Earlier this year, EMC introduced a new product aimed at a market they labeled content addressed storage. Ostensibly, this type of storage is a repository for data that needs to be archived but also needs to be handy for occasional access.
Data that fits that profile includes electronicdocuments, medical images (MRIs, X-rays, etc.),archived e-mail, check images, broadcast content,satellite images -- things that users don't accessfrequently but should nevertheless be availablequickly when needed.
Does a market exist for storage systems specific tothese documents? Is an entirely new storagearchitecture required to store this type of data?
Mario and Scott, your two faithful Virgils in storagehell, have only mixed answers to offer.
Let's start with the specs of the EMC system.
Obviously, that kind of data calls for largerepositories, but not necessarily lightning-fastaccess: FC (Fibre Channel) or even SCSI disks would beoverkill.
Appropriately, EMC's brainchild Centera is filled withseveral cheap ATA drives that give a customer up to19.2TB per cabinet. Sixteen cabinets clusteredtogether give 307.2TB, and seven clusters in a domaingive you just over 2PB of capacity.
On the software side, with CentraStor, EMC uses aproprietary content-addressing scheme that assigns aunique address to the item, one that stays with thatcontent permanently.
Let's clarify. Using Centera, your file will beindependently parked somewhere, and your applicationwill only hold a receipt (the content address) bearinga unique ID. No other information is needed.
As in valet parking, to retrieve your file, just handthe receipt to the attendant. The Centera attendantcan detect data corruptions by running an algorithm onthe content and comparing the results with the contentaddress receipt. That's clean and efficient, we must say.
But here is our complaint: SANs and NAS are already twoseparate storage architectures that will merge overtime. Centera's proposal involves a whole newarchitecture that must be managed separately. Doesthat make sense?
Additionally, content of this type is most likelyalready stored elsewhere. That means you'd have tomigrate all your existing records to a separate system.
And forget getting rid of your tape libraries. AlthoughCentera offers centralized and secure storage forlong-lived records, you're still going to have toarchive many of them. That means using tape or opticalto get them to an off-site location.
So what is the real advantage of Centera? We're notsure yet. The alternative, of course, is using whatyou already have -- your high performance SAN, plusoptical disks and tape libraries. But isn't thatoverkill? Or is it too little, too late?