Autonomic storage system based on automatic learning

In this paper, we present a system capable of improving the I/O performance in an automatic way. This system is able to learn the behavior of the applications running on top and find the best data placement in the disk in order to improve the I/O performance. This system is built by three independent modules. The first one is able to learn the behavior of a workload in order to be able to reproduce its behavior later on, without a new execution. The second module is a drive modeler that is able to learn how a storage drive works taking it as a "black box". Finally, the third module generates a set of placement alternatives and uses the afore mentioned models to predict the performance each alternative will achieve. We tested the system with five benchmarks and the system was able to find better alternatives in most cases and improve the performance significantly (up to 225%). Most important, the performance predicted where always very accurate (less that 10% error).