ADSM-L

Re: opinion on AIT vs LTO and 3570 tape technology?

2002-06-03 10:54:22
Subject: Re: opinion on AIT vs LTO and 3570 tape technology?
From: Remco Post <r.post AT SARA DOT NL>
Date: Mon, 3 Jun 2002 16:52:32 +0200
On Mon, 3 Jun 2002 06:07:07 -0500
"Mark Stapleton" <stapleto AT BERBEE DOT COM> wrote:

> From: ADSM: Dist Stor Manager [mailto:ADSM-L AT VM.MARIST DOT EDU]On Behalf Of
> Lisa Cabanas
> > I had briefly thought about HSM, but the enormous number of files and
> > directories makes it sound like a really bad idea to me.  Any thoughts?
>
> The HSM issue is not a matter of the number of files and directories, but
> rather an issue of frequency of access. If the files are generated and
> then rarely accessed, HSM would make sense, given if the following is
> true:
> 1. The customer is *really* tight on disk space, and
> 2. The files are infrequently accessed, but need to be immediately
> available.
>
> HSM is a more complex issue if you're dealing with Windows client boxes.
> You'll have to look at a solution like OTG DiskXtender for non-UNIX
> clients.
> HSM actually doesn't make a lot of sense, in these days where disk space
> is not much more expensive than tape space.
>
HSM is a real nice solution in High performance environments where users
create lots of data, want to keep it forever, but do not want to be bothered
with learning how to use archiving. It is still a lot cheaper than diskspace
in a really fast storage array.

> --
> Mark Stapleton (stapleton AT berbee DOT com)
> Certified TSM consultant
> Certified AIX system engineer
> MSCE


--
Met vriendelijke groeten,
Met vriendelijke groeten,

Remco Post

SARA - Stichting Academisch Rekencentrum Amsterdam    http://www.sara.nl
High Performance Computing  Tel. +31 20 592 8008    Fax. +31 20 668 3167

"I really didn't foresee the Internet. But then, neither did the computer
industry. Not that that tells us very much of course - the computer industry
didn't even foresee that the century was going to end." -- Douglas Adams
<Prev in Thread] Current Thread [Next in Thread>