Optimizing Data Partitioning for Data-Parallel Computing
Performance of data-parallel computing (e.g., MapReduce, DryadLINQ) heavily depends on its data partitions. Solutions implemented by the current state of the art systems are far from optimal. Techniques proposed by the database community to find optimal data partitions are not directly applicable when complex user-defined functions and data models are involved. The authors outline their solution, which draws expertise from various fields such as programming languages and optimization, and present their preliminary results. Recent advances in distributed execution engines and high-level language support have greatly simplified the development of large-scale, distributed data-intensive applications.