From owner-freebsd-stable Sun Jul 8 5:59:31 2001 Delivered-To: freebsd-stable@freebsd.org Received: from hotmail.com (law2-f64.hotmail.com [216.32.181.64]) by hub.freebsd.org (Postfix) with ESMTP id C4AD937B403 for ; Sun, 8 Jul 2001 05:59:28 -0700 (PDT) (envelope-from kmays2000@hotmail.com) Received: from mail pickup service by hotmail.com with Microsoft SMTPSVC; Sun, 8 Jul 2001 05:59:28 -0700 Received: from 65.1.108.216 by lw2fd.hotmail.msn.com with HTTP; Sun, 08 Jul 2001 12:59:28 GMT X-Originating-IP: [65.1.108.216] From: "Kenneth Mays" To: stable@FreeBSD.ORG Subject: Re: Benchmarks from SysAdmin mag Date: Sun, 08 Jul 2001 08:59:28 -0400 Mime-Version: 1.0 Content-Type: text/plain; format=flowed Message-ID: X-OriginalArrivalTime: 08 Jul 2001 12:59:28.0730 (UTC) FILETIME=[D29C9BA0:01C107AD] Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG As for the benchmarks, I did notice: 1. the choice of EXT2 for Linux and UFS for the other Unix platforms. 2. The mention of "out of the box" but then kernel tweaking. Well, it starts to alter your readings when you setup different filesystems and/or start tweaking the system. I felt they should have consulted the FreeBSD people on how to get the most of of the v4.2 and did the same from the other vendor. I notice between the versions of 4.2-R and v4.3Stable that options that were turned off by default are now back on which would have changed some results in disk I/O. So, should the developers expect reviews like this and setup releases with all optimizations turned on for high loads and fast disk I/O?? How many times do we read articles where a reviewer hasn't tweaked the right variable or turned on the right switch?? Rebutting this article calls for people to reinvent what was done and then say what should have been done for FreeBSD to merit a respectable benchmark with the mentioned application "MailEngine". Otherwise, you have to take the article for what it is - someone's opinion - whether truely credible or not. Based on the information they had and experience they had with the product could alter their decisions. I'm sure we would see interesting results on different distributions of Linux or variants of BSD. WIndows 2000 vs WinXP RC-1 vs WIn 9x/Me. I think there is so much to know when architecting a solution on a particular platform that it is hard to make a informed decision without considered ALL the facts involved. Just by the comments I've read on the article, I would take it that Sys Admin should revisit the article with all external opinions considered. Ken _________________________________________________________________ Get your FREE download of MSN Explorer at http://explorer.msn.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message