{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T06:24:28Z","timestamp":1789194268976,"version":"build-2803163510"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T00:00:00Z","timestamp":1549843200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"European Regional Development Funds","award":["MOBTT75"],"award-info":[{"award-number":["MOBTT75"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2019,12]]},"DOI":"10.1007\/s10586-019-02914-4","type":"journal-article","created":{"date-parts":[[2019,2,11]],"date-time":"2019-02-11T12:56:17Z","timestamp":1549889777000},"page":"1347-1377","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Big SQL systems: an experimental evaluation"],"prefix":"10.1007","volume":"22","author":[{"given":"Victor","family":"Aluko","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2503-523X","authenticated-orcid":false,"given":"Sherif","family":"Sakr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,2,11]]},"reference":[{"issue":"12","key":"2914_CR1","doi-asserted-by":"publisher","first-page":"2050","DOI":"10.14778\/2824032.2824137","volume":"8","author":"D Abadi","year":"2015","unstructured":"Abadi, D., Babu, S., \u00d6zcan, F., Pandis, I.: Sql-on-hadoop systems: tutorial. Proc. VLDB Endow. 8(12), 2050\u20132051 (2015)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"2914_CR2","doi-asserted-by":"publisher","first-page":"922","DOI":"10.14778\/1687627.1687731","volume":"2","author":"A Abouzeid","year":"2009","unstructured":"Abouzeid, A., Bajda-Pawlikowski, K., Abadi, D., Silberschatz, A., Rasin, A.: Hadoopdb: an architectural hybrid of mapreduce and dbms technologies for analytical workloads. Proc. VLDB Endow. 2(1), 922\u2013933 (2009)","journal-title":"Proc. VLDB Endow."},{"issue":"10","key":"2914_CR3","first-page":"1151","volume":"11","author":"K Ammar","year":"2018","unstructured":"Ammar, K., \u00d6zsu, M.T.: Experimental analysis of distributed graph systems. PVLDB 11(10), 1151\u20131164 (2018)","journal-title":"PVLDB"},{"key":"2914_CR4","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2742797","volume-title":"Spark SQL: Relational Data Processing in Spark","author":"M Armbrust","year":"2015","unstructured":"Armbrust, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J., Ghodsi, A., Zaharia, M.: Spark SQL: Relational Data Processing in Spark. SIGMOD, Chicago (2015)"},{"key":"2914_CR5","doi-asserted-by":"crossref","unstructured":"Cao, P., Gowda, B., Lakshmi, S., Narasimhadevara, C., Nguyen, P., Poelman, J., Poess, M., Rabl, T.: From bigbench to tpcx-bb: standardization of a big data benchmark. In: Technology Conference on Performance Evaluation and Benchmarking, pp. 24\u201344. Springer (2016)","DOI":"10.1007\/978-3-319-54334-5_3"},{"issue":"4","key":"2914_CR6","first-page":"28","volume":"36","author":"P Carbone","year":"2015","unstructured":"Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., Tzoumas, K.: Apache flink: stream and batch processing in a single engine. Bull. IEEE Comput. Soc. Tech. Commun. Data Eng. 36(4), 28\u201338 (2015)","journal-title":"Bull. IEEE Comput. Soc. Tech. Commun. Data Eng."},{"key":"2914_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Y., Qin, X., Bian, H., Chen, J., Dong, Z., Du, X., Gao, Y., Liu, D., Lu, J., Zhang, H.: A study of sql-on-hadoop systems. In: Proceedings of the Workshop on Big Data Benchmarks, Performance Optimization, and Emerging Hardware, pp. 154\u2013166. Springer (2014)","DOI":"10.1007\/978-3-319-13021-7_12"},{"key":"2914_CR8","volume-title":"Tajo: A Distributed Data Warehouse System on Large Clusters","author":"H Choi","year":"2013","unstructured":"Choi, H., Son, J., Yang, H., Ryu, H., Lim, B., Kim, S., Chung, Y.D.: Tajo: A Distributed Data Warehouse System on Large Clusters. ICDE, Oslo (2013)"},{"key":"2914_CR9","unstructured":"Dean, J., Ghemawa, S.: MapReduce: Simplified Data Processing on Large Clusters. In: OSDI, pp. 137\u2013150 (2004)"},{"key":"2914_CR10","doi-asserted-by":"crossref","unstructured":"Floratou, A., \u00d6zcan, F., Schiefer, B.: Benchmarking sql-on-hadoop systems: Tpc or not tpc? In: Proceedings of the Workshop on Big Data Benchmarks, pp. 63\u201372, Springer (2014)","DOI":"10.1007\/978-3-319-20233-4_7"},{"key":"2914_CR11","doi-asserted-by":"crossref","unstructured":"Ghazal, A., Rabl, T., Hu, M., Raab, F., Poess, M., Crolotte, A., Jacobsen, H.-A.: Bigbench: towards an industry standard benchmark for big data analytics. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, pp. 1197\u20131208. ACM (2013)","DOI":"10.1145\/2463676.2463712"},{"key":"2914_CR12","doi-asserted-by":"crossref","unstructured":"Ghazal, A., Ivanov, T., Kostamaa, P., Crolotte, A., Voong, R., Al-Kateb, M., Ghazal, W., Zicari, R.V.: Bigbench V2: the new and improved bigbench. In: Proceedings of the 33rd IEEE International Conference on Data Engineering, ICDE 2017, San Diego, CA, USA, 19\u201322 April 2017, pp. 1225\u20131236 (2017)","DOI":"10.1109\/ICDE.2017.167"},{"key":"2914_CR13","doi-asserted-by":"publisher","DOI":"10.1145\/2588555.2595630","volume-title":"Major Technical Advancements in Apache Hive","author":"Y Huai","year":"2014","unstructured":"Huai, Y., Chauhan, A., Gates, A., Hagleitner, G., Hanson, E.N., O\u2019Malley, O., Pandey, J., Yuan, Y., Lee, R., Zhang, X.: Major Technical Advancements in Apache Hive. SIGMOD, Chicago (2014)"},{"key":"2914_CR14","doi-asserted-by":"crossref","unstructured":"Ivanov, T., Beer, M.-G.: Performance evaluation of spark sql using bigbench. In: Big Data Benchmarking, pp. 96\u2013116. Springer (2015)","DOI":"10.1007\/978-3-319-49748-8_6"},{"key":"2914_CR15","doi-asserted-by":"crossref","unstructured":"Ivanov, T., Singhal, R.: Abench: Big data architecture stack benchmark. In: Proceedings of the Companion of the 2018 ACM\/SPEC International Conference on Performance Engineering, ICPE 2018, Berlin, Germany, 09\u201313 April 2018, pp. 13\u201316 (2018)","DOI":"10.1145\/3185768.3186300"},{"key":"2914_CR16","unstructured":"Karimov, J., Rabl, T., Katsifodimos, A., Samarev, R., Heiskanen, H., Markl, V.: Benchmarking distributed stream data processing systems. In: 34th IEEE International Conference on Data Engineering, ICDE 2018, Paris, France, 16\u201319 April 2018, pp. 1507\u20131518, (2018)"},{"key":"2914_CR17","doi-asserted-by":"crossref","unstructured":"Kornacker, M., Behm, A., Bittorf, V., Bobrovytsky, T., Ching, C., Choi, A., Erickson, J., Grund, M., Hecht, D., Jacobs, M., Joshi, I., Kuff, L., Kumar, D., Leblang, A., Li, N., Pandis, I., Robinson, H., Rorke, D., Rus, S., Russell, J., Tsirogiannis, D., Wanderman-Milne, S., Yoder, M.: Impala: A Modern. Open-Source SQL Engine for Hadoop. In: Proceedings of the CIDR (2015)","DOI":"10.1007\/978-3-658-11589-0_8"},{"issue":"70","key":"2914_CR18","first-page":"1","volume":"6","author":"D Laney","year":"2001","unstructured":"Laney, D.: 3d data management: controlling data volume, velocity and variety. META Group Res. Note 6(70), 1 (2001)","journal-title":"META Group Res. Note"},{"issue":"5","key":"2914_CR19","first-page":"835","volume":"11","author":"Y Liu","year":"2018","unstructured":"Liu, Y., Guo, S., Hu, S., Rabl, T., Jacobsen, H., Li, J., Wang, J.: Performance evaluation and optimization of multi-dimensional indexes in hive. IEEE Trans. Serv. Comput. 11(5), 835\u2013849 (2018)","journal-title":"IEEE Trans. Serv. Comput."},{"issue":"1","key":"2914_CR20","first-page":"330","volume":"3","author":"S Melnik","year":"2010","unstructured":"Melnik, S., Gubarev, A., Long, J.J., Romer, G., Shivakumar, S., Tolton, M., Vassilakis, T.: Dremel: interactive analysis of web-scale datasets. PVLDB 3(1), 330\u2013339 (2010)","journal-title":"PVLDB"},{"issue":"3","key":"2914_CR21","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1007\/s10619-014-7172-8","volume":"34","author":"A Mesmoudi","year":"2016","unstructured":"Mesmoudi, A., Hacid, M.-S., Toumani, F.: Benchmarking sql on mapreduce systems using large astronomy databases. Distrib. Parall. Databases 34(3), 347\u2013378 (2016)","journal-title":"Distrib. Parall. Databases"},{"key":"2914_CR22","unstructured":"Nambiar, R.O., Poess, M.: The making of tpc-ds. In: Proceedings of the 32nd international conference on Very large data bases, pp. 1049\u20131058. VLDB Endowment (2006)"},{"key":"2914_CR23","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D.J., DeWitt, D.J., Madden, S., Stonebraker, M.: A comparison of approaches to large-scale data analysis. In: SIGMOD (2009)","DOI":"10.1145\/1559845.1559865"},{"key":"2914_CR24","doi-asserted-by":"crossref","unstructured":"Qin, X., Chen, Y., Chen, J., Li, S., Liu, J., Zhang, H.: The performance of sql-on-hadoop systems-an experimental study. In: 2017 IEEE International Congress on Big Data (BigData Congress), pp. 464\u2013471. IEEE (2017)","DOI":"10.1109\/BigDataCongress.2017.68"},{"key":"2914_CR25","doi-asserted-by":"crossref","unstructured":"Saha, B., Shah, H., Seth, S., Vijayaraghavan, G., Murthy, A.C., Curino, C.: Apache Tez: A unifying framework for modeling and building data processing applications. In: SIGMOD (2015)","DOI":"10.1145\/2723372.2742790"},{"key":"2914_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-38776-5","volume-title":"Big Data 2.0 Processing Systems: A Survey","author":"S Sakr","year":"2016","unstructured":"Sakr, S.: Big Data 2.0 Processing Systems: A Survey. Springer, New York (2016)"},{"issue":"1","key":"2914_CR27","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1145\/2522968.2522979","volume":"46","author":"S Sakr","year":"2013","unstructured":"Sakr, S., Liu, A., Fayoumi, A.G.: The family of mapreduce and large-scale data processing systems. ACM Comput. Surv. 46(1), 11 (2013)","journal-title":"ACM Comput. Surv."},{"key":"2914_CR28","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In: MSST (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"2914_CR29","doi-asserted-by":"crossref","unstructured":"Thusoo, A., Shao, Z., Anthony, S., Borthakur, D., Jain, N., Sarma, J.S., Murthy, R., Liu, H.: Data warehousing and analytics infrastructure at Facebook. In: SIGMOD (2010)","DOI":"10.1145\/1807167.1807278"},{"key":"2914_CR30","doi-asserted-by":"crossref","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., Evans, R., Graves, T., Lowe, J., Shah, H., Seth, S., Saha, B., Curino, C., O\u2019Malley, O., Radia, S., Reed, B., Baldeschwieler, E.: Apache Hadoop YARN: yet another resource negotiator. In: SOCC (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"2914_CR31","volume-title":"Hadoop: The Definitive Guide","author":"T White","year":"2012","unstructured":"White, T.: Hadoop: The Definitive Guide. O\u2019Reilly Media, Newton (2012)"},{"key":"2914_CR32","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: HotCloud (2010)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10586-019-02914-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02914-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-019-02914-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T19:15:55Z","timestamp":1581362155000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10586-019-02914-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,11]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["2914"],"URL":"https:\/\/doi.org\/10.1007\/s10586-019-02914-4","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,11]]},"assertion":[{"value":"26 August 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 February 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}