Performance optimization for querying social network data
Abstract
In this paper, we report about benchmark experiments and results from optimizing database connectivity for querying social networking data from Apache Shindig in a Neo4j database. We built on our experiments from [1] and tried to improve performance of the current RESTful http connection in comparison to JDBC in order to fully utilize performance benefits of the graph database compared to relational database management systems. We implemented a database driver based on WebSockets. We found that BSON is a better data transfer format than JSON and compression increases performance in some settings while decreasing it in others. Multiple WebSocket connections are needed to scale to a high number of client requests and fully utilize database performance. Multi-threading is another key factor for scalability. Implementing a kind of stored procedure, we were able to further increase throughput and decrease response times.
mehrMehr zum Titel
| Titel | Performance optimization for querying social network data |
|---|---|
| Medien | Joint EDBT/ICDT 2014 Workshop GraphQ, Athens, Greece; 03/2014 |
| Verlag | --- |
| Heft | --- |
| Band | --- |
| ISBN | --- |
| Verfasser/Herausgeber | F. Holzschuher, Prof. Dr. René Peinl |
| Seiten | --- |
| Veröffentlichungsdatum | 03.03.2014 |
| Projekttitel | --- |
| Zitation | Holzschuher, F.; Peinl, René (2014): Performance optimization for querying social network data. Joint EDBT/ICDT 2014 Workshop GraphQ, Athens, Greece; 03/2014. |