{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T22:33:32Z","timestamp":1761863612862,"version":"3.41.0"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319448800"},{"type":"electronic","value":"9783319448817"}],"license":[{"start":{"date-parts":[[2016,1,1]],"date-time":"2016-01-01T00:00:00Z","timestamp":1451606400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1007\/978-3-319-44881-7_11","type":"book-chapter","created":{"date-parts":[[2016,10,27]],"date-time":"2016-10-27T07:11:13Z","timestamp":1477552273000},"page":"205-240","source":"Crossref","is-referenced-by-count":11,"title":["Fault Tolerance in MapReduce: A Survey"],"prefix":"10.1007","author":[{"given":"Bunjamin","family":"Memishi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shadi","family":"Ibrahim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mar\u00eda S.","family":"P\u00e9rez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriel","family":"Antoniu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,10,28]]},"reference":[{"key":"11_CR1","unstructured":"Ananthanarayanan, G., Agarwal, S., Kandula, S., Greenberg, A., Stoica, I., Harlan, D., Harris, E.: Scarlett: coping with skewed content popularity in mapreduce clusters. In: Proceedings of the Sixth Conference on Computer Systems, ACM, New York, NY, USA, EuroSys \u201911, pp. 287\u2013300, (2011). http:\/\/doi.acm.org\/10.1145\/1966445.1966472"},{"key":"11_CR2","unstructured":"Ananthanarayanan, G., Ghodsi, A., Shenker, S., Stoica, I.: Effective straggler mitigation: Attack of the clones. In: Proceedings of the 10th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201913, pp. 185\u2013198, (2013). http:\/\/dl.acm.org\/citation.cfm?id=2482626.2482645"},{"key":"11_CR3","unstructured":"Ananthanarayanan, G., Hung, M.C.C., Ren, X., Stoica, I., Wierman, A., Yu, M.: GRASS: trimming stragglers in approximation analytics. In: Proceedings of the 11th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201914, pp. 289\u2013302, (2014). http:\/\/dl.acm.org\/citation.cfm?id=2616448.2616475"},{"key":"11_CR4","unstructured":"Ananthanarayanan, G., Kandula, S., Greenberg, A., Stoica, I., Lu, Y., Saha, B., Harris, E.: Reining in the outliers in map-reduce clusters using Mantri. In: Proceedings of the 9th USENIX conference on Operating Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, OSDI\u201910, pp. 1\u201316, (2010). http:\/\/dl.acm.org\/citation.cfm?id=1924943.1924962"},{"key":"11_CR5","unstructured":"Apache Zookeeper: (2015). http:\/\/zookeeper.apache.org\/"},{"key":"11_CR6","unstructured":"Armbrust, M., Xin, R.S., Lian, C., Huai, Y., Liu, D., Bradley, J.K., Meng, X., Kaftan, T., Franklin, M.J., Ghodsi, A., Zaharia, M.: Spark sql: Relational data processing in spark. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data, ACM, New York, NY, USA, SIGMOD \u201915, pp. 1383\u20131394 (2015). http:\/\/doi.acm.org\/10.1145\/2723372.2742797"},{"issue":"1","key":"11_CR7","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/TDSC.2004.2","volume":"1","author":"A Avizienis","year":"2004","unstructured":"Avizienis, A., Laprie, J.C., Randell, B., Landwehr, C.E.: Basic concepts and taxonomy of dependable and secure computing. IEEE Trans. Dependable Secure Comput. 1(1), 11\u201333 (2004)","journal-title":"IEEE Trans. Dependable Secure Comput."},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Barborak, M., Dahbura, A., Malek, M.: The consensus problem in fault-tolerant computing. ACM Comput. Surv. 25(2), 171\u2013220 (1993). http:\/\/doi.acm.org\/10.1145\/152610.152612","DOI":"10.1145\/152610.152612"},{"key":"11_CR9","unstructured":"Borthakur, D., Gray, J., Sarma, J.S., Muthukkaruppan, K., Spiegelberg, N., Kuang, H., Ranganathan, K., Molkov, D., Menon, A., Rash, S., Schmidt, R., Aiyer, A.: Apache Hadoop goes realtime at Facebook. In: Proceedings of the 2011 ACM SIGMOD International Conference on Management of data, ACM, New York, NY, USA, SIGMOD \u201911, pp. 1071\u20131080 (2011). http:\/\/doi.acm.org\/10.1145\/1989323.1989438"},{"key":"11_CR10","doi-asserted-by":"crossref","unstructured":"Bressoud, T.C., Kozuch, M.A.: Cluster fault-tolerance: An experimental evaluation of checkpointing and MapReduce through simulation. In: Proceedings of the 2009 IEEE International Conference on Cluster Computing and Workshops, IEEE, pp. 1\u201310 (2009). http:\/\/ieeexplore.ieee.org\/lpdocs\/epic03\/wrapper.htm?arnumber=5289185","DOI":"10.1109\/CLUSTR.2009.5289185"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"Cachin, C., Guerraoui, R., Rodrigues, L.: Introduction to Reliable and Secure Distributed Programming (2. ed.). Springer (2011)","DOI":"10.1007\/978-3-642-15260-3"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Chaiken, R., Jenkins, B., Larson, P., Ramsey, B., Shakib, D., Weaver, S., Zhou, J.: SCOPE: Easy and Efficient Parallel Processing of Massive Data Sets. Proc. VLDB Endow 1(2), 1265\u20131276 (2008). http:\/\/dl.acm.org\/citation.cfm?id=1454159.1454166","DOI":"10.14778\/1454159.1454166"},{"issue":"4","key":"11_CR13","doi-asserted-by":"publisher","first-page":"954","DOI":"10.1109\/TC.2013.15","volume":"63","author":"Q Chen","year":"2014","unstructured":"Chen, Q., Liu, C., Xiao, Z.: Improving mapreduce performance using smart speculative execution strategy. IEEE Trans. Comput. 63(4), 954\u2013967 (2014). doi: 10.1109\/TC.2013.15","journal-title":"IEEE Trans. Comput."},{"key":"11_CR14","unstructured":"Chohan, N., Castillo, C., Spreitzer, M., Steinder, M., Tantawi, A., Krintz, C.: See spot run: using spot instances for MapReduce workflows. In: Proceedings of the 2nd USENIX Conference on Hot Topics in Cloud Computing, USENIX Association, Berkeley, CA, USA, HotCloud\u201910, pp. 7\u20137 (2010). http:\/\/dl.acm.org\/citation.cfm?id=1863103.1863110"},{"key":"11_CR15","unstructured":"Clement, A., Kapritsos, M., Lee, S., Wang, Y., Alvisi, L., Dahlin, M., Riche, T.: Upright cluster services. In: Proceedings of the ACM SIGOPS 22nd Symposium on Operating Systems Principles, ACM, New York, NY, USA, SOSP \u201909, pp. 277\u2013290 (2009). http:\/\/doi.acm.org\/10.1145\/1629575.1629602"},{"key":"11_CR16","unstructured":"Condie, T., Conway, N., Alvaro, P., Hellerstein, J.M., Elmeleegy, K., Sears, R.: MapReduce online. In: Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201910, pp. 21\u201321 (2010). http:\/\/dl.acm.org\/citation.cfm?id=1855711.1855732"},{"key":"11_CR17","doi-asserted-by":"publisher","unstructured":"Correia, M., Costa, P., Pasin, M., Bessani, A., Ramos, F., Verissimo, P.: On the feasibility of byzantine fault-tolerant mapreduce in clouds-of-clouds. In: 2012 IEEE 31st Symposium on Reliable Distributed Systems (SRDS), pp. 448\u2013453 (2012). doi: 10.1109\/SRDS.2012.46","DOI":"10.1109\/SRDS.2012.46"},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Costa, P., Pasin, M., Bessani, A., Correia, M.: Byzantine Fault-Tolerant MapReduce: Faults are Not Just Crashes. In: Proceedings of the 3rd IEEE Second International Conference on Cloud Computing Technology and Science, IEEE Computer Society, Washington, DC, USA, CLOUDCOM \u201911, pp. 17\u201324 (2010). http:\/\/dx.doi.org\/10.1109\/CloudCom.2010.25","DOI":"10.1109\/CloudCom.2010.25"},{"key":"11_CR19","unstructured":"Dean, J., Ghemawat, S., Inc, G.: MapReduce: simplified data processing on large clusters. In: Proceedings of the 6th Conference on Symposium on Operating Systems Design & Implementation, USENIX Association, OSDI\u201904 (2004)"},{"key":"11_CR20","unstructured":"Dean, J.: Building software systems at google and lessons learned. Stanford EE Computer Systems Colloquium (2010). http:\/\/www.stanford.edu\/class\/ee380\/Abstracts\/101110-slides.pdf"},{"key":"11_CR21","unstructured":"Dinu, F., Ng, T.S.E.: Hadoop\u2019s Overload Tolerant Design Exacerbates Failure Detection and Recovery. In: Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation, ACM, New York, NY, USA, NetDB\u201911, pp. 1\u20137 (2011)"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Dinu, F., Ng, T.E.: Understanding the effects and implications of compute node related failures in Hadoop. In: HPDC \u201912: Proceedings of the 21st International Symposium on High-Performance Parallel and Distributed Computing, ACM, New York, NY, USA, pp. 187\u2013198 (2012). http:\/\/doi.acm.org\/10.1145\/2287076.2287108","DOI":"10.1145\/2287076.2287108"},{"key":"11_CR23","unstructured":"Facebook, Inc.: (2015). https:\/\/www.facebook.com\/"},{"key":"11_CR24","unstructured":"Facebook, I.: Under the Hood: Scheduling MapReduce jobs more efficiently with Corona (2012). http:\/\/www.facebook.com\/notes\/facebook-engineering\/under-the-hood-scheduling-mapreduce-jobs-more-efficiently-with-corona\/10151142560538920"},{"issue":"5","key":"11_CR25","doi-asserted-by":"crossref","first-page":"961","DOI":"10.1016\/j.jnca.2009.04.002","volume":"32","author":"G Fedak","year":"2009","unstructured":"Fedak, G., He, H., Cappello, F.: BitDew: A data management and distribution service with multi-protocol file transfer and metadata abstraction. J Netw. Compu. Appl. 32(5), 961\u2013975 (2009)","journal-title":"J Netw. Compu. Appl."},{"key":"11_CR26","unstructured":"Gonzalez, J.E., Xin, R.S., Dave, A., Crankshaw, D., Franklin, M.J., Stoica, I.: Graphx: Graph processing in a distributed dataflow framework. In: Proceedings of the 11th USENIX Conference on Operating Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, OSDI\u201914, pp. 599\u2013613 (2014). http:\/\/dl.acm.org\/citation.cfm?id=2685048.2685096"},{"key":"11_CR27","unstructured":"Hadoop Releases: (2015). http:\/\/hadoop.apache.org\/releases.html"},{"key":"11_CR28","unstructured":"Hindman, B., Konwinski, A., Zaharia, M., Ghodsi, A., Joseph, A.D., Katz, R., Shenker, S., Stoica, I.: Mesos: A Platform for Fine-grained Resource Sharing in the Data Center. In: Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201911, pp. 22\u201322 (2011). http:\/\/dl.acm.org\/citation.cfm?id=1972457.1972488"},{"key":"11_CR29","unstructured":"How-to: Set Up a Hadoop Cluster with Network Encryption: (2013). http:\/\/blog.cloudera.com\/blog\/2013\/03\/how-to-set-up-a-hadoop-cluster-with-network-encryption\/"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Ibrahim, S., Phuong, T.A., Antoniu, G.: An Eye on the Elephant in the Wild: A Performance Evaluation of Hadoop\u2019s Schedulers Under Failures. In: Workshop on Adaptive Resource Management and Scheduling for Cloud Computing (ARMS-CC-2015), held in conjunction with PODC\u201915 (2015)","DOI":"10.1007\/978-3-319-28448-4_11"},{"key":"11_CR31","unstructured":"Introduction to Hadoop Security: (2013). http:\/\/www.cloudera.com\/content\/cloudera\/en\/home.html"},{"key":"11_CR32","unstructured":"Isard, M., Budiu, M., Yu, Y., Birrell, A., Fetterly, D.: Dryad: distributed data-parallel programs from sequential building blocks. In: Proceedings of the 2nd ACM SIGOPS\/EuroSys 2007, ACM, New York, NY, USA, EuroSys \u201907, pp. 59\u201372 (2007). http:\/\/doi.acm.org\/10.1145\/1272996.1273005"},{"key":"11_CR33","doi-asserted-by":"publisher","unstructured":"Jin, H., Ibrahim, S., Qi, L., Cao, H., Wu, S., Shi, X.: The MapReduce programming model and implementations. Cloud Computing: Principles and Paradigms pp. 373\u2013390. doi: 10.1002\/9780470940105.ch14","DOI":"10.1002\/9780470940105.ch14"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Jin, H., Qiao, K., Sun, X.H., Li, Y.l.: Performance under Failures of MapReduce Applications. In: Proceedings of the 2011 11th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing, IEEE Computer Society, Washington, DC, USA, CCGRID \u201911, pp. 608\u2013609 (2011). http:\/\/dx.doi.org\/10.1109\/CCGrid.2011.84","DOI":"10.1109\/CCGrid.2011.84"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Jin, H., Sun, X.H.: Performance comparison under failures of MPI and MapReduce: An Analytical Approach. Future Gener. Comput. Syst. 29(7), 1808\u20131815 (2013). http:\/\/dx.doi.org\/10.1016\/j.future.2013.01.013","DOI":"10.1016\/j.future.2013.01.013"},{"key":"11_CR36","unstructured":"Kerberos: The Network Authentication Protocol: (2015). http:\/\/web.mit.edu\/kerberos\/"},{"key":"11_CR37","unstructured":"Ko, S.Y., Hoque, I., Cho, B., Gupta, I.: Making cloud intermediate data fault-tolerant. In: Proceedings of the 1st ACM Symposium on Cloud Computing, ACM, New York, NY, USA, SoCC \u201910, pp. 181\u2013192 (2010). http:\/\/doi.acm.org\/10.1145\/1807128.1807160"},{"key":"11_CR38","unstructured":"Ko, S.Y., Hoque, I., Cho, B., Gupta, I.: On availability of intermediate data in cloud computations. In: Proceedings of the 12th conference on Hot topics in operating systems, USENIX Association, Berkeley, CA, USA, HotOS\u201909, pp. 6\u20136 (2009). http:\/\/dl.acm.org\/citation.cfm?id=1855568.1855574"},{"key":"11_CR39","unstructured":"Lin, H., Ma, X., Archuleta, J., Feng, W.c., Gardner, M., Zhang, Z.: MOON: MapReduce On Opportunistic eNvironments. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, ACM, New York, NY, USA, HPDC \u201910, pp. 95\u2013106 (2010). http:\/\/doi.acm.org\/10.1145\/1851476.1851489"},{"key":"11_CR40","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02136-7","volume-title":"Data-Intensive Text Processing with MapReduce.","author":"J Lin","year":"2010","unstructured":"Lin, J., Dyer, C.: Data-Intensive Text Processing with MapReduce. Tech. rep., University of Maryland, College Park (2010)"},{"key":"11_CR41","doi-asserted-by":"publisher","unstructured":"Liu, H., Orban, D.: Cloud MapReduce: A MapReduce implementation on top of a cloud operating system. In: 2011 11th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 464\u2013474 (2011). doi: 10.1109\/CCGrid.2011.25","DOI":"10.1109\/CCGrid.2011.25"},{"key":"11_CR42","unstructured":"Liu, H.: Cutting MapReduce Cost with Spot Market. In: Proceedings of the 3rd USENIX Conference on Hot topics in Cloud Computing, USENIX Association, Berkeley, CA, USA, HotCloud\u201911, pp. 5\u20135 (2011). https:\/\/www.usenix.org\/conference\/hotcloud11\/cutting-mapreduce-cost-spot-market"},{"key":"11_CR43","doi-asserted-by":"publisher","unstructured":"Memishi, B., Ibrahim, S., P\u00e9rez, M.S., Antoniu, G.: On the Dynamic Shifting of the MapReduce Timeout. In: Kannan, R., Rasool, R.U., Jin, H., Balasundaram, S. (eds) Managing and Processing Big Data in Cloud Computing, IGI Global, Hershey, Pennsylvania (USA), pp. 1\u201322 (2016). doi: 10.4018\/978-1-4666-9767-6","DOI":"10.4018\/978-1-4666-9767-6"},{"key":"11_CR44","doi-asserted-by":"crossref","unstructured":"Memishi, B., P\u00e9rez, M.S., Antoniu, G.: Diarchy: An Optimized Management Approach for MapReduce Masters. Procedia Comput. Sci. 51, 9\u201318 (2015). http:\/\/www.sciencedirect.com\/science\/article\/pii\/S1877050915009874 . International Conference On Computational Science, ICCS Computational Science at the Gates of Nature","DOI":"10.1016\/j.procs.2015.05.179"},{"key":"11_CR45","unstructured":"Microsoft, Inc.: (2015). http:\/\/www.microsoft.com\/"},{"key":"11_CR46","doi-asserted-by":"crossref","unstructured":"Mone, G.: Beyond Hadoop. Commun. ACM 56(1), 22\u201324 (2013). http:\/\/doi.acm.org\/10.1145\/2398356.2398364","DOI":"10.1145\/2398356.2398364"},{"key":"11_CR47","unstructured":"Okorafor, E., Patrick, M.K.: Availability of Jobtracker machine in Hadoop\/MapReduce Zookeeper coordinated clusters. Adv. Comput.: An Int. J. 3(3), 19\u201330 (2012). http:\/\/www.chinacloud.cn\/upload\/2012-07\/12072600543782.pdf"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Pan, X., Tan, J., Kavulya, S., Gandhi, R., Narasimhan, P.: Ganesha: blackBox diagnosis of MapReduce systems. SIGMETRICS Perform. Eval. Rev. 37(3), 8\u201313 (2010). http:\/\/doi.acm.org\/10.1145\/1710115.1710118","DOI":"10.1145\/1710115.1710118"},{"key":"11_CR49","doi-asserted-by":"crossref","unstructured":"Phan, T.D., Ibrahim, S., Antoniu, G., Boug\u00e9, L.: On Understanding the energy impact of speculative execution in Hadoop. In: IEEE International Conference on Green Computing and Communications (GreenCom 2015), Sydney, Australia (2015). https:\/\/hal.inria.fr\/hal-01238055","DOI":"10.1109\/DSDIS.2015.45"},{"key":"11_CR50","unstructured":"RedHat: A guide for developers using the JBoss Enterprise SOA Platform (2008). http:\/\/www.redhat.com\/docs\/en-US\/JBoss_SOA_Platform\/4.3.GA\/html\/Programmers_Guide\/index.html, programmersGuide"},{"key":"11_CR51","unstructured":"Roy, I., Setty, S.T.V., Kilzer, A., Shmatikov, V., Witchel, E.: Airavat: security and privacy for MapReduce. In: Proceedings of the 7th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201910, pp. 20\u201320 (2010). http:\/\/dl.acm.org\/citation.cfm?id=1855711.1855731"},{"key":"11_CR52","unstructured":"Shih, J.: Hadoop security overview\u2014from security infrastructure deployment to high-level services. Hadoop & BigData Technology Conference (2012). www.hbtc2012.hadooper.cn\/subject\/keynotep8shihongliang.pdf"},{"key":"11_CR53","unstructured":"Sorting 1PB with MapReduce: (2013). http:\/\/googleblog.blogspot.com\/2008\/11\/sorting-1pb-with-mapreduce.html"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Stonebraker, M., Abadi, D., DeWitt, D.J., Madden, S., Paulson, E., Pavlo, A., Rasin, A.: MapReduce and parallel DBMSs: friends or foes? Commun. ACM 53:64\u201371 (2010). http:\/\/doi.acm.org\/10.1145\/1629175.1629197","DOI":"10.1145\/1629175.1629197"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Tang, B., Moca, M., Chevalier, S., He, H., Fedak, G.: Towards MapReduce for Desktop Grid Computing. In: Proceedings of the 2010 International Conference on P2P, Parallel, Grid, Cloud and Internet Computing, IEEE Computer Society, Washington, DC, USA, 3PGCIC \u201910, pp. 193\u2013200 (2010). http:\/\/dx.doi.org\/10.1109\/3PGCIC.2010.33","DOI":"10.1109\/3PGCIC.2010.33"},{"key":"11_CR56","unstructured":"The Apache Hadoop Project: (2015). http:\/\/hadoop.apache.org\/"},{"key":"11_CR57","unstructured":"Vavilapalli, V.K., Murthy, A.C., Douglas, C., Agarwal, S., Konar, M., Evans, R., Graves, T., Lowe, J., Shah, H., Seth, S., Saha, B., Curino, C., O\u2019Malley, O., Radia, S., Reed, B., Baldeschwieler, E.: Apache Hadoop YARN: Yet Another Resource Negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, ACM, New York, NY, USA, SoCC \u201913, p. 5:1\u20135:16 (2013). http:\/\/doi.acm.org\/10.1145\/2523616.2523633"},{"key":"11_CR58","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: 17th Annual Meeting of the IEEE\/ACM International Symposium on Modelling, Analysis and Simulation of Computer and Telecommunication Systems, IEEE, MASCOTS 2009, pp. 1\u201311","DOI":"10.1109\/MASCOT.2009.5366973"},{"key":"11_CR59","unstructured":"Wang, F., Qiu, J., Yang, J., Dong, B., Li, X., Li, Y.: Hadoop high availability through metadata replication. In: Proceedings of the First International Workshop on Cloud Data Management, ACM, New York, NY, USA, CloudDB \u201909, pp. 37\u201344 (2009). http:\/\/doi.acm.org\/10.1145\/1651263.1651271"},{"key":"11_CR60","unstructured":"Warneke, D., Kao, O.: Nephele: Efficient parallel data processing in the cloud. In: Proceedings of the 2Nd Workshop on Many-Task Computing on Grids and Supercomputers, ACM, New York, NY, USA, MTAGS \u201909, pp. 8:1\u20138:10 (2009). http:\/\/doi.acm.org\/10.1145\/1646468.1646476"},{"key":"11_CR61","unstructured":"White, T.: Hadoop\u2014The Definitive Guide: Storage and Analysis at Internet Scale (3. ed., revised and updated). O\u2019Reilly (2012)"},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Xiao, Y.: Achieving accountable MapReduce in cloud computing. Future Gener. Comput. Syst. 30, 1\u201313 (2014). http:\/\/dx.doi.org\/10.1016\/j.future.2013.07.001","DOI":"10.1016\/j.future.2013.07.001"},{"key":"11_CR63","doi-asserted-by":"crossref","unstructured":"Xu, H., Lau, W.C.: Optimization for speculative execution in a MapReduce-like cluster. In: 2015 IEEE Conference on Computer Communications, INFOCOM 2015, Kowloon, Hong Kong, April 26\u20131May 1, 2015, pp. 1071\u20131079. http:\/\/dx.doi.org\/10.1109\/INFOCOM.2015.7218480","DOI":"10.1109\/INFOCOM.2015.7218480"},{"key":"11_CR64","doi-asserted-by":"publisher","unstructured":"Xu, H., Lau, W.C.: Speculative execution for a single job in a mapreduce-like system. In: 2014 IEEE 7th International Conference on Cloud Computing (CLOUD), pp. 586\u2013593 (2014). doi: 10.1109\/CLOUD.2014.84","DOI":"10.1109\/CLOUD.2014.84"},{"key":"11_CR65","unstructured":"Yahoo! Inc: (2015). http:\/\/www.yahoo.com\/"},{"key":"11_CR66","doi-asserted-by":"publisher","unstructured":"Yildiz, O., Ibrahim, S., Phuong, T.A., Antoniu, G.: Chronos: Failure-aware scheduling in shared Hadoop clusters. In: IEEE International Conference on Big Data (BigData 2015), pp 313\u2013318 (2015). doi: 10.1109\/BigData.2015.7363770","DOI":"10.1109\/BigData.2015.7363770"},{"key":"11_CR67","unstructured":"Yu, Y., Isard, M., Fetterly, D., Budiu, M., Erlingsson, U., Gunda, P.K., Currey, J.: DryadLINQ: a system for general-purpose distributed data-parallel computing using a high-level language. In: Proceedings of the 8th USENIX Conference on Operating Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, OSDI\u201908, pp. 1\u201314 (2008). http:\/\/dl.acm.org\/citation.cfm?id=1855741.1855742"},{"key":"11_CR68","unstructured":"Zaharia, M., Chowdhury, M., Das, T., Dave, A., Ma, J., McCauley, M., Franklin, M.J., Shenker, S., Stoica, I.: Resilient distributed datasets: A fault-tolerant abstraction for in-memory cluster computing. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, USENIX Association, Berkeley, CA, USA, NSDI\u201912, pp. 2\u20132 (2012). http:\/\/dl.acm.org\/citation.cfm?id=2228298.2228301"},{"key":"11_CR69","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: Cluster computing with working sets. In: Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing, USENIX Association, Berkeley, CA, USA, HotCloud\u201910, pp. 10\u201310 (2010). http:\/\/dl.acm.org\/citation.cfm?id=1863103.1863113"},{"key":"11_CR70","unstructured":"Zaharia, M., Das, T., Li, H., Hunter, T., Shenker, S., Stoica, I.: Discretized streams: Fault-tolerant streaming computation at scale. In: Proceedings of the Twenty-Fourth ACM Symposium on Operating Systems Principles, ACM, New York, NY, USA, SOSP \u201913, pp. 423\u2013438 (2013). http:\/\/doi.acm.org\/10.1145\/2517349.2522737"},{"key":"11_CR71","unstructured":"Zaharia, M., Das, T., Li, H., Shenker, S., Stoica, I.: Discretized streams: An efficient and fault-tolerant model for stream processing on large clusters. In: Proceedings of the 4th USENIX Conference on Hot Topics in Cloud Ccomputing, USENIX Association, Berkeley, CA, USA, HotCloud\u201912, pp. 10\u201310 (2012). http:\/\/dl.acm.org\/citation.cfm?id=2342763.2342773"},{"key":"11_CR72","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, USENIX Association, Berkeley, CA, USA, OSDI\u201908, pp. 29\u201342 (2008). http:\/\/dl.acm.org\/citation.cfm?id=1855741.1855744"},{"key":"11_CR73","doi-asserted-by":"crossref","unstructured":"Zhu, H., Haopeng, C.: Adaptive failure detection via heartbeat under Hadoop. In: Proceedings of the 2011 IEEE Asia-Pacific Services Computing Conference, IEEE, New York, NY, USA, ApSCC\u201911, pp. 231\u2013238 (2011)","DOI":"10.1109\/APSCC.2011.46"}],"container-title":["Computer Communications and Networks","Resource Management for Big Data Platforms"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-44881-7_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T21:41:07Z","timestamp":1749678067000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-44881-7_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"ISBN":["9783319448800","9783319448817"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-44881-7_11","relation":{},"ISSN":["1617-7975","2197-8433"],"issn-type":[{"type":"print","value":"1617-7975"},{"type":"electronic","value":"2197-8433"}],"subject":[],"published":{"date-parts":[[2016]]}}}