{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:44:34Z","timestamp":1740123874700,"version":"3.37.3"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T00:00:00Z","timestamp":1591315200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T00:00:00Z","timestamp":1591315200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"South China University of Technology Start-up","award":["D61600470"],"award-info":[{"award-number":["D61600470"]}]},{"name":"Guangzhou Technology","award":["201707010148"],"award-info":[{"award-number":["201707010148"]}]},{"name":"The New Generation of Artificial Intelligence In Guangdong","award":["2018B0107003"],"award-info":[{"award-number":["2018B0107003"]}]},{"name":"Doctoral Startup Program of Guangdong Natural Science Foundation","award":["2018A030310408"],"award-info":[{"award-number":["2018A030310408"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61370062","61866038"],"award-info":[{"award-number":["61370062","61866038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Key Science and Technology Program of Henan Province","award":["202102210152"],"award-info":[{"award-number":["202102210152"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2021,2]]},"DOI":"10.1007\/s10766-020-00662-2","type":"journal-article","created":{"date-parts":[[2020,6,5]],"date-time":"2020-06-05T12:02:42Z","timestamp":1591358562000},"page":"25-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Task-Aware Fine-Grained Storage Selection Mechanism for In-Memory Big Data Computing Frameworks"],"prefix":"10.1007","volume":"49","author":[{"given":"Bo","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8602-7754","authenticated-orcid":false,"given":"Jie","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jialei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaoshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Deyu","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,6,5]]},"reference":[{"unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: Proceedings of the 6th Conference on Symposium on Operating Systems Design & Implementation, San Francisco, CA, p. 10 (2004)","key":"662_CR1"},{"doi-asserted-by":"crossref","unstructured":"Isard, M., Budiu, M., Yu, Y., et al.: Dryad: distributed data-parallel programs from sequential building blocks. In: Proceedings of the 2nd ACM SIGOPS\/EuroSys European Conference on Computer Systems 2007, pp. 59\u201372. ACM, Lisbon, Portugal (2007)","key":"662_CR2","DOI":"10.1145\/1272996.1273005"},{"key":"662_CR3","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1109\/TKDE.2015.2427795","volume":"27","author":"H Zhang","year":"2015","unstructured":"Zhang, H., Chen, G., Ooi, B.C., et al.: In-memory big data management and processing: a survey. IEEE Trans. Knowl. Data Eng. 27, 1920\u20131948 (2015). https:\/\/doi.org\/10.1109\/TKDE.2015.2427795","journal-title":"IEEE Trans. Knowl. Data Eng."},{"unstructured":"Zaharia, M., Chowdhury, M., Das, T., et al.: 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, San Jose, CA, p. 2 (2012)","key":"662_CR4"},{"doi-asserted-by":"crossref","unstructured":"Yu, Y., Wang, W., Zhang, J., et al.: LRC: dependency-aware cache management for data analytics clusters. In: Proceedings of INFOCOM, Atlanta, GA, USA, pp. 1\u20139 (2017)","key":"662_CR5","DOI":"10.1109\/INFOCOM.2017.8057007"},{"doi-asserted-by":"crossref","unstructured":"Choi, I.S., Yang, W., Kee, Y.S.: Early experience with optimizing I\/O performance using high-performance SSDs for in-memory cluster computing. In: Proceedings of IEEE International Conference on Big Data (Big Data 2015) (2015), pp. 1073\u20131083","key":"662_CR6","DOI":"10.1109\/BigData.2015.7363861"},{"unstructured":"Xin, R.: Project Tungsten (Spark 1.5 Phase 1). https:\/\/issues.apache.org\/jira\/browse\/SPARK-7075. Accessed 1 Mar 2019","key":"662_CR7"},{"key":"662_CR8","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1007\/s10766-016-0470-1","volume":"45","author":"Y Geng","year":"2017","unstructured":"Geng, Y., Shi, X., Pei, C., et al.: LCS: an efficient data eviction strategy for spark. Int. J. Parallel Program. 45, 1285\u20131297 (2017). https:\/\/doi.org\/10.1007\/s10766-016-0470-1","journal-title":"Int. J. Parallel Program."},{"doi-asserted-by":"crossref","unstructured":"Koliopoulos, A.K., Yiapanis, P., Tekiner, F., et al.: Towards automatic memory tuning for in-memory Big Data analytics in clusters. In: Proceedings of IEEE International Congress on Big Data (BigData Congress 2016), pp. 353\u2013356 (2016)","key":"662_CR9","DOI":"10.1109\/BigDataCongress.2016.56"},{"doi-asserted-by":"crossref","unstructured":"Saha, B., Shah, H., Seth, S., et al.: Apache Tez: a unifying framework for modeling and building data processing applications. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. ACM, Melbourne, Victoria, Australia, pp. 1357\u20131369 (2015)","key":"662_CR10","DOI":"10.1145\/2723372.2742790"},{"doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., et al.: The Hadoop distributed file system. In: Proceedings of IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST 2010), pp. 1\u201310 (2010)","key":"662_CR11","DOI":"10.1109\/MSST.2010.5496972"},{"doi-asserted-by":"crossref","unstructured":"Zaharia, M., Borthakur, D., Sarma, J.S., et al.: Delay scheduling: a simple technique for achieving locality and fairness in cluster scheduling. In: Proceedings of the 5th European Conference on Computer Systems, pp. 265\u2013278. ACM, Paris, France (2010)","key":"662_CR12","DOI":"10.1145\/1755913.1755940"},{"doi-asserted-by":"crossref","unstructured":"Li, M., Tan, J., Wang, Y., et al.: SparkBench: a comprehensive benchmarking suite for in memory data analytic platform Spark. In: Proceedings of the 12th ACM International Conference on Computing Frontiers, pp. 1\u20138. ACM, Ischia, Italy (2015)","key":"662_CR13","DOI":"10.1145\/2742854.2747283"},{"doi-asserted-by":"crossref","unstructured":"Zhao, Y., Hu, F., Chen, H.: An adaptive tuning strategy on spark based on in-memory computation characteristics. In: Proceedings of the 18th International Conference on Advanced Communication Technology (ICACT2016), pp. 484\u2013488 (2016)","key":"662_CR14","DOI":"10.1109\/ICACT.2016.7423441"},{"key":"662_CR15","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1147\/sj.92.0078","volume":"9","author":"RL Mattson","year":"1970","unstructured":"Mattson, R.L., Gecsei, J., Slutz, D.R., et al.: Evaluation techniques for storage hierarchies. IBM Syst. J. 9, 78\u2013117 (1970). https:\/\/doi.org\/10.1147\/sj.92.0078","journal-title":"IBM Syst. J."},{"key":"662_CR16","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1145\/321623.321632","volume":"18","author":"AV Aho","year":"1971","unstructured":"Aho, A.V., Denning, P.J., Ullman, J.D.: Principles of optimal page replacement. J. ACM 18, 80\u201393 (1971). https:\/\/doi.org\/10.1145\/321623.321632","journal-title":"J. ACM"},{"key":"662_CR17","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1145\/235543.235544","volume":"14","author":"P Cao","year":"1996","unstructured":"Cao, P., Felten, E.W., Karlin, A.R., et al.: Implementation and performance of integrated application-controlled file caching, prefetching, and disk scheduling. ACM Trans. Comput. Syst. 14, 311\u2013343 (1996). https:\/\/doi.org\/10.1145\/235543.235544","journal-title":"ACM Trans. Comput. Syst."},{"key":"662_CR18","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1145\/224057.224064","volume":"29","author":"RH Patterson","year":"1995","unstructured":"Patterson, R.H., Gibson, G.A., Ginting, E., et al.: Informed prefetching and caching. SIGOPS Oper. Syst. Rev. 29, 79\u201395 (1995). https:\/\/doi.org\/10.1145\/224057.224064","journal-title":"SIGOPS Oper. Syst. Rev."},{"unstructured":"Ananthanarayanan, G., Ghodsi, A., Wang, A., et al.: PACMan: coordinated memory caching for parallel jobs. In: Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation, p. 20. USENIX Association, San Jose, CA (2012)","key":"662_CR19"},{"doi-asserted-by":"crossref","unstructured":"Xu, L., Li, M., Zhang, L., et al.: MEMTUNE: dynamic memory management for in-memory data analytic platforms. In: Proceedings of IEEE International Parallel and Distributed Processing Symposium, pp. 383\u2013392 (2016)","key":"662_CR20","DOI":"10.1109\/IPDPS.2016.105"},{"unstructured":"Feng, L.: Research and implementation of memory optimization based on parallel computing engine spark. M.S. Dissertation, Tsinghua University, China (2013)","key":"662_CR21"},{"doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, K., Gao, C.: A new scheme for cache optimization based on cluster computing framework spark. In: Proceedings of 8th International Symposium on Computational Intelligence and Design (ISCID 2015), pp. 114\u2013117 (2015)","key":"662_CR22","DOI":"10.1109\/ISCID.2015.30"},{"key":"662_CR23","doi-asserted-by":"publisher","first-page":"2473","DOI":"10.1002\/cpe.3584","volume":"28","author":"M Duan","year":"2016","unstructured":"Duan, M., Li, K., Tang, Z., et al.: Selection and replacement algorithms for memory performance improvement in Spark. Concurr. Comput. Pract. Exp. 28, 2473\u20132486 (2016)","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"662_CR24","first-page":"278","volume":"45","author":"C Bian","year":"2016","unstructured":"Bian, C., Yu, C., Ying, C., et al.: Self-adaptive strategy for cache management in spark. Chin. J. Electron. 45, 278\u2013284 (2016)","journal-title":"Chin. J. Electron."},{"unstructured":"Spark Tuning. Online Referencing. http:\/\/spark.apache.org\/docs\/latest\/tuning.html\/#tuning-spark. Accessed 1 Mar 2019","key":"662_CR25"},{"unstructured":"Wang, G.L., Xu, J.G., Liu, R.F.: A performance automatic optimization method for spark. Patent 105868019 A, CN (2016)","key":"662_CR26"},{"key":"662_CR27","first-page":"1111","volume":"4","author":"H Herodotou","year":"2011","unstructured":"Herodotou, H., Babu, S.: Profiling, what-if analysis, and cost-based optimization of MapReduce programs. VLDB 4, 1111\u20131122 (2011)","journal-title":"VLDB"},{"unstructured":"Herodotou, H., Lim, H., Luo, G., et al.: Starfish: a self-tuning system for Big Data analytics. In: Proceedings of Fifth Biennial Conference on Innovative Data Systems Research (CIDR2011), Asilomar, CA, USA, pp. 261\u2013272 (2011)","key":"662_CR28"},{"doi-asserted-by":"crossref","unstructured":"Liu, C., Zeng, D., Yao, H., et al.: MR-COF: a genetic MapReduce configuration optimization framework. In: Proceedings of the 15th International Conference of Algorithms and Architectures for Parallel Processing (ICA3PP 2015), pp. 344\u2013357(2015)","key":"662_CR29","DOI":"10.1007\/978-3-319-27140-8_24"},{"doi-asserted-by":"crossref","unstructured":"Yigitbasi, N., Willke, T.L., Liao, G., et al.: Towards machine learning-based auto-tuning of MapReduce. In: Proceedings of the 2013 IEEE 21st International Symposium on Modelling, Analysis & Simulation of Computer and Telecommunication Systems, pp. 11\u201320 (2013)","key":"662_CR30","DOI":"10.1109\/MASCOTS.2013.9"},{"doi-asserted-by":"crossref","unstructured":"Chen, C.O., Zhuo, Y.Q., Yeh, C.C., et al.: Machine learning-based configuration parameter tuning on Hadoop system. In: Proceedings of IEEE International Congress on Big Data, pp. 386\u2013392 (2015)","key":"662_CR31","DOI":"10.1109\/BigDataCongress.2015.64"},{"key":"662_CR32","first-page":"11","volume":"38","author":"QA Chen","year":"2016","unstructured":"Chen, Q.A., Feng, L., Yue, C., et al.: Parameter optimization for spark jobs based on runtime data analysis. China Comput. Eng. Sci. 38, 11\u201319 (2016)","journal-title":"China Comput. Eng. Sci."},{"key":"662_CR33","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.3786","author":"M Khan","year":"2017","unstructured":"Khan, M., Huang, Z., Li, M., et al.: Optimizing Hadoop parameter settings with gene expression programming guided PSO. Concurr. Comput. Pract. Exp. (2017). https:\/\/doi.org\/10.1002\/cpe.3786","journal-title":"Concurr. Comput. Pract. Exp."},{"doi-asserted-by":"crossref","unstructured":"Li, M., Zeng, L., Meng, S., et al.: MRONLINE: MapReduce online performance tuning. In: Proceedings of the 23rd International Symposium on High-Performance Parallel and Distributed Computing, pp. 165\u2013176. ACM, Vancouver, BC, Canada (2014)","key":"662_CR34","DOI":"10.1145\/2600212.2600229"},{"doi-asserted-by":"crossref","unstructured":"Cheng, D., Rao, J., Guo, Y., et al.: Improving MapReduce performance in heterogeneous environments with adaptive task tuning. In: Proceedings of the 15th International Middleware Conference, pp. 97\u2013108. ACM, Bordeaux, France (2014)","key":"662_CR35","DOI":"10.1145\/2663165.2666089"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-020-00662-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10766-020-00662-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-020-00662-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,4]],"date-time":"2021-06-04T23:49:13Z","timestamp":1622850553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10766-020-00662-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,6,5]]},"references-count":35,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,2]]}},"alternative-id":["662"],"URL":"https:\/\/doi.org\/10.1007\/s10766-020-00662-2","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2020,6,5]]},"assertion":[{"value":"26 March 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 May 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 June 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}