From owner-freebsd-current@FreeBSD.ORG Mon Jan 19 04:18:32 2004 Return-Path: Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 1655316A4CE for ; Mon, 19 Jan 2004 04:18:32 -0800 (PST) Received: from mail.gmx.net (pop.gmx.de [213.165.64.20]) by mx1.FreeBSD.org (Postfix) with SMTP id 30B4143D1F for ; Mon, 19 Jan 2004 04:18:30 -0800 (PST) (envelope-from andreas-moeller@gmx.net) Received: (qmail 19006 invoked by uid 65534); 19 Jan 2004 12:18:28 -0000 Received: from p5084B91C.dip.t-dialin.net (EHLO gmx.net) (80.132.185.28) by mail.gmx.net (mp012) with SMTP; 19 Jan 2004 13:18:28 +0100 X-Authenticated: #1940550 Message-ID: <400BCB12.5060705@gmx.net> Date: Mon, 19 Jan 2004 13:18:26 +0100 From: Andreas Moeller User-Agent: Mozilla/5.0 (X11; U; FreeBSD i386; en-US; rv:1.6) Gecko/20040117 X-Accept-Language: de-de, de, en-us, en MIME-Version: 1.0 To: hscholz@raisdorf.net References: <4009ADE7.2060101@gmx.net> <20040119122417.69b2fa94@goanna.raisdorf.net> In-Reply-To: <20040119122417.69b2fa94@goanna.raisdorf.net> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit X-Mailman-Approved-At: Mon, 19 Jan 2004 06:28:30 -0800 cc: current@FreeBSD.org Subject: Re: fxp(4) TCP checksum offloading X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.1 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: Mon, 19 Jan 2004 12:18:32 -0000 >>I got an Intel PRO/100 S NIC (Intel 82550 chip) which supports TCP >>checksum offloading. I am also able to load the microcode necessary in >> >>order to activate that feature: >> >>fxp0: Microcode loaded, int_delay: 1000 usec bundle_max: 6 > > > That ain't TCP checksum offloading, that is IRQ mitigation. > When using IRQ mitigation the FIFO buffer in the network card is used to > 'delay' interrupts. Up to 6 packets will be buffered for up to 1000usec > before raising an interrupt. In case more than one packet arrives during > the 1000usec period only one interrupt is triggered instead of multiple > thus reducing the time spend for context switching and handling the > interrupts. I understand. Thank you for explaining this to me. After further reading of the ifconfig(8) manual I assume that the fxp(4) driver doesn't support user-configuration of checksum offloading but enables this feature if it recognizes hardware capable of it. Is this correct? My ifconfig(8) output looks as follows: fxp0: flags=8843 mtu 1500 options=3 inet 192.168.0.2 netmask 0xffffff00 broadcast 192.168.0.255 inet6 fe80::202:b3ff:fe4c:9c32%fxp0 prefixlen 64 scopeid 0x1 ether 00:02:b3:4c:9c:32 media: Ethernet autoselect (100baseTX ) status: active >>Unfortunately, when enabled, network connections (at least those based >> >>on TCP) start timing out while ping remains working flawlessly. The >>system in question is running latest -CURRENT source as of today. > > > I cannot reproduce this problem since my box is running 1000baseSX. > > As of 5.2-REL you have to enable the sshd and in case security is set to > 'extreme' sshd won't be fired up. Do you have sshd_enable="YES" in > /etc/rc.conf? Yes I do, but I do not set any securelevel. When booting with IRQ mitigation enabled I have to hit ^C and abort the start of the ssh daemon because otherwise the boot process won't proceed. >>Any ideas? (Is there a way to unload the microcode again besides >>rebooting the system?) > > > $ ifconfig fxp0 -link0 Thanks!