Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!news.rmit.EDU.AU!news.unimelb.EDU.AU!munnari.OZ.AU!news.ecn.uoknor.edu!qns3.qns.com!imci4!newsfeed.internetmci.com!info.ucla.edu!galaxy.ucr.edu!noise.ucr.edu!news.service.uci.edu!news.intelenet.com!newshost.neptune.net!jonpike From: jonpike@neptune.net (Jon Pike) Newsgroups: comp.os.linux.development.apps,comp.os.linux.development.system,comp.os.linux.x,comp.os.linux.hardware,comp.os.linux.setup,comp.unix.bsd.386bsd.misc,comp.unix.bsd.bsdi.misc,comp.unix.bsd.netbsd.misc,comp.unix.bsd.freebsd.misc Subject: Re: Why to not buy Matrox Millennium Followup-To: comp.os.linux.development.apps,comp.os.linux.development.system,comp.os.linux.x,comp.os.linux.hardware,comp.os.linux.setup,comp.unix.bsd.386bsd.misc,comp.unix.bsd.bsdi.misc,comp.unix.bsd.netbsd.misc,comp.unix.bsd.freebsd.misc Date: 10 Apr 1996 20:31:55 GMT Organization: Neptune.Net (Neptune Consulting Group, Inc.) Lines: 29 Message-ID: <4kh5rr$pen@neptune.neptune.net> References: <4jn4qp$6p@darkstar.my.lan> <stephenkDp7nHo.369@netcom.com> <4jrhth$66a@hoopoe.psc.edu> <4jve3t$cfe@hermes.synopsys.com> <4k0m0f$68j@hoopoe.psc.edu> <4k0r5l$g2@siberia.gtri.gatech.edu> <slrn4m83ih.gn.notting@wen.raleigh.ibm.com> NNTP-Posting-Host: neptune.neptune.net X-Newsreader: TIN [version 1.2 PL2] Xref: euryale.cc.adfa.oz.au comp.os.linux.development.apps:14356 comp.os.linux.development.system:21103 comp.os.linux.x:29077 comp.os.linux.hardware:36043 comp.os.linux.setup:49983 comp.unix.bsd.386bsd.misc:526 comp.unix.bsd.bsdi.misc:3103 comp.unix.bsd.netbsd.misc:2886 comp.unix.bsd.freebsd.misc:17085 Bill Nottingham (notting@raleigh.ibm.com) wrote: : John M. Mills <jmills@ccrf-news.gtri.gatech.edu> said... : :If anyone has a URL for this, it would be useful to post it. : You can get it at: : http://plastique.stanford.edu/~laik/benchmarks/index.html : in PostScript form. : (brought to you by the wonders of AltaVista...) I belive this address is changed now, but has a forward.. The Linux kernel used was 1.2.8, not even the "final" (1.2.13) one in the stable line... it was current when they made the tests, which says something about how far back they were. I had mailed Lai, and he reported a NFS test done more recently... (and now available on their Web page) with I think, 1.3.68 and 69, before and after the addidtion of cached writes. Linux ended up going from about 400-600K read and write xfer rate to +600K write/20Mbyte read rates! FreeBSD was only about 17Mbyte/sec on reads! There was a thread on this in the Kernel developers mailing list, a while back.. (may still be in the Linux NET archives), where newer tests put the later kernels equal to or ahead of FreeBSD in most networking areas. Linus commented on how things have improved dramatically in most of the network code, with more to come.. I wish I had some of the test results handy.. Kevin Lai did mention the possibility of more tests on newer kernels in the future.. also, their test suite of programs used for that paper is available on the above mentioned site.. give em a shot!.