On Cache Replacement Policies for Servicing Mixed Data Intensive Query Workloads

When data analysis applicationsare employed in a multi-client environment, a data server must service multiple si-multaneous queries, each of which may employ complex user-defined data structures and operations on the data. It is then necessary to harness inter- and intra-query com-monalitiesand system resources to improve the performance of the data server. We have developed a framework and customizable middleware to enable reuse of intermediate and final results among queries, through an in-memory ac-tive semantic cache and user-defined transformation func-tions. Since resources such as processing power and mem-ory space are limited on the machine hosting the server, ef-fective scheduling of incoming queries and efficient cache replacement policies are challenging issues that must be ad-dressed. We have worked on the scheduling problem in ear-lier work, and in this paper we describe and evaluate several cache replacement policies. We present experimental eval-uation of the policies on a shared-memory parallel system using two applications from different application domains.