{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T21:33:55Z","timestamp":1743111235730,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030129804"},{"type":"electronic","value":"9783030129811"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-12981-1_42","type":"book-chapter","created":{"date-parts":[[2019,2,6]],"date-time":"2019-02-06T16:59:55Z","timestamp":1549472395000},"page":"595-609","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["How Good is Query Optimizer in Spark?"],"prefix":"10.1007","author":[{"given":"Zujie","family":"Ren","sequence":"first","affiliation":[]},{"given":"Na","family":"Yun","sequence":"additional","affiliation":[]},{"given":"Youhuizi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Wan","sequence":"additional","affiliation":[]},{"given":"Yuan","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lihua","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Xinxin","family":"Fan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,7]]},"reference":[{"key":"42_CR1","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1186\/1471-2105-11-S12-S1","volume":"11","author":"RC Taylor","year":"2010","unstructured":"Taylor, R.C.: An overview of the Hadoop\/MapReduce\/HBase framework and its current applications in bioinformatics. BMC Bioinform. 11, S1 (2010)","journal-title":"BMC Bioinform."},{"issue":"1\u20132","key":"42_CR2","doi-asserted-by":"publisher","first-page":"330","DOI":"10.14778\/1920841.1920886","volume":"3","author":"S Melnik","year":"2010","unstructured":"Melnik, S., et al.: Dremel: interactive analysis of web-scale datasets. Proc. VLDB Endow. 3(1\u20132), 330\u2013339 (2010)","journal-title":"Proc. VLDB Endow."},{"issue":"4","key":"42_CR3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1002\/(SICI)1097-0134(19980301)30:4<357::AID-PROT3>3.0.CO;2-G","volume":"30","author":"P Ducarme","year":"1998","unstructured":"Ducarme, P., Rahman, M., Brasseur, R.: IMPALA: a simple restraint field to simulate the biological membrane in molecular structure studies. Proteins Struct. Funct. Bioinform. 30(4), 357\u2013371 (1998)","journal-title":"Proteins Struct. Funct. Bioinform."},{"key":"42_CR4","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In: USENIX Conference on Hot Topics in Cloud Computing, p. 10 (2010)"},{"issue":"3\u20134","key":"42_CR5","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1007\/s41060-016-0027-9","volume":"1","author":"S Salloum","year":"2016","unstructured":"Salloum, S., Dautov, R., Chen, X., Peng, P.X., Huang, J.Z.: Big data analytics on apache spark. Int. J. Data Sci. Anal. 1(3\u20134), 145\u2013164 (2016)","journal-title":"Int. J. Data Sci. Anal."},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Armbrust, M., et al.: Spark SQL: relational data processing in spark. In: SIGMOD 2015, pp. 1383\u20131394. ACM (2015)","DOI":"10.1145\/2723372.2742797"},{"issue":"11","key":"42_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M., et al.: Apache spark: a unified engine for big data processing. Commun. ACM 59(11), 56\u201365 (2016)","journal-title":"Commun. ACM"},{"key":"42_CR8","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/j.jss.2016.11.038","volume":"125","author":"J Ma","year":"2017","unstructured":"Ma, J., et al.: Logical query optimization for cloudera impala system. J. Syst. Softw. 125, 35\u201346 (2017)","journal-title":"J. Syst. Softw."},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Naacke, H., Cur\u00e9, O., Amann, B.: SPARQL query processing with apache spark. arXiv preprint arXiv:1604.08903 (2016)","DOI":"10.1145\/3078447.3078448"},{"issue":"3","key":"42_CR10","first-page":"19","volume":"18","author":"G Graefe","year":"1995","unstructured":"Graefe, G.: The cascades framework for query optimization. IEEE Data Eng. Bull. 18(3), 19\u201329 (1995)","journal-title":"IEEE Data Eng. Bull."},{"key":"42_CR11","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1007\/978-94-015-9198-0_74","volume-title":"Integrated Design and Manufacturing in Mechanical Engineering","author":"AMK Esawi","year":"1999","unstructured":"Esawi, A.M.K., Ashby, M.F.: Cost-based ranking for manufacturing process selection. In: Batoz, J.L., Chedmail, P., Cognet, G., Fortin, C. (eds.) Integrated Design and Manufacturing in Mechanical Engineering, pp. 603\u2013610. Springer, Dordrecht (1999). https:\/\/doi.org\/10.1007\/978-94-015-9198-0_74"},{"key":"42_CR12","unstructured":"Wu, J.-M., Zhou, J.: Research of optimization rule of SQL based on oracle database. J. Shaanxi Univ. Technol. (2013)"},{"issue":"4","key":"42_CR13","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/s007780050026","volume":"5","author":"G Antoshenkov","year":"1996","unstructured":"Antoshenkov, G., Ziauddin, M.: Query processing and optimization in oracle RDB. VLDB J. Int. J. Very Large Data Bases 5(4), 229\u2013237 (1996)","journal-title":"VLDB J. Int. J. Very Large Data Bases"},{"key":"42_CR14","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S.: An overview of query optimization in relational systems. In: Proceedings of the seventeenth ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems, pp. 34\u201343. ACM (1998)","DOI":"10.1145\/275487.275492"},{"issue":"11","key":"42_CR15","doi-asserted-by":"crossref","first-page":"1111","DOI":"10.14778\/3402707.3402746","volume":"4","author":"H Herodotou","year":"2011","unstructured":"Herodotou, H., Babu, S.: Profiling, what-if analysis, and cost-based optimization of mapreduce programs. Proc. VLDB Endow. 4(11), 1111\u20131122 (2011)","journal-title":"Proc. VLDB Endow."},{"key":"42_CR16","doi-asserted-by":"crossref","unstructured":"Chiba, T., Onodera, T.: Workload characterization and optimization of TPC-H queries on apache spark. In: IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), pp. 112\u2013121. IEEE (2016)","DOI":"10.1109\/ISPASS.2016.7482079"},{"key":"42_CR17","unstructured":"Liang, W., Zheng, Y.: TPC-H analysis and test tool design. Comput. Eng. Appl. (2007)"},{"key":"42_CR18","unstructured":"Transaction processing performance council. http:\/\/www.tpc.org"},{"issue":"1","key":"42_CR19","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1145\/234313.234367","volume":"28","author":"YE Ioannidis","year":"1996","unstructured":"Ioannidis, Y.E.: Query optimization. ACM Comput. Surv. (CSUR) 28(1), 121\u2013123 (1996)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"42_CR20","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1145\/335191.335419","volume":"29","author":"P Roy","year":"2000","unstructured":"Roy, P., Seshadri, S., Sudarshan, S., Bhobe, S.: Efficient and extensible algorithms for multi query optimization. ACM SIGMOD Rec. 29, 249\u2013260 (2000)","journal-title":"ACM SIGMOD Rec."},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Graefe, G., DeWitt, D.J.: The EXODUS Optimizer Generator, vol. 16. ACM (1987)","DOI":"10.1145\/38714.38734"},{"key":"42_CR22","unstructured":"Barbas, P.M.: Database query optimization, 21 January 2014. US Patent 8,635,206"},{"issue":"3","key":"42_CR23","doi-asserted-by":"publisher","first-page":"204","DOI":"10.14778\/2850583.2850594","volume":"9","author":"V Leis","year":"2015","unstructured":"Leis, V., Gubichev, A., Mirchev, A., Boncz, P., Kemper, A., Neumann, T.: How good are query optimizers, really? Proc. VLDB Endow. 9(3), 204\u2013215 (2015)","journal-title":"Proc. VLDB Endow."},{"key":"42_CR24","doi-asserted-by":"crossref","unstructured":"Kocsis, Z.A., Drake, J.H., Carson, D., Swan, J.: Automatic improvement of apache spark queries using semantics-preserving program reduction. In: Proceedings of the 2016 on Genetic and Evolutionary Computation Conference Companion, pp. 1141\u20131146. ACM (2016)","DOI":"10.1145\/2908961.2931692"},{"key":"42_CR25","unstructured":"Liu, C.: Research on SparkSQL query optimization based on cost model (2016)"},{"key":"42_CR26","unstructured":"Zhang, L.: Research on query analysis and optimization based on spark system (2016)"},{"key":"42_CR27","unstructured":"Wang, Z.: Spark issue. https:\/\/issues.apache.org\/jira\/browse\/SPARK-16026"}],"container-title":["Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","Collaborative Computing: Networking, Applications and Worksharing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-12981-1_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,26]],"date-time":"2020-11-26T22:18:17Z","timestamp":1606429097000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-12981-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030129804","9783030129811"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-12981-1_42","relation":{},"ISSN":["1867-8211","1867-822X"],"issn-type":[{"type":"print","value":"1867-8211"},{"type":"electronic","value":"1867-822X"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"7 February 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CollaborateCom","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Collaborative Computing: Networking, Applications and Worksharing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"colcom2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/collaboratecom.eai-conferences.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"http:\/\/confy.eai.eu","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"77","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"33","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"20","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"43% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information"}}]}}