[KLUG Hardware] re: 3rd party reviews / RAID

[Mike Williams]

>From: "Bryan J. Smith" <b.j.smith@ieee.org>
>To: hardware@kalamazoolinux.org
>Cc: members@kalamazoolinux.org
>Date: 20 May 2002 12:50:33 -0400
>Subject: [KLUG Hardware] Re: New mob
>Reply-To: hardware@kalamazoolinux.org
>
>When it comes to hard drives, I hit StorageReview.COM (
>http://www.storagereview.com ).  Although some of their info and
>thermal
>testing is adequate, I feel their benchmarks are a not deep enough --
>especially when it comes to RAID.  They seem to use far too many
>utilities designed for single disks -- whereas RAID cards should be
>slammed with lots of I/O and, more importantly, just I/O requests (to
>see where they "crack" under the load)

Most of the stuff I've read recently, from MaximumPC and others, suggests
that IDE RAID 0 doesn't gain you much, at least with the Promise and such
controllers.  I seem to remember somebody (Adam?) ranting against them as
not even being true RAID cards but regular IDE controllers being sneaky.  I
built my current system with a Promise RAID 0 array, but I'm kinda
regretting it.  Performance increase is minimal, and I know I've opened
myself up to roughly double the possibility of catastrophic hard drive
failure.

Somebody correct me if I'm wrong, but in general, RAID 0 can actually slow
you down.  In reading, which is the majority of hard drive activity unless
you're editing video or something, rotational latency is the biggest speed
factor.  Rotational latency being the time you have to wait for the piece
of data you're interested in coming around to the read head.  In a stripe
set, you have to wait for the data to come around on both drives, which
increases the odds that you'll be waiting closer to the maximum time.  SCSI
RAID arrays have always been able to synchronize the drives so they rotate
together, but I've never heard of such a thing in IDE.