EDS: An Efficient Data Selection policy for search engine storage architectures

Xinhua Dong, Ruixuan Li, Heng He, Xiwu Gu, Mudar Sarem, Meikang Qiu, Keqin Li

Abstract: Highlights•We introduce, define and analyze the knapsack problem in different storage architectures.•We find some critical factors via derivation and comparison.•We present an Efficient Data Selection (EDS) policy for search engine cache management.•We carry out a series of experiments to study essential factors of the data selection.•Extensive experiments show that the EDS policy using static cache further improves the performance of search engines.