From owner-freebsd-fs@FreeBSD.ORG Sun Dec 20 12:09:18 2009 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 7E1D8106566C; Sun, 20 Dec 2009 12:09:18 +0000 (UTC) (envelope-from bra@fsn.hu) Received: from people.fsn.hu (people.fsn.hu [195.228.252.137]) by mx1.freebsd.org (Postfix) with ESMTP id 891238FC0A; Sun, 20 Dec 2009 12:09:17 +0000 (UTC) Received: by people.fsn.hu (Postfix, from userid 1001) id EF6D51CC5E2; Sun, 20 Dec 2009 13:09:15 +0100 (CET) X-CRM114-Version: 20090423-BlameSteveJobs ( TRE 0.7.6 (BSD) ) MF-ACE0E1EA [pR: 23.0207] X-CRM114-CacheID: sfid-20091220_13091_7B0D6D98 X-CRM114-Status: Good ( pR: 23.0207 ) Message-ID: <4B2E13E9.9000108@fsn.hu> Date: Sun, 20 Dec 2009 13:09:13 +0100 From: Attila Nagy User-Agent: Mozilla/5.0 (X11; U; Linux i686; en-US; rv:1.8.1.23) Gecko/20090817 Thunderbird/2.0.0.23 Mnenhy/0.7.6.0 MIME-Version: 1.0 To: Thomas Burgess References: <20091030223225.GI5120@datapipe.com> <4AEB6D79.5070703@feral.com> <4B2E0FA9.1050003@fsn.hu> In-Reply-To: X-Stationery: 0.4.10 Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.3 (people.fsn.hu); Sun, 20 Dec 2009 13:09:15 +0100 (CET) Cc: freebsd-fs@freebsd.org Subject: Re: Plans for Logged/Journaled UFS 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: Sun, 20 Dec 2009 12:09:18 -0000 For that problem, it can be true, the machine in speak has only 1 GB RAM (i386), although 8 disks. The freeze is a different beast, I've got it on 32-64 GB RAM machines (with NFS), and on 8 GB machines serving stuff with ftp/http/rsync/etc (no NFS). I'm not sure that the NFS and the non-NFS case is the same though. Thomas Burgess wrote: > > I think it depends on hardware and setup. I've noticed the "zfs > problem" with SOME machines when it comes to rtorrent (the rtorrent > process will be stuck "waiting for disk" but on other machines it's > fine. > > The machines i've had the most problem with are single drive less than > 2 gb ram. > > I've got rtorrent and zfs working fine on plenty of machines with 2-3 > hard drives and 4-8 gb ram. > > On Sun, Dec 20, 2009 at 6:51 AM, Attila Nagy > wrote: > > Matthew Jacob wrote: > > Hussain Ali wrote: > > > ZFS doesnt suffice for may use cases - so just wondering > if this is in > the works. > > > > Which use cases can you name? > > Reliable data storage. :( > > Sadly, ZFS in FreeBSD is still very far from being stable. For > example I have NFS servers running on ZFS, and they freeze about > every week. It seems it's related to NFS. > I can't even get to the debugger. After sending an NMI, the kernel > writes "NMI ... going to debugger" eight times (those machines > have 8 CPU cores) and nothing happens, I can only reset. > > Another machine just looses ZFS access (all processes stuck in IO) > on i386 if I run rtorrent with unlimited bandwidth with some > torrents, or some disk intensive spam filtering. Access to UFS > filesystems are still OK. > > Also, running UFS and ZFS seems to have problems in 8-STABLE with > UFS eating out memory from ZFS. > _______________________________________________ > freebsd-fs@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-fs > To unsubscribe, send any mail to > "freebsd-fs-unsubscribe@freebsd.org > " > >