• Data center news, conferences and training
• Conferences
• Training
• Magazine
• Video
• Census
• Awards
• About Us
• MyDcD

I see that Gartner predicts that by 2016, 60% of new data centres will be 40% smaller while supporting a 300% increased workload.  However the last twenty years doesnt seem to support that. What Gartner seem to have ignored is the historical delta between the growth in compute capacity and demand for digital services.  If you take Moores' Law as an indicator of compute capacity growth then this new 'prediction' should have already happened several times over, but it hasn't.  Since the replacement of mainframes by servers in the very late 80s there has been a steady growth in both raised-floor space and power density - simply because demand for services has outstripped Moores' Law, i.e. more than a 40%CAGR.  With the the current internet traffic growth at >40%CAGR and mobile data already exponentially accelerating this trend is sure to continue beyond the next 3 years?  So I would have thought that Gartner should not be predicting the '60% smaller' bit unless they know of a paradigm shift in chip technology?  Maybe they do, but I doubt it will impact the general market inside five years.

But let's remind ourselves that some 'experts' have got it all wrong in the past:

"There is no reason why anyone would want to have a computer in their home"

(Ken Olson, President Chairman & Founder of Digital Equipment Corp, 1977)

... and that, of course, includes me!