Threading writes and reads into HBase.

I created this issue to be the overall issue for threading to increase read and write performance in HBase and to keep it as a discussion place about threading of these elements in general. Today we are doing batching of writes and from 0.20 you will be able to do that for reads too. The thing is that the batching procedure doesn't use the ability to run these different queries at the same time, but more like a series of queries. I think that after getting a good stable 0.20 system down we should try to add threading to increase throughput for both reading and writing. At the top level of these calls I don't think that is is goin gto be to hard to do this in parallel, where it gets a little bit more complicated is when you get down to running a get query on memcache and all the storefiles at the same time, but above that I don't see it being to hard. I do think that this should not be a part of 0.20 but rather an optimization in 0.21 or so.