SP^2Bench: A SPARQL Performance Benchmark

Abstract

Recently, the SPARQL query language for RDF has reached the W3C recommendation status. In response to this emerging standard, the database community is currently exploring efficient storage techniques for RDF data and evaluation strategies for SPARQL queries. A meaningful analysis and comparison of these approaches necessitates a comprehensive and universal benchmark platform. To this end, we have developed SP 2 Bench, a publicly available, language-specific SPARQL performance benchmark. SP 2 Bench is settled in the DBLP scenario and comprises both a data generator for creating arbitrarily large DBLP-like documents and a set of carefully designed benchmark queries. The generated documents mirror key characteristics and social-world distributions encountered in the original DBLP data set, while the queries implement meaningful requests on top of this data, covering a variety of SPARQL operator constellations and RDF access patterns. As a proof of concept, we apply SP 2 Bench to existing engines and discuss their strengths and weaknesses that follow immediately from the benchmark results.

An Efficient Light Solver for Querying the Semantic Web

“…Counter-intuitively, q6 is actually more difficult than q7. Possible reasons are given in [17]. Castor has better results than Sesame for the former query and behaves similarly to Sesame on the latter.…”

“…To assess the feasibility and the performances of our approach, we have run queries from the SPARQL Performance Benchmark (SP 2 Bench) [17]. SP 2 Bench consists of a deterministic program generating an RDF dataset of configurable size, and 12 representative queries.…”

Streaming the Web: Reasoning over dynamic data

“…In particular, they use simulated DBLP datasets created with the SP 2 Bench [90] and test the scalability on the input size (number of triples) and on the size of the window under analysis. The measured results show the benefits of integration and query optimization, with CQELS providing execution times that are up to more than 1000 times lower than the other approaches.…”

ParlBench: A SPARQL Benchmark for Electronic Publishing Applications

“…The SPARQL Performance Benchmark (SP 2 Bench) [7] is settled in the DBLP scenario. SP 2 Bench queries are carefully designed to test the behavior of RDF stores in relation to common SPARQL constructs, different operator constellations and RDF access patterns.…”