@inproceedings{313c366aa3a440c3a106176b16eb02ec,
title = "Resource Planning for SPARQL Query Execution on Data Sharing Platforms",
abstract = "To increase performance, data sharing platforms often make use of clusters of nodes where certain tasks can be executed in parallel. Resource planning and especially deciding how many processors should be chosen to exploit parallel processing is complex in such a setup as increasing the number of processors does not always improve runtime due to communication overhead. Instead, there is usually an optimum number of processors for which using more or fewer processors leads to less efficient runtimes. In this paper, we present a cost model based on widely used statistics (VoiD) and show how to compute the optimum number of processors that should be used to evaluate a particular SPARQL query over a particular configuration and RDF dataset. Our first experiments show the general applicability of our approach but also how shortcomings in the used statistics limit the potential of optimization.",
keywords = "resource planning, SPARQL, data sharing",
author = "Stefan Hagedorn and Katja Hose and Kai-Uwe Sattler and J{\"u}rgen Umbrich",
year = "2014",
language = "English",
volume = "1264",
series = "CEUR Workshop Proceedings",
publisher = "CEUR Workshop Proceedings",
editor = "Olaf Hartig and Aidan Hogan and Juan Sequeda",
booktitle = "Consuming Linked Data (COLD 2014)",
note = "5th International Workshop on Consuming Linked Data (COLD 2014) ; Conference date: 20-10-2014",
}