From owner-freebsd-hackers Sun Feb 18 12:41:31 1996 Return-Path: owner-hackers Received: (from root@localhost) by freefall.freebsd.org (8.7.3/8.7.3) id MAA02693 for hackers-outgoing; Sun, 18 Feb 1996 12:41:31 -0800 (PST) Received: from hauki.clinet.fi (root@hauki.clinet.fi [194.100.0.1]) by freefall.freebsd.org (8.7.3/8.7.3) with ESMTP id MAA02687 for ; Sun, 18 Feb 1996 12:41:28 -0800 (PST) Received: from newzetor.clinet.fi (root@newzetor.clinet.fi [194.100.0.11]) by hauki.clinet.fi (8.7.3/8.6.4) with ESMTP id WAA27275; Sun, 18 Feb 1996 22:41:23 +0200 (EET) Received: (hsu@localhost) by newzetor.clinet.fi (8.7.3/8.6.4) id WAA01110; Sun, 18 Feb 1996 22:41:17 +0200 (EET) Date: Sun, 18 Feb 1996 22:41:17 +0200 (EET) Message-Id: <199602182041.WAA01110@newzetor.clinet.fi> From: Heikki Suonsivu To: joerg_wunsch@uriah.heep.sax.de (Joerg Wunsch) Cc: freebsd-hackers@freebsd.org In-reply-to: J Wunsch's message of 17 Feb 1996 10:26:45 +0200 Subject: Re: Web server locks up... but not quite. (?) Organization: Clinet Ltd, Espoo, Finland References: <199602170804.JAA08102@uriah.heep.sax.de> Sender: owner-hackers@freebsd.org Precedence: bulk In article <199602170804.JAA08102@uriah.heep.sax.de> J Wunsch writes: Hmm, we've also experienced these symptoms at sax.sax.de (small local non-commercial ISP), and i admit that i've basically been suspecting hardware in the first place. Your reports make me nervous however that it might be software. The system is plain 2.0.5R. If it were software, it would happen with specific set of hardware. We see it on all machines here. Brian, if you got physical access to the box, try placing a simple card into the PC that hooks ISA pins A1/B1 to a pushbutton. Pushing it will cause an NMI (``IO channel check condition''), hopefully leaving you a coredump. Anyone with a good source of ready-made cards? This might not help, we often find things being locked up when they try to write the coredump. Our machine is located in an mostly operator-less machine room at the University, i've already been playing with the idea to build a watchdog card that lowers the IOCHCK signal (and finally gives up 5 minutes later and issues a RESET). Someone proposed an interrupt-level software watchdog. I proposed a crash button on keyboard (almost always the keyboard driver is still there). -- Heikki Suonsivu, T{ysikuu 10 C 83/02210 Espoo/FINLAND, hsu@clinet.fi mobile +358-40-5519679 work +358-0-4375360 fax -4555276 home -8031121