From mboxrd@z Thu Jan 1 00:00:00 1970 From: Lennert Buytenhek Subject: Re: [E1000-devel] Transmission limit Date: Fri, 3 Dec 2004 00:25:31 +0100 Message-ID: <20041202232531.GA30948@xi.wantstofly.org> References: <1101499285.1079.45.camel@jzny.localdomain> <16811.8052.678955.795327@robur.slu.se> <1101821501.1043.43.camel@jzny.localdomain> <20041130134600.GA31515@xi.wantstofly.org> <1101824754.1044.126.camel@jzny.localdomain> <20041201001107.GE4203@xi.wantstofly.org> <1101863399.4663.54.camel@sfeldma-mobl.dsl-verizon.net> <16813.58484.343629.570703@robur.slu.se> <1101919791.5198.15.camel@localhost.localdomain> <16815.23964.93437.411404@robur.slu.se> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: sfeldma@pobox.com, jamal , P@draigBrady.com, mellia@prezzemolo.polito.it, e1000-devel@lists.sourceforge.net, Jorge Manuel Finochietto , Giulio Galante , netdev@oss.sgi.com Return-path: To: Robert Olsson Content-Disposition: inline In-Reply-To: <16815.23964.93437.411404@robur.slu.se> Sender: netdev-bounce@oss.sgi.com Errors-to: netdev-bounce@oss.sgi.com List-Id: netdev.vger.kernel.org On Thu, Dec 02, 2004 at 07:23:24PM +0100, Robert Olsson wrote: > Below is little patch to clean skb at xmit. It's old jungle trick Jamal > and I used w. tulip. Note we can now even decrease the size of TX ring. > > It can increase TX performance from 800 kpps to > 1125128pps 576Mb/sec (576065536bps) errors: 0 > 1124946pps 575Mb/sec (575972352bps) errors: 0 > > But suffers from scheduling problems as the previous patch. Often we just get > 582108pps 298Mb/sec (298039296bps) errors: 0 Robert, there is something weird with your setup with packets sizes under 160 bytes. Can you check if you also get wildly variable numbers on a baseline kernel perhaps? The numbers you sent me of packet size vs. pps were very jumpy as well, even at 10M pkts per run. --L