Graph Placement and Query Performance in a Data Center

Most real-world networks (including financial, health, transportation, social, citation, and sensor networks) evolve over time. Their evolution can be modeled as a series of graph snapshots that represent those networks at different points in time. Our distributed dynamic graph database, G*, provided efficient cluster-based storage and querying of graph snapshots by taking advantage of their commonalities. With the modern Internet of Things, however, the environment of continuously generated graph snapshots imbues classic challenges of data distribution with renewed significance. In response to this, we have extended G* to address these new challenges. In this paper we examine two snapshot placement schemes and their effects on query performance in a cloud / data center environment.