From owner-freebsd-stable@FreeBSD.ORG Mon Oct 13 23:48:08 2014 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2001:1900:2254:206a::19:1]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by hub.freebsd.org (Postfix) with ESMTPS id 76D22B19 for ; Mon, 13 Oct 2014 23:48:08 +0000 (UTC) Received: from luigi.brtsvcs.net (luigi.brtsvcs.net [IPv6:2607:fc50:1000:1f00::2]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id 5198C3F9 for ; Mon, 13 Oct 2014 23:48:08 +0000 (UTC) Received: from chombo.houseloki.net (unknown [IPv6:2601:7:400:640:21c:c0ff:fe7f:96ee]) by luigi.brtsvcs.net (Postfix) with ESMTPSA id 7D9F62D4F9B; Mon, 13 Oct 2014 16:48:00 -0700 (PDT) Received: from [IPv6:2601:7:2580:674:baca:3aff:fe83:bd29] (unknown [IPv6:2601:7:2580:674:baca:3aff:fe83:bd29]) by chombo.houseloki.net (Postfix) with ESMTPSA id 14AFEF37; Mon, 13 Oct 2014 16:47:58 -0700 (PDT) Message-ID: <543C64AA.1000307@bluerosetech.com> Date: Mon, 13 Oct 2014 16:47:54 -0700 From: Darren Pilgrim Reply-To: freebsd-stable User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64; rv:24.0) Gecko/20100101 Thunderbird/24.6.0 MIME-Version: 1.0 To: "Matthew D. Fuller" Subject: Re: getting to 4K disk blocks in ZFS References: <540FF3C4.6010305@ish.com.au> <54100258.2000505@freebsd.org> <5410F0B4.9040808@ish.com.au> <543C1E7B.4090204@bluerosetech.com> <20141013191903.GR2161@over-yonder.net> In-Reply-To: <20141013191903.GR2161@over-yonder.net> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-stable X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.18-1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 13 Oct 2014 23:48:08 -0000 On 10/13/2014 12:19 PM, Matthew D. Fuller wrote: > On Mon, Oct 13, 2014 at 11:48:27AM -0700 I heard the voice of > Darren Pilgrim, and lo! it spake thus: >> >> If the default is 4k and (for the limited time they're still common) >> you use true 512b disks, you can waste space. Sure, but how much >> space? > > The median file in /usr/ports is 408 bytes. Over 90% of the files are > under 2k, which means the wastage for them is over 100% (before > counting what gain compression might get). A little offhand mathery > says it's about 78% extra overhead on the whole. > > And that includes the almost hundred megs (over 22% of the total size > of the FS) for the INDEX.db, plus the ~90 megs of the flat INDEX files > (another 20%). If you pull those out, the overhead is 130%. The worst case is about 140%. But that's 140% of 388 MB, so we go from tiny to somewhat less tiny. Huge slack is expected in small, populous datasets. I'd much rather have the integrity assurance and performance gains, instead of saving a few hundred MB out of a multi-terabyte pool.