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 _______________________________________________ Beowulf mailing list, [email protected] sponsored by Penguin Computing To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf
