{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T08:16:36Z","timestamp":1780647396306,"version":"3.54.1"},"reference-count":85,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T00:00:00Z","timestamp":1644796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61972118"],"award-info":[{"award-number":["61972118"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013096","name":"Science and Technology Project of State Grid","doi-asserted-by":"publisher","award":["5700{202018194A-0-0-00,SGSDXT00DKJS1900040"],"award-info":[{"award-number":["5700{202018194A-0-0-00,SGSDXT00DKJS1900040"]}],"id":[{"id":"10.13039\/501100013096","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2022,6]]},"DOI":"10.1007\/s00607-022-01056-7","type":"journal-article","created":{"date-parts":[[2022,2,14]],"date-time":"2022-02-14T21:02:45Z","timestamp":1644872565000},"page":"1425-1460","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Scalability and performance analysis of BDPS in clouds"],"prefix":"10.1007","volume":"104","author":[{"given":"Yuegang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongyang","family":"Ou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congfeng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christophe","family":"C\u00e9rin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,2,14]]},"reference":[{"key":"1056_CR1","unstructured":"AdOC. http:\/\/www.labri.fr\/perso\/ejeannot\/old\/adoc\/adoc.html"},{"key":"1056_CR2","unstructured":"Alibaba Cloud E-MapReduce. https:\/\/www.alibabacloud.com\/products\/emapreduce\/"},{"key":"1056_CR3","unstructured":"Amazon EMR. https:\/\/aws.amazon.com\/emr\/"},{"key":"1056_CR4","unstructured":"Apache HBase. https:\/\/hbase.apache.org\/"},{"key":"1056_CR5","unstructured":"Baidu BMR. https:\/\/cloud.baidu.com\/product\/bmr.html"},{"key":"1056_CR6","unstructured":"BDAS Spark SQL. https:\/\/spark.apache.org\/sql\/"},{"key":"1056_CR7","unstructured":"BZIP2. https:\/\/www.sourceware.org\/bzip2\/"},{"key":"1056_CR8","unstructured":"Cloudera Impala. https:\/\/www.cloudera.com\/products\/open-source\/apache-hadoop\/impala.html"},{"key":"1056_CR9","unstructured":"CloudSuite. http:\/\/cloudsuite.ch\/"},{"key":"1056_CR10","unstructured":"Flink. https:\/\/flink.apache.org\/"},{"key":"1056_CR11","unstructured":"GZIP. http:\/\/www.gzip.org\/"},{"key":"1056_CR12","unstructured":"Hadoop. https:\/\/hadoop.apache.org\/"},{"key":"1056_CR13","unstructured":"Hive. https:\/\/hive.apache.org\/"},{"key":"1056_CR14","unstructured":"LZO. http:\/\/www.oberhumer.com\/opensource\/lzo\/"},{"key":"1056_CR15","unstructured":"Microsoft Azure HDInsight. https:\/\/azure.microsoft.com\/en-us\/services\/hdinsight\/"},{"key":"1056_CR16","unstructured":"OrangeFS. http:\/\/www.orangefs.org\/"},{"key":"1056_CR17","unstructured":"SNAPPY. http:\/\/google.github.io\/snappy\/"},{"key":"1056_CR18","unstructured":"Spark. https:\/\/spark.csdn.net\/"},{"key":"1056_CR19","doi-asserted-by":"publisher","unstructured":"Ahmad AAS, Andras P (2018) Measuring the scalability of cloud-based software services. In: 2018 IEEE world congress on services (SERVICES). IEEE, pp 5\u20136. https:\/\/doi.org\/10.1109\/SERVICES.2018.00016","DOI":"10.1109\/SERVICES.2018.00016"},{"key":"1056_CR20","unstructured":"Ahmad F, Lee S, Thottethodi M, Vijaykumar T (2012) PUMA: purdue mapreduce benchmarks suite"},{"key":"1056_CR21","doi-asserted-by":"publisher","unstructured":"Amdahl GM (1967) Validity of the single processor approach to achieving large scale computing capabilities. In: Proceedings of the April 18-20, 1967, spring joint computer conference. ACM, pp 483\u2013485. https:\/\/doi.org\/10.1145\/1465482.1465560","DOI":"10.1145\/1465482.1465560"},{"key":"1056_CR22","doi-asserted-by":"publisher","unstructured":"Appuswamy R, Gkantsidis C, Narayanan D, Hodson O, Rowstron A (2013) Scale-up vs scale-out for Hadoop: time to rethink? In: Proceedings of the 4th annual symposium on cloud computing. ACM, p\u00a020. https:\/\/doi.org\/10.1145\/2523616.2523629","DOI":"10.1145\/2523616.2523629"},{"issue":"1","key":"1056_CR23","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1089\/big.2013.1509","volume":"1","author":"C Baru","year":"2013","unstructured":"Baru C, Bhandarkar M, Nambiar R, Poess M, Rabl T (2013) Benchmarking big data systems and the bigdata top100 list. Big Data 1(1):60\u201364. https:\/\/doi.org\/10.1089\/big.2013.1509","journal-title":"Big Data"},{"key":"1056_CR24","doi-asserted-by":"publisher","unstructured":"Chang BR, Tsai HF, Wang YA (2016) Optimized multiple platforms for big data analysis. In: 2016 IEEE second international conference on multimedia Big Data (BigMM). IEEE, pp 155\u2013158. https:\/\/doi.org\/10.1109\/BigMM.2016.61","DOI":"10.1109\/BigMM.2016.61"},{"key":"1056_CR25","doi-asserted-by":"publisher","unstructured":"Chen Q, Zhang D, Guo M, Deng Q, Guo S (2010) Samr: a self-adaptive mapreduce scheduling algorithm in heterogeneous environment. In: 2010 10th IEEE international conference on computer and information technology. IEEE, pp 2736\u20132743. https:\/\/doi.org\/10.1109\/CIT.2010.458","DOI":"10.1109\/CIT.2010.458"},{"key":"1056_CR26","doi-asserted-by":"publisher","unstructured":"Cooper BF, Silberstein A, Tam E, Ramakrishnan R, Sears R (2010) Benchmarking cloud serving systems with YCSB. In: Proceedings of the 1st ACM symposium on cloud computing. ACM, pp 143\u2013154. https:\/\/doi.org\/10.1145\/1807128.1807152","DOI":"10.1145\/1807128.1807152"},{"key":"1056_CR27","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/j.future.2014.01.001","volume":"36","author":"E Dede","year":"2014","unstructured":"Dede E, Fadika Z, Govindaraju M, Ramakrishnan L (2014) Benchmarking MapReduce implementations under different application scenarios. Future Gener Comput Syst 36:389\u2013399. https:\/\/doi.org\/10.1016\/j.future.2014.01.001","journal-title":"Future Gener Comput Syst"},{"key":"1056_CR28","doi-asserted-by":"publisher","unstructured":"Dharanipragada J, Padala S, Kammili B, Kumar V (2017) Tula: a disk latency aware balancing and block placement strategy for Hadoop. In: 2017 IEEE international conference on Big Data (Big Data). IEEE, pp 2853\u20132858. https:\/\/doi.org\/10.1109\/BigData.2017.8258253","DOI":"10.1109\/BigData.2017.8258253"},{"key":"1056_CR29","unstructured":"Echihabi K, Zoumpatianos K, Palpanas T (2020) Big sequence management: on scalability. In: Proceedings of the IEEE international conference on Big Data. IEEE BigData"},{"issue":"1","key":"1056_CR30","doi-asserted-by":"publisher","first-page":"65","DOI":"10.5815\/ijitcs.2017.01.08","volume":"9","author":"SA Elmubarak","year":"2017","unstructured":"Elmubarak SA, Yousif A, Bashir MB (2017) Performance based ranking model for cloud SaaS services. Int J Inf Technol Comput Sci 9(1):65\u201371. https:\/\/doi.org\/10.5815\/ijitcs.2017.01.08","journal-title":"Int J Inf Technol Comput Sci"},{"key":"1056_CR31","doi-asserted-by":"publisher","unstructured":"Ferdman M, Adileh A, Kocberber O, Volos S, Alisafaee M, Jevdjic D, Kaynak C, Popescu AD, Ailamaki A, Falsafi B (2012) Clearing the clouds: a study of emerging scale-out workloads on modern hardware. In: ACM SIGPLAN Notices, vol\u00a047. ACM, pp 37\u201348. https:\/\/doi.org\/10.1145\/2150976.2150982","DOI":"10.1145\/2150976.2150982"},{"key":"1056_CR32","doi-asserted-by":"publisher","unstructured":"Gao J, Manjula K, Roopa P, Sumalatha E, Bai X, Tsai WT, Uehara T (2012) A cloud-based TaaS infrastructure with tools for SaaS validation, performance and scalability evaluation. In: 4th IEEE international conference on cloud computing technology and science proceedings. IEEE, pp 464\u2013471. https:\/\/doi.org\/10.1109\/CloudCom.2012.6427555","DOI":"10.1109\/CloudCom.2012.6427555"},{"key":"1056_CR33","doi-asserted-by":"publisher","unstructured":"Gao J, Pattabhiraman P, Bai X, Tsai WT (2011) SaaS performance and scalability evaluation in clouds. In: Proceedings of 2011 IEEE 6th international symposium on service oriented system (SOSE). IEEE, pp 61\u201371. https:\/\/doi.org\/10.1109\/SOSE.2011.6139093","DOI":"10.1109\/SOSE.2011.6139093"},{"key":"1056_CR34","doi-asserted-by":"crossref","unstructured":"Garate-Escamilla AK, El\u00a0Hassani AH, Andres E (2019) Big data scalability based on spark machine learning libraries. In: Proceedings of the 2019 3rd international conference on Big Data research, pp 166\u2013171","DOI":"10.1145\/3372454.3372469"},{"key":"1056_CR35","doi-asserted-by":"publisher","unstructured":"Garg N, Janakiram D (2018) Sparker: optimizing spark for heterogeneous clusters. In: 2018 IEEE international conference on cloud computing technology and science (CloudCom). IEEE, pp 1\u20138. https:\/\/doi.org\/10.1109\/CloudCom2018.2018.00017","DOI":"10.1109\/CloudCom2018.2018.00017"},{"key":"1056_CR36","doi-asserted-by":"publisher","unstructured":"Ghasemi E, Chow P (2016) Accelerating Apache Spark big data analysis with fpgas. In: 2016 Intl IEEE conferences on ubiquitous intelligence & computing, advanced and trusted computing, scalable computing and communications, cloud and Big Data computing, internet of people, and smart world congress (UIC\/ATC\/ScalCom\/CBDCom\/IoP\/SmartWorld). IEEE, pp 737\u2013744. https:\/\/doi.org\/10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0119","DOI":"10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0119"},{"key":"1056_CR37","doi-asserted-by":"publisher","unstructured":"Ghazal A, Rabl T, Hu M, Raab F, Poess M, Crolotte A, Jacobsen HA (2013) BigBench: Towards an industry standard benchmark for big data analytics. In: Proceedings of the 2013 ACM SIGMOD international conference on Management of data. ACM, pp 1197\u20131208. https:\/\/doi.org\/10.1145\/2463676.2463712","DOI":"10.1145\/2463676.2463712"},{"key":"1056_CR38","doi-asserted-by":"publisher","unstructured":"Govindaraju V, Idicula S, Agrawal S, Vardarajan V, Raghavan A, Wen J, Balkesen C, Giannikis G, Agarwal N, Sedlar E (2017) Big data processing: scalability with extreme single-node performance. In: 2017 IEEE international congress on Big Data (BigData Congress). IEEE, pp 129\u2013136. https:\/\/doi.org\/10.1109\/BigDataCongress.2017.26","DOI":"10.1109\/BigDataCongress.2017.26"},{"issue":"8","key":"1056_CR39","first-page":"12","volume":"4","author":"A Grama","year":"1996","unstructured":"Grama A, Gupta A, Kumar V (1996) Isoefficiency function: a scalability metric for parallel algorithms and architectures. IEEE Trans Parallel Distrib Syst 4(8):12\u201321","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"1056_CR40","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1109\/88.242438","volume":"1","author":"AY Grama","year":"1993","unstructured":"Grama AY, Gupta A, Kumar V (1993) Isoefficiency: measuring the scalability of parallel algorithms and architectures. IEEE Parallel Distrib Technol Syst Appl 1(3):12\u201321. https:\/\/doi.org\/10.1109\/88.242438","journal-title":"IEEE Parallel Distrib Technol Syst Appl"},{"issue":"5","key":"1056_CR41","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1145\/2773212.2789974","volume":"13","author":"N Gunther","year":"2015","unstructured":"Gunther N, Puglia P, Tomasette K (2015) Hadoop superlinear scalability. Queue 13(5):20. https:\/\/doi.org\/10.1145\/2773212.2789974","journal-title":"Queue"},{"issue":"6","key":"1056_CR42","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1109\/TPDS.2016.2587645","volume":"28","author":"Y Guo","year":"2016","unstructured":"Guo Y, Rao J, Cheng D, Zhou X (2016) Ishuffle: improving hadoop performance with shuffle-on-write. IEEE Trans Parallel Distrib Syst 28(6):1649\u20131662. https:\/\/doi.org\/10.1109\/TPDS.2016.2587645","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"5","key":"1056_CR43","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1145\/42411.42415","volume":"31","author":"JL Gustafson","year":"1988","unstructured":"Gustafson JL (1988) Reevaluating Amdahl\u2019s law. Commun ACM 31(5):532\u2013533. https:\/\/doi.org\/10.1145\/42411.42415","journal-title":"Commun ACM"},{"key":"1056_CR44","doi-asserted-by":"crossref","unstructured":"Henning S, Hasselbring W (2021) How to measure scalability of distributed stream processing engines? In: Companion of the ACM\/SPEC international conference on performance engineering, pp 85\u201388","DOI":"10.1145\/3447545.3451190"},{"key":"1056_CR45","doi-asserted-by":"publisher","unstructured":"Huang S, Huang J, Dai J, Xie T, Huang B (2010) The HiBench benchmark suite: characterization of the MapReduce-based data analysis. In: 2010 IEEE 26th international conference on data engineering workshops (ICDEW 2010). IEEE, pp 41\u201351 (2010). https:\/\/doi.org\/10.1109\/ICDEW.2010.5452747","DOI":"10.1109\/ICDEW.2010.5452747"},{"issue":"1","key":"1056_CR46","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/TPDS.2015.2398438","volume":"27","author":"K Hwang","year":"2015","unstructured":"Hwang K, Bai X, Shi Y, Li M, Chen WG, Wu Y (2015) Cloud performance modeling with benchmark evaluation of elastic scaling strategies. IEEE Trans Parallel Distrib Syst 27(1):130\u2013143. https:\/\/doi.org\/10.1109\/TPDS.2015.2398438","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1056_CR47","doi-asserted-by":"publisher","unstructured":"Hwang K, Shi Y, Bai X (2014) Scale-out vs. scale-up techniques for cloud performance and productivity. In: 2014 IEEE 6th international conference on cloud computing technology and science. IEEE, pp 763\u2013768. https:\/\/doi.org\/10.1109\/CloudCom.2014.66","DOI":"10.1109\/CloudCom.2014.66"},{"key":"1056_CR48","doi-asserted-by":"publisher","unstructured":"Iosup A, Epema D (2006) Grenchmark: a framework for analyzing, testing, and comparing grids. In: Sixth IEEE international symposium on cluster computing and the grid (CCGRID\u201906), vol\u00a01. IEEE, pp 313\u2013320. https:\/\/doi.org\/10.1109\/CCGRID.2006.49","DOI":"10.1109\/CCGRID.2006.49"},{"key":"1056_CR49","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1016\/j.comcom.2020.01.004","volume":"151","author":"C Jiang","year":"2020","unstructured":"Jiang C, Fan T, Gao H, Shi W, Liu L, Cerin C, Wan J (2020) Energy aware edge computing: a survey. Comput Commun 151:556\u2013580","journal-title":"Comput Commun"},{"issue":"12","key":"1056_CR50","doi-asserted-by":"publisher","first-page":"4395","DOI":"10.3390\/s18124395","volume":"18","author":"C Jiang","year":"2018","unstructured":"Jiang C, Fan T, Qiu Y, Wu H, Zhang J, Xiong N, Wan J (2018) Interdomain I\/O optimization in virtualized sensor networks. Sensors 18(12):4395. https:\/\/doi.org\/10.3390\/s18124395","journal-title":"Sensors"},{"key":"1056_CR51","doi-asserted-by":"publisher","first-page":"22495","DOI":"10.1109\/ACCESS.2019.2897898","volume":"7","author":"C Jiang","year":"2019","unstructured":"Jiang C, Han G, Lin J, Jia G, Shi W, Wan J (2019) Characteristics of co-allocated online services and batch jobs in internet data centers: a case study from Alibaba cloud. IEEE Access 7:22495\u201322508","journal-title":"IEEE Access"},{"key":"1056_CR52","doi-asserted-by":"crossref","unstructured":"Jiang C, Qiu Y, Shi W, Ge Z, Wang J, Chen S, Cerin C, Ren Z, Xu G, Lin J (2020) Characterizing co-located workloads in Alibaba cloud datacenters. IEEE Trans Cloud Comput","DOI":"10.1109\/TCC.2020.3034500"},{"key":"1056_CR53","doi-asserted-by":"publisher","unstructured":"Jiang C, Wang Y, Ou D, Li Y, Zhang J, Wan J, Luo B, Shi W (2017) Energy efficiency comparison of hypervisors. Sustain Comput Inform Syst. https:\/\/doi.org\/10.1016\/j.suscom.2017.09.005","DOI":"10.1016\/j.suscom.2017.09.005"},{"key":"1056_CR54","doi-asserted-by":"publisher","unstructured":"Jiang C, Wang Y, Ou D, Luo B, Shi W (2017) Energy proportional servers: where are we in 2016? In: 2017 IEEE 37th international conference on distributed computing systems (ICDCS). IEEE, pp 1649\u20131660. https:\/\/doi.org\/10.1109\/ICDCS.2017.285","DOI":"10.1109\/ICDCS.2017.285"},{"key":"1056_CR55","doi-asserted-by":"crossref","unstructured":"Jiang C, Wang Y, Ou D, Qiu Y, Li Y, Wan J, Luo B, Shi W, Cerin C (2018) Ease: energy efficiency and proportionality aware virtual machine scheduling. In: 2018 30th international symposium on computer architecture and high performance computing (SBAC-PAD). IEEE, pp 65\u201368","DOI":"10.1109\/CAHPC.2018.8645948"},{"issue":"6","key":"1056_CR56","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1109\/71.862209","volume":"11","author":"P Jogalekar","year":"2000","unstructured":"Jogalekar P, Woodside M (2000) Evaluating the scalability of distributed systems. IEEE Trans Parallel Distrib Syst 11(6):589\u2013603. https:\/\/doi.org\/10.1109\/71.862209","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1056_CR57","doi-asserted-by":"publisher","unstructured":"Kim K, Jeon K, Han H, Kim S.g, Jung H, Yeom HY (2008) Mrbench: a benchmark for MapReduce framework. In: 2008 14th IEEE international conference on parallel and distributed systems. IEEE, pp 11\u201318. https:\/\/doi.org\/10.1109\/ICPADS.2008.70","DOI":"10.1109\/ICPADS.2008.70"},{"key":"1056_CR58","doi-asserted-by":"publisher","unstructured":"Lee JY, Lee JW, Kim SD, et\u00a0al (2009) A quality model for evaluating software-as-a-service in cloud computing. In: 2009 seventh ACIS international conference on software engineering research, management and applications. IEEE, pp 261\u2013266. https:\/\/doi.org\/10.1109\/SERA.2009.43","DOI":"10.1109\/SERA.2009.43"},{"key":"1056_CR59","doi-asserted-by":"publisher","unstructured":"Li M, Tan J, Wang Y, Zhang L, Salapura V (2015) Sparkbench: a comprehensive benchmarking suite for in memory data analytic platform Spark. In: Proceedings of the 12th ACM international conference on computing frontiers. ACM, p\u00a053. https:\/\/doi.org\/10.1145\/2742854.2747283","DOI":"10.1145\/2742854.2747283"},{"issue":"11","key":"1056_CR60","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. https:\/\/doi.org\/10.1109\/TPDS.2017.2712635","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"3","key":"1056_CR61","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1109\/MIC.2018.032501520","volume":"22","author":"J Lin","year":"2018","unstructured":"Lin J (2018) Scale up or scale out for graph processing? IEEE Internet Comput 22(3):72\u201378. https:\/\/doi.org\/10.1109\/MIC.2018.032501520","journal-title":"IEEE Internet Comput"},{"key":"1056_CR62","doi-asserted-by":"publisher","unstructured":"Marco VS, Taylor B, Porter B, Wang Z (2017) Improving Spark application throughput via memory aware task co-location: a mixture of experts approach. In: Proceedings of the 18th ACM\/IFIP\/USENIX middleware conference. ACM, pp 95\u2013108. https:\/\/doi.org\/10.1145\/3135974.3135984","DOI":"10.1145\/3135974.3135984"},{"key":"1056_CR63","doi-asserted-by":"publisher","unstructured":"Meena M, Bharadi VA (2016) Performance analysis of cloud based software as a service (SaaS) model on public and hybrid cloud. In: 2016 symposium on colossal data analysis and networking (CDAN). IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/CDAN.2016.7570951","DOI":"10.1109\/CDAN.2016.7570951"},{"issue":"6","key":"1056_CR64","doi-asserted-by":"publisher","first-page":"31","DOI":"10.11896\/j.issn.1002-137X.2017.06.005","volume":"44","author":"H Meng","year":"2017","unstructured":"Meng H, Yu S, Liu F, Xiao N (2017) Research on memory management and cache replacement policies in Spark. Comput Sci 44(6):31\u201335. https:\/\/doi.org\/10.11896\/j.issn.1002-137X.2017.06.005","journal-title":"Comput Sci"},{"key":"1056_CR65","doi-asserted-by":"publisher","unstructured":"Ming Z, Luo, C, Gao W, Han R, Yang Q, Wang L, Zhan J (2013) BDGS: a scalable big data generator suite in big data benchmarking. In: Advancing Big Data benchmarks. Springer, pp 138\u2013154. https:\/\/doi.org\/10.1007\/978-3-319-10596-3_11","DOI":"10.1007\/978-3-319-10596-3_11"},{"key":"1056_CR66","doi-asserted-by":"publisher","unstructured":"Nguyen N, Khan MMH, Albayram Y, Wang K (2017) Understanding the influence of configuration settings: an execution model-driven framework for Apache Spark platform. In: 2017 IEEE 10th international conference on cloud computing (CLOUD). IEEE, pp 802\u2013807. https:\/\/doi.org\/10.1109\/CLOUD.2017.119","DOI":"10.1109\/CLOUD.2017.119"},{"key":"1056_CR67","doi-asserted-by":"publisher","unstructured":"Nguyen N, Khan MMH, Wang K (2016) Csminer: an automated tool for analyzing changes in configuration settings across multiple versions of large scale cloud software. In: 2016 IEEE 9th international conference on cloud computing (CLOUD). IEEE, pp 472\u2013480. https:\/\/doi.org\/10.1109\/CLOUD.2016.0069","DOI":"10.1109\/CLOUD.2016.0069"},{"key":"1056_CR68","unstructured":"Ousterhout K, Rasti R, Ratnasamy S, Shenker S, Chun BG (2015) Making sense of performance in data analytics frameworks. In: 12th $$\\{$$USENIX$$\\}$$ symposium on networked systems design and implementation ($$\\{$$NSDI$$\\}$$ 15), pp 293\u2013307"},{"key":"1056_CR69","doi-asserted-by":"publisher","unstructured":"Pirzadeh P, Carey M, Westmann T (2017) A performance study of big data analytics platforms. In: 2017 IEEE international conference on Big Data (Big Data). IEEE, pp 2911\u20132920. https:\/\/doi.org\/10.1109\/BigData.2017.8258260","DOI":"10.1109\/BigData.2017.8258260"},{"issue":"4","key":"1056_CR70","doi-asserted-by":"publisher","first-page":"646","DOI":"10.3390\/en12040646","volume":"12","author":"Y Qiu","year":"2019","unstructured":"Qiu Y, Jiang C, Wang Y, Ou D, Li Y, Wan J (2019) Energy aware virtual machine scheduling in data centers. Energies 12(4):646. https:\/\/doi.org\/10.3390\/en12040646","journal-title":"Energies"},{"key":"1056_CR71","doi-asserted-by":"crossref","unstructured":"Ra\u00efs I, Balouek-Thomert D, Orgerie A.C, Lef\u00e8vre L, Parashar M (2019) Leveraging energy-efficient non-lossy compression for data-intensive applications. In: 2019 international conference on high performance computing & simulation (HPCS). IEEE","DOI":"10.1109\/HPCS48598.2019.9188058"},{"key":"1056_CR72","doi-asserted-by":"publisher","unstructured":"Ruan X, Chen H (2017) Improving Shuffle I\/O performance for big data processing using hybrid storage. In: 2017 international conference on computing, networking and communications (ICNC). IEEE, pp 476\u2013480. https:\/\/doi.org\/10.1109\/ICCNC.2017.7876175","DOI":"10.1109\/ICCNC.2017.7876175"},{"key":"1056_CR73","doi-asserted-by":"publisher","unstructured":"Sandel R, Shtern M, Fokaefs M, Litoiu M (2015) Evaluating cluster configurations for big data processing: an exploratory study. In: 2015 IEEE 9th international symposium on the maintenance and evolution of service-oriented and cloud-based environments (MESOCA). IEEE, pp 23\u201330. https:\/\/doi.org\/10.1109\/MESOCA.2015.7328122","DOI":"10.1109\/MESOCA.2015.7328122"},{"key":"1056_CR74","doi-asserted-by":"publisher","unstructured":"Siegmund N, Grebhahn A, Apel S, K\u00e4stner C (2015) Performance-influence models for highly configurable systems. In: Proceedings of the 2015 10th joint meeting on foundations of software engineering. ACM, pp 284\u2013294. https:\/\/doi.org\/10.1145\/2786805.2786845","DOI":"10.1145\/2786805.2786845"},{"issue":"6","key":"1056_CR75","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1109\/71.285606","volume":"5","author":"X-H Sun","year":"1994","unstructured":"Sun X-H, Rover DT (1994) Scalability of parallel algorithm-machine combinations. IEEE Trans Parallel Distrib Syst 5(6):599\u2013613. https:\/\/doi.org\/10.1109\/71.285606","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"1056_CR76","doi-asserted-by":"publisher","unstructured":"Tsai WT, Huang Y, Shao Q (2011) Testing the scalability of SaaS applications. In: 2011 IEEE international conference on service-oriented computing and applications (SOCA). IEEE, pp 1\u20134. https:\/\/doi.org\/10.1109\/SOCA.2011.6166245","DOI":"10.1109\/SOCA.2011.6166245"},{"key":"1056_CR77","doi-asserted-by":"publisher","unstructured":"Wang G, Xu J, He B (2016) A novel method for tuning configuration parameters of Spark based on machine learning. In: 2016 IEEE 18th international conference on high performance computing and communications; IEEE 14th international conference on smart city; IEEE 2nd international conference on data science and systems (HPCC\/SmartCity\/DSS). IEEE, pp 586\u2013593. https:\/\/doi.org\/10.1109\/HPCC-SmartCity-DSS.2016.0088","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0088"},{"key":"1056_CR78","doi-asserted-by":"publisher","unstructured":"Wang K, Khan MMH (2015) Performance prediction for Apache Spark platform. In: 2015 IEEE 17th international conference on high performance computing and communications, 2015 IEEE 7th international symposium on cyberspace safety and security, and 2015 IEEE 12th international conference on embedded software and systems. IEEE, pp 166\u2013173. https:\/\/doi.org\/10.1109\/HPCC-CSS-ICESS.2015.246","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"1056_CR79","doi-asserted-by":"publisher","unstructured":"Wang K, Khan MMH, Nguyen N, Gokhale S (2016) Modeling interference for Apache Spark jobs. In: 2016 IEEE 9th international conference on cloud computing (CLOUD). IEEE, pp 423\u2013431. https:\/\/doi.org\/10.1109\/CLOUD.2016.0063","DOI":"10.1109\/CLOUD.2016.0063"},{"key":"1056_CR80","unstructured":"Wang L, Zhan J, Gao W, Jiang Z, Ren R, He X, Luo C, Lu G, Li J (2018) BOPS, not FLOPS! A new metric and roofline performance model for datacenter computing. arXiv preprint arXiv:1801.09212"},{"key":"1056_CR81","doi-asserted-by":"publisher","unstructured":"Wang L, Zhan J, Luo C, Zhu Y, Yang Q, He Y, Gao W, Jia Z, Shi Y, Zhang S, et\u00a0al (2014) Bigdatabench: a big data benchmark suite from internet services. In: 2014 IEEE 20th international symposium on high performance computer architecture (HPCA). IEEE, pp 488\u2013499. https:\/\/doi.org\/10.1109\/HPCA.2014.6835958","DOI":"10.1109\/HPCA.2014.6835958"},{"key":"1056_CR82","doi-asserted-by":"publisher","unstructured":"Xia Y, Yang F (2017\/04) Locality-based partitioning for Spark. In: 2017 5th international conference on frontiers of manufacturing science and measuring technology (FMSMT 2017). Atlantis Press. https:\/\/doi.org\/10.2991\/fmsmt-17.2017.233","DOI":"10.2991\/fmsmt-17.2017.233"},{"issue":"1","key":"1056_CR83","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TCC.2015.2464808","volume":"6","author":"R Xie","year":"2015","unstructured":"Xie R, Jia X (2015) Data transfer scheduling for maximizing throughput of big-data computing in cloud systems. IEEE Trans Cloud Comput 6(1):87\u201398. https:\/\/doi.org\/10.1109\/TCC.2015.2464808","journal-title":"IEEE Trans Cloud Comput"},{"key":"1056_CR84","doi-asserted-by":"publisher","unstructured":"Xu L, Li M, Zhang L, Butt AR, Wang Y, Hu ZZ (2016) MEMTUNE: dynamic memory management for in-memory data analytic platforms. In: 2016 IEEE international parallel and distributed processing symposium (IPDPS), pp 383\u2013392. IEEE. https:\/\/doi.org\/10.1109\/IPDPS.2016.105","DOI":"10.1109\/IPDPS.2016.105"},{"key":"1056_CR85","doi-asserted-by":"publisher","unstructured":"Yigitbasi N, Iosup A, Epema D, Ostermann S (2009) C-meter: a framework for performance analysis of computing clouds. In: 2009 9th IEEE\/ACM international symposium on cluster computing and the grid. IEEE, pp 472\u2013477. https:\/\/doi.org\/10.1109\/CCGRID.2009.40","DOI":"10.1109\/CCGRID.2009.40"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-022-01056-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00607-022-01056-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-022-01056-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T19:05:46Z","timestamp":1654110346000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00607-022-01056-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,14]]},"references-count":85,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["1056"],"URL":"https:\/\/doi.org\/10.1007\/s00607-022-01056-7","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,14]]},"assertion":[{"value":"5 May 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}