From owner-freebsd-hackers Mon Mar 11 03:53:53 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id DAA03407 for hackers-outgoing; Mon, 11 Mar 1996 03:53:53 -0800 (PST) Received: from nixpbe.pdb.sni.de (mail.sni.de [192.109.2.33]) by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id DAA03402 for ; Mon, 11 Mar 1996 03:53:47 -0800 (PST) Received: (from nerv@localhost) by nixpbe.pdb.sni.de (8.6.12/8.6.12) id MAA14681 for hackers@freebsd.org; Mon, 11 Mar 1996 12:53:27 +0100 Message-Id: <199603111153.MAA14681@nixpbe.pdb.sni.de> Subject: Re: Comparing FreeBSD and other OSs To: koshy@india.hp.com (A JOSEPH KOSHY) Date: Mon, 11 Mar 96 12:49:54 MET From: Greg Lehey Cc: hackers@freebsd.org (Hackers; FreeBSD) In-Reply-To: <199603071045.AA184325548@fakir.india.hp.com>; from "A JOSEPH KOSHY" at Mar 07, 96 4:15 pm X-Mailer: xmail 2.4 (based on ELM 2.2 PL16) Sender: owner-hackers@freebsd.org X-Loop: FreeBSD.org Precedence: bulk > >>>>>> "jkh" == Jordan K Hubbard said: >>>>>> "gl" == Greg Lehey said: > > jkh> So many people ask me for comparative data on the two operating > jkh> systems that I think it's time to give them what they want. > [...elided...] > > gl> The current FreeBSD/Linux comparison is only part of a larger > gl> question: which operating system should I install on my PC? > [...elided...] > > I would also love to see comparisions done with Netware, Windows NT, SCO > and others so that users get valuable information about the choices > available to them. I have this feeling that many more people use Netware- / > Windows- based PC networks than any form of Unix; many because of ignorance of > the alternatives that are available to them. > > They live with egregious performance on costly hardware and lousy stability > to boot. I think they deserve a better deal :). > > If we are going to take up the benchmarking effort seriously, we probably > should have comparisions with the current "market-leaders" in PC OSes and > networking products. I think we're in complete agreement here. > The tough part is probably locating / creating portable benchmarks. Well, I went to see a man about a horse yesterday, and while we were waiting for somebody to bring it out, he said: "You know, we're in the same business. Our company is just installing a Web server". So I asked what software they were using, and was told NT. I suggested that this might not be the best choice, and he said "Well, we're only 5 people. They tell me that we might run into trouble if we have more than 15 concurrent accesses". Now I can't remember the performance figures for FreeBSD, and he didn't say what kind of machine it would be, but there's nothing cheaper than a 100 MHz 486 nowadays, so it sounds to me like FreeBSD would run rings round the NT box. So I thought up a scenario: We contact a number of manufacturers and computer magazines, world-wide, and set up a benchmark web server machine. Every day, we change the operating system, but we don't tell anybody what the OS de jour is. We invite everybody on the web to try to access it, and to tell us what they think of the perceived response time. At the same time, we monitor the performance (and, of course, down time if the be any). This would have the advantage of being a benchmark in the public eye, and one in which the BSD OSs would have a clear lead. Any thoughts? Greg