DaDiSi is an API to create and test data distribution policies in a (simulated) storage environment. With it you can create a virtual storage architecture and fill it with "data" that will be placed according to your description. This can be useful to evaluate properties like load balancing, distribution fairness, memory consumption or efficiency among others, and compare several strategies according to these parameters. Note however that the framework does not simulate the internal mechanisms of storage devices or interconnection networks, therefore any timing measure should be taken only as an indication of the performance of the strategy.
As a research tool, it has been used extensively to evaluate and compare several pseudo-randomized data distribution strategies like Consistent Hashing, CRUSH, RUSH, Share, Redundant Share and Random Slicing. The results of this evaluation can be seen in the paper "Reliable and Randomized Data Distribution Strategies for Large Scale Storage Systems".