A generic flow algorithm for shared filter ordering problems

We consider a fundamental flow maximization problem that arises during the evaluation of multiple overlapping queries defined on a data stream, in a heterogenous parallel environment. Each query is a conjunction of boolean filters, and each filter could be shared across multiple queries. We are required to design an evaluation plan that evaluates filters against stream items in order to determine the set of queries satisfied by each item. The evaluation plan specifies for each item: (i) the subset of filters evaluated for this item and the order of their evaluations, and (ii) the processor on which each filter evaluation occurs. Our goal is to design an evaluation plan which maximizes the total throughput (flow) of the stream handled by the plan, without violating the processor capacities. Filter ordering has received extensive attention in singleprocessor settings, with the objective of minimizing the total cost of filter evaluations: in particular, efficient (approximation) algorith...

• Type: Conference
• Year: 2008
• Where: PODS
• Authors: Zhen Liu, Srinivasan Parthasarathy 0002, Anand Ranganathan, Hao Yang
• Keywords: Database, Filter Ordering, Filter Ordering Algorithm, Filter Ordering Problem, PODS 2008