From owner-freebsd-fs@FreeBSD.ORG Sat Jan 23 14:35:02 2010 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:4f8:fff6::34]) by hub.freebsd.org (Postfix) with ESMTP id 5256C106566B for ; Sat, 23 Jan 2010 14:35:02 +0000 (UTC) (envelope-from doug@polands.org) Received: from hrndva-omtalb.mail.rr.com (hrndva-omtalb.mail.rr.com [71.74.56.125]) by mx1.freebsd.org (Postfix) with ESMTP id 084338FC12 for ; Sat, 23 Jan 2010 14:35:01 +0000 (UTC) X-Authority-Analysis: v=1.0 c=1 a=GSN_Y9T6cv4A:10 a=QNyOmuW7hx_2i3oR08AA:9 a=gD7rSQgncZlKzIFUK0rFvdNyP0IA:4 X-Cloudmark-Score: 0 X-Originating-IP: 75.87.219.217 Received: from [75.87.219.217] ([75.87.219.217:55929] helo=haran.polands.org) by hrndva-oedge03.mail.rr.com (envelope-from ) (ecelerity 2.2.2.39 r()) with ESMTP id 7B/FB-19161-4190B5B4; Sat, 23 Jan 2010 14:35:01 +0000 Received: from [172.16.1.37] (sichem-wifi.polands.org [172.16.1.37]) by haran.polands.org (8.14.3/8.14.3) with ESMTP id o0NEYxkO034898; Sat, 23 Jan 2010 08:35:00 -0600 (CST) (envelope-from doug@polands.org) Message-ID: <4B5B0913.3050107@polands.org> Date: Sat, 23 Jan 2010 08:34:59 -0600 From: Doug Poland User-Agent: Mozilla/5.0 (X11; U; Linux i686 (x86_64); en-US; rv:1.9.1.7) Gecko/20100111 Thunderbird/3.0.1 MIME-Version: 1.0 To: Artem Belevich References: <4B58976E.1020402@polands.org> <4B58D4D3.80009@egr.msu.edu> <20100122042843.GA8858@polands.org> <1308c71eec426200d4c34b926bba8806.squirrel@email.polands.org> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: Repeatable ZFS "kmem map too small" panic on 8.0-STABLE X-BeenThere: freebsd-fs@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Filesystems List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 23 Jan 2010 14:35:02 -0000 On 2010-01-22 20:33, Artem Belevich wrote: > > > Ignore my previous email. Something else is probably at play here. If > I were right, then you should have ended up with vm.kmem_size=8G. > However, in your case it's 2G. Beats me why. > I apologize, when I captured the sysctls, I was running with different values in /boot/loader.conf than what we were discussing. While I was waiting for a response, I was experimenting with a recommendation to run kmem_size = 1/2 phy RAM and arc_max 1/2 of kmem_size. This is what I have now: # cat /boot/loader.conf vfs.root.mountfrom="zfs:bethesda" vfs.zfs.arc_max="1G" vm.kmem_size="20G" zfs_load="YES" # sysctl hw.physmem vm.kmem_size vm.kmem_size_max vfs.zfs.arc_max hw.physmem: 4102688768 vm.kmem_size: 3668041728 vm.kmem_size_max: 329853485875 vfs.zfs.arc_max: 1073741824 # unixbench fstime fsbuffer fsdisk panic: kmem_malloc(131072): kmem_map too small: 3593236480 total allocated -- Regards, Doug