The paper addresses the problem of expensive network infrastructure in data centers and the fact that the current topologies are under provisioned for the bisection bandwidth. Authors propose to replace the current topologies using large core switches (currently 10Gbps) with a fat-tree topology formed only by smaller switches (currently 1Gbps). This helps in: reducing costs, increase bisection bandwidth, increase fault tolerance and reduce energy consumption.
The problem seems real particularly with the cloud computing presumably requiring more bandwidth between data center nodes (at least due to higher utilization). The solution is interesting.
There are two main issues created by adopting such a solution: load balancing becomes much harder due to the large variety of smaller size paths, and wiring is more complex. Authors address both problems by proposing both a static load balancing using a two level routing algorithm and possibly a per (large) flow scheduling using a centralized scheduler. To improve wiring, authors propose a packaging solution.
I liked the paper and I think it will be influential in the next 10 year, not necessarily through deployments of this form but due to potentially triggering a paradigm shift in data center design.