*BSD News Article 65331


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!newshost.telstra.net!asstdc.scgt.oz.au!metro!metro!news.cs.su.oz.au!harbinger.cc.monash.edu.au!news.mira.net.au!news.vbc.net!news.cais.net!chi-news.cic.net!newsspool.doit.wisc.edu!night.primate.wisc.edu!sdd.hp.com!hamblin.math.byu.edu!park.uvsc.edu!usenet
From: Terry Lambert <terry@lambert.org>
Newsgroups: comp.unix.bsd.freebsd.misc
Subject: Re: FreeBSD Losing to Linux - Please Help
Date: 4 Apr 1996 06:03:30 GMT
Organization: Utah Valley State College, Orem, Utah
Lines: 44
Message-ID: <4jvoni$pli@park.uvsc.edu>
References: <4ju4rb$67q@post.gsfc.nasa.gov>
NNTP-Posting-Host: hecate.artisoft.com

kjeffers@nastg.gsfc.nasa.gov (Karen Jefferson x2857) wrote:
] 
] We are in the midst of a development project which uses alot of UDP 
] and serial communications.
] 
] Although our preference had been to use FreeBSD, the UDP
] performance was terrible (200 Kbps over Ethernet), and we
] kept getting ENOBUF errors  which  makes FreeBSD an unacceptable choice.
] Our previous posts for possible parameters to tune didn't
] turn up anything helpful, and messages to freebsd.org haven't been
] answered yet.
] 
] The TCP performance was the same for both Linux and FreeBSD, and UDP
] testing on all other platforms in our facility proved okay for Solaris,
] SunOS, & SCO.
] 
] Is there anything we can do to improve the UDP performance of FreeBSD?
] Why does it care about buffering for UDP?  Please respond via email
] to tjeffers@nastg.gsfc.nasa.gov.  Thanks.

I believe this has been answered (where it was also posted) on the
-questions list.

I think that what you are actually seeing is not what you think
you are seeing.

The "ENOBUF" error is a transmit drop, which gets no notification
at all in the other OS's.  I believe that all OS's will have to
implement some type of error return from UDP sends (like this)
to deal with the issues of Frame Relay, ATM, and IPv6 source
quench, so eventually the apps will have to understand it, unless
the kernel backs them off against their will.

Garrett Wollman (probably via the -hackers  or -current list,
not -questions) would be the final source on this, I think.

If you have really found a bug, it will be fixed.


                                        Terry Lambert
                                        terry@cs.weber.edu
---
Any opinions in this posting are my own and not those of my present
or previous employers.