The Days of Raised Floors are Numbered

Print Friendly, PDF & Email

Stephen Bigelow writes that raised floors may be going the way of the dodo.

According to TechTarget’s 2010 Data Center Decisions survey, 59% of IT respondents use raised flooring in their current data center, but only 43% expect to use raised floors in a future data center. Slabbed floors are also falling into disuse, with 33% of respondents using slabbed floors in the current data center, but only 19% planning slabbed floors for a future data center. In fact 38% of IT professionals don’t know what kind of flooring they will use in the future.

Bigelow goes on to say that while raised floors have been around for a long time, they just don’t provide enough cooling for today’s high-density, 42U rack enclosures. And having written my share of Cray site planning manuals, I can tell you that a dirty, cluttered underfloor full of cables and pipes makes a pretty lousy plenum for air to move through. Full Story


  1. […] This post was mentioned on Twitter by insideHPC, kml. kml said: RT @insideHPC: Just in: The Days of Raised Floors are Numbered […]


  1. Raised floors are still very useful to “hide” the water pipes underneath the racks to feed cold water into these. We use the “under” the floor area solely for water and a little bit of air cooling all cables (mains, network) are fed from the ceiling. Very nice way to separate things.

  2. I was puzzled by the numerous unwarranted assumptions in this article. Why should underfloor spaces necessarily be “filthy”? I know mine isn’t, though I plan to pull all the tiles and vacuum when we do a major equipment transition.

    Another problem is the unsupported claim that hot/cold aisles are somehow less efficient than in-row or in-rack. Why would that be? The big squirrel-cage blowers in a CRAC is quite efficient for the CFM. in-row/rack systems have smaller, less efficient fans and have to make the air flow u-turn. But really, if you’re dissipating >15KW, why not go straight to a rack-back heat exchanger and a coolant loop? Is there an implicit assumption here that heat densities are growing (per-socket dissipation is certainly not.)