There's a lot of angst out there about data-center crowding and the associated twin devils of power and cooling. The problem primarily stems from high-density servers being shoved into data centers that were not designed to provide power or cooling at the rate of hundreds of watts per square foot. This isn't news to most of you; you're living it.

What is new, at least according to Forester, is that server replacement is in the top five IT spending priorities, whereas last year it wasn't on the list at all. Just above it on the list are "consolidate IT infrastructure" and "replace or upgrade existing application systems," both of which sound like they'll require server upgrades to me.

You'd think that everyone in the server supply chain, from Intel and AMD to Hewlett-Packard and IBM, would be ecstatic about this finding. But those confining data-center walls and limited cooling capabilities have both put a damper on the server vendors' glee and spurred this interest in upgrades. But the walls have been confining for a while now, so we can look elsewhere for what's driving the upsurge in interest.

One driver certainly is the capability and capacity of the current and next generation of servers. Servers with dual quad-core processors will be common and reasonably priced by this fall. When filled with tens to hundreds of gigabytes of memory and deployed in pairs, these systems make a fine target for server consolidation. This, combined with hardware support for virtualization and the continued improvement in hypervisor technology, means legacy hardware can and should be replaced by virtual machines. The result of this consolidation will be a trend toward more capable servers, but a slowing in the overall growth of server sales. But is now the time to jump on the consolidation bandwagon?

Network Computing tends to look at products in terms of five areas: performance, manageability, scalability, reliability and security. In practice, server consolidation has proved itself in terms of performance, scalability and reliability. Manageability of new technology always lags these other evaluation segments, but we're seeing excellent work on this front too (look for our cover story on virtualization management later this year).

That leaves security as the final question. You can bet that everyone who can make a dime on questioning the security of virtualization will be doing so; the drumbeat has started and is increasing in volume. But while the security threat is real—and you should be concerned about it—it's also overstated. If you can eliminate 10 or 20 servers running outdated versions of NT in favor of a single consolidated pair of servers, the task of securing the environment should be simpler, or at least no more complex. If you're considering a server consolidation project, do it. Be mindful of security, but don't be dissuaded by the nattering nabobs of negativity.

Art Wittmann is editor in chief of Network Computing. Write to him at awittmann@nwc.com.