ADSM-L

Re: [ADSM-L] HSM practical limit?

2007-07-13 14:11:32
Subject: Re: [ADSM-L] HSM practical limit?
From: Paul Zarnowski <psz1 AT CORNELL DOT EDU>
To: ADSM-L AT VM.MARIST DOT EDU
Date: Fri, 13 Jul 2007 14:05:48 -0400
At 09:57 AM 7/13/2007, Stapleton, Mark wrote:
[...] in these days of decent cheap disk getting cheaper and more
decent all the time, HSM's day is pretty much past [...]


Mark,

I agree that HSM's value has diminished over time, and I also
question whether there is still a place for it.  We used TSM's HSM
once before, many years ago, and abandoned it when the cost of disk came down.

However, I am now facing requirements for a new application that I
think might actually be a good fit for HSM.  It involves (1) very
large average object size (on the order of 10M-100M each), (2) vast
amounts of storage (60TB/year growth), (3) an extremely low reference
rate, and (4) an extremely low, or non-existant, change rate.

Our mind is definitely not made up to go with HSM.  We are simply
evaluating it as one of a few alternatives.  On paper, it still looks
less expensive than the cheapest disk we can find, but I'm not sure
how much of a headache it will be to manage.  Thus my question.

Thanks to both you and Richard for responding.

..Paul



--
Paul Zarnowski                            Ph: 607-255-4757
Manager, Storage Services                 Fx: 607-255-8521
719 Rhodes Hall, Ithaca, NY 14853-3801    Em: psz1 AT cornell DOT edu

<Prev in Thread] Current Thread [Next in Thread>