From owner-freebsd-questions@FreeBSD.ORG Tue Dec 28 23:48:57 2004 Return-Path: Delivered-To: freebsd-questions@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 0D2D816A4CE for ; Tue, 28 Dec 2004 23:48:57 +0000 (GMT) Received: from cicero2.cybercity.dk (cicero2.cybercity.dk [212.242.40.53]) by mx1.FreeBSD.org (Postfix) with ESMTP id 84B0A43D41 for ; Tue, 28 Dec 2004 23:48:56 +0000 (GMT) (envelope-from cr@it.dk) Received: from user1.cybercity.dk (user1.cybercity.dk [212.242.41.34]) by cicero2.cybercity.dk (Postfix) with ESMTP id 3BA781910C1 for ; Wed, 29 Dec 2004 00:48:55 +0100 (CET) Received: from localhost (port1922.ds1-vbr.adsl.cybercity.dk [212.242.174.229]) by user1.cybercity.dk (Postfix) with SMTP id 07AA774FBE5 for ; Wed, 29 Dec 2004 00:48:55 +0100 (CET) From: Christian R. To: freebsd-questions@freebsd.org Date: Wed, 29 Dec 2004 00:46:45 +0100 Message-ID: <13s3t01kdpd1gtik7rouq2gmpevkgr13h4@4ax.com> X-Mailer: Forte Agent 1.93/32.576 English (American) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable Subject: FreeBSD 5.3-STABLE crashes on Dell PowerEdge 2850 X-BeenThere: freebsd-questions@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: User questions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 28 Dec 2004 23:48:57 -0000 I have installed FreeBSD 5.3-STABLE i386 on a new Dell PowerEdge 2850, but it crashes under load. I can't figure why. Has anyone succeeded running FreeBSD 5.3 on this hardware? =46ollowing is the output from console made by two random crashes. Crash #1: =46atal trap 12: page fault while in kernel mode cpuid =3D 0; apic id =3D 00 fault virtual address =3D 0x24 fault code =3D supervisor read, page not present instruction pointer =3D 0x8:0xc039733e stack pointer =3D 0x10:0xee15dc44 frame pointer =3D 0x10:0xee15dc6c code segment =3D base 0x0, limit 0xfffff, type 0x1b =3D DPL 0, pres 1, def32 1, gran 1 processor eflags =3D resume, IOPL =3D 0 current process =3D 122 (pagedaemon) trap number =3D 12 panic: page fault cpuid =3D 0 boot() called on cpu#0 Uptime: 4m58s Cannot dump. No dump device definded. Automatic reboot in 15 seconds - press a key on the console to abort Rebooting... cpu_reset called on cpu#0 cpu_reset: Stopping other CPUs spin lock sched lock held by 0xc8b97190 for > 5 seconds Crash #2: fault virtual address =3D 0x24 fault code =3D supervisor read, page not present instruction pointer =3D 0x8:xc3555da stack pointer =3D 0x10:0xf08adaa4 frame pointer =3D 0x10:0xf08adacc code segment =3D base 0x0, limit 0xfffff, type 0x1b =3D DPL 0, pres 1, def32 1, gran 1 processor eflags =3D resume, IOPL =3D 0 current process =3D 610 (sshd) trap number =3D 12 panic: page fault cpuid =3D 1 =46atal double fault: eip =3D 0xc032674a esp =3D 0xec564ff8 ebp =3D 0xec565010 cpuid =3D 2; apic id =3D 06 =46atal double fault: eip =3D 0xc032674a esp =3D 0xee46eff4 ebp =3D 0xee46f00c cpuid =3D 3; apic id =3D 07 spin lock sched lock held by 0xc8ad97d0 for > 5 seconds Running for example "make buildworld" or rsync could make the server crash, but it doesn't seems to crash, when it runs the distributed.net client (100% CPU load), so I don't think it is a overheating problem. The server has following configuration: 2x Intel Xeon 3.4 GHz (800 MHz =46SB), 6x 1 GB DDR2 ECC RAM and Perc 4e/Di (LSI Logic/amr driver). I have compiled the kernel with SMP of course and PAE because of >4 GB memory. I have removed all the unnecessary devices. I have been running memtest (http://www.memtest.org/) without any errors. Would it maybe be better to run the AMD64 version of FreeBSD 5.3? I think the i386 version should be more stable?