From owner-freebsd-hackers  Tue Aug 27 00:40:29 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id AAA21823
          for hackers-outgoing; Tue, 27 Aug 1996 00:40:29 -0700 (PDT)
Received: from root.com (implode.root.com [198.145.90.17])
          by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id AAA21817
          for <hackers@freebsd.org>; Tue, 27 Aug 1996 00:40:27 -0700 (PDT)
Received: from localhost (localhost [127.0.0.1]) by root.com (8.7.5/8.6.5) with SMTP id AAA16690; Tue, 27 Aug 1996 00:40:24 -0700 (PDT)
Message-Id: <199608270740.AAA16690@root.com>
X-Authentication-Warning: implode.root.com: Host localhost [127.0.0.1] didn't use HELO protocol
To: matthew@scruz.net (Matthew Kaufman)
cc: matthew@nic.scruz.net (Matthew Kaufman), hackers@freebsd.org
Subject: Re: questions 
In-reply-to: Your message of "Tue, 27 Aug 1996 00:32:21 PDT."
             <199608270732.AAA21300@scruz.net> 
From: David Greenman <dg@root.com>
Reply-To: dg@root.com
Date: Tue, 27 Aug 1996 00:40:24 -0700
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

>Original message <199608270725.AAA16651@root.com>
>From: David Greenman <dg@root.com>
>Date: Aug 27,  0:25
>Subject: Re: questions
>> 
>>    Probably not. You need to be more specific about how much larger you're
>> making the map (for a busy WWW server, set NMBCLUSTERS=4000).
>
>It is at 3584 today... but I don't know if it was that high last time
>it died. At least with FreeBSD, it doesn't panic when it runs out
>(many thanks to whoever made that improvement)

   That would be me, but I've never been able to get the code to reclaim
packet reassembly resources (to avoid the deadlock) to work properly. I think
it works but just doesn't help the problem much. The whole issue of running
out of buffers needs to be better handled, but it's low on my list.

-DG

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