Distributed RDF query answering with dynamic data exchange

Evaluating joins over RDF data stored in a shared-nothing server cluster is key to processing truly large RDF datasets. To the best of our knowledge, the existing approaches use a variant of the data exchange operator that is inserted into the query plan statically (i.e., at query compile time) to s...

全面介紹

書目詳細資料
Main Authors: Potter, A, Motik, B, Nenov, Y, Horrocks, I
格式: Conference item
出版: Springer 2016
_version_ 1826299901930110976
author Potter, A
Motik, B
Nenov, Y
Horrocks, I
author_facet Potter, A
Motik, B
Nenov, Y
Horrocks, I
author_sort Potter, A
collection OXFORD
description Evaluating joins over RDF data stored in a shared-nothing server cluster is key to processing truly large RDF datasets. To the best of our knowledge, the existing approaches use a variant of the data exchange operator that is inserted into the query plan statically (i.e., at query compile time) to shuffle data between servers. We argue that such approaches often miss opportunities for local computation, and we present a novel solution to distributed query answering that consists of two main components. First, we present a query answering algorithm based on dynamic data exchange, which exploits data locality to maximise the amount of computation on a single server. Second, we present a partitioning algorithm for RDF data based on graph partitioning whose aim is to increase data locality. We have implemented our approach in the RDFox system, and our performance evaluation suggests that our techniques outperform the state of the art by up to an order of magnitude in terms of query evaluation times, network communication, and memory use.
first_indexed 2024-03-07T05:08:59Z
format Conference item
id oxford-uuid:daea191b-a3d0-4c5f-95fe-6ca5280b0e6a
institution University of Oxford
last_indexed 2024-03-07T05:08:59Z
publishDate 2016
publisher Springer
record_format dspace
spelling oxford-uuid:daea191b-a3d0-4c5f-95fe-6ca5280b0e6a2022-03-27T09:06:36ZDistributed RDF query answering with dynamic data exchangeConference itemhttp://purl.org/coar/resource_type/c_5794uuid:daea191b-a3d0-4c5f-95fe-6ca5280b0e6aSymplectic Elements at OxfordSpringer2016Potter, AMotik, BNenov, YHorrocks, IEvaluating joins over RDF data stored in a shared-nothing server cluster is key to processing truly large RDF datasets. To the best of our knowledge, the existing approaches use a variant of the data exchange operator that is inserted into the query plan statically (i.e., at query compile time) to shuffle data between servers. We argue that such approaches often miss opportunities for local computation, and we present a novel solution to distributed query answering that consists of two main components. First, we present a query answering algorithm based on dynamic data exchange, which exploits data locality to maximise the amount of computation on a single server. Second, we present a partitioning algorithm for RDF data based on graph partitioning whose aim is to increase data locality. We have implemented our approach in the RDFox system, and our performance evaluation suggests that our techniques outperform the state of the art by up to an order of magnitude in terms of query evaluation times, network communication, and memory use.
spellingShingle Potter, A
Motik, B
Nenov, Y
Horrocks, I
Distributed RDF query answering with dynamic data exchange
title Distributed RDF query answering with dynamic data exchange
title_full Distributed RDF query answering with dynamic data exchange
title_fullStr Distributed RDF query answering with dynamic data exchange
title_full_unstemmed Distributed RDF query answering with dynamic data exchange
title_short Distributed RDF query answering with dynamic data exchange
title_sort distributed rdf query answering with dynamic data exchange
work_keys_str_mv AT pottera distributedrdfqueryansweringwithdynamicdataexchange
AT motikb distributedrdfqueryansweringwithdynamicdataexchange
AT nenovy distributedrdfqueryansweringwithdynamicdataexchange
AT horrocksi distributedrdfqueryansweringwithdynamicdataexchange