From owner-freebsd-stable Sun Feb 3 18: 7:42 2002 Delivered-To: freebsd-stable@freebsd.org Received: from netau1.alcanet.com.au (ntp.alcanet.com.au [203.62.196.27]) by hub.freebsd.org (Postfix) with ESMTP id D4EC337B428 for ; Sun, 3 Feb 2002 18:07:37 -0800 (PST) Received: from mfg1.cim.alcatel.com.au (mfg1.cim.alcatel.com.au [139.188.23.1]) by netau1.alcanet.com.au (8.9.3 (PHNE_22672)/8.9.3) with ESMTP id NAA15323; Mon, 4 Feb 2002 13:07:34 +1100 (EDT) Received: from gsmx07.alcatel.com.au by cim.alcatel.com.au (PMDF V5.2-32 #37645) with ESMTP id <01KDVLBU6L7K5IK6P5@cim.alcatel.com.au>; Mon, 4 Feb 2002 13:07:41 +1100 Received: (from jeremyp@localhost) by gsmx07.alcatel.com.au (8.11.6/8.11.6) id g1427VY80730; Mon, 04 Feb 2002 13:07:31 +1100 Content-return: prohibited Date: Mon, 04 Feb 2002 13:07:30 +1100 From: Peter Jeremy Subject: Re: Strange lock-ups during backup over nfs after adding 1024M RAM In-reply-to: <1427021336.20020201123650@ur.ru>; from sg@ur.ru on Fri, Feb 01, 2002 at 12:36:50PM +0500 To: Sergey Gershtein Cc: freebsd-stable@FreeBSD.ORG Mail-Followup-To: Sergey Gershtein , freebsd-stable@FreeBSD.ORG Message-id: <20020204130730.B72285@gsmx07.alcatel.com.au> MIME-version: 1.0 Content-type: text/plain; charset=us-ascii Content-disposition: inline User-Agent: Mutt/1.2.5i References: <20020126204941.H17540-100000@resnet.uoregon.edu> <1931130530386.20020128130947@ur.ru> <20020130073449.B78919@gsmx07.alcatel.com.au> <791310002584.20020130150111@ur.ru> <20020131111153.Y72285@gsmx07.alcatel.com.au> <1427021336.20020201123650@ur.ru> Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk List-ID: List-Archive: (Web Archive) List-Help: (List Instructions) List-Subscribe: List-Unsubscribe: X-Loop: FreeBSD.ORG On 2002-Feb-01 12:36:50 +0500, Sergey Gershtein wrote: >Here's what "vmstat -m" says about "FFS node": > >Memory statistics by type Type Kern > Type InUse MemUse HighUse Limit Requests Limit Limit Size(s) > ... > FFS node152293 76147K 76479K102400K 3126467 0 0 512 > ... One oddity here is the Size - "FFS node" is used to allocate struct inode's and they should be 256 bytes on i386. Are you using something other than an i386 architecture? Unless this is a cut-and-paste error, I suspect something is radically wrong with your kernel. >And this is even without the backup and the lock-up. Definitely "FFS >node" is hitting the limit while all other values are far below >limits. Could you tell me how I can increase "FFS node" limit further? By default, the memory limit is 1/2 vm_kmem_size, which is 1/3 physical memory, capped to 200MB. Which means you've hit the default cap. You can increase this limit with the loader environment kern.vm.kmem.size (see loader(8) for details). (This is also capped at twice the physical memory - which won't affect you). Before you go overboard increasing this, note that the kernel virtual address space is only 1GB. How many open files do you expect on your box? Is it reasonable for there to be >150,000 active inodes? Does "vfscache" have around the same number of InUse entries as "FFS node"? What is the output of "sysctl vfs"? Peter PS: I'm still hoping that one of the FS gurus will step in and point out what's wrong. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message