Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 9/18/84; site brl-sem.ARPA
Path: utzoo!watmath!clyde!burl!ulysses!allegra!mit-eddie!genrad!panda!talcott!harvard!seismo!brl-tgr!brl-sem!ron
From: ron@brl-sem.ARPA (Ron Natalie <ron>)
Newsgroups: net.bugs.4bsd,net.unix-wizards
Subject: Re: Loss of RFNM (w/fix)
Message-ID: <423@brl-sem.ARPA>
Date: Fri, 11-Oct-85 19:41:57 EDT
Article-I.D.: brl-sem.423
Posted: Fri Oct 11 19:41:57 1985
Date-Received: Mon, 14-Oct-85 03:31:47 EDT
References: <2476@ut-ngp.UTEXAS>
Distribution: net
Organization: Ballistic Research Lab
Lines: 18
Xref: watmath net.bugs.4bsd:1800 net.unix-wizards:15219

> Subject: Loss of RFNMs on ARPAnet hosts
> Index:	/sys/netimp/if_imp.h 4.2BSD
> 
> /*
>  * When IMPMTU based on 8159 is advertised as the TCP maximum
>  * segment size, it exercises a bug in the LH/DH-11 that causes small
>  * messages (e.g. RFNMs) to be dropped.  So we just arbitrarily
>  * shrink this number until it falls below the bug threshold.
>  * #define      IMPMTU          ((8159 / NBBY) & ~01)
>  *                                ^^^^
>  */
> #define IMPMTU          ((8000 / NBBY) & ~01)
> 
This BUG fix, while it will work, is WRONG.  Reading carefully you
will find that the EOM bit may not be set on the 8159/NBBY byte.
You should set the input DMA to IMPMTU+2 to avoid this problem.

-Ron