Do We Need Specialized Graph Databases?: Benchmarking Real-Time Social Networking Applications

With the advent of online social networks, there is an increasing demand for storage and processing of graph-structured data. Social networking applications pose new challenges to data management systems due to demand for real-time querying and manipulation of the graph structure. Recently, several systems specialized systems for graph-structured data have been introduced. However, whether we should abandon mature RDBMS technology for graph databases remains an ongoing discussion. In this paper we present an graph database benchmarking architecture built on the existing LDBC Social Network Benchmark. Our proposed architecture stresses the systems with an interactive transactional workload to better simulate the real-time nature of social networking applications. Using this improved architecture, we evaluated a selection of specialized graph databases, RDF stores, and RDBMSes adapted for graphs. We do not find that specialized graph databases provide definitively better performance.