{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T21:28:41Z","timestamp":1689888521332},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2019,6,17]],"date-time":"2019-06-17T00:00:00Z","timestamp":1560729600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,17]],"date-time":"2019-06-17T00:00:00Z","timestamp":1560729600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front. Comput. Sci."],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11704-018-6586-2","type":"journal-article","created":{"date-parts":[[2018,12,29]],"date-time":"2018-12-29T02:20:20Z","timestamp":1546050020000},"page":"960-975","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Reducing partition skew on MapReduce: an incremental allocation approach"],"prefix":"10.1007","volume":"13","author":[{"given":"Zhuo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Suo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Pan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhanhuai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,6,17]]},"reference":[{"issue":"1","key":"6586_CR1","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S. Mapreduce: simplified data processing on large clusters. Communications of the ACM, 2008, 51(1): 107\u2013113","journal-title":"Communications of the ACM"},{"issue":"3","key":"6586_CR2","first-page":"31","volume":"46","author":"F Li","year":"2014","unstructured":"Li F, Ooi B C, \u00d6zsu M T, Wu S. Distributed data management using mapreduce. ACM Computing Surveys (CSUR), 2014, 46(3): 31","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"6586_CR3","volume-title":"Hadoop","author":"A Hadoop","year":"2009","unstructured":"Hadoop A. Hadoop, 2009"},{"key":"6586_CR4","first-page":"57","volume-title":"Proceedings of the 7th Workshop on Large-Scale Distributed Systems for Information Retrieval","author":"J Lin","year":"2009","unstructured":"Lin J. The curse of zipf and limits to parallelization: a look at the stragglers problem in mapreduce. In: Proceedings of the 7th Workshop on Large-Scale Distributed Systems for Information Retrieval. 2009, 57\u201362"},{"key":"6586_CR5","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/SC.Companion.2012.253","volume-title":"Proceedings of the 2012^SC Companion: High Performance Computing, Networking Storage and Analysis","author":"K Ren","year":"2012","unstructured":"Ren K, Gibson G, Kwon Y C, Balazinska M, Howe B. Hadoop\u2019s adolescence; a comparative workloads analysis from three research clusters. In: Proceedings of the 2012 SC Companion: High Performance Computing, Networking Storage and Analysis. 2012, 1452"},{"key":"6586_CR6","volume-title":"Load balancing map-reduce communications for efficient executions of applications in a cloud","author":"S C Racha","year":"2012","unstructured":"Racha S C. Load balancing map-reduce communications for efficient executions of applications in a cloud. Project Report, 2012"},{"key":"6586_CR7","first-page":"2397","volume-title":"Proceedings of the 20th^ACM International Conference on Information and Knowledge Management","author":"L Kolb","year":"2011","unstructured":"Kolb L, Thor A, Rahm E. Block-based load balancing for entity resolution with mapreduce. In: Proceedings of the 20th ACM International Conference on Information and Knowledge Management. 2011, 2397\u20132400"},{"key":"6586_CR8","first-page":"618","volume-title":"Proceedings of the 28th^IEEE International Conference on Data Engineering","author":"L Kolb","year":"2012","unstructured":"Kolb L, Thor A, Rahm E. Load balancing for mapreduce-based entity resolution. In: Proceedings of the 28th IEEE International Conference on Data Engineering. 2012, 618\u2013629"},{"key":"6586_CR9","first-page":"574","volume-title":"Proceedings of the 1st International Conference on Cloud Computing and Services Science","author":"B Gufler","year":"2011","unstructured":"Gufler B, Augsten N, Reiser A, Kemper A. Handing data skew in mapreduce. In: Proceedings of the 1st International Conference on Cloud Computing and Services Science. 2011, 574\u2013583"},{"key":"6586_CR10","first-page":"522","volume-title":"Proceedings of the 28th^IEEE International Conference on Data Engineering","author":"B Gufler","year":"2012","unstructured":"Gufler B, Augsten N, Reiser A, Kemper A. Load balancing in mapreduce based on scalable cardinality estimates. In: Proceedings of the 28th IEEE International Conference on Data Engineering. 2012, 522\u2013533"},{"issue":"9","key":"6586_CR11","doi-asserted-by":"publisher","first-page":"2520","DOI":"10.1109\/TPDS.2014.2350972","volume":"26","author":"Q Chen","year":"2015","unstructured":"Chen Q, Yao J, Xiao Z. Libra: lightweight data skew mitigation in mapreduce. IEEE Transactions on Parallel and Distributed System, 2015, 26(9): 2520\u20132533","journal-title":"IEEE Transactions on Parallel and Distributed System"},{"key":"6586_CR12","first-page":"23","volume":"1","author":"D DeWitt","year":"2008","unstructured":"DeWitt D, Stonebraker M. Mapreduce: a major step backwards. The Database Column, 2008, 1: 23","journal-title":"The Database Column"},{"key":"6586_CR13","volume-title":"Open Cirrus Summit","author":"Y C Kwon","year":"2011","unstructured":"Kwon Y C, Balazinska M, Howe B, Rolia J. A study of skew in mapreduce applications. Open Cirrus Summit, 2011, 11"},{"key":"6586_CR14","first-page":"13","volume-title":"Proceedings of the 3rd^ACM Symposium on Cloud Computing","author":"A Rasmussen","year":"2012","unstructured":"Rasmussen A, Conley M, Kapoor R, Lam U T, Porter G, Vahdat A. Themis: an I\/O-efficient MapReduce. In: Proceedings of the 3rd ACM Symposium on Cloud Computing. 2012, 13"},{"issue":"10","key":"6586_CR15","doi-asserted-by":"publisher","first-page":"853","DOI":"10.14778\/2536206.2536213","volume":"6","author":"K Ren","year":"2013","unstructured":"Ren K, Kwon Y C, Balazinska M, Howe B. Hadoop\u2019s adolescence: an analysis of hadoop usage in scientific workloads. Proceedings of the VLDB Endowment, 2013, 6(10): 853\u2013864","journal-title":"Proceedings of the^VLDB Endowment"},{"issue":"13","key":"6586_CR16","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.14778\/2733004.2733005","volume":"7","author":"J Shi","year":"2014","unstructured":"Shi J, Zou J, Lu J, Cao Z, Li S, Wang C. Mrtuner: a toolkit to enable holistic optimization for mapreduce jobs. Proceedings of the VLDB Endowment, 2014, 7(13): 1319\u20131330","journal-title":"Proceedings of the^VLDB Endowment"},{"key":"6586_CR17","volume-title":"Scheduling and Load Balancing in Parallel and Distributed Systems","author":"B A Shirazi","year":"1995","unstructured":"Shirazi B A, Kavi K M, Hurson A R. Scheduling and Load Balancing in Parallel and Distributed Systems. Los Alamitos: IEEE Computer Society Press, 1995"},{"key":"6586_CR18","volume-title":"Scheduling Divisible Loads in Parallel and Distributed Systems","author":"V Bharadwaj","year":"1996","unstructured":"Bharadwaj V, Ghose D, Mani V, Robertazzi T G. Scheduling Divisible Loads in Parallel and Distributed Systems. New York: John Wiley & Sons, 1996"},{"key":"6586_CR19","first-page":"17","volume-title":"Proceedings of the 2nd^IEEE International Conference on Cloud Computing Technology and Science","author":"S Ibrahim","year":"2010","unstructured":"Ibrahim S, Jin H, Lu L,Wu S, He B. Leen: locality\/fairness-aware key partitioning for mapreduce in the cloud. In: Proceedings of the 2nd IEEE International Conference on Cloud Computing Technology and Science. 2010, 17\u201324"},{"issue":"4","key":"6586_CR20","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s12083-013-0213-7","volume":"6","author":"S Ibrahim","year":"2013","unstructured":"Ibrahim S, Jin H, Lu L, He B, Antoniu G. Handling partitioning skew in mapreduce using leen. Peer-to-Peer Networking and Applications, 2013, 6(4): 409\u2013424","journal-title":"Peer-to-Peer Networking and Applications"},{"key":"6586_CR21","first-page":"652","volume-title":"Proceedings of the 6th^IEEE International Conference on Cloud Computing","author":"P Dhawalia","year":"2013","unstructured":"Dhawalia P, Kailasam S, Janakiram D. Chisel: a resource savvy approach for handling skew in mapreduce applications. In: Proceedings of the 6th IEEE International Conference on Cloud Computing. 2013, 652\u2013660"},{"key":"6586_CR22","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1145\/2247596.2247646","volume-title":"Proceedings of the 15th International Conference on Extending Database Technology","author":"R Vernica","year":"2012","unstructured":"Vernica R, Balmin A, Beyer K S, Ercegovac V. Adaptive mapreduce using situation-aware mappers. In: Proceedings of the 15th International Conference on Extending Database Technology. 2012, 420\u2013431"},{"key":"6586_CR23","first-page":"16","volume-title":"Proceedings of the 3rd^ACM Symposium on Cloud Computing","author":"S R Ramakrishnan","year":"2012","unstructured":"Ramakrishnan S R, Swart G, Urmanov A. Balancing reducer skew in mapreduce workloads using progressive sampling. In: Proceedings of the 3rd ACM Symposium on Cloud Computing. 2012, 16"},{"key":"6586_CR24","first-page":"486","volume-title":"Proceedings of the 28th^IEEE International Conference on Data Engineering","author":"R Grover","year":"2012","unstructured":"Grover R, Carey M J. Extending map-reduce for efficient predicatebased sampling. In: Proceedings of the 28th IEEE International Conference on Data Engineering. 2012, 486\u2013497"},{"key":"6586_CR25","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/2213836.2213840","volume-title":"Proceedings of the 2012^ACM SIGMOD International Conference on Management of Data","author":"Y C Kwon","year":"2012","unstructured":"Kwon Y C, Balazinska M, Howe B, Rolia J. Skewtune: mitigating skew in mapreduce applications. In: Proceedings of the 2012 ACM SIGMOD International Conference on Management of Data. 2012, 25\u201336"},{"key":"6586_CR26","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1145\/2608020.2608021","volume-title":"Proceedings of the 6th International Workshop on Data Intensive Distributed Computing","author":"P Dhawalia","year":"2014","unstructured":"Dhawalia P, Kailasam S, Janakiram D. Chisel++: handling partitioning skew in mapreduce framework using efficient range partitioning technique. In: Proceedings of the 6th International Workshop on Data Intensive Distributed Computing. 2014, 21\u201328"},{"issue":"8","key":"6586_CR27","doi-asserted-by":"publisher","first-page":"704","DOI":"10.14778\/2212351.2212353","volume":"5","author":"A Metwally","year":"2012","unstructured":"Metwally A, Faloutsos C. V-smart-join: a scalable mapreduce framework for all-pair similarity joins of multisets and vectors. Proceedings of the VLDB Endowment, 2012, 5(8):704\u2013715","journal-title":"Proceedings of the^VLDB Endowment"},{"key":"6586_CR28","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/j.procs.2014.05.014","volume":"29","author":"M A H Hassan","year":"2014","unstructured":"Hassan M A H, Bamha M, Loulergue F. Handling data-skew effects in join operations using mapreduce. Procedia Computer Science, 2014, 29: 145\u2013158","journal-title":"Procedia Computer Science"},{"key":"6586_CR29","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1145\/1807128.1807140","volume-title":"Proceedings of the 1st^ACM Symposium on Cloud Computing","author":"Y C Kwon","year":"2010","unstructured":"Kwon Y C, Balazinska M, Howe B, Rolia J. Skew-resistant parallel processing of feature-extracting scientific user-defined functions. In: Proceedings of the 1st ACM Symposium on Cloud Computing. 2010, 75\u201386"},{"key":"6586_CR30","volume-title":"Sampling Techniques","author":"W G Cochran","year":"2007","unstructured":"Cochran W G. Sampling Techniques. New York: John Wiley & Sons, 2007"},{"issue":"3","key":"6586_CR31","doi-asserted-by":"publisher","first-page":"384","DOI":"10.1016\/S0022-0000(75)80008-0","volume":"10","author":"J D Ullman","year":"1975","unstructured":"Ullman J D. NP-complete scheduling problems. Journal of Computer and System Sciences, 1975, 10(3): 384\u2013393","journal-title":"Journal of Computer and System Sciences"},{"issue":"2","key":"6586_CR32","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1137\/0117039","volume":"17","author":"R L Graham","year":"1969","unstructured":"Graham R L. Bounds on multiprocessing timing anomalies. SIAM Journal on Applied Mathematics, 1969, 17(2): 416\u2013429","journal-title":"SIAM Journal on Applied Mathematics"},{"key":"6586_CR33","first-page":"165","volume-title":"Bounds on the performance of scheduling algorithms. Computer and Job Scheduling Theory","author":"R L Graham","year":"1976","unstructured":"Graham R L. Bounds on the performance of scheduling algorithms. Computer and Job Scheduling Theory, 1976, 165\u2013227"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-018-6586-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11704-018-6586-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-018-6586-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,9]],"date-time":"2022-09-09T07:02:09Z","timestamp":1662706929000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11704-018-6586-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,17]]},"references-count":33,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["6586"],"URL":"https:\/\/doi.org\/10.1007\/s11704-018-6586-2","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,17]]},"assertion":[{"value":"12 December 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2017","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}