Date: Thu, 21 Mar 2002 11:27:47 -0800 (PST) From: Matthew Dillon <dillon@apollo.backplane.com> To: "Jim King" <jim@jimking.net> Cc: "David Greenman" <dg@root.com>, <questions@FreeBSD.ORG> Subject: Re: Problems with large disk. (> 1 TB) Message-ID: <200203211927.g2LJRlN00599@apollo.backplane.com> References: <20020321191258.J64325-100000@woozle.rinet.ru> <200203211715.g2LHFeo21349@apollo.backplane.com> <007d01c1d108$fbbfa930$779a8486@jking>
next in thread | previous in thread | raw e-mail | index | archive | help
:
:"Matthew Dillon" <dillon@apollo.backplane.com> wrote:
:> Or, for example, you could take 12 160G disks, split each one into
:> two 80G partitions (say 'd' and 'e'), and the RAID-5 all the 'd'
:> partitions together into a 800G logical drive and RAID-5 all the
:> 'e' partitions together into another 800G logical drive.
:
:What's the advantage of doing this vs. one 800GB RAID5 volume on 6 of the
:drives and another 800GB RAID5 volume on the other 6 drives? Or was your
:example just for illustration?
Just an illustration, though a very pertainant one considering (a) the
direction that drive capacities are going -- straight up, and (b) at
least insofar as general read performance goes, the more spindles
you have the better. So unless there are other requirements that
prevent it and assuming one doesn't go overboard, I usually try
to spread the disk load out at least a little.
-Matt
Matthew Dillon
<dillon@backplane.com>
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-questions" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200203211927.g2LJRlN00599>