From owner-freebsd-current@FreeBSD.ORG Wed Oct 12 23:48:18 2005 Return-Path: X-Original-To: freebsd-current@freebsd.org 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 2028C16A41F for ; Wed, 12 Oct 2005 23:48:18 +0000 (GMT) (envelope-from Emanuel.strobl@gmx.net) Received: from mail.gmx.net (mail.gmx.net [213.165.64.21]) by mx1.FreeBSD.org (Postfix) with SMTP id 1E67243D48 for ; Wed, 12 Oct 2005 23:48:16 +0000 (GMT) (envelope-from Emanuel.strobl@gmx.net) Received: (qmail invoked by alias); 12 Oct 2005 23:48:15 -0000 Received: from flb.schmalzbauer.de (EHLO cale.flintsbach.schmalzbauer.de) [62.245.232.135] by mail.gmx.net (mp007) with SMTP; 13 Oct 2005 01:48:15 +0200 X-Authenticated: #301138 From: Emanuel Strobl To: freebsd-current@freebsd.org Date: Thu, 13 Oct 2005 01:48:09 +0200 User-Agent: KMail/1.8.1 References: <200510121250.20515@harrymail> <20051012153407.W48006@fledge.watson.org> In-Reply-To: <20051012153407.W48006@fledge.watson.org> X-Birthday: Oct. 6th 1972 X-CelPhone: +49 (0) 173 9967781 X-Tel: +49 (0) 89 18947781 X-Country: Germany X-Address: Munich, 80686 X-OS: FreeBSD MIME-Version: 1.0 Content-Disposition: inline Message-Id: <200510130148.14383@harrymail> Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 Cc: Robert Watson Subject: Re: Ugly BETA5 crashes, VM fault (with trace) X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 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: Wed, 12 Oct 2005 23:48:18 -0000 Am Mittwoch, 12. Oktober 2005 16:34 CEST schrieb Robert Watson: > On Wed, 12 Oct 2005, Emanuel Strobl wrote: > > my desktop box crashed for severla weeks every few days and since > > beta5 was withoug kdb I had to rebuild a debugging kernel to get this > > recorded (no dump was written, so nothing in /var/crash) Like > > mentioned, I see the crash every view days, I think when having > > simultaniously NFS and local disk load. Please tell me if I can > > provide more info! > > I take it you have zero-copy sockets enabled? Do the panics happen if > you don't have it enabled? Yes, you are right, I have zero-copy sockets enabled (I don't have decent HW so I tried to gain as much as possible options I don't really understand... :() I'll rebuild a debug kernel without zero_copy_sockets and see if it happens again, but as I wrote the crash happens only every few days, possibly not within the next whole week... But I'll remove it and keep you informed... Thanks, -Harry > > Robert N M Watson > > > -Harry > > > > Fatal trap 12: page fault while in kernel mode > > fault virtual address = 0x5a > > fault code = supervisor read, page not present > > instruction pointer = 0x20:0xc06ec5a9 > > stack pointer = 0x28:0xdad2c99c > > frame pointer = 0x28:0xdad2ca88 > > code segment = base 0x0, limit 0xfffff, type 0x1b > > = DPL 0, pres 1, def32 1, gran 1 > > processor eflags = interrupt enabled, resume, IOPL = 0 > > current process = 741 (kdeinit) > > [thread pid 741 tid 100102 ] > > Stopped at vm_fault+0x239: cmpw $0,0x5a(%eax) > > db> trace > > Tracing pid 741 tid 100102 td 0xc2470a80 > > vm_fault(c1443000,c144f000,2,0,c2470a80) at vm_fault+0x239 > > trap_pfault(dad2cb14,0,c144fff4,dad2cae8,c144fff4) at > > trap_pfault+0x156 trap(c0790008,28,c0850028,dad2ccb4,2000) at > > trap+0x38e > > calltrap() at calltrap+0x5 > > --- trap 0xc, eip = 0xc06fd0ce, esp = 0xdad2cb54, ebp = 0xdad2cb68 --- > > vm_page_cowsetup(c144ffb8,0,c079615b,82,dad2cbf4) at > > vm_page_cowsetup+0x2e socow_setup(c1ef2300,dad2ccb4,2,2c4,1) at > > socow_setup+0x98 > > sosend(c29f4858,0,dad2ccb4,0,0) at sosend+0x56b > > soo_write(c284d090,dad2ccb4,c26f5980,0,c2470a80) at soo_write+0x87 > > dofilewrite(c2470a80,f,c284d090,dad2ccb4,ffffffff) at dofilewrite+0x85 > > kern_writev(c2470a80,f,dad2ccb4,8100ff4,de10) at kern_writev+0x65 > > write(c2470a80,dad2cd04,c,422,3) at write+0x4f > > syscall(805003b,3b,bfbf003b,805c000,f) at syscall+0x2c0 > > Xint0x80_syscall() at Xint0x80_syscall+0x1f > > --- syscall (4, FreeBSD ELF32, write), eip = 0x293791ab, esp = > > 0xbfbfe15c, ebp = > > 0xbfbfe178 --- > > db> >