From owner-freebsd-stable@FreeBSD.ORG Thu Mar 3 21:43:31 2005 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 A935316A4CF for ; Thu, 3 Mar 2005 21:43:31 +0000 (GMT) Received: from oz.twisted.net (oz.twisted.net [69.211.34.241]) by mx1.FreeBSD.org (Postfix) with ESMTP id A2A2043D2D for ; Thu, 3 Mar 2005 21:43:29 +0000 (GMT) (envelope-from troy@twisted.net) Received: from localhost (localhost [127.0.0.1]) by oz.twisted.net (Postfix) with ESMTP id 05177599C63 for ; Thu, 3 Mar 2005 15:43:30 -0600 (CST) Received: from oz.twisted.net ([127.0.0.1]) by localhost (oz.twisted.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 11292-08 for ; Thu, 3 Mar 2005 15:43:29 -0600 (CST) Received: from localhost.localdomain (think.twisted.net [172.16.0.15]) by oz.twisted.net (Postfix) with ESMTP id 8CC2C599BB1 for ; Thu, 3 Mar 2005 15:43:29 -0600 (CST) From: Troy To: freebsd-stable@freebsd.org Content-Type: text/plain Date: Thu, 03 Mar 2005 15:43:27 -0600 Message-Id: <1109886207.1233.22.camel@think.twisted.net> Mime-Version: 1.0 X-Mailer: Evolution 2.0.4 FreeBSD GNOME Team Port Content-Transfer-Encoding: 7bit X-Virus-Scanned: by amavisd-new at twisted.net Subject: RELENG_5 dc0 and dc1 watchdog timeouts - IRQ issues? X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list Reply-To: troy@twisted.net List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 03 Mar 2005 21:43:31 -0000 I recently upgraded this machine from 4.x to 5.x and am seeing a lot of watchdog timeouts. I've been trying to track down how to stop the constant watchdog timeouts that I'm experiencing and figured to post to the list. The box is running IPFW and has two NICs. Originally I was using a separate physical Nic (xl0) and after seeing the watchdog timeouts, I switched to a different card. I am now using 2 ports on a quad card and barely pushing traffic through it. Every time I experience a watchdog timeout, packets stall creating chaos for performance. I noticed that it's output errors as opposed to drops. I found a post where someone was talking about problems with getting IRQ resources. From the bootup messages below you can see that I'm seeing errors and again tried to follow other threads where people had the same problems but never got a decent answer. I'm not sure what I can do to fix these problems, but clearly the performance is horrible. Any thoughts? -Troy from /var/log/messages ============================= Mar 3 15:15:55 kernel: dc0: watchdog timeout Mar 3 15:16:11 kernel: dc0: watchdog timeout Mar 3 15:13:49 kernel: dc1: watchdog timeout Bootup messages =============== adv1: Invalid baseport of 0x0 specified. Nearest valid baseport is 0x100 failing probe adv1: Invalid baseport of 0x40 specified. Nearest valid baseport is 0x100 failing probe adv1: Invalid baseport of 0x70 specified. Nearest valid baseport is 0x100 failing probe adv1: Invalid baseport of 0xf0 specified. Nearest valid baseport is 0x100 failing probe adv1: Invalid baseport of 0x4d0 specified. Nearest valid baseport is 0x330 failing probe unknown: can't assign resources (port) unknown: at port 0x60 on isa0 adv1: Invalid baseport of 0x61 specified. Nearest valid baseport is 0x100 failing probe unknown: can't assign resources (memory) unknown: can't assign resources (irq) unknown: at irq 12 on isa0 unknown: can't assign resources (port) unknown: at port 0x3f8-0x3ff on isa0 unknown: can't assign resources (port) unknown: can't assign resources (port) unknown: can't assign resources (port) DC0 Interface ============= netstat -Idc0 -d Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll Drop dc0 1500 00:80:c8:b9:99:b1 472393 0 451110 82 0 0 DC1 Interface ============= netstat -Idc1 -d Name Mtu Network Address Ipkts Ierrs Opkts Oerrs Coll Drop dc1 1500 00:80:c8:b9:99:b2 474155 0 459074 92 0 0