From owner-freebsd-current@FreeBSD.ORG Sat Oct 6 02:09:46 2007 Return-Path: Delivered-To: freebsd-current@FreeBSD.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 6351A16A41A; Sat, 6 Oct 2007 02:09:46 +0000 (UTC) (envelope-from des@des.no) Received: from tim.des.no (tim.des.no [194.63.250.121]) by mx1.freebsd.org (Postfix) with ESMTP id 23DCA13C481; Sat, 6 Oct 2007 02:09:46 +0000 (UTC) (envelope-from des@des.no) Received: from tim.des.no (localhost [127.0.0.1]) by spam.des.no (Postfix) with ESMTP id C467220BC; Sat, 6 Oct 2007 04:09:36 +0200 (CEST) X-Spam-Tests: AWL X-Spam-Learn: disabled X-Spam-Score: -0.0/3.0 X-Spam-Checker-Version: SpamAssassin 3.2.3 (2007-08-08) on tim.des.no Received: from ds4.des.no (des.no [80.203.243.180]) by smtp.des.no (Postfix) with ESMTP id 3AFCC20BB; Sat, 6 Oct 2007 04:09:36 +0200 (CEST) Received: by ds4.des.no (Postfix, from userid 1001) id E8F8B84486; Sat, 6 Oct 2007 04:09:35 +0200 (CEST) From: =?utf-8?Q?Dag-Erling_Sm=C3=B8rgrav?= To: Pawel Jakub Dawidek References: <20071005000046.GC92272@garage.freebsd.pl> Date: Sat, 06 Oct 2007 04:09:35 +0200 In-Reply-To: <20071005000046.GC92272@garage.freebsd.pl> (Pawel Jakub Dawidek's message of "Fri\, 5 Oct 2007 02\:00\:46 +0200") Message-ID: <86r6k9ouxs.fsf@ds4.des.no> User-Agent: Gnus/5.110006 (No Gnus v0.6) Emacs/22.1 (berkeley-unix) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: freebsd-fs@FreeBSD.org, freebsd-current@FreeBSD.org Subject: Re: ZFS kmem_map too small. 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: Sat, 06 Oct 2007 02:09:46 -0000 Pawel Jakub Dawidek writes: > We'are about to branch RELENG_7 and I'd like to start discussion with > folks that experience 'kmem_map too small' panic with the latest HEAD. I've been getting it recently (twice in the last ten days). Intel E6600 with 4 GB RAM running an amd64 kernel from September 25. After the first panic, I increased kmem_size_max to 2G so that I now have: des@ds4 ~% sysctl -h vm | grep kmem vm.kmem_size_scale: 3 vm.kmem_size_max: 2,147,483,648 vm.kmem_size_min: 0 vm.kmem_size: 1,381,412,864 After the second panic, I set kmem_size_max to 4G and kmem_size to 2G in loader.conf, but I haven't rebooted yet. No backtraces because the watchdog kicked in and rebooted the machine. I now have tace_on_panic=3D1 and debugger_on_panic=3D0, so next time I should get at least a backtrace, and a dump if I'm lucky. Both panics occurred during the nightly rsync of my imap spool from my mail server to my file server, where it is kept in a compressed dataset which I snapshot every day. The spool currently contains about 1.5 M files with an average size of slightly less than 8 kB. DES --=20 Dag-Erling Sm=C3=B8rgrav - des@des.no