From owner-freebsd-ipfw@FreeBSD.ORG Mon Jul 27 13:20:22 2009 Return-Path: Delivered-To: freebsd-ipfw@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 942C5106566C for ; Mon, 27 Jul 2009 13:20:22 +0000 (UTC) (envelope-from j.m.sandford@hotmail.co.uk) Received: from col0-omc1-s9.col0.hotmail.com (col0-omc1-s9.col0.hotmail.com [65.55.34.19]) by mx1.freebsd.org (Postfix) with ESMTP id 7367C8FC1C for ; Mon, 27 Jul 2009 13:20:22 +0000 (UTC) (envelope-from j.m.sandford@hotmail.co.uk) Received: from COL110-W10 ([65.55.34.8]) by col0-omc1-s9.col0.hotmail.com with Microsoft SMTPSVC(6.0.3790.3959); Mon, 27 Jul 2009 06:08:22 -0700 Message-ID: X-Originating-IP: [192.165.213.18] From: Mark Sandford To: Date: Mon, 27 Jul 2009 14:08:22 +0100 Importance: Normal MIME-Version: 1.0 X-OriginalArrivalTime: 27 Jul 2009 13:08:22.0390 (UTC) FILETIME=[51956960:01CA0EBB] Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.5 Subject: Using dummynet to restrict bandwidth with more than 2 active pipes / queues X-BeenThere: freebsd-ipfw@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: IPFW Technical Discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 27 Jul 2009 13:20:22 -0000 Hi all=2C =20 I've been using dummynet for a while to perform degraded network testing wh= ich has been really useful. =20 Recently=2C we wanted to measure the performance limits of it on our hardware. To do this we setup a machine with 8 interfaces paired into 4 ethernet bridges. =20 We are having throughput issues when more than 2 pipes are being used simultaneously. These issues appear to be independent of the bandwidths specified. For example: We set two traffic generators transmitting at 30Mbps across two of the brid= ges (pipes)=2C sending 1000 byte UDP packets (1042 bytes on the wire) for a= 20 second period. These are passed through dummynet pipes set up to restrict the bandwidth to= 20Mbps at the bridge and we can see from the ipfw counters that all the pa= ckets hit the right rules and only the right rules. We the capture on the far end and can see that bandwidth has been restricte= d to 20Mbps as specified. All good! :o) The problem comes when we add any extra flows. The above example is repeated but with two extra traffic generators transmi= tting at just one packet per second each across a further two pipes. Again we can see from the counters that the packets all arrive at ipfw=2C h= owever we only get 10Mbps at the receiving end (and we get a number of pack= et_drops logged at dummynet). We feel we must have missed something obvious but after over a week of read= ing / testing we're running out of ideas. Is anyone able / willing to help? ~~~~~~~~~~~~~~~~~~~~~~~~ Mark Sandford email: j.m.sandford@hotmail.co.uk mob: 07990 565976 ~~~~~~~~~~~~~~~~~~~~~~~~ _________________________________________________________________ Celebrate a decade of Messenger with free winks=2C emoticons=2C display pic= s=2C and more. http://clk.atdmt.com/UKM/go/157562755/direct/01/=