Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.ecn.uoknor.edu!news.eng.convex.com!newshost.convex.com!bcm.tmc.edu!cs.utexas.edu!swrinde!howland.reston.ans.net!newsfeed.internetmci.com!in1.uu.net!news-m01.ny.us.ibm.net!ausnews.austin.ibm.com!rtpnews.raleigh.ibm.com!news@rtpnews.raleigh.ibm.com From: tjevans@raleigh.ibm.com (Thomas Evans) Newsgroups: comp.unix.bsd.freebsd.misc Subject: Larry McVoy vs John Dyson vs Linus Date: 17 Jul 1996 13:57:15 GMT Organization: ISSC South Region, RTP, NC Lines: 21 Message-ID: <4sirfr$1fn0@rtpnews.raleigh.ibm.com> NNTP-Posting-Host: evans.raleigh.ibm.com X-Newsreader: knews 0.9.6 I think this thread has been beaten to death, the subject "TCP latency" doesn't even apply. Larry: thanks for making LMBENCH available. John: if you don't like it, write your own or change it (I assume the source is available). Linus: thanks for starting Linux Benchmarks are tools, you have to know how to use them to get good results. For example many people run benchmarks on systems connected to busy lans instead of isolated lans, not knowing that ARPs/Broadcasts can account for a significant amount of CPU time. I use both FreeBSD and Linux, both have their good points and bad points. Both are better than Windows ;-), I prefer Linux cause its better supported (for example: ZIP and Token Ring support), seems easier to use. I use FreeBSD cause its the standard, its code is better documented thanks to Leffler/Stevens, and its copyright gives me more freedom in using the code. Both are better than Windoze ;-) Regards, -- Tom Evans tjevans@raleigh.ibm.com These views are my own, etc, etc