Zipkin based cluster-wide request tracing

Zipkin (http://zipkin.io) is a distributed tracing system that started at Twitter.

Infinispan should integrate with it so that we can trace individual cache requests in terms of which components it touches and how long it takes in each, and also when the cache requests end up going to other nodes (plus see which remote components it touches).

The idea is that this should give us a better idea of what a particular operation does in terms of how many nodes it goes to, and what it does in each. This would be hugely beneficial to be able to better analyse performance issues.

A key advantage of Zipkin is that it can be run in production since it can be configured to only track a fraction of all requests, making it even more valuable from the monitoring POV.