A Demonstration of Lusail: Querying Linked Data at Scale

Essam Mansour, Ibrahim Abdelaziz, Mourad Ouzzani, Ashraf Aboulnaga, Panos Kalnis

Abstract

There has been a proliferation of datasets available as interlinked RDF data accessible through SPARQL endpoints. This has led to the emergence of various applications in life science, distributed social networks, and Internet of Things that need to integrate data from multiple endpoints. We will demonstrate Lusail; a system that supports the need of emerging applications to access tens to hundreds of geo-distributed datasets. Lusail is a geo-distributed graph engine for querying linked RDF data. Lusail delivers out- standing performance using (i) a novel locality-aware query decomposition technique that minimizes the intermediate data to be accessed by the subqueries, and (ii) selectivity-awareness and parallel query execution to reduce network latency and to increase parallelism. During the demo, the audience will be able to query actually deployed RDF end- points as well as large synthetic and real benchmarks that we have deployed in the public cloud. The demo will also show that Lusail outperforms state-of-the-art systems by orders of magnitude in terms of scalability and response time.
BibTeX
@inproceedings{mansour2017demonstration,
  author = {Essam Mansour and Ibrahim Abdelaziz and Mourad Ouzzani and Ashraf Aboulnaga and Panos Kalnis},
  title = {{A Demonstration of Lusail: Querying Linked Data at Scale}},
  booktitle = {SIGMOD},
  year = {2017},
  doi = {10.1145/3035918.3058731},
}

Loading related content...

Figure