From owner-freebsd-questions@FreeBSD.ORG Sat Jan 22 06:13:56 2005 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 3D52916A4CE for ; Sat, 22 Jan 2005 06:13:56 +0000 (GMT) Received: from web53910.mail.yahoo.com (web53910.mail.yahoo.com [206.190.36.220]) by mx1.FreeBSD.org (Postfix) with SMTP id C05D043D41 for ; Sat, 22 Jan 2005 06:13:55 +0000 (GMT) (envelope-from stheg_olloydson@yahoo.com) Received: (qmail 96497 invoked by uid 60001); 22 Jan 2005 06:13:55 -0000 Comment: DomainKeys? See http://antispam.yahoo.com/domainkeys DomainKey-Signature: a=rsa-sha1; q=dns; c=nofws; s=s1024; d=yahoo.com; b=MuvuWVMq272D8d9hg+kGqD0ox242mwOWt00ApRRX2mx87Jj961h/7EpUVtxLAGs1VZDs4CiKoE0a4ehVO1cjqHwuc9ETiDHpFcE2/nIM8lbzWgMtf9IsUH3oKF7gPdP/OFGeWLv6d5KZSqnajVZo/b6exytuZaeBS/bytORfGSI= ; Message-ID: <20050122061355.96495.qmail@web53910.mail.yahoo.com> Received: from [68.18.53.121] by web53910.mail.yahoo.com via HTTP; Fri, 21 Jan 2005 22:13:54 PST Date: Fri, 21 Jan 2005 22:13:54 -0800 (PST) From: stheg olloydson To: linicks@gmail.com MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii cc: freebsd-questions@freebsd.org Subject: Re: FreeBSD 5.3 I/O Performance / Linux 2.6.10 X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 22 Jan 2005 06:13:56 -0000 it was said: >However, after performing a number of I/O and Postgresql tests on >different equipment, the performance proved to be considerably faster >when using Fedora. Fedora with XFS was the clear performance winner >in every test, followed by Fedora with EXT3, then FreeBSD. I was >surprised to find such a dramatic difference between Fedora with XFS >and FreeBSD. In almost every test Fedora(XFS) was dramatically >faster performing the exact same operations on the same hardware. >Are there any good reasons for such a difference. Your thoughts are >appreciated. > >Thanks! >--Nick Pavlica Hello, Although your email has all the classic hallmarks of a troll, I will rise to the bait. You need to post your hardware and software configs for both OSs, along with your test methodology to get anything other than the email equivalent shrug of the shoulders. The software configs need to include your kernel conf, make.conf, dmesg, etc. and their Linux counterparts. In the test methodology, include the names of whatever benchmarking software, if any, that you used. Don't forget the stats that showed the claimed perfomance difference. Throw in anything else you think that one would need to reproduce your tests. Regards, stheg P.S. If the "name" in your addy is meant to be phonetically identical to the name "Linux", it isn't. Linus pronounces it "lee-nooks", where the oo sound is the same as in smooth, not foot (neutrally-accented American pronunciation). After living in the States for some time now, I know Americans say it the same way you apparently do, but as with most things these days, just because an American says it doesn't make it true.