From owner-freebsd-amd64@FreeBSD.ORG Sat Nov 13 06:18:44 2004 Return-Path: Delivered-To: freebsd-amd64@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 5878116A4CE; Sat, 13 Nov 2004 06:18:44 +0000 (GMT) Received: from rwcrmhc11.comcast.net (rwcrmhc11.comcast.net [204.127.198.35]) by mx1.FreeBSD.org (Postfix) with ESMTP id 077DB43D39; Sat, 13 Nov 2004 06:18:42 +0000 (GMT) (envelope-from clint@0lsen.net) Received: from 0lsen.net ([24.20.127.157]) by comcast.net (rwcrmhc11) with ESMTP id <200411130618260130064db9e>; Sat, 13 Nov 2004 06:18:36 +0000 Received: by 0lsen.net (Postfix, from userid 1001) id 8F2E7176F5; Fri, 12 Nov 2004 22:18:25 -0800 (PST) Date: Fri, 12 Nov 2004 22:18:25 -0800 From: Clint Olsen To: Peter Wemm Message-ID: <20041113061825.GS25188@0lsen.net> References: <200411131134.21189.doconnor@gsoft.com.au> <200411121739.40804.peter@wemm.org> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <200411121739.40804.peter@wemm.org> User-Agent: Mutt/1.4.2.1i Organization: NULlsen Network X-Disclaimer: Mutt Bites! cc: freebsd-current@freebsd.org cc: FreeBSD current mailing list cc: FreeBSD amd64 mailing list Subject: Re: [PATCH] if_sk(4) rx/tx "hangs" X-BeenThere: freebsd-amd64@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Porting FreeBSD to the AMD64 platform List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Nov 2004 06:18:44 -0000 On Nov 12, Peter Wemm wrote: > I think he was saying he created a 1GB file from the contents of > /dev/urandom and then timed the transfer of this over 100Mbit/sec link. > > Anyway, the point was that it worked! Could the problem with the K8V SE > really be as simple as we've been hardcoding 128K of ram for a device > that only has 64K? So, are you suggesting that it's worth testing this patch? I'm on 5.3-STABLE, and I got so pissed off last night with my sk0 interface that I brought the machine down and disabled the onboard network and installed a Linksys 100Mbit card. My board is the ASUS P4P800-SE, but I believe the interfaces are the same/similar. My favorite way to hang it was to use gtk-gnutella. Massive amounts of small-sized inbound traffic seemed to bring on the hang (the tell-tale 'watchdog timeout' kernel message). -Clint