[Beowulf] Station wagon full of tapes

Greg Lindahl lindahl at pbm.com
Tue May 26 15:14:57 PDT 2009

On Tue, May 26, 2009 at 09:54:15AM -0400, Chris Dagdigian wrote:

> - Once we process the data to get the derived results, the primary data 
> just needs to go somewhere cheap

If you only rarely re-read the primary data, I'd think a stack of SATA
drives in a cabinet would probably do the trick. Two sets, one
off-site. And that will be cheaper than S3; you pay only the disk
hardware cost plus a very modest amount of labor. You don't have to
pay for a server to which all the disks can be simultaneously plugged
into. Amazon is providing too much.

Companies like BlacX sell external SATA enclosures that you can plug a
raw disk into. Very convenient for this purpose.

And you don't have to worry about Amazon keeping your DNA
confidential. That's a very big deal with most human DNA.

Finally, note that this amount of data is considered small by high
energy physics people.

-- greg

More information about the Beowulf mailing list