{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T07:47:14Z","timestamp":1759132034459},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,11,8]],"date-time":"2013-11-08T00:00:00Z","timestamp":1383868800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1007\/s10766-013-0288-z","type":"journal-article","created":{"date-parts":[[2013,11,7]],"date-time":"2013-11-07T14:02:55Z","timestamp":1383832975000},"page":"489-507","source":"Crossref","is-referenced-by-count":19,"title":["An Adaptive and Memory Efficient Sampling Mechanism for Partitioning in MapReduce"],"prefix":"10.1007","volume":"43","author":[{"given":"Kenn","family":"Slagter","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Hsien","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeh-Ching","family":"Chung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,11,8]]},"reference":[{"key":"288_CR1","unstructured":"Apache Software Foundation, \u201cHadoop\u201d, http:\/\/hadoop.apache.org\/core"},{"key":"288_CR2","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/MMUL.2010.70","volume":"18","author":"K Candan","year":"2011","unstructured":"Candan, K., Kim, J.W., Nagarkar, P., Nagendra, M., Yu, R.: RanKloud: scalable multimedia data processing in server clusters. IEEE MultiMed. 18, 64\u201377 (2011)","journal-title":"IEEE MultiMed."},{"key":"288_CR3","unstructured":"Chang, F., Dean, J., Ghemawat, S., Hsieh, W.C., Wallach, D.A., Burrows, M., Chandra, T., Fikes, A., Gruber, R.E.: Bigtable: a distributed storage system for structured data. In: 7th USENIX Symposium on Operating Systems Design and Implementation, pp. 205\u2013218 (2006)"},{"key":"288_CR4","doi-asserted-by":"crossref","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, 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"288_CR5","doi-asserted-by":"crossref","unstructured":"Fadika, Z., Govindaraju, M.: Delma: dynamically elastic mapreduce framework for cpu-intensive applications. In: IEEE\/ACM International Symposium on Cluster, Cloud and Grid, Computing, pp.454\u2013463 (2011)","DOI":"10.1109\/CCGrid.2011.71"},{"key":"288_CR6","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.-T.: The google file system. In: ACM SIGOPS Operating Systems Review, ACM, pp. 29\u201343 (2003)","DOI":"10.1145\/1165389.945450"},{"key":"288_CR7","unstructured":"Groot, S., Kitsuregawa, M.: Jumbo: Beyond MapReduce for Workload Balancing. VLDB, Phd Workshop (2010)"},{"key":"288_CR8","unstructured":"HBase, http:\/\/hadoop.apache.org\/hbase\/"},{"issue":"12","key":"288_CR9","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1145\/506309.506312","volume":"20","author":"S Heinz","year":"2002","unstructured":"Heinz, S., Zobel, J., Williams, H.: Burst tries: a fast, efficient data structure for string keys. Trans. Inf. Syst. (TOIS) 20(12), 192\u2013223 (2002)","journal-title":"Trans. Inf. Syst. (TOIS)"},{"key":"288_CR10","doi-asserted-by":"crossref","unstructured":"Jiang, W., Agrawal, G.: Ex-mate: data intensive computing with large reduction objects and its application to graph mining. In: Cluster, Cloud and Grid Computing (CCGrid): 11th IEEE\/ACM International Symposium on, IEEE 2011, pp. 475\u2013484 (2011)","DOI":"10.1109\/CCGrid.2011.18"},{"key":"288_CR11","doi-asserted-by":"crossref","unstructured":"Jin, C., Vecchiola, C., Buyya, R.: MRPGA: an extension of MapReduce for parallelizing genetic algorithms. In: IEEE Fourth International Conference on eScience pp. 214\u2013221 (2008)","DOI":"10.1109\/eScience.2008.78"},{"key":"288_CR12","doi-asserted-by":"crossref","unstructured":"Kavulya, S., Tan, J., Gandhi, R., Narasimhan, P.: An analysis of traces from a production mapreduce cluster. In: Cluster, Cloud and Grid Computing (CCGrid), 2010 10th IEEE\/ACM International Conference, pp. 94\u2013103 (2010)","DOI":"10.1109\/CCGRID.2010.112"},{"issue":"13","key":"288_CR13","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1002\/cpe.906","volume":"17","author":"A Krishnan","year":"2005","unstructured":"Krishnan, A.: GridBLAST: a globus-based high-throughput implementation of BLAST in a Grid computing framework. Concurr. Comput. Pract. Exp. 17(13), 1607\u20131623 (2005)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"288_CR14","doi-asserted-by":"crossref","unstructured":"Liu, H., Orban, D.: Cloud mapreduce: a mapreduce implementation on top of a cloud operating system. In: 11th IEEE\/ACM International Symposium, pp. 464\u2013474 (2011)","DOI":"10.1109\/CCGrid.2011.25"},{"key":"288_CR15","doi-asserted-by":"crossref","unstructured":"Lynden, S., Tanimura, Y., Kojima, I., Matono, A.: Dynamic data redistribution for MapReduce joins. In: IEEE International Conference on Coud Computing Technology and Science, pp. 713\u2013717 (2011)","DOI":"10.1109\/CloudCom.2011.111"},{"key":"288_CR16","unstructured":"Matsunaga, A., Tsugawa, M., Fortes, J.: \u201cProgramming abstractions for data intensive computing on clouds and grids. In: IEEE Fourth International Conference on eScience, pp. 489\u2013493 (2008)"},{"key":"288_CR17","doi-asserted-by":"crossref","unstructured":"Miceli, C., Miceli, M., Jha, S., Kaiser, H., Merzky, A.: Programming abstractions for data intensive computing on clouds and grids. In: IEEE\/ACM International Symposium on Cluster Computing and the Grid, pp. 480\u2013483 (2009)","DOI":"10.1109\/CCGRID.2009.87"},{"key":"288_CR18","unstructured":"O\u2019Malley, O.: TeraByte Sort on Apache Hadoop (2008)"},{"key":"288_CR19","doi-asserted-by":"crossref","unstructured":"Panda, B., Riedewald, M., Fink, D.: The model-summary problem and a solution for trees. In: Data Engineering, International Conference on Data, Engineering, pp. 452\u2013455 (2010)","DOI":"10.1109\/ICDE.2010.5447912"},{"key":"288_CR20","doi-asserted-by":"crossref","unstructured":"Papadimitriou, S., Sun, J.: Disco: distributed co-clustering with map-reduce: a case study towards petabyte-scale end-to-end mining. In: IEEE International Conference on Data Mining, p. 519 (2008)","DOI":"10.1109\/ICDM.2008.142"},{"key":"288_CR21","doi-asserted-by":"crossref","unstructured":"Shafer, J., Rixner, S., Cox, A.L.: The Hadoop distributed filesystem: balancing portability and performance. In: IEEE International Symposium on Performance Analysis of System and Software(ISPASS), p. 123 (2010)","DOI":"10.1109\/ISPASS.2010.5452045"},{"key":"288_CR22","doi-asserted-by":"crossref","unstructured":"Slagter, K., Hsu, C.-H., Chung, Y.-C., Zhang, D.: An improved partitioning mechanism for optimizing massive data analysis using MapReduce. J. Supercomput. 66(1), 539\u2013555 (2013)","DOI":"10.1007\/s11227-013-0924-9"},{"key":"288_CR23","doi-asserted-by":"crossref","unstructured":"Stockinger, H., Pagni, M., Cerutti, L., Falquet, L.: Grid approach to embarrassingly parallel CPU-intensive bioinformatics problems. In: IEEE International Conference on e-Science and Grid Computing (2006)","DOI":"10.1109\/E-SCIENCE.2006.261142"},{"key":"288_CR24","unstructured":"Tan, J., Pan, X., Kavulya, S., Gandhi, R., Narasimhan, P.: Mochi: visual log-analysis based tools for debugging Hadoop. In: USENIX Workshop on Hot Topics in Cloud Computing (HotCloud) (2009)"},{"key":"288_CR25","doi-asserted-by":"crossref","unstructured":"Vashishtha, H., Smit, M., Stroulia, E.: Moving text analysis tools to the cloud. In: IEEE World Congress on Services, pp. 110\u2013112 (2010)","DOI":"10.1109\/SERVICES.2010.91"},{"key":"288_CR26","doi-asserted-by":"crossref","unstructured":"Verma, A., Llora, X., Goldberg, D.E., Campbell, R.H.: Scaling genetic algorithms using mapreduce. In: Intelligent Systems Design and Applications (2009)","DOI":"10.1109\/ISDA.2009.181"},{"key":"288_CR27","unstructured":"White, T.: \u201cHadoop the definitive guide 2nd edition\u201d, Published Oreilly (2010)"},{"key":"288_CR28","doi-asserted-by":"crossref","unstructured":"Xu, W., Huang, L., Fox, A., Patterson, D., Jordan, M.I.: Detecting large-scale system problems by mining console logs. In: Proceedings of the ACM SIGOPS 22nd Symposium on Operating Systems Principles (2009)","DOI":"10.1145\/1629575.1629587"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0288-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-013-0288-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-013-0288-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T04:26:35Z","timestamp":1564633595000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-013-0288-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,11,8]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2015,6]]}},"alternative-id":["288"],"URL":"https:\/\/doi.org\/10.1007\/s10766-013-0288-z","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"value":"0885-7458","type":"print"},{"value":"1573-7640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,11,8]]}}}