*BSD News Article 78977


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.mel.connect.com.au!news.mel.aone.net.au!imci4!newsfeed.internetmci.com!www.nntp.primenet.com!nntp.primenet.com!news-peer.gsl.net!news.gsl.net!portc01.blue.aol.com!newsstand.cit.cornell.edu!news.acsu.buffalo.edu!news.drenet.dnd.ca!crc-news.doc.ca!nott!bcarh189.bnr.ca!nrchh45.rich.nt.com!ferret.ocunix.on.ca!resurrect
From: hyc@frisky.la.platsol.com (Howard Chu)
Newsgroups: comp.unix.bsd.freebsd.misc,comp.protocols.appletalk
Subject: Re: netatalk, CAP, and FreeBSD 2.1
Date: 20 Sep 1996 18:03:21 -0700
Organization: Locus Computing Corporation, Los Angeles, California
Lines: 24
Message-ID: <R.51vesp$10gv@frisky.la.platsol.com>
References: <3238851B.41C67EA6@best.com> <323C9757.167EB0E7@whistle.com>
NNTP-Posting-Host: frisky.la.platsol.com
Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:27828 comp.protocols.appletalk:22602

Reposting article removed by rogue canceller.

In article <323C9757.167EB0E7@whistle.com>,
Julian Elischer  <julian@whistle.com> wrote:
%Leo Cazares wrote:
%> Question for users of CAP on FreeBSD:
%> How long does it take to copy a 1 Meg file from FreeBSD to a Mac?
%> ( I am asking because it takes many minutes when I know that
%> it should take less than 1 minute )

%The speed isn't "amazing" considering that afpd is a user-level process
%but it took 11 seconds to copy a 1.13 MB file to the desktop from
%my freeBSD machine.. 
%The FreeBSD machine has slow disks and is only a 486-66,
%and the time includes startup time,
%and the mac is quite old, so I'm not sure which part is the
%bottleneck, but it seems to be a lot better than what you saw..

Just as another datapoint, my PowerMac 8500/120 sustains ~400KB/sec transfer
rates to a Gateway P5-90 running PC-Interface/Macintosh on SCO OpenServer 5.
Our AFP server is also a user-level process, with the AppleTalk stack
implemented in a collection of STREAMS drivers. There's still a little room for
improvement, but not too much more than that. ATP is just too limiting...
-- 
Howard Chu				Principal Member of Technical Staff
hyc@locus.com				PLATINUM technology, Los Angeles Lab