From owner-freebsd-current@FreeBSD.ORG Thu Oct 14 17:28:16 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 C13FD16A4CE for ; Thu, 14 Oct 2004 17:28:16 +0000 (GMT) Received: from corbulon.video-collage.com (aldan.algebra.com [216.254.65.224]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5162C43D1F for ; Thu, 14 Oct 2004 17:28:16 +0000 (GMT) (envelope-from mi+mx@aldan.algebra.com) Received: from 250-217.customer.cloud9.net (195-11.customer.cloud9.net [168.100.195.11])i9EHSEt2004094 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Thu, 14 Oct 2004 13:28:15 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) Received: from localhost (mteterin@localhost [127.0.0.1]) i9EHS2eH078554 for ; Thu, 14 Oct 2004 13:28:03 -0400 (EDT) (envelope-from mi+mx@aldan.algebra.com) From: Mikhail Teterin Organization: Virtual Estates, Inc. To: freebsd-current@FreeBSD.org Date: Thu, 14 Oct 2004 13:28:01 -0400 User-Agent: KMail/1.7 MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Content-Disposition: inline Message-Id: <200410141328.02027@misha-mx.virtual-estates.net> X-Virus-Scanned: clamd / ClamAV version devel-20040615, clamav-milter version 0.73a on corbulon.video-collage.com X-Virus-Status: Clean X-Scanned-By: MIMEDefang 2.43 X-Mailman-Approved-At: Fri, 15 Oct 2004 12:06:38 +0000 Subject: panic du jour: vnode_pager_getpages: unexpected missing page 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: Thu, 14 Oct 2004 17:28:16 -0000 I'm debugging a program making heavy us of mmap(). Contrary to what man-page says, I expected it to be possible to mmap() regions larger than 2Gb on amd64, and mmap() did, indeed succeeded for a 3.7Gb file. However some time into running the program exited on signal 6 (ABRT). A minute or so after that the whole system panic-ed: vnode_pager_getpages: unexpected missing page: first addr: -1, foff 0x080006000, vnp_size 0x0b5d20000 The machine runs yesterday's -current, has a single Opteron CPU and 2Gb of RAM. There was very little IO at the time of death (according to the frozen `systat 1 -vm'). 1) Am I wrong, and mmap-ing more than 2Gb is not supposed to work even on a 64-bit system? 2) How can I help in eliminating this panic? 3) Should I go back to the latest 5.3-beta, or is the -current kernel not dramatically more unstable? Thanks, -mi