Social Network-Aware Disk Management
Disk access patterns of social networking applications are different from those of traditional applications. However, today's disk layout techniques are not adapted to social networking workloads and thus suffer in performance. In this paper, the authors first present disk layout techniques that leverage community structure in the social graph to make placement decisions. Second, they build a layout manager called the Bondhu system that incorporates the techniques. They integrate Bondhu into the popular Neo4j graph database engine. The trace driven experimental results show that the Bondhu system improves the median response time by as much as 48%.