1 Introduction
Cloud storage systems keep gaining attentions from both academia and industry nowadays. From classical systems for general data services, such as Google's GFS [1], Amazon's Dynamo [2], Facebook's Cassandra [3], to newly designed systems with specialities, such as Haystack [4], Megastore [5], Spanner [6], various distributed storage systems were constructed to satisfy the increasing demand of online data-intensive applications that require massive scalability, efficient manageability, reliable availability, and low latency in the storage layer. Many works have been proposed for designing new indexing scheme and data management system to support large-scale data analytical jobs and high concurrent OLTP queries [7], [8], [9], [10].