From mboxrd@z Thu Jan  1 00:00:00 1970
From: Ben Greear <greearb@candelatech.com>
Subject: Re: [Bonding-devel] Re: [RFC][bonding] Improve VLAN support on top
 of bonding
Date: Tue, 15 Jul 2003 11:13:58 -0700
Sender: netdev-bounce@oss.sgi.com
Message-ID: <3F144466.8010003@candelatech.com>
References: <Pine.LNX.4.44.0307151054350.5112-100000@sasami.anime.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii; format=flowed
Content-Transfer-Encoding: 7bit
Cc: Shmulik Hen <shmulik.hen@intel.com>,
   bond-devel <bonding-devel@lists.sourceforge.net>,
   linux-net <linux-net@vger.kernel.org>, linux-netdev <netdev@oss.sgi.com>,
   "David S. Miller" <davem@redhat.com>, Jeff Garzik <jgarzik@pobox.com>,
   Jay Vosburgh <fubar@us.ibm.com>, Amir Noam <amir.noam@intel.com>,
   Noam Marom <noam.marom@intel.com>,
   Tsippy Mendelson <tsippy.mendelson@intel.com>
Return-path: <netdev-bounce@oss.sgi.com>
To: Dan Hollis <goemon@anime.net>
In-Reply-To: <Pine.LNX.4.44.0307151054350.5112-100000@sasami.anime.net>
Errors-to: netdev-bounce@oss.sgi.com
List-Id: netdev.vger.kernel.org

Dan Hollis wrote:
> On Tue, 15 Jul 2003, Ben Greear wrote:
> 
>>I'd consider ignoring the HW accel unless you can prove it actually helps
>>performance to a noticeable degree.  I have never seen results of any benchmarking
>>related to this...
> 
> 
> For gigabit ethernet, it makes a *H*U*G*E* difference.

I'm curious to see numbers.  The VLAN shim is only inserting
a small shim header, at at most shifting the first part of the packet
when sent a pre-built packet.

Maybe the hw-accel turns on tcp checksumming or something too??

> 
> -Dan


-- 
Ben Greear <greearb@candelatech.com>       <Ben_Greear AT excite.com>
President of Candela Technologies Inc      http://www.candelatech.com
ScryMUD:  http://scry.wanfear.com     http://scry.wanfear.com/~greear