*BSD News Article 87812


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!news.wildstar.net!news.ececs.uc.edu!news.kei.com!news.mathworks.com!arclight.uoregon.edu!news.bc.net!nntp.portal.ca!cynic.portal.ca!not-for-mail
From: cjs@cynic.portal.ca (Curt Sampson)
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: 29 Jan 1997 14:18:09 -0800
Organization: Internet Portal Services, Inc.
Lines: 55
Message-ID: <5coib1$jvv@cynic.portal.ca>
References: <32DFFEAB.7704@usa.net> <5cm5h3$bfg@lynx.dac.neu.edu> <5cmv5q$k6d@cynic.portal.ca> <5co7vd$lvt@lynx.dac.neu.edu>
NNTP-Posting-Host: cynic.portal.ca
Xref: euryale.cc.adfa.oz.au comp.os.linux.misc:155036 comp.os.linux.networking:66585 comp.os.linux.setup:94526 comp.unix.bsd.misc:2119 comp.os.ms-windows.nt.advocacy:51335 comp.os.os2.advocacy:264282

In article <5co7vd$lvt@lynx.dac.neu.edu>,
Michael Kagalenko <mkagalen@lynx.dac.neu.edu> wrote:

> That is because you did not make any points pertaining to the discussion;
> that is, how well Linux netwroking code performance compares with
> BSD code performance.

Perhaps you have difficulty reading. I reproduce below the first
few lines of my article, which quote the previous two articles. I
would like you to explain to me exactly where performance comes in
to it.

:> 1. Design and source code quality. The quality of the design and
:> source code in the BSD kernels is far, far above that of Linux.
:
:Not clear about that.  For example, BSD uses mbufs, while Linux uses

I don't see the word performance there. I see the words `design
and source code quality.' This is why I...

>...talk about organization of the code, and
> how BSD's code is written in the way you consider better.

Yes. In the way that anbody who can program his way out of a paper
bag considers better. If you don't believe me, just read the comments
in the source code from the people who work on the Linux code. For
example, when we look at definition of `struct device' in netdevice.h,
we see the comment `Actually, this whole structure is a big mistake.'
If you read _Linux Internals_ (published by Addison-Wesley; I think
that's the title--the book's at home but I can get a reference if
anyone really wants one) it discusses a much, much older kernel
that's a major revision level behind, and, says pretty much the
same thing. Will this kind of rubbish ever be fixed? Perhaps Linux
users are going to find it more important to write a third tulip
device driver instead, because two different device drivers for
the same piece of hardare just isn't enough.

>]I think the performance it really affects is that of the programmers.
>
> Well, I read this as indirect acknowledgement that BSD's and Linux's
> networking performs rather similarly well.

Two years ago it did not. I've not done any testing recently or
seen any tests that I would consider more than tentative, but from
everything I'm still hearing, Linux networking still does not
perform as well as BSD networking. However, this is not an issue
that I really care to debate; so if you wish to assert that Linux
networking is just as good without some solid testing to support
you, I'm not going to refute that.

cjs
-- 
Curt Sampson    cjs@portal.ca		Info at http://www.portal.ca/
Internet Portal Services, Inc.	
Vancouver, BC   (604) 257-9400		De gustibus, aut bene aut nihil.