From mboxrd@z Thu Jan 1 00:00:00 1970 X-Spam-Checker-Version: SpamAssassin 3.4.4 (2020-01-24) on polar.synack.me X-Spam-Level: X-Spam-Status: No, score=-1.9 required=5.0 tests=BAYES_00 autolearn=ham autolearn_force=no version=3.4.4 X-Google-Language: ENGLISH,ASCII-7-bit X-Google-Thread: 103376,3cd3b8571c28b75f X-Google-Attributes: gid103376,public X-Google-Thread: 1067ce,c3fb2e547555e41a X-Google-Attributes: gid1067ce,public X-Google-ArrivalTime: 2003-09-01 21:17:35 PST Path: archiver1.google.com!news1.google.com!newsfeed.stanford.edu!news-spur1.maxwell.syr.edu!news.maxwell.syr.edu!newsfeed.icl.net!newsfeed.fjserv.net!proxad.net!freenix!skynet.be!skynet.be!louie!tlk!not-for-mail Sender: lbrenta@lbrenta Newsgroups: comp.lang.ada,alt.os.multics Subject: Re: A Customer's Request For Open Source Software References: <3F4828D9.8050700@attbi.com> <3F4EA616.30607@attbi.com> <3F512BD1.8010402@attbi.com> <3F52AA5F.8080607@attbi.com> <3F53B88E.7040405@attbi.com> From: Ludovic Brenta Date: 02 Sep 2003 06:16:47 +0200 Message-ID: User-Agent: Gnus/5.09 (Gnus v5.9.0) Emacs/21.2 MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Organization: -= Belgacom Usenet Service =- NNTP-Posting-Host: 217.136.9.196 X-Trace: 1062476239 reader1.news.skynet.be 3647 217.136.9.196:39504 X-Complaints-To: usenet-abuse@skynet.be Xref: archiver1.google.com comp.lang.ada:42053 alt.os.multics:2007 Date: 2003-09-02T06:16:47+02:00 List-Id: Christopher Browne writes: > I think it would be a mistake, today, to assume hot-swappable CPUs > as a basic function of the hardware. It has proven a lot more > economical to put additional rackmounted computers onto a rack, and > separate the functions across multiple buses. > > Futurists keep imagining that we are right around the corner from > the situation where it will make sense to buy computers that have > huge arrays of CPUs; while Apple may be very proud of their dual-PPC > "G5" systems, prices of multi-CPU "backplanes" remain stunningly > higher than those for single-CPU hardware, and there doesn't seem to > be good reason for that to change soon. In fact, mainframes have had this kind of capability for quite some time now. And the people who use them take hot-swapped CPUs for granted. The only reason why they don't convey an image of futurism is that they still program in COBOL :) Yes, mainframe-class hardware costs more than commodity PCs, but there are situations where this is economically sensible because racks upon racks of small independent computers mean huge sysadmin costs. I have been personally involved in managing several racks of 32 Linux blade servers and I can tell you that this kind of approach simply does not scale from a human perspective. More info here: http://www-1.ibm.com/servers/eserver/zseries/library/techpapers/gm130260.html (I am not affiliated with IBM). -- Ludovic Brenta.