{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T18:58:08Z","timestamp":1778266688688,"version":"3.51.4"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030596118","type":"print"},{"value":"9783030596125","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-59612-5_2","type":"book-chapter","created":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T15:56:47Z","timestamp":1600358207000},"page":"13-22","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A Performance Prediction Model for Spark Applications"],"prefix":"10.1007","author":[{"given":"Muhammad Usama","family":"Javaid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmed Amir","family":"Kanoun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Florian","family":"Demesmaeker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amine","family":"Ghrab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sabri","family":"Skhiri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.future.2018.06.032","volume":"89","author":"Z Chao","year":"2018","unstructured":"Chao, Z., Shi, S., Gao, H., Luo, J., Wang, H.: A gray-box performance model for apache spark. Future Gener. Comput. Syst. 89, 58\u201367 (2018)","journal-title":"Future Gener. Comput. Syst."},{"key":"2_CR2","unstructured":"Zaharia, M., et al.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, NSDI 2012, Berkeley, CA, USA, p. 2. USENIX Association (2012)"},{"key":"2_CR3","unstructured":"Herodotou, H., et al.: Starfish: a self-tuning system for big data analytics. In: CIDR, pp. 261\u2013272 (2011)"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Lama, P., Zhou, X.: Aroma: automated resource allocation and configuration of MapReduce environment in the cloud. In: Proceedings of the 9th International Conference on Autonomic Computing, ICAC 2012, pp. 63\u201372. ACM, New York (2012)","DOI":"10.1145\/2371536.2371547"},{"key":"2_CR5","unstructured":"Zaharia, M., Konwinski, A., Joseph, A.D., Katz, R., Stoica, I.: Improving MapReduce performance in heterogeneous environments. In: Proceedings of the 8th USENIX Conference on Operating Systems Design and Implementation, OSDI 2008, Berkeley, CA, USA, pp. 29\u201342. USENIX Association (2008)"},{"key":"2_CR6","first-page":"28","volume":"9","author":"K Kambatla","year":"2009","unstructured":"Kambatla, K., Pathak, A., Pucha, H.: Towards optimizing Hadoop provisioning in the cloud. Hot Top. Cloud Comput. 9, 28\u201330 (2009)","journal-title":"Hot Top. Cloud Comput."},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Wu, D., Gokhale, A.: A self-tuning system based on application profiling and performance analysis for optimizing Hadoop MapReduce cluster configuration. In: 20th Annual International Conference on High Performance Computing, pp. 89\u201398, December 2013","DOI":"10.1109\/HiPC.2013.6799133"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, R., Li, M., Hildebrand, D.: Finding the big data sweet spot: towards automatically recommending configurations for Hadoop clusters on docker containers. In: 2015 IEEE International Conference on Cloud Engineering, pp. 365\u2013368, March 2015","DOI":"10.1109\/IC2E.2015.101"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Wang, K., Khan, M.M.H.: Performance prediction for apache spark platform. In: Proceedings of the 2015 IEEE 17th International Conference on High Performance Computing and Communications, 2015 IEEE 7th International Symposium on Cyberspace Safety and Security, and 2015 IEEE 12th International Conference on Embedded Software and Systems, HPCC-CSS-ICESS 2015, Washington, DC, USA, pp. 166\u2013173. IEEE Computer Society (2015)","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Yigitbasi, N., Willke, T.L., Liao, G., Epema, D.H.J.: Towards machine learning-based auto-tuning of MapReduce. In: 2013 IEEE 21st International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems, pp. 11\u201320 (2013)","DOI":"10.1109\/MASCOTS.2013.9"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Singhal, R., Phalak, C., Singh, P.: Spark job performance analysis and prediction tool, pp. 49\u201350, April 2018","DOI":"10.1145\/3185768.3185772"},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.bdr.2017.05.001","volume":"11","author":"A Gounaris","year":"2017","unstructured":"Gounaris, A., Torres, J.: A methodology for spark parameter tuning. Big Data Res. 11, 22\u201332 (2017)","journal-title":"Big Data Res."},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Wang, G., Xu, J., He, B.: A novel method for tuning configuration parameters of spark based on machine learning. In: 2016 IEEE 18th International Conference on High Performance Computing and Communications, IEEE 14th International Conference on Smart City, IEEE 2nd International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS), pp. 586\u2013593, December 2016","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0088"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Bao, L., Liu, X., Chen, W.: Learning-based automatic parameter tuning for big data analytics frameworks. CoRR, abs\/1808.06008 (2018)","DOI":"10.1109\/BigData.2018.8622018"},{"issue":"4","key":"2_CR15","doi-asserted-by":"publisher","first-page":"3767","DOI":"10.1016\/j.aej.2018.03.006","volume":"57","author":"S Mustafa","year":"2018","unstructured":"Mustafa, S., Elghandour, I., Ismail, M.A.: A machine learning approach for predicting execution time of spark jobs. Alexandria Eng. J. 57(4), 3767\u20133778 (2018)","journal-title":"Alexandria Eng. J."},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Herodotou, H., Babu, S.: Profiling, what-if analysis, and cost-based optimization of MapReduce programs (2011)","DOI":"10.14778\/3402707.3402746"}],"container-title":["Lecture Notes in Computer Science","Big Data \u2013 BigData 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59612-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:31:11Z","timestamp":1726662671000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59612-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030596118","9783030596125"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59612-5_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 September 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"BIGDATA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Big Data","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Honolulu, HI","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bigdata2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.bigdatacongress.org\/2020\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}