Data Center Darwinism

A Sun IT architect says consolidation is not a silver bullet for many complex data centers.

Most data centers are complex ecosystems, in which a variety of hardware and technologies must coexist. Getting them to work together is not a trivial matter, and presents a special challenge in re-architecting a data center that has maxed out its cooling capacity.

Consolidation and virtualization are key solutions to the challenges found in many of today's data centers. But these are tough problems, and there is no silver bullet to fix them. That's the message from Lou Springer, an IT Architect at Sun Microsystems' data center consolidation group, in Fear and Loathing in the Data Center, a post today on his blog, Inchoate Curmudgeon. It's a compelling read. Here's an excerpt:

Increasingly, the situations we deal with are quite desperate. There is no more space or power. Data center power and cooling costs are bankrupting the companies they serve. By the time we get involved in these situations, and by the time my group shows up, we are facing a pretty tense crowd (mob?). ... The typical troubled data center is a sprawl of different architectures, configurations and nuances of the software and IT services that make them up, belied by even in the most seemingly homogeneous row-after-row of machine-after-machine, all just the same, data centers.

Springer writes that most of those machines, in aggregate, run at less than 10% utilization. In many cases the mess is a legacy of previous IT management, and the current team is doing the best it can to keep it all working.


But now they've run out of space or power or cooling and the crisis has come to a head. That's when the specialists are called, and folks like Springer arrive to assess the options.

The point is, you don't just consolidate this stuff without doing something about the chaos. There is no silver bullet. ... Legitimately, many of the things that must be done to architectures to clean up the mess don't add a lot of immediately visible business value. If you were call the business unit to talk about 'fixing' his service in these situations, they really do not understand.

Springer is not without hope. He sees Ruby on Rails as a tool woth the potential to address many of the problems he encounters in data centers. "I pray that these new Rails applications, in some huge flood of data center Darwinism, will wash away a lot of the nastier things we see now," Springer writes.