From owner-freebsd-fs@FreeBSD.ORG Mon Jan 10 20:44:37 2011 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 7AFB51065675 for ; Mon, 10 Jan 2011 20:44:37 +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 334C38FC18 for ; Mon, 10 Jan 2011 20:44:36 +0000 (UTC) Received: by people.fsn.hu (Postfix, from userid 1001) id 97D33706E08; Mon, 10 Jan 2011 21:44:35 +0100 (CET) X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.2 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MF-ACE0E1EA [pR: 12.3386] X-CRM114-CacheID: sfid-20110110_21443_94D71404 X-CRM114-Status: Good ( pR: 12.3386 ) X-Spambayes-Classification: ham; 0.00 Message-ID: <4D2B6FB2.2000506@fsn.hu> Date: Mon, 10 Jan 2011 21:44:34 +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: Bob Friesenhahn References: <4D0A09AF.3040005@FreeBSD.org> <4D1F7008.3050506@fsn.hu> <4D29A198.4070107@fsn.hu> <20110110085756.GA1744@garage.freebsd.pl> <4D2B423F.2000403@fsn.hu> In-Reply-To: Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-fs@freebsd.org Subject: Re: New ZFSv28 patchset for 8-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: Mon, 10 Jan 2011 20:44:37 -0000 On 01/10/2011 07:18 PM, Bob Friesenhahn wrote: > On Mon, 10 Jan 2011, Attila Nagy wrote: >> >> Having this choice is good, and in this case enabling this makes >> sense for me. I don't know any reasons about why you wouldn't use all >> of your L2ARC space (apart from sparing the quickly wearing out flash >> space and move disk heads instead), but I'm sure Brendan made this >> choice with a good reason. >> If you get an answer, please tell us. :) > > Consider that your L2ARC device might be bandwidth limited to > 100-240MB/second while your main storage is capable of 1000MB or > 2000MB second sequential data transfer. This a good reason to not > simply put all data (which does not fit in normal ARC) into L2ARC. ARC > is supposed to be adaptive ... > > Bob Well, yes, that's a valid point for having such a switch, so the user can decide which is better for him. For me, for this use case, the two SSDs can serve more bandwidth than the 24 SATA disks, so it's definitely worth it. Those disks can do 60-70 MBps sequentially, and all file transfers are sequential here. There are just many of them, so this becomes semi-random IO. Caching in the L2ARC helps a lot here.