From owner-freebsd-current@FreeBSD.ORG Fri Feb 22 10:01:06 2008 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 0C6DD16A409 for ; Fri, 22 Feb 2008 10:01:06 +0000 (UTC) (envelope-from raul@pop.isdefe.es) Received: from mail1.isdefe.es (mail1.isdefe.es [194.15.213.239]) by mx1.freebsd.org (Postfix) with ESMTP id C451B13C474 for ; Fri, 22 Feb 2008 10:01:05 +0000 (UTC) (envelope-from raul@pop.isdefe.es) Received: from [10.100.147.125] (opera.isdefe.es [194.15.213.193]) by mail1.isdefe.es (Postfix) with ESMTP id 033835C36; Fri, 22 Feb 2008 10:42:41 +0100 (CET) Message-ID: <47BE9910.7030501@pop.isdefe.es> Date: Fri, 22 Feb 2008 10:42:40 +0100 From: Raul User-Agent: Thunderbird 2.0.0.9 (Windows/20071031) MIME-Version: 1.0 To: Christoph Schug References: <20080221035014.GB26427@cdnetworks.co.kr> <20080221050635.GC26427@cdnetworks.co.kr> <20080221143748.GE10726@lega.schug.net> In-Reply-To: <20080221143748.GE10726@lega.schug.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 8bit Cc: Pyun YongHyeon , FreeBSD Current , Robert Backhaus Subject: Re: Packet corruption in re0 (and em0 too) X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 22 Feb 2008 10:01:06 -0000 First of all, it's my first post here ... Thanks to everybody that made FreeBSD possible. Christoph Schug escribió: > I am having the very same problem on a rented Hetzner DS8000 root Sorry to say, I think that 'me too' My re0 comes with the motherboard, a Gigabyte GA-MA69G-S3H (AMD 690G chipset). I've tried yesterday with RELENG_7_0 (RC3) and RELENG_7, same behavior on both. I've returned to RELENG_7_0 and plug an em0 but, in my case, the same behavior happens. I left the box by night compiling CURRENT and this morning I've run my 'stress tests' (once again with re0) ... the box break to gdb as far I remember (too sleepy, sorry). Well, at least no garbage over the link BD. The fastest method I found to reproduce the problem is receive a compresed tar (with good compression ratio) over the network (using nc, 100 Mbps fdx), pipe through tar that decompress and write it on disk (a lot of MB/s and tps looking at 'systat -vm'). The source tar file is about 5Gb and link always fails before EOF :|. The em0 is brand new so no idea if it works right. It would be the first one that fail to me (great stuff intel ;) ... I'm pretty confident about the switch and allow setting flow control, duplex negotiation, dot1q and so on. I'll be glad to test whatever you suggest on that box. Regards, Raul