From owner-freebsd-hackers  Sat Jun 24 13:48:20 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id NAB24137
          for hackers-outgoing; Sat, 24 Jun 1995 13:48:20 -0700
Received: from Root.COM (implode.Root.COM [198.145.90.1])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id NAA24129
          for <hackers@freebsd.org>; Sat, 24 Jun 1995 13:48:17 -0700
Received: from corbin.Root.COM (corbin [198.145.90.18]) by Root.COM (8.6.11/8.6.5) with ESMTP id NAA00805; Sat, 24 Jun 1995 13:48:08 -0700
Received: from localhost (localhost [127.0.0.1]) by corbin.Root.COM (8.6.11/8.6.5) with SMTP id NAA00597; Sat, 24 Jun 1995 13:48:30 -0700
Message-Id: <199506242048.NAA00597@corbin.Root.COM>
To: Network Coordinator <nc@ai.net>
cc: hackers@freebsd.org
Subject: Re: FreeBSD as a router 
In-reply-to: Your message of "Sat, 24 Jun 95 16:39:12 EDT."
             <Pine.BSF.3.91.950624162711.1447G-100000@aries.ai.net> 
From: David Greenman <davidg@Root.COM>
Reply-To: davidg@Root.COM
Date: Sat, 24 Jun 1995 13:48:25 -0700
Sender: hackers-owner@freebsd.org
Precedence: bulk

>>    On a fast Pentium, it is possible to route packets at a rate >70Mbits/sec
>> in FreeBSD-current. ...but this is talking raw data throughput. In terms of
>> packets/sec, we don't do so well...about 10000 packets/sec is about tops. This
>> is less than 1/10th the capability of 100BASE-TX.
>> 
>
>[I'm not questioning your results here, just curious.] How did you get 
>the estimate of performance on a pentium? I tried [just to see a ball 
>park figure] a tcpblast on 127.0.0.1 on a moderately loaded 486/66 and 
>got about 1.1 Megabytes/second or 9.1 Mbits/second. I seem to have some 
>foggy idea that the top limit of an ISA motherboard is about 10 
>megabits/second, but that sounds too much like the standard ether limit. 

   Um, we were talking about router performance...not the ability to send data
through a TCP socket to localhost. Very different things.

>On a pentium, we are under the assumption that the bus and processor 
>aren't the limiting factor, and just BSD is slowing things down. So what 
>is it?

   I think we should assume high performance hardware. The difference in cost
between a Pentium-90 w/PCI (bus mastering DMA) ethernet card and a 486/66
w/ISA ether is fairly small these days (unless of course you already have the
486/66...). The limitation is definately software at this point. That's why we
do well in bytes/sec, but poorly in packets/sec.

>high. On higher utilized networks, I can't imagine 10-12 ms latency on a 
>80 megabit stream of packets is a problem. 

   We're not talking anywhere near that much delay. ...More like 700-800us.
Again, the problem isn't latency or 'bandwidth'. The problem is packets/sec.

-DG