From owner-freebsd-hackers  Sun Mar 10 09:56:12 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id JAA10827
          for hackers-outgoing; Sun, 10 Mar 1996 09:56:12 -0800 (PST)
Received: from Root.COM (implode.Root.COM [198.145.90.17])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id JAA10821
          for <hackers@freebsd.org>; Sun, 10 Mar 1996 09:56:09 -0800 (PST)
Received: from localhost (localhost [127.0.0.1]) by Root.COM (8.6.12/8.6.5) with SMTP id JAA14619; Sun, 10 Mar 1996 09:56:18 -0800
Message-Id: <199603101756.JAA14619@Root.COM>
X-Authentication-Warning: implode.Root.COM: Host localhost didn't use HELO protocol
To: dennis@etinc.com (dennis)
cc: hackers@freebsd.org
Subject: Re: slow network response 
In-reply-to: Your message of "Sun, 10 Mar 1996 11:47:27 EST."
             <199603101647.LAA11085@etinc.com> 
From: David Greenman <davidg@Root.COM>
Reply-To: davidg@Root.COM
Date: Sun, 10 Mar 1996 09:56:17 -0800
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

>>>Thanks Rodney, but go luck.  Traceroute tell me the routes looks good,
>>>but the average numbers on loopback are still very high.  I re-examined my
>>>routing tables and there doesn't seem to be anything that stands out.
>>>Even checked my cables.
>>>
>>>Anyknown problems with a 3Com-509B-combo on thinnet(BNC). I don't recall
>>>any myself.
>>>
>>>Again, any help folks is appreciated.  Thanks!
>>
>>   What do you have in /etc/hosts, and what does "localhost" resolve to?
>>
>>-DG
>>
>>David Greenman
>>Core-team/Principal Architect, The FreeBSD Project
>>
>
>I had a MB that just couldn't run a 3COM-509. I got huge delays, and putting
>the 
>board in another box indicated that there was nothing wrong with the card. I
>never did figure out what it was (since i don't normally use them), although it
>was a PCI '486 and I suspect it had something to do with the implementation
>of the ISA bridge.....
>
>Plugged in an NE2000 and it worked fine.

   Hmmm...I think the problem is that the interrupt either isn't configured
properly or the interrupt doesn't work for some reason. The 3c509 driver has
a kludge in it that allows it to recover from lost interrupts at a rate of
once per second. If the interrupt didn't work at all for some reason, then
the card would process a small burst of packets every second - and would be
very slow indeed.

-DG

David Greenman
Core-team/Principal Architect, The FreeBSD Project