Skip to Main content Skip to Navigation
Conference papers

Views and Transactional Storage for Large Graphs

Abstract : A growing number of applications store and analyze graph-structured data. These applications impose challenging infrastructure demands due to a need for scalable, high-throughput, and low-latency graph processing. Existing state-of-the-art storage systems and data processing systems are limited in at least one of these dimensions, and simply layering these technologies is inadequate.We present Concerto, a graph store based on distributed, in-memory data structures. In addition to enabling efficient graph traversals by co-locating graph nodes and associated edges where possible, Concerto provides transactional updates while scaling to hundreds of nodes. Concerto introduces graph views to denote sub-graphs on which user-defined functions can be invoked. Using graph views, programmers can perform event-driven analysis and dynamically optimize application performance. Our results show that Concerto is significantly faster than in-memory MySQL, in-memory Neo4j, and GemFire for graph insertions as well as graph queries. We demonstrate the utility of Concerto’s features in the design of two real-world applications: real-time incident impact analysis on a road network and targeted advertising in a social network.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.inria.fr/hal-01480781
Contributor : Hal Ifip <>
Submitted on : Wednesday, March 1, 2017 - 5:32:56 PM
Last modification on : Wednesday, August 7, 2019 - 12:18:06 PM
Document(s) archivé(s) le : Tuesday, May 30, 2017 - 6:02:41 PM

File

978-3-642-45065-5_15_Chapter.p...
Files produced by the author(s)

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Michael Lee, Indrajit Roy, Alvin Auyoung, Vanish Talwar, K. Jayaram, et al.. Views and Transactional Storage for Large Graphs. 14th International Middleware Conference (Middleware), Dec 2013, Beijing, China. pp.287-306, ⟨10.1007/978-3-642-45065-5_15⟩. ⟨hal-01480781⟩

Share

Metrics

Record views

178

Files downloads

392