From owner-freebsd-fs@FreeBSD.ORG Fri Apr 9 11:15:19 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 E043D106564A for ; Fri, 9 Apr 2010 11:15:19 +0000 (UTC) (envelope-from me@lexasoft.ru) Received: from relay.wahome.ru (relay.wahome.ru [95.211.21.141]) by mx1.freebsd.org (Postfix) with ESMTP id A57AD8FC12 for ; Fri, 9 Apr 2010 11:15:19 +0000 (UTC) Received: from mmx.lexasoft.ru (mmx.lexasoft.ru [92.241.160.6]) by relay.wahome.ru (Postfix) with ESMTP id B94896B21CC for ; Fri, 9 Apr 2010 15:12:21 +0400 (MSD) Received: from [10.100.0.2] (petrovich-telecom-gw.wahome.ru [77.91.225.38]) by mmx.lexasoft.ru (Postfix) with ESMTPSA id 65DD928491 for ; Fri, 9 Apr 2010 15:15:18 +0400 (MSD) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Apple Message framework v1077) From: Alexey Tarasov In-Reply-To: <4BBEE533.2050507@icyb.net.ua> Date: Fri, 9 Apr 2010 15:15:17 +0400 Content-Transfer-Encoding: quoted-printable Message-Id: <96786FB1-DD39-4E22-B942-B87C15E164B0@lexasoft.ru> References: <201003291616.27838.Pascal.Stumpf@cubes.de> <9D752CC7-5CCA-454D-8BEC-F3D5E6F8445C@lexasoft.ru> <46D5776E-39F0-48A7-B1C0-B844BF5147C5@lexasoft.ru> <4BBEE533.2050507@icyb.net.ua> To: freebsd-fs@freebsd.org X-Mailer: Apple Mail (2.1077) Subject: Re: ZFS raidz and 4k sector disks 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: Fri, 09 Apr 2010 11:15:20 -0000 Hello. I see considerably increased performance when creating over gnop -S 4096 = virtual disk. Even when I create zpool over raw disks the performance is = very bad and concurent writes stalls. When using gnop, zfs works VERY = fast! Btw, here is another discussion, may be there is a bug in a mav@ commit, = because he has added support for >512 sector size: = http://lists.freebsd.org/pipermail/freebsd-current/2010-April/016495.html =D0=9F=D1=80=D0=B5=D0=B2=D0=B5=D0=B4 =D0=A3=D0=BA=D1=80=D0=B0=D0=B8=D0=BD=D0= =B5! =3D) On 09.04.2010, at 12:28, Andriy Gapon wrote: > on 08/04/2010 16:55 Alexey Tarasov said the following: >> Hello. >>=20 >> I've tried all methods and realized that unfortunately the only = working >> method is gnop. So you can't use these disks for ZFS at all now. >=20 > Why? And what are you actually trying to do? > My understanding was that even with 512-byte sectors ZFS still aligns = its > on-disk data with > 4K alignment. > Do you see otherwise? What problem do you have? >=20 > --=20 > Andriy Gapon -- Alexey Tarasov (\__/)=20 (=3D'.'=3D)=20 E[: | | | | :]=D0=97=20 (")_(")