From owner-freebsd-hackers Sun Apr 15 21:37:59 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from homer.softweyr.com (bsdconspiracy.net [208.187.122.220]) by hub.freebsd.org (Postfix) with ESMTP id CB71337B43F; Sun, 15 Apr 2001 21:37:56 -0700 (PDT) (envelope-from wes@softweyr.com) Received: from [127.0.0.1] (helo=softweyr.com ident=55ec35fc744f4083832c055185db7b68) by homer.softweyr.com with esmtp (Exim 3.16 #1) id 14p0lk-0000KW-00; Sun, 15 Apr 2001 22:37:44 -0600 Message-ID: <3ADA7717.BFFF01AB@softweyr.com> Date: Sun, 15 Apr 2001 22:37:44 -0600 From: Wes Peters Organization: Softweyr LLC X-Mailer: Mozilla 4.75 [en] (X11; U; Linux 2.2.12 i386) X-Accept-Language: en MIME-Version: 1.0 To: Bakul Shah Cc: Robert Watson , r.hyunseog@ieee.org, hackers@freebsd.org Subject: Re: Interesting article. References: <200104101733.NAA09610@renown.cnchost.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Bakul Shah wrote: > > Though, a lack of good Unicode support on FreeBSD seems like > a legitimate enough reason for the move. Yes, it would, if it were true, see /usr/ports/devel/libunicode. > Regardless, note that doubling of the performance meant they > saved anywhere from $10M to $20M (5000 servers x (price + > maintenance of each server) - development and testing costs). > Another doubling would still save them $5M or so! I'd take > that challenge if I can get 50% of the savings!:-) In order to determine if they really made any savings or not -- I notice that they've increased the number of servers at Hotmail from 3,400 to 5,000 - you'd also have to determine how much they could have improved the performance by merely writing their code as an Apache module. In my experience, if they were running on a relatively unmodified Apache CGI interface and using compiled C or C++ CGI's, they could easily double their performance by making the same code into a module, an exercise that should take a couple of experienced programmers a few weeks to do, at worst. They specifically mention the process-per-socket model in Apache, but don't mention attempting to do any performance tuning on it. The obvious first experiment would be a pre-forked server; another would be to replace the process per socket with a single process and I/O selection via select(2) or kqueue(2). So, was that 18 month development project really necessary from a technical standpoint, or only justified as a marketing cost? Nobody outside Microsoft management will ever really know. -- "Where am I, and what am I doing in this handbasket?" Wes Peters Softweyr LLC wes@softweyr.com http://softweyr.com/ To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message