We need blade standards, but not yet

Look at the three server blade systems in this blade server roundup: three different enclosure designs, three different physical shapes and connector sets for the server blade, three different arrangements for power supplies, expansion modules, and daughter cards, and three different management interfaces. What the world cries out for is a server-blade standard: one slot design and one electrical backplane and power-connection specification.

Such an industry standard could spur innovation in the server-blade market. Different companies could create their own servers, switches, storage arrays, and appliances to fit into an industry standard enclosure. Other firms might specialize in designing and building industry standard blade enclosures — some big, some small, some portable, some freestanding.

Of course, such a standard would inevitably lead to the creation of a hypothetical Server Blade Industry Association (SBIA), which would not only promote the blade concept, but also would certify vendors’ hardware and software as conforming to the specification. Through logo programs and public plug-fest shootouts at Networld + Interop, this SBIA could do for blade computing what the Wi-Fi Alliance has done for popularizing wireless networking.

Yet as tempting as a blade standard or even a blade association would be, the time isn’t yet right. Only a handful of companies are working in the blade server market, but they’re innovating like crazy. Compare the three 19-inch rack-based systems in this review with, say, the Egenera Inc. BladeFrame 24-inch rack solution, or the ultrahigh-density Pentium III-based offerings from vendors such as Hewlett-Packard Co. and RLX Technologies Inc. It’s far too early for the industry to begin converging on one — or even two or three — different blade form factors and interconnect specifications, not to mention determining a common design for power, cooling, and management.

At this point in the evolution of the blade platform, it’s still the Wild West, and that’s the way it should be. Vendors must be free to experiment, without limitations. In a year or two, when patterns of blade-server usage begin to emerge, and when early adopters begin to hit the wall on performance, scalability, and expandability, only then will it be time to begin the debate about industry-standardization.