IBM has struck back at HP's trashing of its blade server systems. The two companies are vying for the position of top dog in the blade server market with IBM is currently on top. Blade servers are one of the few remaining high-margin, proprietary hardware sectors in the IT industry.

Last week, HP announced the results of laboratory-based research which it claimed showed that HP's blades run cooler than IBM's, and use less energy as a result.

Specifically, HP said its lab report, produced by Sine Nomine Associates, showed that its BladeSystem c-Class uses up to 27 per cent less power than the IBM BladeCenter-H in similar configurations. It said that the benchmarks reflect real-world customer usage of blade servers.

The lab examined the overall power consumption and external airflow requirements of a variety of blade server and 1U rack server configurations in what HP described as a typical data centre environment, experiencing light to heavy use.

IBM's rebuttal homes in on this paragraph in HP's report: "As soon as more memory or hot-pluggable drives are needed, IBM's use of expansion boards [for additional memory] costs dearly, and the HP BladeSystem with ProLiant BL460c significantly outperforms the IBM BladeCenter-H with HS21. In these tests, the BL460c used only about 340 VA/server versus 407 VA/server for the BladeCenter-H in its minimal 8-DIMM configuration, meaning the HP blade consumed about 16.5 per cent less power than the IBM blade, per server."

IBM retorted: "This IBM configuration is available to give clients greater flexibility and functionality, however it is not likely that a client would be running both."

Fewer than 10 per cent of its customers use these expansion options and very few would choose both, making the test unrealistic and not at all real-world, as HP claimed, said IBM.

IBM's rebuttal said: "HP is validating recent IBM testing stating IBM is more power efficient. IBM testing shows the HS21 with the Memory and I/O Expansion Blade and Storage and Expansion Blade as using 40-50 percent more power than a base HS21. If HP’s results are only showing them as having a 27 percent advantage on this configuration, that validates IBM testing stating IBM is up to 24 percent more energy efficient than HP."

IBM also went on to argue that HP didn't use up to date products in its testing and that "If HP had tested BladeCenter with the current code, IBM is confident it would have resulted in clear IBM leadership in power efficiency per blade."

It's natural for the two biggest blade server companies to want to keep their names in front of the eyes of customers, potential and otherwise. Blade server chassis are proprietary, with no sign of that changing in the near or mid-term future so, like printer ink, blade servers represent a highly profitable lock-in.

What customers might now do is to give more consideration to systems from others in the blade server market - such as Dell and Sun - who have more to gain from being co-operative on price and services.

Existing customers of IBM and HP can take some heart from the fact that both are solidly agreed that the key issues for blade servers are power consumption and cooling.