From owner-freebsd-hackers Tue Apr 7 05:26:29 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id FAA16215 for freebsd-hackers-outgoing; Tue, 7 Apr 1998 05:26:29 -0700 (PDT) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from gilgamesch.bik-gmbh.de (gilgamesch.bik-gmbh.de [194.233.237.91]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id FAA16210 for ; Tue, 7 Apr 1998 05:26:24 -0700 (PDT) (envelope-from cracauer@gilgamesch.bik-gmbh.de) Received: (from cracauer@localhost) by gilgamesch.bik-gmbh.de (8.8.5/8.7.3) id OAA28275; Tue, 7 Apr 1998 14:26:58 +0200 (MET DST) Message-ID: <19980407142658.60535@cons.org> Date: Tue, 7 Apr 1998 14:26:58 +0200 From: Martin Cracauer To: Rob Maher , hackers@FreeBSD.ORG Subject: Re: FreeBSD vs Linux TCP/IP Stacks Mail-Followup-To: Rob Maher , hackers@FreeBSD.ORG References: <3524DF82.51F041C8@istar.ca> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Mailer: Mutt 0.89.1i In-Reply-To: <3524DF82.51F041C8@istar.ca>; from Rob Maher on Fri, Apr 03, 1998 at 01:09:22PM +0000 Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG In <3524DF82.51F041C8@istar.ca>, Rob Maher wrote: > I am preparing a report for a study of the differences between the > FreeBSD and Linux TCP/IP stacks, with respect to which implementation > is more efficient and robust. > > I was wondering if someone may be able to provide me with some > information on any major differences between the two stacks which > may make one stack seem 'better' than the other at handling > large loads of users. With all respect, but I doubt you should write such a report if you have to ask. At the very least you should be able to digg around in the Linux kernel and tell what is derived from BSD and what is home-grown (that requires that Linux'ers didn't though out the original copyright, of course...). But even then, how to judge what differences cause "better" handling of many users? For every difference between the systems, you probably find more than one person from each camp who argues that this change or its absense handles more load, if more efficient or more robust. I see two ways you can proceed: 1) Describe the differences without judging over the effects of the differences. Probably not what magazine editors want. 2) Look around for large machines and ask the administrators about their impressions. Order by number of simulaneous users. cdrom.com is FreeBSD' flagship, see the notes on their site and check the FreeBSD mailing list archives. Good luck, but please don't add to my dislike about journalists. Martin -- %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% Martin Cracauer http://www.cons.org/cracauer BSD User Group Hamburg, Germany http://www.bsdhh.org/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message