{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T04:41:04Z","timestamp":1742964064294,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319639628"},{"type":"electronic","value":"9783319639628"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018]]},"DOI":"10.1007\/978-3-319-63962-8_143-1","type":"book-chapter","created":{"date-parts":[[2018,2,12]],"date-time":"2018-02-12T06:43:27Z","timestamp":1518417807000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Performance Evaluation of Big Data Analysis"],"prefix":"10.1007","author":[{"given":"Jorge","family":"Veiga","sequence":"first","affiliation":[]},{"given":"Roberto R.","family":"Exp\u00f3sito","sequence":"additional","affiliation":[]},{"given":"Juan","family":"Touri\u00f1o","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,1,29]]},"reference":[{"key":"143-1_CR1","unstructured":"Apache Flink (2014) Scalable batch and stream data processing. \n            http:\/\/flink.apache.org\/\n            \n          , [Last visited: Dec 2017]"},{"key":"143-1_CR2","unstructured":"Apache Mahout (2009) Scalable machine learning and data mining. \n            http:\/\/mahout.apache.org\/\n            \n          , [Last visited: Dec 2017]"},{"key":"143-1_CR3","unstructured":"Avery C (2011) Giraph: large-scale graph processing infrastructure on Hadoop. In: 2011 Hadoop summit, Santa Clara, pp 5\u20139"},{"issue":"3","key":"143-1_CR4","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1177\/109434200001400303","volume":"14","author":"S Browne","year":"2000","unstructured":"Browne S, Dongarra J, Garner N, Ho G, Mucci P (2000) A portable programming interface for performance evaluation on modern processors. Int J High Perform Comput Appl 14(3):189\u2013204","journal-title":"Int J High Perform Comput Appl"},{"issue":"10","key":"143-1_CR5","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TSMC.2017.2690673","volume":"47","author":"C Chen","year":"2017","unstructured":"Chen C, Li K, Ouyang A, Tang Z, Li K (2017) GPU-accelerated parallel hierarchical extreme learning machine on Flink for Big Data. IEEE Trans Syst Man Cybern Syst 47(10):2740\u20132753","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"143-1_CR6","doi-asserted-by":"crossref","unstructured":"Choi IS, Yang W, Kee YS (2015) Early experience with optimizing I\/O performance using high-performance SSDs for in-memory cluster computing. In: 2015 IEEE international conference on Big Data (IEEE BigData 2015), Santa Clara, pp 1073\u20131083","DOI":"10.1109\/BigData.2015.7363861"},{"issue":"1","key":"143-1_CR7","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"J Dean","year":"2008","unstructured":"Dean J, Ghemawat S (2008) MapReduce: simplified data processing on large clusters. Commun ACM 51(1):107\u2013113","journal-title":"Commun ACM"},{"key":"143-1_CR8","unstructured":"Enes J, Exp\u00f3sito RR, Touri\u00f1o J (2017) Big Data watchdog: real-time monitoring and profiling. \n            http:\/\/bdwatchdog.dec.udc.es\n            \n          , [Last visited: Dec 2017]"},{"key":"143-1_CR9","doi-asserted-by":"crossref","unstructured":"Fadika Z, Govindaraju M, Canon R, Ramakrishnan L (2012) Evaluating Hadoop for data-intensive scientific operations. In: 5th IEEE international conference on cloud computing (CLOUD\u201912), Honolulu, pp 67\u201374","DOI":"10.1109\/CLOUD.2012.118"},{"key":"143-1_CR10","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.future.2013.12.007","volume":"36","author":"Z Fadika","year":"2014","unstructured":"Fadika Z, Dede E, Govindaraju M, Ramakrishnan L (2014) MARIANE: using MApReduce in HPC environments. Futur Gener Comput Syst 36:379\u2013388","journal-title":"Futur Gener Comput Syst"},{"issue":"4","key":"143-1_CR11","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/TPDS.2010.158","volume":"22","author":"W Fang","year":"2011","unstructured":"Fang W, He B, Luo Q, Govindaraju NK (2011) Mars: accelerating MapReduce with graphics processors. IEEE Trans Parallel Distrib Syst 22(4):608\u2013620","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"143-1_CR12","unstructured":"Gog I, Giceva J, Schwarzkopf M, Vaswani K, Vytiniotis D, Ramalingan G, Costa M, Murray D, Hand S, Isard M (2015) Broom: sweeping out garbage collection from Big Data systems. In: 15th workshop on hot topics in operating systems (HotOS\u201915), Kartause Ittingen"},{"key":"143-1_CR13","doi-asserted-by":"crossref","unstructured":"Gonz\u00e1lez P, Pardo XC, Penas DR, Teijeiro D, Banga JR, Doallo R (2017) Using the cloud for parameter estimation problems: comparing Spark vs MPI with a case-study. In: 17th IEEE\/ACM international symposium on cluster, cloud and grid computing (CCGrid 2017), Madrid, pp 797\u2013806","DOI":"10.1109\/CCGRID.2017.58"},{"key":"143-1_CR14","doi-asserted-by":"crossref","unstructured":"Huang S, Huang J, Dai J, Xie T, Huang B (2010) The HiBench benchmark suite: characterization of the MapReduce-based data analysis. In: 26th IEEE international conference on data engineering workshops (ICDEW\u201910), Long Beach, pp 41\u201351","DOI":"10.1109\/ICDEW.2010.5452747"},{"key":"143-1_CR15","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.future.2016.03.003","volume":"65","author":"YS Lee","year":"2016","unstructured":"Lee YS, Quero LC, Kim SH, Kim JS, Maeng S (2016) ActiveSort: efficient external sorting using active SSDs in the MapReduce framework. Futur Gener Comput Syst 65:76\u201389","journal-title":"Futur Gener Comput Syst"},{"issue":"11","key":"143-1_CR16","doi-asserted-by":"publisher","first-page":"3201","DOI":"10.1109\/TPDS.2017.2712635","volume":"28","author":"Z Li","year":"2017","unstructured":"Li Z, Shen H (2017) Measuring scale-up and scale-out Hadoop with remote and local file systems and selecting the best platform. IEEE Trans Parallel Distrib Syst 28(11):3201\u20133214","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"143-1_CR17","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1007\/s10586-016-0723-1","volume":"20","author":"M Li","year":"2017","unstructured":"Li M, Tan J, Wang Y, Zhang L, Salapura V (2017) SparkBench: a Spark benchmarking suite characterizing large-scale in-memory data analytics. Clust Comput 20(3):2575\u20132589","journal-title":"Clust Comput"},{"key":"143-1_CR18","doi-asserted-by":"crossref","unstructured":"Liang F, Feng C, Lu X, Xu Z (2014) Performance benefits of DataMPI: a case study with BigDataBench. In: 4th workshop on Big Data benchmarks, performance optimization and emerging hardware (BPOE\u201914), Salt Lake City, pp 111\u2013123","DOI":"10.1007\/978-3-319-13021-7_9"},{"issue":"7","key":"143-1_CR19","doi-asserted-by":"publisher","first-page":"762","DOI":"10.14778\/2752939.2752945","volume":"8","author":"D Loghin","year":"2015","unstructured":"Loghin D, Tudor BM, Zhang H, Ooi BC, Teo YM (2015) A performance study of Big Data on small nodes. Proc VLDB Endowment 8(7):762\u2013773","journal-title":"Proc VLDB Endowment"},{"issue":"11","key":"143-1_CR20","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1109\/TPDS.2014.2365784","volume":"26","author":"M Lu","year":"2015","unstructured":"Lu M, Liang Y, Huynh HP, Ong Z, He B, Goh RSM (2015) MrPhi: an optimized MapReduce framework on Intel Xeon Phi coprocessors. IEEE Trans Parallel Distrib Syst 26(11):3066\u20133078","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"12","key":"143-1_CR21","doi-asserted-by":"publisher","first-page":"936","DOI":"10.14778\/2994509.2994513","volume":"9","author":"L Lu","year":"2016","unstructured":"Lu L, Shi X, Zhou Y, Zhang X, Jin H, Pei C, He L, Geng Y (2016a) Lifetime-based memory management for distributed data processing systems. Proc VLDB Endowment 9(12):936\u2013947","journal-title":"Proc VLDB Endowment"},{"key":"143-1_CR22","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/BigData.2016.7840611","volume-title":"2016 IEEE international conference on Big Data (IEEE BigData 2016)","author":"X Lu","year":"2016","unstructured":"Lu X, Shankar D, Gugnani S, Panda DK (2016b) High-performance design of Apache Spark with RDMA and its benefits on various workloads. In: 2016 IEEE international conference on Big Data (IEEE BigData 2016), Washington, DC, pp 253\u2013262"},{"key":"143-1_CR23","doi-asserted-by":"crossref","unstructured":"Malik M, Rafatirah S, Sasan A, Homayoun H (2015) System and architecture level characterization of Big Data applications on big and little core server architectures. In: 2015 IEEE international conference on Big Data (IEEE BigData 2015), Santa Clara, pp 85\u201394","DOI":"10.1109\/BigData.2015.7363745"},{"key":"143-1_CR24","doi-asserted-by":"crossref","unstructured":"Moon S, Lee J, Kee YS (2014) Introducing SSDs to the Hadoop MapReduce framework. In: 7th IEEE international conference on cloud computing (CLOUD\u201914), Anchorage, pp 272\u2013279","DOI":"10.1109\/CLOUD.2014.45"},{"key":"143-1_CR25","doi-asserted-by":"crossref","unstructured":"Neshatpour K, Malik M, Ghodrat MA, Sasan A, Homayoun H (2015) Energy-efficient acceleration of Big Data analytics applications using FPGAs. In: 2015 IEEE international conference on Big Data (IEEE BigData 2015), Santa Clara, pp 115\u2013123","DOI":"10.1109\/BigData.2015.7363748"},{"key":"143-1_CR26","unstructured":"Nguyen K, Fang L, Xu GH, Demsky B, Lu S, Alamian S, Mutlu O (2016) Yak: a high-performance Big-Data-friendly garbage collector. In: 12th USENIX symposium on operating systems design and implementation (OSDI\u201916), Savannah, pp 349\u2013365"},{"key":"143-1_CR27","unstructured":"Sangroya A, Serrano D, Bouchenak S (2012) MRBS: towards dependability benchmarking for Hadoop MapReduce. In: 18th international Euro-par conference on parallel processing workshops (Euro-Par\u201912), Rhodes Island, pp 3\u201312"},{"key":"143-1_CR28","doi-asserted-by":"crossref","unstructured":"Veiga J, Exp\u00f3sito RR, Taboada GL, Touri\u00f1o J (2015) MREv: an automatic MapReduce evaluation tool for Big Data workloads. In: International conference on computational science (ICCS\u201915), Reykjav\u00edk, pp 80\u201389","DOI":"10.1016\/j.procs.2015.05.202"},{"key":"143-1_CR29","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/BigData.2016.7840633","volume-title":"2016 IEEE international conference on Big Data (IEEE BigData 2016)","author":"J Veiga","year":"2016","unstructured":"Veiga J, Exp\u00f3sito RR, Pardo XC, Taboada GL, Touri\u00f1o J (2016a) Performance evaluation of Big Data frameworks for large-scale data analytics. In: 2016 IEEE international conference on Big Data (IEEE BigData 2016), Washington, DC, pp 424\u2013431"},{"key":"143-1_CR30","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1016\/j.compeleceng.2015.11.021","volume":"50","author":"J Veiga","year":"2016","unstructured":"Veiga J, Exp\u00f3sito RR, Taboada GL, Touri\u00f1o J (2016b) Analysis and evaluation of MapReduce solutions on an HPC cluster. Comput Electr Eng 50:200\u2013216","journal-title":"Comput Electr Eng"},{"key":"143-1_CR31","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.future.2016.06.006","volume":"65","author":"J Veiga","year":"2016","unstructured":"Veiga J, Exp\u00f3sito RR, Taboada GL, Touri\u00f1o J (2016c) Flame-MR: an event-driven architecture for MapReduce applications. Futur Gener Comput Syst 65:46\u201356","journal-title":"Futur Gener Comput Syst"},{"key":"143-1_CR32","doi-asserted-by":"crossref","unstructured":"Wang Y, Que X, Yu W, Goldenberg D, Sehgal D (2011) Hadoop acceleration through network levitated merge. In: International conference for high performance computing, networking, storage and analysis (SC\u201911), Seattle, pp 57:1\u201357:10","DOI":"10.1145\/2063384.2063461"},{"key":"143-1_CR33","doi-asserted-by":"crossref","unstructured":"Wang L, Zhan J, Luo C, Zhu Y, Yang Q, He Y, Gao W, Jia Z, Shi Y, Zhang S, Zheng C, Lu G, Zhan K, Li X, Qiu B (2014) BigDataBench: a Big Data benchmark suite from Internet services. In: 20th IEEE international symposium on high-performance computer architecture (HPCA\u201914), Orlando, pp 488\u2013499","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"143-1_CR34","doi-asserted-by":"crossref","unstructured":"Wasi-Ur-Rahman M, Islam NS, Lu X, Jose J, Subramoni H, Wang H, Panda DK (2013) High-performance RDMA-based design of Hadoop MapReduce over InfiniBand. In: 27th IEEE international parallel and distributed processing symposium workshops and PhD forum (IPDPSW\u201913), Boston, pp 1908\u20131917","DOI":"10.1109\/IPDPSW.2013.238"},{"key":"143-1_CR35","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.parco.2016.08.001","volume":"61","author":"P Xuan","year":"2017","unstructured":"Xuan P, Ligon WB, Srimani PK, Ge R, Luo F (2017) Accelerating Big Data analytics on HPC clusters using two-level storage. Parallel Comput 61:18\u201334","journal-title":"Parallel Comput"},{"key":"143-1_CR36","doi-asserted-by":"crossref","unstructured":"Yang D, Zhong X, Yan D, Dai F, Yin X, Lian C, Zhu Z, Jiang W, Wu G (2013) NativeTask: a Hadoop compatible framework for high performance. In: 2013 IEEE international conference on Big Data (IEEE BigData\u201913), Santa Clara, pp 94\u2013101","DOI":"10.1109\/BigData.2013.6691703"},{"key":"143-1_CR37","unstructured":"Yoo T, Yim M, Jeong I, Lee Y, Chun ST (2016) Performance evaluation of in-memory computing on scale-up and scale-out cluster. In: 8th international conference on ubiquitous and future networks (ICUFN\u20196), Vienna, pp 456\u2013461"},{"key":"143-1_CR38","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1109\/BigData.2016.7840613","volume-title":"2016 IEEE international conference on Big Data (IEEE BigData\u201916)","author":"Y Yuan","year":"2016","unstructured":"Yuan Y, Salmi MF, Huai Y, Wang K, Lee R, Zhang X (2016) Spark-GPU: an accelerated in-memory data processing engine on clusters. In: 2016 IEEE international conference on Big Data (IEEE BigData\u201916), Washington, DC, pp 273\u2013283"},{"issue":"11","key":"143-1_CR39","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia M, Xin RS, Wendell P, Das T, Armbrust M, Dave A, Meng X, Rosen J, Venkataraman S, Franklin MJ, Ghodsi A, Gonzalez J, Shenker S, Stoica I (2016) Apache Spark: a unified engine for Big Data processing. Commun ACM 59(11):56\u201365","journal-title":"Commun ACM"}],"container-title":["Encyclopedia of Big Data Technologies"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-63962-8_143-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,10]],"date-time":"2019-05-10T02:22:23Z","timestamp":1557454943000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-63962-8_143-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319639628","9783319639628"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-63962-8_143-1","relation":{},"subject":[],"published":{"date-parts":[[2018]]},"assertion":[{"value":"29 January 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}