From mboxrd@z Thu Jan 1 00:00:00 1970 From: Robin Hill Subject: Re: Stupid question regarding RAID-1 access pattern Date: Wed, 6 Jan 2010 21:37:23 +0000 Message-ID: <20100106213723.GA12318@cthulhu.home.robinhill.me.uk> References: <4B44EB58.2090400@northarc.com> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="2fHTh5uZTiUOsy+g" Return-path: Content-Disposition: inline In-Reply-To: <4B44EB58.2090400@northarc.com> Sender: linux-raid-owner@vger.kernel.org To: "linux-raid@vger.kernel.org" List-Id: linux-raid.ids --2fHTh5uZTiUOsy+g Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Wed Jan 06, 2010 at 02:58:16PM -0500, Curt Hartung wrote: > Tried to ferret out the answer to this myself and so far so bad. >=20 > This just 'popped in there' while I was optimizing something completely= =20 > different... in a RAID-1, writes have to be mirrored of course, thats=20 > what RAID-1 is, but for reads, could they not be sped up by a=20 > significant amount if a storage pattern was chosen such that large=20 > blocks of data were "striped" in an in-order/out-of-order scheme? In=20 > other words, store all the data on both drives, but in huge (2x cache=20 > size) -ish blocks that might allow 50% of a given [large] access to come= =20 > from each drive, with trivial [smaller] reads always coming from one or= =20 > the other chosen at random. >=20 > Downside, I know, is that the data would be organized ina way only the= =20 > raid subsystem would understand, so the niceness of pulling a mirrored=20 > drive out of service and it being a literal copy of the otehr drive=20 > would be lost, but for such a speedup I'd be willing to pay the price of= =20 > always having to access it as a failed set (worst case) through the=20 > md-daemon. >=20 > Am I off into the weeds? I doubt this would help much really. If you're reading sequential data then it's pretty much as quick to keep reading as to seek to the next chunk. If you want a performance and are prepared to throw out strict RAID1 compatibility then RAID10-f2 may be better suited. It still provides the same redundancy but improves read performance by striping (there's some slowdown on writes but not much). Cheers, Robin --=20 ___ =20 ( ' } | Robin Hill | / / ) | Little Jim says .... | // !! | "He fallen in de water !!" | --2fHTh5uZTiUOsy+g Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.11 (GNU/Linux) iEYEARECAAYFAktFApEACgkQShxCyD40xBLhfgCfVlHXBcf3FVWNJRgH/CLmwtob J08AoJwQBtEIRkPwnwWcn2IuQoEy6Bfm =Ft7x -----END PGP SIGNATURE----- --2fHTh5uZTiUOsy+g--