{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T01:59:05Z","timestamp":1725847145682},"publisher-location":"Cham","reference-count":17,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319290058"},{"type":"electronic","value":"9783319290065"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-29006-5_6","type":"book-chapter","created":{"date-parts":[[2016,1,8]],"date-time":"2016-01-08T11:17:54Z","timestamp":1452251874000},"page":"67-80","source":"Crossref","is-referenced-by-count":0,"title":["Evolution from Shark to Spark SQL: Preliminary Analysis and Qualitative Evaluation"],"prefix":"10.1007","author":[{"given":"Xinhui","family":"Tian","sequence":"first","affiliation":[]},{"given":"Gang","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Xiexuan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Jingwei","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,1,9]]},"reference":[{"key":"6_CR1","unstructured":"Big Data Benchmark. https:\/\/amplab.cs.berkeley.edu\/benchmark\/"},{"key":"6_CR2","unstructured":"Spark JIRA. https:\/\/issues.apache.org\/jira\/browse\/SPARK\/"},{"key":"6_CR3","doi-asserted-by":"crossref","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. In: SIGMOD 2015, ACM, New York (2015)","DOI":"10.1145\/2723372.2742797"},{"key":"6_CR4","unstructured":"Dean, J., Ghemawat, S.: Mapreduce: simplified data processing on large clusters. In: OSDI 2004, USENIX Association, Berkeley (2004)"},{"issue":"12","key":"6_CR5","doi-asserted-by":"publisher","first-page":"1295","DOI":"10.14778\/2732977.2733002","volume":"7","author":"A Floratou","year":"2014","unstructured":"Floratou, A., Minhas, U.F., \u00d6zcan, F.: SQL-on-hadoop: Full circle back to shared-nothing database architectures. Proc. VLDB Endowment 7(12), 1295\u20131306 (2014)","journal-title":"Proc. VLDB Endowment"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Huang, S., Huang, J., Dai, J., Xie, T., Huang, B.: The hibench benchmark suite: characterization of the mapreduce-based data analysis. In: 2010 IEEE 26th International Conference on Data Engineering Workshops (ICDEW), pp. 41\u201351. IEEE (2010)","DOI":"10.1109\/ICDEW.2010.5452747"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: EuroSys 2007, New York (2007)","DOI":"10.1145\/1272996.1273005"},{"key":"6_CR8","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., et al.: Impala: a modern, open-source SQL engine for hadoop. In: Proceedings of the Conference on Innovative Data Systems Research CIDR 2015 (2015)","DOI":"10.1007\/978-3-658-11589-0_8"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Li, M., Tan, J., Wang, Y., Zhang, L., Salapura, V.: Sparkbench: a comprehensive benchmarking suite for in memory data analytic platform spark. In: CF 2015, pp. 53:1\u201353:8. ACM, New York (2015)","DOI":"10.1145\/2742854.2747283"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Lu, L., Arpaci-Dusseau, A.C., Arpaci-Dusseau, R.H., Lu, S.: A study of linux file system evolution. In: FAST 2013, USENIX Association, Berkeley (2013)","DOI":"10.1145\/2560012"},{"issue":"1\u20132","key":"6_CR11","doi-asserted-by":"publisher","first-page":"330","DOI":"10.14778\/1920841.1920886","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. Proc. VLDB Endowment 3(1\u20132), 330\u2013339 (2010)","journal-title":"Proc. VLDB Endowment"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Saha, B., Shah, H., Seth, S., Vijayaraghavan, G., Murthy, A., Curino, C.: Apache tez: a unifying framework for modeling and building data processing applications. In: SIGMOD 2015, New York (2015)","DOI":"10.1145\/2723372.2742790"},{"issue":"2","key":"6_CR13","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.14778\/1687553.1687609","volume":"2","author":"A Thusoo","year":"2009","unstructured":"Thusoo, A., Sarma, J.S., Jain, N., Shao, Z., Chakka, P., Anthony, S., Liu, H., Wyckoff, P., Murthy, R.: Hive: a warehousing solution over a map-reduce framework. Proc. VLDB Endow. 2(2), 1626\u20131629 (2009)","journal-title":"Proc. VLDB Endow."},{"key":"6_CR14","unstructured":"Wang, L., Zhan, J., Luo, C., Zhu, Y., Yang, Q., He, Y., Gao, W., Jia, Z., Shi, Y., Zhang, S., Zheng, C., Lu, G., Zhan, K., Li, X., Qiu, B.: Bigdatabench: a big data benchmark suite from internet services. In: 20th IEEE International Symposium on High Performance Computer Architecture, HPCA 2014, Orlando, FL, USA, February 15\u201319, 2014, pp. 488\u2013499 (2014)"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Xin, R.S., Rosen, J., Zaharia, M., Franklin, M.J., Shenker, S., Stoica, I.: Shark: SQL and rich analytics at scale. In: Proceedings of the 2013 ACM SIGMOD International Conference on Management of Data, pp. 13\u201324. ACM (2013)","DOI":"10.21236\/ADA570737"},{"key":"6_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1007\/978-3-319-13021-7_12","volume-title":"Big Data Benchmarks, Performance Optimization, and Emerging Hardware","author":"Y Chen","year":"2014","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: Zhan, J., Rui, H., Weng, C. (eds.) BPOE 2014. LNCS, vol. 8807, pp. 154\u2013166. Springer, Heidelberg (2014)"},{"key":"6_CR17","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., Franklin, M.J., Shenker, S., Stoica, I.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: NSDI 2012, USENIX Association, Berkeley (2012)"}],"container-title":["Lecture Notes in Computer Science","Big Data Benchmarks, Performance Optimization, and Emerging Hardware"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-29006-5_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T05:14:30Z","timestamp":1654060470000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-29006-5_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319290058","9783319290065"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-29006-5_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2016]]}}}