From owner-freebsd-questions Sun Nov 23 00:53:54 1997 Return-Path: Received: (from root@localhost) by hub.freebsd.org (8.8.7/8.8.7) id AAA29325 for questions-outgoing; Sun, 23 Nov 1997 00:53:54 -0800 (PST) (envelope-from owner-freebsd-questions) Received: from luke.cpl.net (luke.cpl.net [207.67.172.194]) by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id AAA29320 for ; Sun, 23 Nov 1997 00:53:49 -0800 (PST) (envelope-from shawn@cpl.net) Received: from cpl.net (root@shawn.cpl.net [207.67.172.196]) by luke.cpl.net (8.8.8/8.6.12) with ESMTP id AAA05842; Sun, 23 Nov 1997 00:53:06 -0800 (PST) Message-ID: <3477EF08.9E605EEE@cpl.net> Date: Sun, 23 Nov 1997 00:53:28 -0800 From: Shawn Ramsey X-Mailer: Mozilla 4.04 [en] (X11; I; Linux 2.0.32 i586) MIME-Version: 1.0 To: Wei Weng CC: freebsd-questions Subject: Re: performance differences References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-questions@freebsd.org X-Loop: FreeBSD.org Precedence: bulk Wei Weng wrote: > > check out : > http://www.techweb.com/se/directlink.cgi?INW19970901S0125 > for the result of performance tests on linux freebsd and >windowsNT. FreeBSD had the best performance in the short run, pulling to an early lead with 100 users, then falling back, we believe, because of some resource bottleneck, but the OS did not produce an error condition to alert us. BSD built on FreeBSD's This thread came up on this list awhile ago. It seems the company that did these tests did not recompile the FreeBSD kernel with MAXMEM, since the machines had 128MB. So the other machines really had double the memory. It would have been interesting to see how it fared with the same amount. I would not be surprised if it came out on top...