Return to BSD News archive
Xref: sserve comp.os.386bsd.questions:12174 comp.os.386bsd.misc:3086 Path: sserve!newshost.anu.edu.au!harbinger.cc.monash.edu.au!msuinfo!agate!howland.reston.ans.net!gatech!psuvax1!news.pop.psu.edu!ra.nrl.navy.mil!sundance!cmetz From: cmetz@sundance.itd.nrl.navy.mil (Craig Metz) Newsgroups: comp.os.386bsd.questions,comp.os.386bsd.misc Subject: Re: Whats wrong with Linux networking ??? Date: 8 Aug 1994 12:07:28 GMT Organization: Information Technology Division, Naval Research Laboratory Lines: 22 Message-ID: <325760$rc9@ra.nrl.navy.mil> References: <Cu107E.Mz3@curia.ucc.ie> <31vo1b$87t@quagga.ru.ac.za> NNTP-Posting-Host: sundance.itd.nrl.navy.mil In article <31vo1b$87t@quagga.ru.ac.za>, Geoff Rehmet <csgr@cs.ru.ac.za> wrote: >In <Cu107E.Mz3@curia.ucc.ie> dave@odyssey.ucc.ie writes: > >>OK, I keep hearing reference to how Linux networking is not as good >>as FreeBSD and so forth >... >>what I want to know is, can anyone back this up with facts ? What >>exactly doesn't Linux do (or does do, but incorrectly) ? > >A major difference I have noticed is that on Linux NFS runs at a >fraction of the speed achieved on FreeBSD. This is mainly due to a far >more simplistic implementation (I didn't compare the code much, but this >is very obvious). Probably a big factor is the absence of the nfsiod >(aka biod in SunOS) in Linux. It might be a good idea to base a >reimplementation on the nqnfs work in 4.4BSD - which implements cache >coherency under NFS via leasing. The Linux NFS implementation, the client side especially, is very bare-bones. Because of this, it couldn't hold a candle to the 4.4BSD NFS implementation. I expect, however, that someone will implement improvements from 4.4BSD.