{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T03:05:55Z","timestamp":1784948755184,"version":"3.55.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T00:00:00Z","timestamp":1643673600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001427","name":"All India Council for Technical Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001427","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2022,10]]},"DOI":"10.1007\/s10586-021-03530-x","type":"journal-article","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T13:03:08Z","timestamp":1643720588000},"page":"3193-3211","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Historical data based approach to mitigate stragglers from the Reduce phase of MapReduce in a heterogeneous Hadoop cluster"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2486-4949","authenticated-orcid":false,"given":"Kamalakant Laxman","family":"Bawankule","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rupesh Kumar","family":"Dewang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anil Kumar","family":"Singh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,1]]},"reference":[{"key":"3530_CR1","doi-asserted-by":"crossref","unstructured":"Arasanal, R.M., Rumani, D.U.: Improving Mapreduce performance through complexity and performance based data placement in heterogeneous Hadoop clusters. In: International Conference on Distributed Computing and Internet Technology, pp. 115\u2013125. Springer (2013)","DOI":"10.1007\/978-3-642-36071-8_8"},{"key":"3530_CR2","doi-asserted-by":"crossref","unstructured":"Bawankule, K.L., Dewang, R.K., Singh, A.K.: Load balancing approach for a Mapreduce job running on a heterogeneous Hadoop cluster. In: International Conference on Distributed Computing and Internet Technology, pp. 289\u2013298. Springer (2021)","DOI":"10.1007\/978-3-030-65621-8_19"},{"key":"3530_CR3","first-page":"1","volume":"23","author":"KL Bawankule","year":"2021","unstructured":"Bawankule, K.L., Dewang, R.K., Singh, A.K.: Historical data based approach for straggler avoidance in a heterogeneous Hadoop cluster. J Ambient Intell. Hum. Comput. 23, 1\u201317 (2021)","journal-title":"J Ambient Intell. Hum. Comput."},{"issue":"3","key":"3530_CR4","doi-asserted-by":"publisher","first-page":"64","DOI":"10.4018\/IJDST.2021070104","volume":"12","author":"KL Bawankule","year":"2021","unstructured":"Bawankule, K.L., Dewang, R.K., Singh, A.K.: Performance analysis of hadoop YARN job schedulers in a multi-tenant environment on HiBench benchmark suite. Int. J. Distrib. Syst. Technol. 12(3), 64\u201382 (2021). https:\/\/doi.org\/10.4018\/IJDST.2021070104","journal-title":"Int. J. Distrib. Syst. Technol."},{"issue":"1","key":"3530_CR5","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. Commun. ACM 51(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"3530_CR6","doi-asserted-by":"crossref","unstructured":"Dhawalia, P., Kailasam, S., Janakiram, D.: Chisel: a resource savvy approach for handling skew in Mapreduce applications. In: 2013 IEEE Sixth International Conference on Cloud Computing, pp. 652\u2013660. IEEE (2013)","DOI":"10.1109\/CLOUD.2013.43"},{"key":"3530_CR7","first-page":"1","volume":"41","author":"R Ghazali","year":"2021","unstructured":"Ghazali, R., Adabi, S., Down, D.G., Movaghar, A.: A classification of Hadoop job schedulers based on performance optimization approaches. Clust. Comput. 41, 1\u201323 (2021)","journal-title":"Clust. Comput."},{"key":"3530_CR8","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 2010), pp. 41\u201351. IEEE (2010)","DOI":"10.1109\/ICDEW.2010.5452747"},{"issue":"5\u20136","key":"3530_CR9","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1007\/s10766-019-00627-0","volume":"47","author":"MA Irandoost","year":"2019","unstructured":"Irandoost, M.A., Rahmani, A.M., Setayeshi, S.: Mapreduce data skewness handling: a systematic literature review. Int. J. Parall. Program. 47(5\u20136), 907\u2013950 (2019)","journal-title":"Int. J. Parall. Program."},{"key":"3530_CR10","doi-asserted-by":"crossref","unstructured":"Kwon, Y., 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, pp. 75\u201386 (2010)","DOI":"10.1145\/1807128.1807140"},{"key":"3530_CR11","doi-asserted-by":"crossref","unstructured":"Kwon, Y., 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, pp. 25\u201336. ACM (2012)","DOI":"10.1145\/2213836.2213840"},{"key":"3530_CR12","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.bdr.2014.07.002","volume":"1","author":"CW Lee","year":"2014","unstructured":"Lee, C.W., Hsieh, K.Y., Hsieh, S.Y., Hsiao, H.C.: A dynamic data placement strategy for Hadoop in heterogeneous environments. Big Data Res. 1, 14\u201322 (2014)","journal-title":"Big Data Res."},{"key":"3530_CR13","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.future.2018.07.043","volume":"90","author":"NS Naik","year":"2019","unstructured":"Naik, N.S., Negi, A., BR, T.B., Anitha, R.: A data locality based scheduler to enhance Mapreduce performance in heterogeneous environments. Future Gener. Comput. Syst. 90, 423\u2013434 (2019)","journal-title":"Future Gener. Comput. Syst."},{"key":"3530_CR14","doi-asserted-by":"crossref","unstructured":"Paik, S.S., Goswami, R.S., Roy, D., Reddy, K.H.: Intelligent data placement in heterogeneous Hadoop cluster. In: International Conference on Next Generation Computing Rechnologies, pp. 568\u2013579. Springer (2017)","DOI":"10.1007\/978-981-10-8657-1_43"},{"issue":"2","key":"3530_CR15","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1007\/s10586-020-03146-7","volume":"24","author":"V Pandey","year":"2021","unstructured":"Pandey, V., Saini, P.: A heuristic method towards deadline-aware energy-efficient Mapreduce scheduling problem in Hadoop yarn. Clust. Comput. 24(2), 683\u2013699 (2021)","journal-title":"Clust. Comput."},{"key":"3530_CR16","first-page":"1","volume":"87","author":"M Sellami","year":"2021","unstructured":"Sellami, M., Mezni, H., Hacid, M.S., Gammoudi, M.M.: Clustering-based data placement in cloud computing: a predictive approach. Clust. Comput. 87, 1\u201326 (2021)","journal-title":"Clust. Comput."},{"issue":"3","key":"3530_CR17","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.future.2010.09.004","volume":"27","author":"S Seneviratne","year":"2011","unstructured":"Seneviratne, S., Levy, D.C.: Task profiling model for load profile prediction. Future Gener. Comput. Syst. 27(3), 245\u2013255 (2011)","journal-title":"Future Gener. Comput. Syst."},{"key":"3530_CR18","first-page":"1","volume":"10","author":"K Shvachko","year":"2010","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R., et al.: The Hadoop distributed file system. MSST 10, 1\u201310 (2010)","journal-title":"MSST"},{"key":"3530_CR19","doi-asserted-by":"crossref","unstructured":"Ubarhande, V., Popescu, A.M., Gonz\u00e1lez-V\u00e9lez, H.: Novel data-distribution technique for hadoop in heterogeneous cloud environments. In: 2015 Ninth International Conference on Complex, Intelligent, and Software Intensive Systems, pp. 217\u2013224. IEEE (2015)","DOI":"10.1109\/CISIS.2015.37"},{"key":"3530_CR20","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., et\u00a0al.: Apache Hadoop yarn: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, p.\u00a05. ACM (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"3530_CR21","doi-asserted-by":"crossref","unstructured":"Wang, B., Jiang, J., Yang, G.: Actcap: accelerating mapreduce on heterogeneous clusters with capability-aware data placement. In: 2015 IEEE Conference on Computer Communications (INFOCOM), pp. 1328\u20131336. IEEE (2015)","DOI":"10.1109\/INFOCOM.2015.7218509"},{"key":"3530_CR22","doi-asserted-by":"crossref","unstructured":"Xie, J., Yin, S., Ruan, X., Ding, Z., Tian, Y., Majors, J., Manzanares, A., Qin, X.: Improving mapreduce performance through data placement in heterogeneous hadoop clusters. In: 2010 IEEE International Symposium on Parallel & Distributed Processing, Workshops and Phd Forum (IPDPSW), pp. 1\u20139. IEEE (2010)","DOI":"10.1109\/IPDPSW.2010.5470880"},{"key":"3530_CR23","doi-asserted-by":"crossref","unstructured":"Ye, X., Huang, M., Zhu, D., Xu, P.: A novel blocks placement strategy for Hadoop. In: 2012 IEEE\/ACIS 11th International Conference on Computer and Information Science, pp. 3\u20137. IEEE (2012)","DOI":"10.1109\/ICIS.2012.11"},{"key":"3530_CR24","first-page":"7","volume":"8","author":"M Zaharia","year":"2008","unstructured":"Zaharia, M., Konwinski, A., Joseph, A.D., Katz, R.H., Stoica, I.: Improving Mapreduce performance in heterogeneous environments. Osdi 8, 7 (2008)","journal-title":"Osdi"},{"issue":"4","key":"3530_CR25","doi-asserted-by":"publisher","first-page":"1691","DOI":"10.1007\/s10586-016-0625-2","volume":"19","author":"X Zhang","year":"2016","unstructured":"Zhang, X., Wu, Y., Zhao, C.: Mrheter: improving Mapreduce performance in heterogeneous environments. Clust. Comput. 19(4), 1691\u20131701 (2016)","journal-title":"Clust. Comput."}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03530-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-021-03530-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03530-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T18:32:44Z","timestamp":1726597964000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-021-03530-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,1]]},"references-count":25,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["3530"],"URL":"https:\/\/doi.org\/10.1007\/s10586-021-03530-x","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,1]]},"assertion":[{"value":"10 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 December 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}