From mboxrd@z Thu Jan 1 00:00:00 1970 From: Keld =?iso-8859-1?Q?J=F8rn?= Simonsen Subject: Re: striping of a 4 drive raid10 Date: Sun, 27 Jan 2008 22:43:08 +0100 Message-ID: <20080127214308.GA14643@rap.rap.dk> References: <20080127193345.GA5426@rap.rap.dk> <18332.58743.852744.907807@tree.ty.sabi.co.UK> Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: <18332.58743.852744.907807@tree.ty.sabi.co.UK> Sender: linux-raid-owner@vger.kernel.org To: Peter Grandi Cc: Linux RAID List-Id: linux-raid.ids On Sun, Jan 27, 2008 at 08:11:35PM +0000, Peter Grandi wrote: > >>> On Sun, 27 Jan 2008 20:33:45 +0100, Keld J=F8rn Simonsen > >>> said: >=20 > keld> Hi I have tried to make a striping raid out of my new 4 x > keld> 1 TB SATA-2 disks. I tried raid10,f2 in several ways: >=20 > keld> 1: md0 =3D raid10,f2 of sda1+sdb1, md1=3D raid10,f2 of sdc1+sdd= 1, md2 =3D raid0 > keld> of md0+md1 > keld> 2: md0 =3D raid0 of sda1+sdb1, md1=3D raid0 of sdc1+sdd1, md2 =3D= raid01,f2 > keld> of md0+md1 > keld> 3: md0 =3D raid10,f2 of sda1+sdb1, md1=3D raid10,f2 of sdc1+sdd= 1, chunksize of=20 > keld> md0 =3Dmd1 =3D128 KB, md2 =3D raid0 of md0+md1 chunksize =3D= 256 KB > keld> 4: md0 =3D raid0 of sda1+sdb1, md1=3D raid0 of sdc1+sdd1, chunk= size > keld> of md0 =3D md1 =3D 128 KB, md2 =3D raid01,f2 of md0+md1 chun= ksize =3D 256 KB >=20 > These stacked RAID levels don't make a lot of sense. >=20 > keld> 5: md0=3D raid10,f4 of sda1+sdb1+sdc1+sdd1 >=20 > This also does not make a lot of sense. Why have four mirrors > instead of two? My error, I did mean f2. Anyway 4 mirrors would make the disk 2 times faster than 2 disks, and g= iven disk prices these days this could make a lot of sense. > Instead, try 'md0 =3D raid10,f2' for example. The first mirror of > will be striped across the outer half of all four drives, and > the second mirrors will be rotated in the inner half of each > drive. >=20 > Which of course means that reads will be quite quick, but writes > and degraded operation will be slower. >=20 > Consider this post for more details: >=20 > http://www.spinics.net/lists/raid/msg18130.html Thanks for the reference. There is also more in the original article on possible layouts of what is now known as raid10,f2 http://marc.info/?l=3Dlinux-raid&m=3D107427614604701&w=3D2 including performance enhancements due to use of the faster outer sectors, and smaller average seek times because you can seek on only half the disk. best regards keld - To unsubscribe from this list: send the line "unsubscribe linux-raid" i= n the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html