From owner-freebsd-fs@FreeBSD.ORG Sat Mar 24 18:41:21 2012 Return-Path: Delivered-To: freebsd-fs@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id D23F31065670 for ; Sat, 24 Mar 2012 18:41:21 +0000 (UTC) (envelope-from j.freebsd-zfs@enone.net) Received: from flabnapple.net (flabnapple.net [216.129.104.99]) by mx1.freebsd.org (Postfix) with ESMTP id BA4D38FC16 for ; Sat, 24 Mar 2012 18:41:21 +0000 (UTC) Received: from [10.0.1.6] (c-98-207-6-192.hsd1.ca.comcast.net [98.207.6.192]) (using TLSv1 with cipher ECDHE-RSA-AES128-SHA (128/128 bits)) (No client certificate requested) by flabnapple.net (Postfix) with ESMTPSA id 4C3A01CC056; Sat, 24 Mar 2012 11:41:21 -0700 (PDT) Mime-Version: 1.0 (Apple Message framework v1084) Content-Type: text/plain; charset=us-ascii From: Taylor In-Reply-To: <20120324174218.00005f63@unknown> Date: Sat, 24 Mar 2012 11:41:20 -0700 Content-Transfer-Encoding: quoted-printable Message-Id: References: <45654FDD-A20A-47C8-B3B5-F9B0B71CC38B@enone.net> <20120324174218.00005f63@unknown> To: Alexander Leidinger X-Mailer: Apple Mail (2.1084) Cc: freebsd-fs@freebsd.org Subject: Re: ZFS extra space overhead for ashift=12 vs ashift=9 raidz2 pool? 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: Sat, 24 Mar 2012 18:41:21 -0000 Alex, Thank you for your response. I'm not particularly concerned about the = overhead of file fragmentation, as most of the space will be take by fairly large files (10's of GiB).=20= My original question concerned the amount of space reported available by = zfs for a freshly-created *empty* raidz2 filesystem. To re-iterate, I find 2.79TiB more space available with ashift=3D9 = (49.62 TiB) vs ashift=3D12 (46.83TiB) for a new 3.64TiB 16-disk raidz2 pool. (I'd like to keep the 4K sector size, because in my limited performance = testing I can write to the the 4K sector size (ashift=3D12) array at ~271MiB/s vs ~228 MiB/s for = the 512-byte sector size (ashift=3D9).) Is this extra filesystem overhead expected for empty ashift=3D12 raidz2 = pools?=20 Is there anyway to reduce this overhead? Cheers, -Taylor On Mar 24, 2012, at 9:42 AM, Alexander Leidinger wrote: > On Fri, 23 Mar 2012 09:30:50 -0700 Taylor > wrote: >=20 >> I'm bringing up a new ZFS filesystem and have noticed something >> strange with respect to the overhead from ZFS. When I create a raidz2 >> pool with 512-byte sectors (ashift=3D9), I have an overhead of 2.59%, >> but when I create the zpool using 4k sectors (ashift=3D12), I have an >> overhead of 8.06%. This amounts to a difference of 2.79TiB in my >> particular application, which I'd like to avoid. :) >>=20 >> (Assuming I haven't done anything wrong. :) ) Is the extra overhead >> for 4k sector (ashift=3D12) raidz2 pools expected? Is there any way = to >> reduce this? >=20 > This depends upon the data you write. >=20 > If your data is always a multiple of 4k, you will have probably less > overhead (there is probably still overhead from ZFS metadata). >=20 > If your data is always only a multiple of 512 byte, you would have = much > less overhead on a ashift=3D9 FS than on a ashift=3D12 FS. >=20 > If the size of your data is random, and always less than 4k, you have > more overhead than if the size of your data is random and always > several GB big. >=20 > Bye, > Alexander. >=20 > --=20 > http://www.Leidinger.net Alexander @ Leidinger.net: PGP ID =3D = B0063FE7 > http://www.FreeBSD.org netchild @ FreeBSD.org : PGP ID =3D = 72077137 >=20