What the Heck Is HyperSCSI?: Page 2 of 3

“It’s a pretty interesting approach,” says Graham Smith, senior I/O planning manager in Hewlett-Packard Co.'s (NYSE: HPQ) Enterprise Unix Division. “It really gets around the problem of offloading TCP/IP.” Smith adds, however, that HP doesn't currently have any plans to support HyperSCSI in any of its products.

And that’s not all. Since HyperSCSI was released as open-source software last year, it’s free and licensed under the GNU General Public License (GPL). “It’s not only free as in beer, but also free as in speech,” says Jesse Keating, systems engineer with Linux desktop vendor Pogo Linux who has experimented with HyperSCSI. “So if you need to make alterations, the code is available... You don’t have to rely on the 'governing bodies' of HyperSCSI to do it.”

With all these advantages, you might expect everyone in the industry to be looking at the new protocol. Instead, the response many people have to questions on the subject is: “HyperWHAT?”

While many industry vendors have been talking about iSCSI for the past couple years, HP’s Smith says it’s hard to say how seriously to take the HyperSCSI push, since it’s mainly only being talked about at the Data Storage Institute. “It looks a little like just another university project,” he says, but allows that, “of course, a lot of good technologies came through that channel.”

In addition to obscurity, HyperSCSI is, of course, also suffering from its share of technological concerns. While putting SCSI on raw Ethernet may speed up performance, there are also disadvantages associated with skirting TCP/IP, Smith says. “Without TCP/IP, it has no real error-recovery mechanism or guarantee that packets get delivered. It also appears to be quite limited in scaleability.”