From owner-freebsd-hackers  Sat Mar  1 09:28:14 1997
Return-Path: <owner-hackers>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id JAA20106
          for hackers-outgoing; Sat, 1 Mar 1997 09:28:14 -0800 (PST)
Received: from etinc.com (et-gw-fr1.etinc.com [204.141.244.98])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id JAA20087
          for <hackers@freebsd.org>; Sat, 1 Mar 1997 09:28:07 -0800 (PST)
Received: from ntws (ntws.etinc.com [204.141.95.142]) by etinc.com (8.8.3/8.6.9) with SMTP id MAA25024; Sat, 1 Mar 1997 12:35:29 -0500 (EST)
Message-Id: <3.0.32.19970301122709.00b1f390@etinc.com>
X-Sender: dennis@etinc.com
X-Mailer: Windows Eudora Pro Version 3.0 (32)
Date: Sat, 01 Mar 1997 12:27:13 -0500
To: dg@root.com, Julian Assange <proff@iq.org>
From: dennis <dennis@etinc.com>
Subject: Re: optimised ip_input 
Cc: hackers@freebsd.org
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"
Sender: owner-hackers@freebsd.org
X-Loop: FreeBSD.org
Precedence: bulk

At 08:21 AM 3/1/97 -0800, you wrote:
>>ip_input() is appalling slow for multi-homed hosts, taking around
>>2 x num_interface_addresses comparisons to detect if a packet is
>>locally destined.
>>
>>I've addressed this with address caching, hashing, and intelligent
>>handling of broadcast addresses. Interested?
>
>   Certainly...I'd like to see the diffs...

A better way of handing the overhead and the complexity  issue is to
keep local addresses in the routing table with a LOCAL flag. This 
eliminates the overhead altogether and simplifies the process:

route=routelookup()
if (route.flags & localflag)
	deal_withit_locally()
else
	forward()

You can argue that in some cases this is more overhead for locally
destined packets, but in todays world (where routing speed is a
primary concern) this is faster most of the time and makes life
easier as it centralizes the structure dependencies.

Just a thought.

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