Return to BSD News archive
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.ecn.uoknor.edu!feed1.news.erols.com!news.bbnplanet.com!cpk-news-hub1.bbnplanet.com!news.sprintlink.net!news-peer.sprintlink.net!gail.ripco.com!nntp.neu.edu!not-for-mail
From: mkagalen@lynx.dac.neu.edu (Michael Kagalenko)
Newsgroups: comp.os.linux.misc,comp.os.linux.networking,comp.os.linux.setup,comp.unix.bsd.misc,comp.os.ms-windows.nt.advocacy,comp.os.os2.advocacy
Subject: Re: Linux vs whatever
Date: 30 Jan 1997 21:22:19 -0500
Organization: Northeastern University, Boston, MA. 02115, USA
Lines: 107
Message-ID: <5crl0r$n1@lynx.dac.neu.edu>
References: <32DFFEAB.7704@usa.net> <5coib1$jvv@cynic.portal.ca> <5cov5p$7hu@lynx.dac.neu.edu> <5cphaj$qvg@cynic.portal.ca>
NNTP-Posting-Host: lynx.dac.neu.edu
Content-Type: text/html
X-No-Archive: yes
Xref: euryale.cc.adfa.oz.au comp.os.linux.misc:155283 comp.os.linux.networking:66746 comp.os.linux.setup:94720 comp.unix.bsd.misc:2155 comp.os.ms-windows.nt.advocacy:51443 comp.os.os2.advocacy:264549
Curt Sampson (cjs@cynic.portal.ca) wrote in article <5cphaj$qvg@cynic.portal.ca> <pre><blink>
]In article <5cov5p$7hu@lynx.dac.neu.edu>,
]Michael Kagalenko <mkagalen@lynx.dac.neu.edu> wrote:
]
]> As I mentioned, that is legitimate subject to discuss, but this
]> thread started by allegiation that Linux networking isn't as good as BSDs.
]
]No, this thread wasn't started with that. My statement that the
]quality of BSD ccode is in general considerably better than the
]quality of NetBSD code was fourteen articles ago.
But this thread is longer then 14 articles. Do you know how to use DejaNews,
or you prefer to appear as idiotic as possible ?
]> I requested some evidence of it, none of were forthcoming so far.
]
]My NFS evidence is available at
]<http://www2.portal.ca/~cjs/computer/benchmark>. So far all of
]the stats I've seen from any Linux user have been far below these
]read benchmarks on any class of machines, and below the write
]benchmarks on machines with similar CPU power.
We already discussed your "bechmarks", I think. You alleged that
sun machines are "486-class hardware". This is unmitigated idiocy.
You further based your statement about Linux on 1 heavily loaded machine,
about which you didn't supply either load, disk controller, bus
type or version of Linux.
]If you have any evidence to the contrary please present it. Saying
]`well, there might be evidence to the contrary' without presenting
]it is like saying `I might toss a ball into the air and it might
]fall upwards to the sky instead of downwards to the ground.'
No, it's not like that. There is nothing wildly implausible about
saying that Linux networking is as good as BSD's
]
]> In other words you have no evidence, but repeat what everyone else is saying.
]
]I do have evidence. I just don't have what I consider to be conclusive
]evidence. But certainly if Linux's NFS performance is so wonderful,
]it shouldn't be hard to present some reasonable figures that match
]my published BSD figures.
NFS performance is not the same as networking performance, - it's only
part of it. Furthemore, you admitted that you
do not have performance figures for Linux machines even for NFS.
]Let's face it; the BSD evidence is here; the very limited Linux
]evidence shows that its networking is not as good as BSD's.
I must have missed that evidence. Could you name articles presenting
it or repost such evidence ?
]It's
]stretches credulity to believe it's some odd coincidence that a)
]the limited evidence we have shows Linux to be a poor performer,
]and b) there are all sorts of people out there with better evidence
]that are reading this discussion and saying `No, I won't post about
]it.'
]
]> This seems to be the most common answer when you press for evidence on
]> the claims re Linux vs BSD networking.
]
]You don't have to press for evidence, you have to produce it.
you have to produce evidence when you are backing some claim. You made
the claim that BSD performance is superior, thus it is you who needs
to back this up. I am allowing that BSD is, indeed, better, but I
have not seen any evidence that it really is.
]You
]have a Linux system or two, I presume. Run the tests, rather than
]complaining that I haven't gone out and installed Linux on my Alpha
](presumably after hand-coding a binary patch to the kernel to get
]around the fact that Linux is too stupid to figure out that it's
]headless) and done the tests for you.
You keep asking me to run tests to prove the points that you make.
That is not reasonable.
]> I am trying
]> to find some evidence, or references to such evidence, to support either position.
]
]No, if you were sincerely trying to find the evidence, you would
]run some tests and publish the figures.
I do not have time and hardware necessary to do it. Furthemore, I
am not making any claims about BSD vs Linux.
] You are trying to weasel
]your way out of actually admitting that, to the best evidence
]available at this time, Linux network performance is slower than
]that of the BSD systems on equivalant hardware.
Please, specfy what evidence you have. And, do not limit it to
NFS performance, since you make claims about "networking performance,"
which is broader class then NFS performance.
--
ABILITY,n. The natural equipment to accomplish some small part of the meaner
ambitions distinguishing able men from dead ones.
-- Ambrose Bierce, "The Devil's Dictionary"