{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T02:05:36Z","timestamp":1780106736925,"version":"3.54.0"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T00:00:00Z","timestamp":1443484800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Grid Computing"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1007\/s10723-015-9350-y","type":"journal-article","created":{"date-parts":[[2015,9,29]],"date-time":"2015-09-29T06:56:50Z","timestamp":1443509810000},"page":"587-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["Improving MapReduce Performance with Partial Speculative Execution"],"prefix":"10.1007","volume":"13","author":[{"given":"Yaoguang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Renjie","family":"Lou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baogang","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2015,9,29]]},"reference":[{"key":"9350_CR1","unstructured":"Ananthanarayanan, G., Kandula, S., Greenberg, A.G., Stoica, I., Lu, Y., Saha, B., Harris, E.: Reining in the outliers in map-reduce clusters using mantri. In: OSDI, 10, 24 (2010)"},{"key":"9350_CR2","unstructured":"Ananthanarayanan, G., Ghodsi, A., Shenker, S., Stoica, I.: Effective straggler mitigation: attack of the clones (2013)"},{"key":"9350_CR3","unstructured":"Apache: Apache hadoop. http:\/\/hadoop.apache.org\/ (2014a)"},{"key":"9350_CR4","unstructured":"Apache: Apache zookeeper. http:\/\/zookeeper.apache.org\/ (2014b)"},{"key":"9350_CR5","unstructured":"Benjamin Gufler ARAK Nikolaus Agustine: Handling data skew in mapreduce (2011)"},{"key":"9350_CR6","doi-asserted-by":"crossref","unstructured":"Bhatotia, P., Wieder, A., Rodrigues, R., Acar, U.A., Pasquin, R.: Incoop: Mapreduce for incremental computations. In: Proceedings of the 2nd ACM Symposium on Cloud Computing, ACM, p 7 (2011)","DOI":"10.1145\/2038916.2038923"},{"key":"9350_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Q., Zhang, D., Guo, M., Deng, Q., Guo, S.: Samr: A self-adaptive mapreduce scheduling algorithm in heterogeneous environment. In: Computer and Information Technology (CIT), 2010 IEEE 10th International Conference on, IEEE, 2736\u20132743 (2010)","DOI":"10.1109\/CIT.2010.458"},{"key":"9350_CR8","doi-asserted-by":"crossref","unstructured":"Cho, B., Rahman, M., Chajed, T., Gupta, I., Abad, C., Roberts, N., Lin, P.: Natjam: Design and evaluation of eviction policies for supporting priorities and deadlines in mapreduce clusters. In: Proceedings of the 4th annual Symposium on Cloud Computing, ACM, 6 (2013)","DOI":"10.1145\/2523616.2523624"},{"key":"9350_CR9","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Elmeleegy, K., Sears, R.: Mapreduce online (2010)"},{"key":"9350_CR10","unstructured":"Curino, C.: [mapreduce-5197]checkpoint service: a library component to facilitate checkpoint of task state. https:\/\/issues.apache.org\/jira\/browse\/MAPREDUCE-5197 (2013)"},{"issue":"1","key":"9350_CR11","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":"9350_CR12","doi-asserted-by":"crossref","unstructured":"Doulkeridis, C., N\u00f8rv\u00e5g, K.: A survey of large-scale analytical query processing in mapreduce. The VLDB Journal 1\u201326 (2013)","DOI":"10.1007\/s00778-013-0319-9"},{"issue":"11","key":"9350_CR13","doi-asserted-by":"crossref","first-page":"985","DOI":"10.14778\/2536222.2536225","volume":"6","author":"K Elmeleegy","year":"2013","unstructured":"Elmeleegy, K.: Piranha: Optimizing short jobs in hadoop. Proc. VLDB Endowment 6(11), 985\u2013996 (2013)","journal-title":"Proc. VLDB Endowment"},{"key":"9350_CR14","doi-asserted-by":"crossref","unstructured":"Eltabakh, M.Y., \u00d6zcan, F., Sismanis, Y., Haas, P.J., Pirahesh, H., Vondrak, J.: Eagle-eyed elephant: split-oriented indexing in hadoop. In: Proceedings of the 16th International Conference on Extending Database Technology, ACM, 89\u2013100 (2013)","DOI":"10.1145\/2452376.2452388"},{"key":"9350_CR15","doi-asserted-by":"crossref","unstructured":"Grover, R., Carey, M.J.: Extending map-reduce for efficient predicate-based sampling. In: Data Engineering (ICDE), 2012 IEEE 28th International Conference on, IEEE, 486\u2013497 (2012)","DOI":"10.1109\/ICDE.2012.104"},{"issue":"3","key":"9350_CR16","doi-asserted-by":"crossref","first-page":"2166","DOI":"10.1016\/j.jpdc.2013.10.003","volume":"74","author":"R Gu","year":"2014","unstructured":"Gu, R., Yang, X., Yan, J., Sun, Y., Wang, B., Yuan, C., Huang, Y.: Shadoop: Improving mapreduce performance by optimizing job execution mechanism in hadoop clusters. J. Parallel Distrib. Comput. 74(3), 2166\u20132179 (2014)","journal-title":"J. Parallel Distrib. Comput."},{"key":"9350_CR17","doi-asserted-by":"crossref","unstructured":"Gufler, B., Augsten, N., Reiser, A., Kemper, A.: Load balancing in mapreduce based on scalable cardinality estimates. In: Data Engineering (ICDE), 2012 IEEE 28th International Conference on, IEEE, 522\u2013533 (2012)","DOI":"10.1109\/ICDE.2012.58"},{"key":"9350_CR18","unstructured":"Guo, Y., Rao, J., Zhou, X.: Ishuffle: Improving hadoop performance with shuffle-on-write. 10th International Conference on Autonomic Computing 107\u2013117 (2013)"},{"key":"9350_CR19","unstructured":"Harringer, M.: Xen-the art of virtualization (2004)"},{"key":"9350_CR20","doi-asserted-by":"crossref","unstructured":"Herodotou, H., Dong, F., Babu, S.: No one (cluster) size fits all: automatic cluster sizing for data-intensive analytics. In: Proceedings of the 2nd ACM Symposium on Cloud Computing, ACM, 18 (2011)","DOI":"10.1145\/2038916.2038934"},{"issue":"3","key":"9350_CR21","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1007\/s10723-014-9298-3","volume":"12","author":"CH Hsu","year":"2014","unstructured":"Hsu, C.H., Lin, C.C., Ts, Hsu: Adaptable scheduling algorithm for grids with resource redeployment capability. J. Grid Computing 12(3), 447\u2013463 (2014)","journal-title":"J. Grid Computing"},{"issue":"11","key":"9350_CR22","doi-asserted-by":"crossref","first-page":"1256","DOI":"10.14778\/2350229.2350244","volume":"5","author":"F Hueske","year":"2012","unstructured":"Hueske, F., Peters, M., Sax, M.J., Rheinl\u00e4nder, A., Bergmann, R., Krettek, A., Tzoumas, K.: Opening the black boxes in data flow optimization. Proc. VLDB Endowment 5(11), 1256\u20131267 (2012)","journal-title":"Proc. VLDB Endowment"},{"issue":"3","key":"9350_CR23","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1145\/1272998.1273005","volume":"41","author":"M Isard","year":"2007","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. ACM SIGOPS Oper. Syst. Rev. 41(3), 59\u201372 (2007)","journal-title":"ACM SIGOPS Oper. Syst. Rev."},{"key":"9350_CR24","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, ACM, 75\u201386 (2010)","DOI":"10.1145\/1807128.1807140"},{"key":"9350_CR25","unstructured":"Kwon, Y., Balazinska, M., Howe, B., Rolia, J., A study of skew in mapreduce applications. Open Cirrus Summit (2011)"},{"key":"9350_CR26","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, ACM, 25\u201336 (2012)","DOI":"10.1145\/2213836.2213840"},{"issue":"1","key":"9350_CR27","first-page":"24","volume":"36","author":"Y Kwon","year":"2013","unstructured":"Kwon, Y., Ren, K., Balazinska, M., Howe, B., Rolia, J.: Managing skew in hadoop. IEEE Data Eng Bull 36(1), 24\u201333 (2013)","journal-title":"IEEE Data Eng Bull"},{"issue":"10","key":"9350_CR28","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.14778\/2336664.2336675","volume":"5","author":"N Laptev","year":"2012","unstructured":"Laptev, N., Zeng, K., Zaniolo, C.: Early accurate results for advanced analytics on mapreduce. Proc. VLDB Endowment 5(10), 1028\u20131039 (2012)","journal-title":"Proc. VLDB Endowment"},{"issue":"11","key":"9350_CR29","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.14778\/2350229.2350239","volume":"5","author":"H Lim","year":"2012","unstructured":"Lim, H., Herodotou, H., Babu, S.: Stubby: A transformation-based optimizer for mapreduce workflows. Proc. VLDB Endowment 5(11), 1196\u20131207 (2012)","journal-title":"Proc. VLDB Endowment"},{"key":"9350_CR30","doi-asserted-by":"crossref","unstructured":"Logothetis, D., Olston, C., Reed, B., Webb, K.C., Yocum, K.: Stateful bulk processing for incremental analytics (2010)","DOI":"10.1145\/1807128.1807138"},{"key":"9350_CR31","doi-asserted-by":"crossref","unstructured":"Olston, C., Chiou, G., Chitnis, L., Liu, F., Han, Y., Larsson, M., Neumann, A., Rao, V.B., Sankarasubramanian, V., Seth, S., et al.: Nova: continuous pig\/hadoop workflows. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of data, ACM, 1081\u20131090 (2011)","DOI":"10.1145\/1989323.1989439"},{"key":"9350_CR32","doi-asserted-by":"crossref","unstructured":"Onizuka, M., Kato, H., Hidaka, S., Nakano, K., Hu, Z.: Optimization for iterative queries on mapreduce. Proc. VLDB Endowment 7(4) (2013)","DOI":"10.14778\/2732240.2732243"},{"key":"9350_CR33","doi-asserted-by":"crossref","unstructured":"Quian\u00e9-Ruiz, J.A., Pinkel, C., Schad, J., Dittrich, J.: Rafting mapreduce: Fast recovery on the raft. In: Data Engineering (ICDE), 2011 IEEE 27th International Conference on, IEEE, 589\u2013600 (2011)","DOI":"10.1109\/ICDE.2011.5767877"},{"issue":"2","key":"9350_CR34","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/s10723-014-9292-9","volume":"12","author":"MB Qureshi","year":"2014","unstructured":"Qureshi, M.B., Dehnavi, M.M., Min-Allah, N., Qureshi, M.S., Hussain, H., Rentifis, I., Tziritas, N., Loukopoulos, T., Khan, S.U., Xu, C.Z., et al.: Survey on grid resource allocation mechanisms. J. Grid Computing 12(2), 399\u2013441 (2014)","journal-title":"J. Grid Computing"},{"key":"9350_CR35","doi-asserted-by":"crossref","unstructured":"Ramakrishnan, S.R., Swart, G., Urmanov, A.: Balancing reducer skew in mapreduce workloads using progressive sampling. In: Proceedings of the Third ACM Symposium on Cloud Computing, ACM, 16 (2012)","DOI":"10.1145\/2391229.2391245"},{"key":"9350_CR36","doi-asserted-by":"crossref","unstructured":"Rao, S., Ramakrishnan, R., Silberstein, A., Ovsiannikov, M., Reeves, D.: Sailfish: A framework for large scale data processing. In: Proceedings of the Third ACM Symposium on Cloud Computing, ACM, 4 (2012)","DOI":"10.1145\/2391229.2391233"},{"key":"9350_CR37","doi-asserted-by":"crossref","unstructured":"Rasmussen, A., Conley, M., Porter, G., Kapoor, R., Vahdat, A., et al.: Themis: an i\/o-efficient mapreduce. In: Proceedings of the Third ACM Symposium on Cloud Computing, ACM, 13 (2012)","DOI":"10.1145\/2391229.2391242"},{"issue":"3","key":"9350_CR38","doi-asserted-by":"crossref","first-page":"499","DOI":"10.1007\/s10723-014-9299-2","volume":"12","author":"A Rasooli","year":"2014","unstructured":"Rasooli, A., Down, D.G.: Guidelines for selecting hadoop schedulers based on system heterogeneity. J. Grid Computing 12(3), 499\u2013519 (2014)","journal-title":"J. Grid Computing"},{"key":"9350_CR39","doi-asserted-by":"crossref","unstructured":"Reiss, C., Tumanov, A., Ganger, G.R., Katz, R.H., Kozuch, M.A.: Heterogeneity and dynamicity of clouds at scale: Google trace analysis. In: Proceedings of the Third ACM Symposium on Cloud Computing, ACM, 7 (2012)","DOI":"10.1145\/2391229.2391236"},{"key":"9350_CR40","doi-asserted-by":"crossref","unstructured":"Schad, J., Quianee-Ruiz, J. A., Dittrich, J.: Elephant, do not forget everything! efficient processing of growing datasets. In: Cloud Computing (CLOUD), 2013 IEEE Sixth International Conference on, IEEE, 252\u2013259 (2013)","DOI":"10.1109\/CLOUD.2013.67"},{"key":"9350_CR41","doi-asserted-by":"crossref","unstructured":"Sun, X., He, C., Lu, Y.: Esamr: An enhanced self-adaptive mapreduce scheduling algorithm. In: Parallel and Distributed Systems (ICPADS), 2012 IEEE 18th International Conference on, IEEE, 148\u2013155 (2012)","DOI":"10.1109\/ICPADS.2012.30"},{"key":"9350_CR42","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 al.: Apache hadoop yarn: Yet another resource negotiator. In: Proceedings of the 4th annual Symposium on Cloud Computing, ACM, 5 (2013)","DOI":"10.1145\/2523616.2523633"},{"key":"9350_CR43","doi-asserted-by":"crossref","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, ACM, 420\u2013431 (2012)","DOI":"10.1145\/2247596.2247646"},{"issue":"1","key":"9350_CR44","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1007\/s10723-012-9205-8","volume":"10","author":"W Wang","year":"2012","unstructured":"Wang, W., Zeng, G.: Bayesian cognitive model in scheduling algorithm for data intensive computing. J. Grid Computing 10(1), 173\u2013184 (2012)","journal-title":"J. Grid Computing"},{"key":"9350_CR45","doi-asserted-by":"crossref","unstructured":"Wolf, J., Rajan, D., Hildrum, K., Khandekar, R., Kumar, V., Parekh, S., Wu, K.L., Balmin, A.: Flex: A slot allocation scheduling optimizer for mapreduce workloads. In: Middleware 2010, Springer, 1\u201320 (2010)","DOI":"10.1007\/978-3-642-16955-7_1"},{"key":"9350_CR46","doi-asserted-by":"crossref","unstructured":"Wu, S., Li, F., Mehrotra, S., Ooi, B.C.: Query optimization for massively parallel data processing. In: Proceedings of the 2nd ACM Symposium on Cloud Computing, ACM, 12 (2011)","DOI":"10.1145\/2038916.2038928"},{"key":"9350_CR47","unstructured":"Zaharia, M., Konwinski, A., Joseph, A.D., Katz, R.H., Stoica, I.: Improving mapreduce performance in heterogeneous environments (2008)"},{"key":"9350_CR48","doi-asserted-by":"crossref","unstructured":"Zaharia, M., Borthakur, D., Sen Sarma, J., Elmeleegy, K., Shenker, S., Stoica, I.: Delay scheduling: a simple technique for achieving locality and fairness in cluster scheduling. In: Proceedings of the 5th European conference on Computer systems, ACM, 265\u2013278 (2010)","DOI":"10.1145\/1755913.1755940"},{"key":"9350_CR49","unstructured":"Zhang, J., Zhou, H., Chen, R., Fan, X., Guo, Z., Lin, H., Li, J.Y., Lin, W., Zhou, J., Zhou, L.: Optimizing data shuffling in data-parallel computation by understanding user-defined functions (2012a)"},{"issue":"1","key":"9350_CR50","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s10723-012-9204-9","volume":"10","author":"Y Zhang","year":"2012","unstructured":"Zhang, Y, Gao, Q, Gao, L, Wang, C.: Imapreduce: A distributed computing framework for iterative computation. J. Grid Computing 10(1), 47\u201368 (2012b)","journal-title":"J. Grid Computing"}],"container-title":["Journal of Grid Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-015-9350-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10723-015-9350-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10723-015-9350-y","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,31]],"date-time":"2019-08-31T02:32:14Z","timestamp":1567218734000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10723-015-9350-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,9,29]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["9350"],"URL":"https:\/\/doi.org\/10.1007\/s10723-015-9350-y","relation":{},"ISSN":["1570-7873","1572-9184"],"issn-type":[{"value":"1570-7873","type":"print"},{"value":"1572-9184","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,9,29]]}}}