"better options already exists for servers where I am guessing CFS is used." Well, that depends on your workload (which is the thrust of the debate). With one of the HPC products I regularly work with, we have a best-practice of using the noop scheduler instead of cfs - this tiny tweak alone will see at least a 30% improvement in our I/O performance (which is nothing to be sneezed at when we're moving ~700MB/s).
Being able to have pluggable schedulers is great because Linux can be all things to all people and it does make sense to have options (lets not go crazy here - too much choice can also be a bad thing). People talk about the difference between Linux on netbooks and servers for example but even in the "server" space there is VAST difference between small business file & print, clustered Oracle or scientific data acquisition workloads.
I too hope that this debate doesn't go away and also hope that it doesn't become as heated and personal as in the past so that we can all benefit from a selection of good ideas.