owner-freebsd-performance@FreeBSD.ORG Sat Dec 24 16:02:54 2011 Return-Path: Delivered-To: freebsd-performance@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 9421D106564A for ; Sat, 24 Dec 2011 16:02:54 +0000 (UTC) (envelope-from pathiaki2@yahoo.com) Received: from nm27.bullet.mail.sp2.yahoo.com (nm27.bullet.mail.sp2.yahoo.com [98.139.91.97]) by mx1.freebsd.org (Postfix) with SMTP id 553D38FC0A for ; Sat, 24 Dec 2011 16:02:54 +0000 (UTC) Received: from [98.139.91.70] by nm27.bullet.mail.sp2.yahoo.com with NNFMP; 24 Dec 2011 15:50:29 -0000 Received: from [98.139.91.49] by tm10.bullet.mail.sp2.yahoo.com with NNFMP; 24 Dec 2011 15:50:29 -0000 Received: from [127.0.0.1] by omp1049.mail.sp2.yahoo.com with NNFMP; 24 Dec 2011 15:50:29 -0000 X-Yahoo-Newman-Property: ymail-3 X-Yahoo-Newman-Id: 144606.86549.bm@omp1049.mail.sp2.yahoo.com Received: (qmail 22728 invoked by uid 60001); 24 Dec 2011 15:50:28 -0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=yahoo.com; s=s1024; t=1324741828; bh=j3TWe36xPBLNgFQ5HV5uDBsd47Imi3tO9FEDxaUkpPY=; h=X-YMail-OSG:Received:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type; b=Q7hdejNxW75TVk9LD1A5KnCZ5OpLJCLppXX8fNG4D5bx0mv0Vqmn2C/225NeH5E4zT2bswMoJqTn4dmLfK/ku8UVyxTWJiTfwTFyIOsxqAapR7cnQX/G9L3ESStrF/Xj9E0OzBIjI81I51Q9ZC7dR0FGyifvLs6tio4KLQfcTNw= DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; h=X-YMail-OSG:Received:X-Mailer:References:Message-ID:Date:From:Reply-To:Subject:To:Cc:In-Reply-To:MIME-Version:Content-Type; b=QjOqs0ohqYeJ7nMHZf3ZBRidTzHtEb/cIC/dO/MvSLA/0KWaI8zq69U8JWHpb2dBp1HlbeqSmwYO903BaG7oQ7fav0BdRj5QyX8IjT3sRSIX7GqV/f7L/PSEzESjwgSftiTzotWhGgFtNCRQ0iNDsS/2WFK9xxd0KwupIWtkG8E=; X-YMail-OSG: sWX64ZsVM1lEaGbBMTgnjWXYrJ.FSFHBA.Hd5G9KUmt4WQ0 vxpa6FZM5_EXk9IMG3xs7YaKPjVDQ32uDKmJUPQ6.G8MFPHOjaLof2e9wiZr Bki8PuBocAwd.KjVWu2g.8nJNiqrkmCwdEMszr9Pi6G9RudKGgx18zzIRFLV hHDFmQ0u4UKvEQrVj7lSqhdfrIc_CSu.ycixrGFx3QGNgu25dw19zuKuUMOc iVSoPuxEQCGuKkIjAKL3QJJsU9tIysLasJQfll_Mlrd1y5XRhCFZVaQN0raY 4HtU.qOCpuHgTPg2Ufe75Vti.KaNDaQOKfFLt9CRjBtVE4u.Wwn8uYnk80ac LDZnlhekUORLz4__px6xBC84wcgTOFZl5vTVPBZmiapXx7lgP2VcoF_r25Kl Uq_s49j_1NBvnHhNHcYhA.AgHjOqL50UubGUsaFTa2DnWnmfz7.Pz Received: from [72.70.55.190] by web110503.mail.gq1.yahoo.com via HTTP; Sat, 24 Dec 2011 07:50:28 PST X-Mailer: YahooMailWebService/0.8.115.331698 References: <4EF25468.9040204@gmail.com> <4EF2C613.3020609@digsys.bg> <4EF3D68C.2060803@zedat.fu-berlin.de> <20111223074706.1afe4d26@zelda.sugioarto.com> <4EF45C85.9010709@mail.zedat.fu-berlin.de> <4EF46829.6010508@digsys.bg> <4EF5E65C.3060405@mail.zedat.fu-berlin.de> Message-ID: <1324741828.2235.YahooMailNeo@web110503.mail.gq1.yahoo.com> Date: Sat, 24 Dec 2011 07:50:28 -0800 (PST) From: Paul Pathiakis To: "O. Hartmann" , Daniel Kalchev In-Reply-To: <4EF5E65C.3060405@mail.zedat.fu-berlin.de> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Cc: Martin Sugioarto , "freebsd-current@FreeBSD.ORG" , Igor Mozolevsky , "freebsd-performance@FreeBSD.ORG" , "O. Hartmann" , "Daniel@FreeBSD.ORG" Subject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle Linux 6.1 Server X-BeenThere: freebsd-performance@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list Reply-To: Paul Pathiakis List-Id: Performance/tuning List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 24 Dec 2011 16:02:54 -0000 Hi,=0A=0AWell, I don't chime in, usually.=A0 However, enough is enough.=A0 = There are many merits to both *BSD and Linux.=A0 I don't agree with benchma= rks that slant either way, as I'm sure people in both camps will agree.=A0 = Please be adult and just agree to disagree.=A0 Technology applicable to the= problem at hand is the only useful thing that we should all agree on.=A0 P= ersonally, I don't care if it's BSD, a Linux-variant or even Windoze if it = solves the problem.=A0 So, if you would all look at all the time spent vent= ing on this idiocy as time that could have been spent coding, debugging, et= c, think how much time was wasted from people just reading these e-mails.= =A0 (Yes, I do and this was an absolute waste of my time.)=A0 So, if the co= mmunication on the thread was nearly as much going to development and findi= ng issues or the causes of the issues, maybe a scheduler problem would be t= racked down, maybe a benchmark issue would be tracked down.=A0 Maybe people= will stop using RC's versus releases, I don't know.=A0 I really don't care.=A0 Just = please stop with finger pointing and being disgruntled and indignant.=A0 FO= CUS!!=0A=0AI'd love to say something like "Can't we all just get along" but= we are just so polar in our beliefs, I don't see it happening.=A0 Just dro= p it.=A0 If you have something constructive to say, spin off this thread an= d let the primary thread just die.=A0 (It should have a week ago.)=A0 Solve= the benchmarking issue, solve the scheduler issue, just focus.=0A=0APaul P= .=0ACTO/Owner =0A=0AAtlantis Services=0A=0A"Civilized Computing"=0A=0A=0A__= ______________________________=0A From: O. Hartmann =0ATo: Daniel Kalchev =0ACc: Martin Sugioarto= ; freebsd-current@FreeBSD.ORG; Igor Mozolevsky ; freebsd-performance@FreeBSD.ORG; O. Hartmann ; Daniel@FreeBSD.ORG =0ASent: Saturday, December 24, 201= 1 9:49 AM=0ASubject: Re: Benchmark (Phoronix): FreeBSD 9.0-RC2 vs. Oracle L= inux 6.1 Server=0A =0AOn 12/23/11 12:38, Daniel Kalchev wrote:=0A> =0A> =0A= > On 23.12.11 12:48, O. Hartmann wrote:=0A>> Look at Steve Kargls problem. = He investigated a SCHED_ULE problem in a=0A>> way that is far beyond enough= ! He gave tests, insights of his setup,=0A>> bad performance compared to SC= HED_4BSD and what happend? We are still=0A>> stuck with this problem and mo= re and more people realise, that FreeBSD=0A>> does have somewhere a problem= and this seems to be a nasty problem not=0A>> easy to find or investigate.= =0A> =0A> This has made me to realize, that I was having a problem with SCH= ED_ULE=0A> that I was not aware of until now. WOW! :)=0A> =0A> Every schedu= ler has some problem, some fail here some fail there. I am=0A> confident, t= hat the case that Steve Kargls has reported will be resolved.=0A> =0A>> Ano= ther problem is this very elite-feeling closed club. Once you=0A>> managed = it getting into the club of committers or core team members,=0A>> you'll pr= obably fight for your seat ... I dont propose for that=0A>> socialists crap= Linux people tend to be like,=0A> [..]=0A> =0A> You never heard of the "Pe= ople's Republic of Berkeley"? :)=0A> =0A> As for commiter access, this sort= of comments trigger the system=0A> administrator in me. I have seen enough= people, who for the lack of=0A> other excuses always use "but I don't have= enough RIGHTS!". I am evil, I=0A> know....=0A> =0A>> But I follow the illu= sion that if people can see what benchmarks=0A>> reveal, they start thinkin= g and if the facts are starting to give a=0A>> heavy load load on those rej= ecting the facts, they migght change their=0A>> opinion or get hopefully re= placed by more openminded people.=0A> =0A> Here is now it works:=0A> =0A> I= f you see an problem and have a solution: go fix it. Many will be=0A> grate= ful.=0A> If you can't fix it, but have an idea how to fix it, share it. May= will=0A> be grateful.=0A> If you can't fix it and don't have any idea, jus= t say "there is a=0A> problem" and stop there. There are many, many, many l= ike you who just=0A> hold their breath.=0A> =0A> We all learn, every day.= =0A> =0A> Daniel=0A=0ASorry, but your crap is simply breathtaking.=0A=0Aoh