Can Modern Graph Processing Engines Run Concurrent Queries Efficiently?

Abstract

Analytic graph processing has witnessed an ever-growing interest both in industry and academia with the focus on providing the most effective algorithm implementations to maximize single-query performance. In a complex application scenario, where multiple users issue concurrent queries to the analytic graph processing engine, the major performance metric is throughput rather than single-query elapsed time. As of today, there is no single-node graph engine that is designed for concurrent graph processing running multiple queries in parallel.In this work, we analyze the single-node graph engine Galois and extend it to run multiple graph queries concurrently. We perform an extensive evaluation of Galois for various graph algorithms and data sets to gain a fundamental understanding of the performance bottlenecks of existing graph engines. Finally, we derive important insights and conclude that modern graph engines cannot be easily adapted to handle concurrent graph queries efficiently.