{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T16:57:26Z","timestamp":1759683446094,"version":"3.40.4"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2012,11,27]],"date-time":"2012-11-27T00:00:00Z","timestamp":1353974400000},"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":[[2013,8]]},"DOI":"10.1007\/s10766-012-0227-4","type":"journal-article","created":{"date-parts":[[2012,11,26]],"date-time":"2012-11-26T13:28:41Z","timestamp":1353936521000},"page":"495-525","source":"Crossref","is-referenced-by-count":41,"title":["Analytical Performance Models for MapReduce Workloads"],"prefix":"10.1007","volume":"41","author":[{"given":"Emanuel","family":"Vianna","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Comarela","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatiana","family":"Pontes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jussara","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Virg\u00edlio","family":"Almeida","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Wilkinson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harumi","family":"Kuno","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Umeshwar","family":"Dayal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2012,11,27]]},"reference":[{"key":"227_CR1","unstructured":"Apache Software Foundation, Powered by Hadoop. URL http:\/\/wiki.apache.org\/hadoop\/PoweredBy . Access date: 1 July 2012 (2012)"},{"key":"227_CR2","unstructured":"Apache Software Foundation, Official Apache Hadoop Website. URL http:\/\/hadoop.apache.org\/ . Accessed date: 1 July 2012 (2012)"},{"issue":"3","key":"227_CR3","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1016\/j.jpdc.2010.12.004","volume":"71","author":"J. Berli\u0144ska","year":"2011","unstructured":"Berli\u0144ska J., Drozdowski M.: Scheduling divisible MapReduce computations. J. Parallel Distrib. Comput. 71(3), 450\u2013459 (2011)","journal-title":"J. Parallel Distrib. Comput."},{"key":"227_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., Ganapathi, A., Griffith R., Katz, R.: The case for evaluating MapReduce performance using workload suites. In: Proceedings of the 2011 IEEE 19th Annual International Symposium on Modelling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), Singapore, pp. 390\u2013399 (2011)","DOI":"10.1109\/MASCOTS.2011.12"},{"key":"227_CR5","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Elmeleegy, K., Sears R.: MapReduce Online Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation (NSDI), San Jose, California, pp. 21\u201335 (2010)"},{"key":"227_CR6","unstructured":"Dean, J., Ghemawat, S., MapReduce : Simplified data processing on large clusters. In: Proceedings of Operating Systems Design and Implementation (OSDI), San Francisco, California, pp. 137\u2013150 (2004)"},{"issue":"1","key":"227_CR7","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(1), 107\u2013113 (2008)","journal-title":"Commun. ACM"},{"key":"227_CR8","unstructured":"Ganapathi, A.: Predicting and Optimizing System Utilization and Performance via Statistical Machine Learning. Technical Report UCB\/EECS-2009-181. EECS Department, University of California, Berkeley (2009)"},{"key":"227_CR9","doi-asserted-by":"crossref","unstructured":"Ganapathi, A., Kuno, H., Dayal, U., Wiener, J., Fox, A., Jordan, M., Patterson, D. : Predicting multiple metrics for queries: better decisions enabled by machine learning. In: Proceedings of the 2009 IEEE International Conference on Data Engineering (ICDE), Shanghai, China, pp. 592\u2013603 (2009)","DOI":"10.1109\/ICDE.2009.130"},{"key":"227_CR10","unstructured":"Herodotou, H.: Hadoop Performance Models. Technical Report CS-2011-05. Computer Science Department, Duke University. URL http:\/\/arxiv.org\/abs\/1106.0940 (2011)"},{"key":"227_CR11","volume-title":"The Art of Computer Systems Performance Analysis\u2014Techniques for Experimental Design, Measurement, Simulation, and Modeling","author":"R. Jain","year":"1991","unstructured":"Jain R.: The Art of Computer Systems Performance Analysis\u2014Techniques for Experimental Design, Measurement, Simulation, and Modeling. Wiley, London (1991)"},{"issue":"1\u20132","key":"227_CR12","doi-asserted-by":"crossref","first-page":"472","DOI":"10.14778\/1920841.1920903","volume":"3","author":"D.R. Jiang","year":"2010","unstructured":"Jiang D.R., Ooi B.C., Shi L., Wu S.: The performance of MapReduce: an in-depth study. Proc. VLDB Endow 3(1\u20132), 472\u2013483 (2010)","journal-title":"Proc. VLDB Endow"},{"key":"227_CR13","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/3-540-58021-2_7","volume-title":"Queueing Models of Parallel Applications: The Glamis Methodology, Computer Performance Evaluation: Modeling Techniques & Tools (LNCS 794)","author":"H. Jonkers","year":"1994","unstructured":"Jonkers H.: Queueing Models of Parallel Applications: The Glamis Methodology, Computer Performance Evaluation: Modeling Techniques & Tools (LNCS 794), pp. 123\u2013138. Springer, Berlin (1994)"},{"issue":"3","key":"227_CR14","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1145\/2160803.2160873","volume":"39","author":"S. Kim","year":"2011","unstructured":"Kim S., Won J., Han H., Eom H., Yeom H.Y.: Improving hadoop performance in intercloud environments ACM SIGMETRICS. Perform. Eval. Rev. 39(3), 107\u2013109 (2011)","journal-title":"Perform. Eval. Rev."},{"key":"227_CR15","doi-asserted-by":"crossref","unstructured":"Krevat, E., Shiran, T., Anderson, E., Tucek, J., Wylie, J.J. , Ganger, G.R.: Applying Performance Models to Understand Data-intensive Computing Efficiency. Technical Report CMU-PDL-10-108. Carnegie Mellon University, Pittsburgh (2010)","DOI":"10.21236\/ADA532848"},{"issue":"10","key":"227_CR16","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1109\/TSE.1985.231547","volume":"11","author":"C.P. Kruskal","year":"1985","unstructured":"Kruskal C.P., Weiss A.: Allocating independent subtasks on parallel processors. IEEE Trans. Softw. Eng. 11(10), 1001\u20131016 (1985)","journal-title":"IEEE Trans. Softw. Eng."},{"issue":"4","key":"227_CR17","doi-asserted-by":"crossref","first-page":"1048","DOI":"10.2307\/3213214","volume":"17","author":"S. Lavenberg","year":"1980","unstructured":"Lavenberg S., Reiser M.: Stationary state probabilities at arrival instants for closed queueing networks with multiple types of customers. J. Appl. Probab. 17(4), 1048\u20131061 (1980)","journal-title":"J. Appl. Probab."},{"issue":"4","key":"227_CR18","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1145\/2094114.2094118","volume":"40","author":"K.H. Lee","year":"2011","unstructured":"Lee K.H., Lee Y.J., Choi H., Chung Y.D., Moon B.: Parallel data processing with MapReduce: a survey. ACM SIGMOD Record J. 40(4), 11\u201320 (2011)","journal-title":"ACM SIGMOD Record J."},{"issue":"5","key":"227_CR19","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1109\/71.852402","volume":"11","author":"D.R. Liang","year":"2000","unstructured":"Liang D.R., Tripathi S. K.: On performance prediction of parallel computations with precedent constraints. IEEE Trans. Parallel Distrib. Syst. 11(5), 491\u2013508 (2000)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"issue":"3","key":"227_CR20","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1287\/opre.9.3.383","volume":"9","author":"J. Little","year":"1961","unstructured":"Little J.: A proof for the queuing formula: L\u00a0= \u03bb W. Oper. Res. 9(3), 383\u2013387 (1961)","journal-title":"Oper. Res."},{"issue":"3","key":"227_CR21","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/71.80155","volume":"1","author":"V.W. Mak","year":"1990","unstructured":"Mak V.W., Lundstrom S.F.: Predicting performance of parallel computations. IEEE Trans. Parallel Distrib. Syst. 1(3), 257\u2013260 (1990)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"227_CR22","unstructured":"Menasce, D., Dowdy, L., Almeida, V.: Performance by Design: Computer Capacity Planning By Example. Prentice Hall PTR (2004)"},{"key":"227_CR23","doi-asserted-by":"crossref","unstructured":"Morton, K., Balazinska, M., Grossman, D.: ParaTimer: a progress indicator for MapReduce DAGs. In: Proceedings of the 2010 ACM SIGMOD International Conference on Management of Data (SIGMOD), Indianapolis, Indiana, pp. 507\u2013518 (2010)","DOI":"10.1145\/1807167.1807223"},{"key":"227_CR24","doi-asserted-by":"crossref","unstructured":"Pavlo, A., Paulson, E., Rasin, A., Abadi, D., DeWitt, D., Madden, S., Stonebraker, M.: A Comparison of approaches to large-scale data analysis. In: Proceedings of the 2009 ACM SIGMOD International Conference on Management of Data (SIGMOD), Providence, Rhode Island, pp. 165\u2013178 (2009)","DOI":"10.1145\/1559845.1559865"},{"issue":"2","key":"227_CR25","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1145\/322186.322195","volume":"27","author":"M. Reiser","year":"1980","unstructured":"Reiser M., Lavenberg S.S.: Mean-value analysis of closed multichain queuing networks. J. ACM 27(2), 313\u2013322 (1980)","journal-title":"J. ACM"},{"key":"227_CR26","unstructured":"Salza, S., Lavenberg, S.S.: Approximating response time distributions in closed queueing network models of computer performance. In: Proceedings Performance, North Holland, Amsterdam, pp. 133\u2013145 (1981)"},{"issue":"12","key":"227_CR27","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.1109\/TC.1986.1676712","volume":"35","author":"A. Thomasian","year":"1986","unstructured":"Thomasian A., Bay P.F.: Analytic queueing network models for parallel processing of task systems. IEEE Trans. Comput. 35(12), 1045\u20131054 (1986)","journal-title":"IEEE Trans. Comput."},{"key":"227_CR28","volume-title":"Probability and Statistics with Reliability, Queuing and Computer Science Applications","author":"K.S. Trivedi","year":"1882","unstructured":"Trivedi K.S.: Probability and Statistics with Reliability, Queuing and Computer Science Applications. Prentice Hall PTR, Upper Saddle River (1882)"},{"key":"227_CR29","doi-asserted-by":"crossref","unstructured":"Varki, E.: Mean value technique for closed fork-join networks. In: Proceedings of the 1999 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, Atlanta, Georgia, pp. 103\u2013112 (1999)","DOI":"10.1145\/301453.301484"},{"key":"227_CR30","doi-asserted-by":"crossref","unstructured":"Vianna, E.,Comarela, G., Pontes, T., Almeida, J., Almeida, V., Wilkinson, K., Kuno, H., Dayal, U.: Modeling the performance of the Hadoop online prototype. In: Proceedings of the 23rd International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Vit\u00f3ria, Brazil, pp. 152\u2013159 (2011)","DOI":"10.1109\/SBAC-PAD.2011.24"},{"key":"227_CR31","doi-asserted-by":"crossref","unstructured":"Wang, G., Butt, A.R., Pandey, P., Gupta, K.: A simulation approach to evaluating design decisions in MapReduce setups. In: Proceedings of the IEEE International Symposium on Modeling, Analysis Simulation of Computer and Telecommunication Systems (MASCOTS), Imperial College London, UK, pp. 1\u201311 (2009)","DOI":"10.1109\/MASCOT.2009.5366973"},{"key":"227_CR32","doi-asserted-by":"crossref","unstructured":"Wang, G., Butt, A.R., Pandey, P., Gupta, K.: Using realistic simulation for performance analysis of MapReduce setups. In: Proceedings of the 1st ACM Workshop on Large-Scale System and Application Performance (LSAP), Munich, Germany, pp. 19\u201326 (2009)","DOI":"10.1145\/1552272.1552278"},{"issue":"3","key":"227_CR33","doi-asserted-by":"crossref","first-page":"18:1","DOI":"10.1145\/1509288.1509290","volume":"8","author":"N. Weng","year":"2009","unstructured":"Weng N., Wolf T.: Analytic modeling of network processors for parallel workload mapping. ACM Trans. Embed. Comput. Syst. 8(3), 18:1\u201318:29 (2009)","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"227_CR34","volume-title":"Hadoop\u2014The Definitive Guide: Storage and Analysis at Internet Scale","author":"T. White","year":"2011","unstructured":"White T.: Hadoop\u2014The Definitive Guide: Storage and Analysis at Internet Scale. 2nd edn. O\u2019Reilly Media, Sebastopol (2011)","edition":"2"},{"key":"227_CR35","doi-asserted-by":"crossref","unstructured":"Yang, H.C., Dasdan, A., Hsiao, R.L., Parker, D.S.: Map-Reduce-Merge: simplified relational data processing on LargeClusters. In: Proceedings of the 2007 ACM SIGMOD International Conference on Management of Data (SIGMOD), Beijing, China, pp. 1029\u20131040 (2007)","DOI":"10.1145\/1247480.1247602"},{"key":"227_CR36","doi-asserted-by":"crossref","unstructured":"Yang, X., Sun, J.: An Analytical performance model of MapReduce. In: Proceedings of the 2011 IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS), Beijing, China, pp. 306\u2013310 (2011)","DOI":"10.1109\/CCIS.2011.6045080"},{"key":"227_CR37","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), San Diego, California, pp. 29\u201342 (2008)"},{"key":"227_CR38","unstructured":"Zahorjan, J.: The Approximate Solution of Large Queueing Network Models, PhD. Thesis, University of Toronto, Canada (1980)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0227-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-012-0227-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-012-0227-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T20:49:11Z","timestamp":1745354951000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-012-0227-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11,27]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2013,8]]}},"alternative-id":["227"],"URL":"https:\/\/doi.org\/10.1007\/s10766-012-0227-4","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2012,11,27]]}}}