From owner-freebsd-stable@FreeBSD.ORG Sat Mar 6 18:10:03 2004 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id D203D16A4CE for ; Sat, 6 Mar 2004 18:10:03 -0800 (PST) Received: from smtp3.sentex.ca (smtp3.sentex.ca [64.7.153.18]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7602D43D1F for ; Sat, 6 Mar 2004 18:10:03 -0800 (PST) (envelope-from mike@sentex.net) Received: from avscan1.sentex.ca (avscan1.sentex.ca [199.212.134.11]) by smtp3.sentex.ca (8.12.10/8.12.10) with ESMTP id i2729vOp010982; Sat, 6 Mar 2004 21:09:57 -0500 (EST) (envelope-from mike@sentex.net) Received: from lava.sentex.ca (pyroxene.sentex.ca [199.212.134.18]) by avscan1.sentex.ca (8.12.10/8.12.10) with ESMTP id i272A25g026746; Sat, 6 Mar 2004 21:10:02 -0500 (EST) (envelope-from mike@sentex.net) Received: from simian.sentex.net ([192.168.43.27]) by lava.sentex.ca (8.12.9p2/8.12.9) with ESMTP id i272A0Za072060; Sat, 6 Mar 2004 21:10:01 -0500 (EST) (envelope-from mike@sentex.net) Message-Id: <6.0.3.0.0.20040306210359.08fc35a8@209.112.4.2> X-Sender: mdtpop@209.112.4.2 (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 6.0.3.0 Date: Sat, 06 Mar 2004 21:11:09 -0500 To: "Marc G. Fournier" From: Mike Tancsa In-Reply-To: <20040306211328.H13247@ganymede.hub.org> References: <20040306130937.N71806@ganymede.hub.org> <6.0.3.0.0.20040306180314.08adede0@209.112.4.2> <20040306210515.M13247@ganymede.hub.org> <20040306211328.H13247@ganymede.hub.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed X-Virus-Scanned: by amavisd-new cc: freebsd-stable@freebsd.org Subject: Re: Odd network issue ... *very* slow scp between two servers X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sun, 07 Mar 2004 02:10:03 -0000 At 08:20 PM 06/03/2004, Marc G. Fournier wrote: >'k, I'm blind to start with ... I take it that this is the significant >part of the output: > >Name Mtu Network Address Ipkts Ierrs Opkts >Oerrs Coll >em0 1500 00:07:e9:05:1b:2e 760865424 58003349 >775965555 0 0 Yes, extremely significant. >where the fxp devices don't show any Ierrs? That works out to be ~7% ... It has nothing to do with the fxp on the other machine. Its input errors divided by total packets coming in # bc bc 1.06 Copyright 1991-1994, 1997, 1998, 2000 Free Software Foundation, Inc. This is free software with ABSOLUTELY NO WARRANTY. For details type `warranty'. scale=3 58003349/760865424 .076 >Dropping it to 10baseT/UTP appears to improve things by 10x: > >1038785 bytes received in 6.86 seconds (147.89 KB/s) > >And drop'ng it to 100baseTX, half-duplex makes an even larger difference: > >1038785 bytes received in 0.49 seconds (2.01 MB/s) >1038785 bytes received in 0.14 seconds (6.89 MB/s) > >The fxp devices are all running 100baseTX, full-duplex, and doing 10MB/s >between each other ... I would in the following order a) check the settings on the switch. AutoNeg *only* works when both sides are set to auto-neg. If both sides are not auto, make sure both sides are the same for speed and duplex settings. b) try changing the cable. Go with cat6 for the em even if you use 100baseTX. Dont use anything shorter than 3f/1m c) try the card in a different slot on your MB. We have found a few boards where the em is picky about what slot its in and what it potentially shares as an interrupt. d) try a different card ---Mike