{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T21:39:30Z","timestamp":1773524370425,"version":"3.50.1"},"publisher-location":"New York, New York, USA","reference-count":38,"publisher":"ACM Press","license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"COMPETE","award":["POCI-01-0145- FEDER-007043"],"award-info":[{"award-number":["POCI-01-0145- FEDER-007043"]}]},{"name":"FCT","award":["MITP-TB\/CS\/0026\/2013"],"award-info":[{"award-number":["MITP-TB\/CS\/0026\/2013"]}]},{"DOI":"10.13039\/501100001871","name":"Fundacao para a Ciencia e a Tecnologia","doi-asserted-by":"publisher","award":["UID\/CEC\/00319\/2013"],"award-info":[{"award-number":["UID\/CEC\/00319\/2013"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundacao para a Ciencia e a Tecnologia","award":["002814\/2015"],"award-info":[{"award-number":["002814\/2015"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1145\/3105831.3105842","type":"proceedings-article","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T19:35:01Z","timestamp":1501270501000},"page":"242-252","source":"Crossref","is-referenced-by-count":16,"title":["Evaluating SQL-on-Hadoop for Big Data Warehousing on Not-So-Good Hardware"],"prefix":"10.1145","author":[{"given":"Maribel Yasmina","family":"Santos","sequence":"first","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlos","family":"Costa","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o","family":"Galv\u00e3o","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carina","family":"Andrade","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bruno Augusto","family":"Martinho","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Francisca Vale","family":"Lima","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduarda","family":"Costa","sequence":"additional","affiliation":[{"name":"University of Minho, ALGORITMI Research Centre, Portugal"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","reference":[{"key":"key-10.1145\/3105831.3105842-1","unstructured":"Armbrust, M. et al. 2015. Spark sql: Relational data processing in spark. Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data (2015), 1383--1394."},{"key":"key-10.1145\/3105831.3105842-2","doi-asserted-by":"crossref","unstructured":"Chandarana, P. and Vijayalakshmi, M. 2014. Big Data analytics frameworks. 2014 International Conference on Circuits, Systems, Communication and Information Technology Applications (CSCITA) (Apr. 2014), 430--434.","DOI":"10.1109\/CSCITA.2014.6839299"},{"key":"key-10.1145\/3105831.3105842-3","unstructured":"Chang, L. et al. 2014. HAWQ: a massively parallel processing SQL engine in hadoop. Proceedings of the 2014 ACM SIGMOD international conference on Management of data (2014), 1223--1234."},{"key":"key-10.1145\/3105831.3105842-4","doi-asserted-by":"crossref","unstructured":"Chen, M. et al. 2014. Big Data: A Survey. Mobile Networks and Applications. 19, 2 (Apr. 2014), 171--209.","DOI":"10.1007\/s11036-013-0489-0"},{"key":"key-10.1145\/3105831.3105842-5","unstructured":"Chen, Y. et al. 2014. A study of SQL-on-Hadoop systems. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics). 8807, (2014), 154--166."},{"key":"key-10.1145\/3105831.3105842-6","unstructured":"Choi, H. et al. 2013. Tajo: A distributed data warehouse system on large clusters. Data Engineering (ICDE), 2013 IEEE 29th International Conference on (2013), 1320--1323."},{"key":"key-10.1145\/3105831.3105842-7","unstructured":"Clegg, D. 2015. Evolving data warehouse and BI architectures: The big data challenge. TDWI Business Intelligence Journal. 20, 1 (2015), 19--24."},{"key":"key-10.1145\/3105831.3105842-8","doi-asserted-by":"crossref","unstructured":"Floratou, A. et al. 2014. SQL-on-Hadoop: Full Circle Back to Shared-nothing Database Architectures. Proc. VLDB Endow. 7, 12 (Aug. 2014), 1295--1306.","DOI":"10.14778\/2732977.2733002"},{"key":"key-10.1145\/3105831.3105842-9","unstructured":"Golab, L. and Johnson, T. 2014. Data stream warehousing. 2014 IEEE 30th International Conference on Data Engineering (ICDE) (Mar. 2014), 1290--1293."},{"key":"key-10.1145\/3105831.3105842-10","unstructured":"Goss, R.G. and Veeramuthu, K. 2013. Heading towards big data building a better data warehouse for more data, more speed, and more users. Advanced Semiconductor Manufacturing Conference (ASMC), 2013 24th Annual SEMI (2013), 220--225."},{"key":"key-10.1145\/3105831.3105842-11","doi-asserted-by":"crossref","unstructured":"Hashem, I.A.T. et al. 2015. The rise of \"big data\" on cloud computing: Review and open research issues. Information Systems. 47, (Jan. 2015), 98--115.","DOI":"10.1016\/j.is.2014.07.006"},{"key":"key-10.1145\/3105831.3105842-12","doi-asserted-by":"crossref","unstructured":"Hausenblas, M. and Nadeau, J. 2013. Apache drill: interactive ad-hoc analysis at scale. Big Data. 1, 2 (2013), 100--104.","DOI":"10.1089\/big.2013.0011"},{"key":"key-10.1145\/3105831.3105842-13","unstructured":"Hive LLAP Documentation: 2016. https:\/\/cwiki.apache.org\/confluence\/display\/Hive\/LLAP. Accessed: 2016-11-01."},{"key":"key-10.1145\/3105831.3105842-14","doi-asserted-by":"crossref","unstructured":"Huai, Y. et al. 2014. Major Technical Advancements in Apache Hive. Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data (New York, NY, USA, 2014), 1235--1246.","DOI":"10.1145\/2588555.2595630"},{"key":"key-10.1145\/3105831.3105842-15","unstructured":"Kimball, R. and Ross, M. 2013. The data warehouse toolkit: The definitive guide to dimensional modeling. John Wiley & Sons."},{"key":"key-10.1145\/3105831.3105842-16","unstructured":"Kobielus, J. 2012. Hadoop: Nucleus of the next-generation big data warehouse. IBM Data Management Magazine."},{"key":"key-10.1145\/3105831.3105842-17","unstructured":"Kornacker, M. et al. 2015. Impala: A modern, open-source sql engine for hadoop. Proc. CIDR'15 (California, USA, 2015)."},{"key":"key-10.1145\/3105831.3105842-18","doi-asserted-by":"crossref","unstructured":"Krishnan, K. 2013. Data Warehousing in the Age of Big Data. Morgan Kaufmann Publishers Inc.","DOI":"10.1016\/B978-0-12-405891-0.00006-4"},{"key":"key-10.1145\/3105831.3105842-19","doi-asserted-by":"crossref","unstructured":"Madden, S. 2012. From databases to big data. IEEE Internet Computing. 16, 3 (2012), 4--6.","DOI":"10.1109\/MIC.2012.50"},{"key":"key-10.1145\/3105831.3105842-20","unstructured":"Manyika, J. et al. 2011. Big data: The next frontier for innovation, competition, and productivity. McKinsey Global Institute."},{"key":"key-10.1145\/3105831.3105842-21","unstructured":"Marz, N. and Warren, J. 2015. Big Data: Principles and best practices of scalable realtime data systems. Manning Publications Co."},{"key":"key-10.1145\/3105831.3105842-22","doi-asserted-by":"crossref","unstructured":"Mohanty, S. et al. 2013. Big Data imperatives: enterprise Big Data warehouse, BI implementations and analytics. Apress.","DOI":"10.1007\/978-1-4302-4873-6"},{"key":"key-10.1145\/3105831.3105842-23","doi-asserted-by":"crossref","unstructured":"Murthy, R. and Goel, R. 2012. Peregrine: Low-latency Queries on Hive Warehouse Data. XRDS. 19, 1 (Sep. 2012), 40--43.","DOI":"10.1145\/2331042.2331056"},{"key":"key-10.1145\/3105831.3105842-24","unstructured":"NBD-PWG 2015. NIST Big Data Interoperability Framework: Volume 6, Reference Architecture. Technical Report #NIST SP 1500-6. National Institute of Standards and Technology."},{"key":"key-10.1145\/3105831.3105842-25","doi-asserted-by":"crossref","unstructured":"Philip Chen, C.L. and Zhang, C.-Y. 2014. Data-intensive applications, challenges, techniques and technologies: A survey on Big Data. Information Sciences. 275, (Aug. 2014), 314--347.","DOI":"10.1016\/j.ins.2014.01.015"},{"key":"key-10.1145\/3105831.3105842-26","unstructured":"Presto | Distributed SQL Query Engine for Big Data: 2016. https:\/\/prestodb.io\/. Accessed: 2016-10-23."},{"key":"key-10.1145\/3105831.3105842-27","unstructured":"Russom, P. 2016. Data Warehouse Modernization in the Age of Big Data Analytics. The Data Warehouse Institute."},{"key":"key-10.1145\/3105831.3105842-28","unstructured":"Russom, P. 2014. Evolving Data Warehouse Architectures in the Age of Big Data. The Data Warehouse Institute."},{"key":"key-10.1145\/3105831.3105842-29","unstructured":"Shvachko, K. et al. 2010. The Hadoop Distributed File System. 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST) (May 2010), 1--10."},{"key":"key-10.1145\/3105831.3105842-30","unstructured":"Sun, L. et al. 2013. Present Situation and Prospect of Data Warehouse Architecture under the Background of Big Data. Information Science and Cloud Computing Companion (ISCC-C), 2013 International Conference on (2013), 529--535."},{"key":"key-10.1145\/3105831.3105842-31","doi-asserted-by":"crossref","unstructured":"Thusoo, A. et al. 2010. Data Warehousing and Analytics Infrastructure at Facebook. Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data (New York, NY, USA, 2010), 1013--1020.","DOI":"10.1145\/1807167.1807278"},{"key":"key-10.1145\/3105831.3105842-32","unstructured":"Thusoo, A. et al. 2010. Hive-a petabyte scale data warehouse using hadoop. IEEE 26th International Conference on Data Engineering (ICDE) (2010), 996--1005."},{"key":"key-10.1145\/3105831.3105842-33","doi-asserted-by":"crossref","unstructured":"TPC Benchmark ™ H (TPC-H): 2016. http:\/\/www.tpc.org\/tpc_documents_current_versions\/pdf\/tpc-h_v2.17.1.pdf. Accessed: 2016-11-01.","DOI":"10.1109\/ICCE-Berlin.2016.7684695"},{"key":"key-10.1145\/3105831.3105842-34","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K. et al. 2013. Apache Hadoop YARN: Yet Another Resource Negotiator. Proceedings of the 4th Annual Symposium on Cloud Computing (New York, NY, USA, 2013), 5:1--5:16.","DOI":"10.1145\/2523616.2523633"},{"key":"key-10.1145\/3105831.3105842-35","unstructured":"Wang, H. et al. 2011. LinearDB: A Relational Approach to Make Data Warehouse Scale Like MapReduce. Database Systems for Advanced Applications. J.X. Yu et al., eds. Springer Berlin Heidelberg. 306--320."},{"key":"key-10.1145\/3105831.3105842-36","unstructured":"Ward, J.S. and Barker, A. 2013. Undefined By Data: A Survey of Big Data Definitions. arXiv:1309.5821 [cs.DB]. (Sep. 2013)."},{"key":"key-10.1145\/3105831.3105842-37","unstructured":"White, T. 2015. Hadoop: The Definitive Guide: Storage and Analysis at Internet Scale. O'Reilly Media."},{"key":"key-10.1145\/3105831.3105842-38","doi-asserted-by":"crossref","unstructured":"Wouw, S. van et al. 2015. An Empirical Performance Evaluation of Distributed SQL Query Engines. Proceedings of the 6th ACM\/SPEC International Conference on Performance Engineering (New York, NY, USA, 2015), 123--131.","DOI":"10.1145\/2668930.2688053"}],"event":{"name":"the 21st International Database Engineering & Applications Symposium","location":"Bristol, United Kingdom","acronym":"IDEAS 2017","number":"21","sponsor":["Univ of the West of England, University of the West of England","BytePress","Concordia University"],"start":{"date-parts":[[2017,7,12]]},"end":{"date-parts":[[2017,7,14]]}},"container-title":["Proceedings of the 21st International Database Engineering & Applications Symposium on - IDEAS 2017"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3105831.3105842","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/dl.acm.org\/ft_gateway.cfm?id=3105842&ftid=1896571&dwn=1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T18:41:57Z","timestamp":1750790517000},"score":1,"resource":{"primary":{"URL":"http:\/\/dl.acm.org\/citation.cfm?doid=3105831.3105842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1145\/3105831.3105842","relation":{},"subject":[],"published":{"date-parts":[[2017]]}}}