From owner-freebsd-fs@FreeBSD.ORG Wed Feb 3 12:48:33 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 B3C78106566B for ; Wed, 3 Feb 2010 12:48:33 +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 6AC168FC17 for ; Wed, 3 Feb 2010 12:48:32 +0000 (UTC) Received: by people.fsn.hu (Postfix, from userid 1001) id 7BDD02087A6; Wed, 3 Feb 2010 13:48:31 +0100 (CET) X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MF-ACE0E1EA [pR: 17.2525] X-CRM114-CacheID: sfid-20100203_13483_3BA244CE X-CRM114-Status: Good ( pR: 17.2525 ) Message-ID: <4B69709E.1090601@fsn.hu> Date: Wed, 03 Feb 2010 13:48:30 +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: =?UTF-8?B?VG9tbWkgTMOkdHRp?= References: <4B694689.2030704@fsn.hu> <4B696CB7.7070607@fsn.hu> In-Reply-To: X-Stationery: 0.4.10 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 8bit X-Greylist: Sender succeeded SMTP AUTH, not delayed by milter-greylist-4.2.3 (people.fsn.hu); Wed, 03 Feb 2010 13:48:30 +0100 (CET) Cc: freebsd-fs@freebsd.org Subject: Re: Machine stops for some seconds with ZFS 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: Wed, 03 Feb 2010 12:48:33 -0000 Tommi Lätti wrote: >> I'm not sure about these are being the same. When I see these "stops", >> nothing happens. gstat shows no IO, and everything goes very quiet for some >> painful (10s of) seconds. Also, buildworld doesn't do too heavy IO, at least >> for these drives. >> > > Well that's what I experienced. iostat says 0, machine is kind of > responsive, unless you try to read or write from the zfs pool.. > Oh, that wasn't clear to me, so you are also experiencing a total blackout in disk IO. I'm not sure how this could be traced. > >> BTW, we are doing tests in a completely different environment with ZFS and >> NFS (15k drives, with BBWC), and it seems something similar happens there >> too, resulting in a freeze in the end. >> >>> Combine with 5400 rpm consumer drives... well... >>> >>> >> Doesn't really count, but these drives are 7k2. >> > > If it's a zfs arc problem it would definitely manifest on 15k drives > too, what I meant that the impact might be unnoticeable. But since I > don't have a nice SAN to test with right now I can't try it out with > 100+ disks. > I'm still not getting the point. If you see zero IO during the problem, how would a faster storage make impact on its visibility?