Servicing Mixed Data Intensive Query Workloads

摘要: When data analysis applications are employed in a multiclient environment, server must service multiple simultaneous queries, each of which may employ complex user-defined structures and operations on the data. It is then necessary to harness interand intra-query commonalities system resources improve performance server. We have developed framework customizable middleware enable reuse intermediate final results among through an in-memory semantic cache transformation functions. Since such as processing power memory space limited machine hosting server, effective scheduling incoming queries efficient replacement policies challenging issues that be addressed. addressed problem earlier work, this paper we describe evaluate several policies. present experimental evaluation shared-memory parallel using two from different domains.