{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T05:10:10Z","timestamp":1716268210356},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T00:00:00Z","timestamp":1642550400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2022,4]]},"DOI":"10.1007\/s10586-022-03541-2","type":"journal-article","created":{"date-parts":[[2022,1,19]],"date-time":"2022-01-19T11:03:07Z","timestamp":1642590187000},"page":"1421-1439","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Dynamic\u00a0data\u00a0replacement\u00a0and\u00a0adaptive\u00a0scheduling\u00a0policies\u00a0in\u00a0spark"],"prefix":"10.1007","volume":"25","author":[{"given":"Chunlin","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qianqian","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youlong","family":"Luo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,19]]},"reference":[{"key":"3541_CR1","unstructured":"Manyika, J., Chui, M., Brown, B., et al. Big data: The next frontier for innovation, competition, and productivity[R\/OL]. The Mekinsey Global Institute, Las Vegas (2011). http:\/\/www.mckinsey.com\/insights\/business_technology\/big_data_the_next_frontier_for_innovation"},{"issue":"10","key":"3541_CR2","first-page":"181","volume":"47","author":"K Armstrong","year":"2014","unstructured":"Armstrong, K.: Big data: a revolution that will transform how we live, work, and think. Math. Comput. Educ. 47(10), 181\u2013183 (2014)","journal-title":"Math. Comput. Educ."},{"key":"3541_CR3","doi-asserted-by":"publisher","first-page":"107807","DOI":"10.1016\/j.comnet.2021.107807","volume":"186","author":"C Li","year":"2021","unstructured":"Li, C., Song, M., Zhang, Q., Luo, Y.: Cluster load based content distribution and speculative execution for geographically distributed cloud environment. Comput. Netw. 186, 107807 (2021)","journal-title":"Comput. Netw."},{"key":"3541_CR4","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.jpdc.2020.04.012","volume":"143","author":"C Li","year":"2020","unstructured":"Li, C., Song, M., Zhang, M., Luo, Y.: Effective replica management for improving reliability and availability in edge-cloud computing environment. J. Parallel Distrib. Comput. 143, 107\u2013128 (2020)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"6","key":"3541_CR5","first-page":"647","volume":"27","author":"J Lig","year":"2012","unstructured":"Lig, J., Cheng, X.Q.: Research status and scientific thinking of big data. Bull. Chin. Acad. Sci 27(6), 647\u2013657 (2012)","journal-title":"Bull. Chin. Acad. Sci"},{"issue":"4","key":"3541_CR6","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1007\/s10723-015-9350-y","volume":"13","author":"Y Wang","year":"2015","unstructured":"Wang, Y., Lu, W., Lou, R., et al.: Improving map reduce performance with partial speculative execution. J. Grid Comput. 13(4), 587\u2013604 (2015)","journal-title":"J. Grid Comput."},{"key":"3541_CR7","doi-asserted-by":"crossref","unstructured":"Grolinger, K., Hayes, M., Higashino, W.A., et al.: Challenges for map reduce in big data. In: 2014 IEEE World Congress on Services (SERVICES), pp 182\u2013189 (2014)","DOI":"10.1109\/SERVICES.2014.41"},{"key":"3541_CR8","unstructured":"Huang, C.Q., Yang, S.Q., Tang, J.C., et al.: RDD share: reusing results of spark RDD. In: IEEE International Conference on Data Science in Cyberspace. IEEE (2017)."},{"key":"3541_CR9","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.ins.2019.12.049","volume":"516","author":"C Li","year":"2020","unstructured":"Li, C., Bai, J., Chen, Y., Luo, Y.: Resource and replica management strategy for optimizing financial cost and user experience in edge cloud computing system. Inf. Sci. 516, 33\u201355 (2020)","journal-title":"Inf. Sci."},{"key":"3541_CR10","unstructured":"He, Z., Huang, Q., Li, Z., et al.: Resource and replica management strategy in spark SQL using task stealing. Int. J. Parallel Program. (2020)"},{"key":"3541_CR11","unstructured":"Jyothi, S.A., Curino, C., Menache, I., et al.: Morpheus: towards automated SLOs for enterprise clusters. In: Usenix Conference on Operating Systems Design and Implementation, pp. 117\u2013134. USENIX Association Berkeley (2016)."},{"key":"3541_CR12","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, p. 2. USENIX Association, Berkeley (2012)"},{"key":"3541_CR13","doi-asserted-by":"crossref","unstructured":"Xu, L., Min, L., Li, Z., et al.: MEMTUNE: dynamic memory management for in-memory data analytic platforms. In: 2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE (2016)","DOI":"10.1109\/IPDPS.2016.105"},{"issue":"8","key":"3541_CR14","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. 28(8), 2473\u20132486 (2016)","journal-title":"Concurr. Comput."},{"key":"3541_CR15","unstructured":"Liu, H., Tan, L.: New RDD partition weight cache replacement algorithm in spark. J. Chin. Comput. Syst. (2018)."},{"key":"3541_CR16","unstructured":"Chen, T.Y., Zhang, L.X., Ken-Li, L.I., et al.: Optimization of RDD Cache Replacement Strategy Optimization in Spark Framework. (2019)"},{"key":"3541_CR17","unstructured":"Wang, Y., Lei, T., et al.: A Lowest Cost RDD Caching Strategy for Spark. (2019)"},{"key":"3541_CR18","doi-asserted-by":"crossref","unstructured":"Wang, B., Tang, J., Zhang, R., et al. (2019) LCRC: a dependency-aware cache management policy for spark. In: 2018 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Ubiquitous Computing & Communications, Big Data & Cloud Computing, Social Computing & Networking, Sustainable Computing & Communications (ISPA\/IUCC\/BDCloud\/SocialCom\/SustainCom). IEEE (2019)","DOI":"10.1109\/BDCloud.2018.00140"},{"key":"3541_CR19","first-page":"99","volume":"4","author":"S Wason","year":"2017","unstructured":"Wason, S., Kumar, P., Rathi, S.: Dynamic memory allocation. J. Comput. Sci. Eng. 4, 99\u2013103 (2017)","journal-title":"J. Comput. Sci. Eng."},{"issue":"1","key":"3541_CR20","doi-asserted-by":"publisher","first-page":"2223","DOI":"10.1007\/s10586-017-1466-3","volume":"22","author":"K Wang","year":"2019","unstructured":"Wang, K., Khan, M., Nguyen, N., et al.: Design and implementation of an analytical framework for interference aware job scheduling on Apache Spark platform. Clust. Comput. 22(1), 2223\u20132237 (2019)","journal-title":"Clust. Comput."},{"key":"3541_CR21","first-page":"1","volume":"99","author":"A Zainab","year":"2021","unstructured":"Zainab, A., Ghrayeb, A., Abu-Rub, H., et al.: Distributed tree-based machine learning for short-term load forecasting with apache spark. IEEE Access 99, 1 (2021)","journal-title":"IEEE Access"},{"key":"3541_CR22","doi-asserted-by":"crossref","unstructured":"Hu, Z., Li, D., Zhang, Y., et al.: Branch scheduling: dag-aware scheduling for speeding up data-parallel jobs. In: the International Symposium (2019)","DOI":"10.1145\/3326285.3329071"},{"key":"3541_CR23","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.jpdc.2020.03.010","volume":"141","author":"T Zhuo","year":"2020","unstructured":"Zhuo, T., Az, A., Xz, A., et al.: Dynamic memory-aware scheduling in spark computing environment. J. Parallel Distrib. Comput. 141, 10\u201322 (2020)","journal-title":"J. Parallel Distrib. Comput."},{"issue":"3","key":"3541_CR24","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TPDS.2018.2866581","volume":"30","author":"H Jin","year":"2019","unstructured":"Jin, H., Chen, F., Wu, S., et al.: Towards low-latency batched stream processing by pre-scheduling. IEEE Trans. Parallel Distrib. Syst. 30(3), 710\u2013722 (2019)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3541_CR25","doi-asserted-by":"crossref","unstructured":"Li, H., Wang, H., Fang, S., et al.: An energy-aware scheduling algorithm for big data applications in Spark. Clust. Comput. 23(11) (2020).","DOI":"10.1007\/s10586-019-02947-9"},{"key":"3541_CR26","first-page":"1","volume":"99","author":"Z Fu","year":"2020","unstructured":"Fu, Z., Tang, Z., Yang, L., et al.: An optimal locality-aware task scheduling algorithm based on bipartite graph modelling for spark applications. IEEE Trans. Parallel Distrib. Syst. 99, 1 (2020)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"3541_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Y., Liu, L., Ding, Z.: DAG-aware joint task scheduling and cache management in spark clusters. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE (2020)","DOI":"10.1109\/IPDPS47924.2020.00047"},{"key":"3541_CR28","doi-asserted-by":"publisher","first-page":"102699","DOI":"10.1016\/j.parco.2020.102699","volume":"100","author":"Z Fu","year":"2020","unstructured":"Fu, Z., Tang, Z., Yang, L., et al.: ImRP: A predictive partition method for data skew alleviation in spark streaming environment. Parallel Comput. 100, 102699 (2020)","journal-title":"Parallel Comput."},{"issue":"62","key":"3541_CR29","first-page":"492","volume":"9","author":"RN Boubela","year":"2016","unstructured":"Boubela, R.N., Klaudius, K., Wolfgang, H., et al.: Big data approaches for the analysis of large-scale fMRI data using apache spark and GPU processing: a demonstration on resting-state fMRI data from the human connectome project. Front. Neurosci. 9(62), 492 (2016)","journal-title":"Front. Neurosci."},{"issue":"1","key":"3541_CR30","first-page":"8","volume":"113","author":"S Gopalani","year":"2015","unstructured":"Gopalani, S., Arora, R., Gopalani, S., et al.: Comparing apache spark and map reduce with performance analysis using K-means. Int. J. Comput. Appl. 113(1), 8\u201311 (2015)","journal-title":"Int. J. Comput. Appl."},{"issue":"1","key":"3541_CR31","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/2071379.2071383","volume":"8","author":"M Frigo","year":"2012","unstructured":"Frigo, M., Leiserson, C.E., Prokop, H., et al.: Cache-oblivious algorithms. ACM Trans. Algorithms 8(1), 4 (2012)","journal-title":"ACM Trans. Algorithms"},{"key":"3541_CR32","doi-asserted-by":"crossref","unstructured":"Yu, Y., Wei, W., Zhang, J., et al. LRC: dependency-aware cache management for data analytics clusters. In: IEEE INFOCOM 2017\u2014IEEE Conference on Computer Communications. IEEE (2017)","DOI":"10.1109\/INFOCOM.2017.8057007"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-022-03541-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-022-03541-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-022-03541-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,19]],"date-time":"2022-03-19T20:22:38Z","timestamp":1647721358000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-022-03541-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,19]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["3541"],"URL":"https:\/\/doi.org\/10.1007\/s10586-022-03541-2","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,19]]},"assertion":[{"value":"25 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}