Date: Wed, 4 Oct 2006 10:21:25 -0500 From: "Matthew D. Fuller" <fullermd@over-yonder.net> To: Pete French <petefrench@ticketswitch.com> Cc: jasen.gibson@ge.com, freebsd-amd64@freebsd.org Subject: Re: suggestions for SATA RAID cards Message-ID: <20061004152125.GK75501@over-yonder.net> In-Reply-To: <E1GV8PT-0007YK-Bh@dilbert.firstcallgroup.co.uk> References: <20061004145928.GH75501@over-yonder.net> <E1GV8PT-0007YK-Bh@dilbert.firstcallgroup.co.uk>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Oct 04, 2006 at 04:11:47PM +0100 I heard the voice of Pete French, and lo! it spake thus: > > Blocksize in RAID 1? > > Yes, it puzzled me too! I think the Compaq controllers only have 0+1 > though, so you need to give a stripe size even with only two drives > mirrored - and if you watch the activity lights and do a sequential > read it flips from one drive to the other. I would guess that's nothing to do with blocks or striping per se. A single big file won't be laid out 'sequentially' on the disk; the filesystem tries to avoid filling up cylinder blocks. It puts enough in given places that the seek costs are pretty low. So, after reading one bit a while, it'll seek somewhere and start another read. The controller could issue that read to another component of the mirror; I'd expect a sufficiently smart RAID controller to even out across the disks, even when there's only one process reading (not that the controller knows anything about 'processes', but...) -- Matthew Fuller (MF4839) | fullermd@over-yonder.net Systems/Network Administrator | http://www.over-yonder.net/~fullermd/ On the Internet, nobody can hear you scream.
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20061004152125.GK75501>