From owner-freebsd-stable@FreeBSD.ORG Tue Jul 26 17:03:14 2005 Return-Path: X-Original-To: freebsd-stable@freebsd.org 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 2650316A41F for ; Tue, 26 Jul 2005 17:03:14 +0000 (GMT) (envelope-from m@obmail.net) Received: from stewie.obfuscated.net (stewie.obfuscated.net [66.118.188.125]) by mx1.FreeBSD.org (Postfix) with ESMTP id 9013E43D45 for ; Tue, 26 Jul 2005 17:03:13 +0000 (GMT) (envelope-from m@obmail.net) Received: from [192.168.1.101] (unknown [66.118.170.134]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (No client certificate requested) by stewie.obfuscated.net (Postfix) with ESMTP id BDA076104; Tue, 26 Jul 2005 13:03:12 -0400 (EDT) In-Reply-To: <3146.192.168.1.190.1122393780.squirrel@webmail.devrandom.org.uk> References: <4309.192.168.1.190.1122341800.squirrel@webmail.devrandom.org.uk> <20050726021340.5410A2073@towerrecords.minidns.net> <1904.192.168.1.190.1122383968.squirrel@webmail.devrandom.org.uk> <6.2.1.2.0.20050726092241.055c2620@64.7.153.2> <2294.192.168.1.190.1122385648.squirrel@webmail.devrandom.org.uk> <3146.192.168.1.190.1122393780.squirrel@webmail.devrandom.org.uk> Mime-Version: 1.0 (Apple Message framework v730) X-Priority: 3 (Normal) Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed Message-Id: <9B5AF38C-0525-44B0-80FD-1EBAB4B31CF4@obmail.net> Content-Transfer-Encoding: 7bit From: Michael Conlen Date: Tue, 26 Jul 2005 13:03:10 -0400 To: Chris Howells X-Mailer: Apple Mail (2.730) Cc: freebsd-stable@freebsd.org, Claus Guttesen Subject: Re: em(4) stops passing data X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 26 Jul 2005 17:03:14 -0000 On Jul 26, 2005, at 12:03 PM, Chris Howells wrote: > > On Tue, July 26, 2005 3:39 pm, Claus Guttesen said: > > >> I applied the em-patch that was announced a few days ago to two >> servers with an Intel em-gbit-nic resetting during load. It's only >> been running for one day so I don't know whether my problem is gone. >> But so far I haven't seen any regression. The servers are >> connected to >> a Dell-switch. >> > > Doesn't fix the problem for me regrettably :( I can reproduce the > problem > within seconds of starting a large file transfers. I got the > ethernet card > from eBay but I've ordered a brand new one to try -- I wonder if > there's > any chance it could be faulty. I often find that if I have a cable that is less than perfect the card will seem to work but with some heavy load the switch takes the port down and it stays down until I ifconfig down & up the interface. In every instance replacing the cable takes care of the problem. -- Michael Conlen