Highspeed Graph Processing Exploiting Main-Memory Column Stores

Abstract

A popular belief in the graph database community is that relational database management systems are generally ill-suited for efficient graph processing. This might apply for analytic graph queries performing iterative computations on the graph, but does not necessarily hold true for short-running, OLTP-style graph queries. In this paper we argue that, instead of extending a graph database management system with traditional relational operators—predicate evaluation, sorting, grouping, and aggregations among others—one should consider adding a graph abstraction and graph-specific operations, such as graph traversals and pattern matching, to relational database management systems. We use an exemplary query from the interactive query workload of the ldbc social network benchmark and run it against our enhanced in-memory, columnar relational database system to support our claims. Our performance measurements indicate that a columnar rdbms—extended by graph-specific operators and data structures—can serve as a foundation for high-speed graph processing on big memory machines with non-uniform memory access and a large number of available cores.