GeaBase: a high-performance distributed graph database for industry-scale applications. (8th November 2019)

• Record Type: Journal Article
• Authors: Fu, Zhisong; Wu, Zhengwei; Li, Houyi; Li, Yize; Wu, Min; Chen, Xiaojie; Ye, Xiaomeng; Yu, Benquan; Hu, Xi
• Is Part Of: International journal of high performance computing and networking. Volume 15:Number 1/2(2019)
• Page Start: 12
• Page End: 21
• Publication Date: 2019-11-08
• Subjects: distributed -- graph database -- high-performance -- graph query language; High performance computing -- Periodicals; Computer networks -- Periodicals; High performance computing; Periodicals; 004.05
• Languages: English
• ISSNs: 1740-0562

Abstract

Graph analytics have been gaining traction rapidly in the past few years. It has a wide array of application areas in the industry, ranging from e-commerce, social networks and recommendation systems to fraud detection and virtually any problem that requires insights into data connections, not just data itself. In this paper, we present GeaBase, a new distributed graph database that provides the capability to store and analyse graph-structured data in real-time at massive scale. We describe the details of the system and the implementation, including novel update architecture, called update centre (UC), and a new language that is suitable for both graph traversal and analytics. We also compare the performance of GeaBase to a widely used open-source graph database Titan . Experiments show that GeaBase is up to 182x faster than Titan in our testing scenarios. We also achieve 22x higher throughput on social network workloads in the comparison.