{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T15:15:27Z","timestamp":1725981327478},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319936581"},{"type":"electronic","value":"9783319936598"}],"license":[{"start":{"date-parts":[[2018,6,19]],"date-time":"2018-06-19T00:00:00Z","timestamp":1529366400000},"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":[[2019]]},"DOI":"10.1007\/978-3-319-93659-8_97","type":"book-chapter","created":{"date-parts":[[2018,6,18]],"date-time":"2018-06-18T14:00:55Z","timestamp":1529330455000},"page":"1047-1057","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on Data Storage and Processing Optimization Based on Federation HDFS and Spark"],"prefix":"10.1007","author":[{"given":"Fangzhou","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"He","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenkang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,6,19]]},"reference":[{"key":"97_CR1","doi-asserted-by":"crossref","unstructured":"Leung, S.T., Leung, S.T., Leung, S.T.: The Google file system. In: Nineteenth ACM Symposium on Operating Systems Principles, pp. 29\u201343. ACM (2003)","DOI":"10.1145\/1165389.945450"},{"key":"97_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1365815.1365816","volume":"26","author":"F Chang","year":"2008","unstructured":"Chang, F., Dean, J., Ghemawat, S., et al.: Bigtable: a distributed storage system for structured data. ACM Trans. Comput. Syst. 26, 1\u201326 (2008)","journal-title":"ACM Trans. Comput. Syst."},{"issue":"1","key":"97_CR3","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1145\/1327452.1327492","volume":"51","author":"Jeffrey Dean","year":"2008","unstructured":"Dean, J., Ghemawat, S.: MapReduce: simplified data processing on large clusters. In: Conference on Symposium on Operating Systems Design & Implementation, p. 10. USENIX Association (2008)","journal-title":"Communications of the ACM"},{"key":"97_CR4","first-page":"6238","volume":"5","author":"PS Honnutagi","year":"2014","unstructured":"Honnutagi, P.S.: The Hadoop distributed file system. Int. J. Comput. Sci. Inf. Technol. 5, 6238\u20136243 (2014)","journal-title":"Int. J. Comput. Sci. Inf. Technol."},{"key":"97_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3233\/JHS-170580","volume":"24","author":"P Li","year":"2018","unstructured":"Li, P., Dong, L., Xu, H., Lau, T.F.: Spark\u2019s operation time predictive in cloud computing environment based on SRC-WSVR. J. High Speed Netw. 24, 49\u201362 (2018)","journal-title":"J. High Speed Netw."},{"key":"97_CR6","unstructured":"Zaharia, M., Chowdhury, M., Das, T., et al.: Resilient distributed datasets: a fault-tolerant abstraction for in-memory cluster computing. In: Usenix Conference on Networked Systems Design and Implementation, p. 2. USENIX Association (2012)"},{"key":"97_CR7","doi-asserted-by":"crossref","unstructured":"Samadi, Y., Zbakh, M., Tadonki, C.: Comparative study between Hadoop and Spark based on Hibench benchmarks. In: International Conference on Cloud Computing Technologies and Applications, pp. 267\u2013275. IEEE (2017)","DOI":"10.1109\/CloudTech.2016.7847709"},{"key":"97_CR8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.future.2016.06.027","volume":"78","author":"Z Tang","year":"2018","unstructured":"Tang, Z., Zhang, X., Li, K., Li, K.: An intermediate data placement algorithm for load balancing in Spark computing environment. Future Gener. Comput. Syst 78, 287\u2013301 (2018)","journal-title":"Future Gener. Comput. Syst"},{"key":"97_CR9","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1016\/j.ins.2017.11.064","volume":"432","author":"MR Karim","year":"2018","unstructured":"Karim, M.R., Cochez, M., Beyan, O.D., Ahmed, C.F., Decker, S.: Mining maximal frequent patterns in transactional databases and dynamic data streams: a spark-based approach. Inf. Sci. 432, 278\u2013300 (2018)","journal-title":"Inf. Sci."},{"key":"97_CR10","doi-asserted-by":"crossref","first-page":"1575","DOI":"10.1093\/bioinformatics\/btx010","volume":"33","author":"UF Petrillo","year":"2017","unstructured":"Petrillo, U.F., Roscigno, G., Cattaneo, G., Giancarlo, R.: FASTdoop: a versatile and efficient library for the input of FASTA and FASTQ files for MapReduce Hadoop bioinformatics applications. Bioinformatics 33, 1575\u20131577 (2017)","journal-title":"Bioinformatics"},{"issue":"8","key":"97_CR11","doi-asserted-by":"publisher","first-page":"e3974","DOI":"10.1002\/cpe.3974","volume":"29","author":"Jinkyu Jeong","year":"2016","unstructured":"Jeong, J., Choi, D.H., Jo, H.: Enhancing network I\/o performance for a virtualized Hadoop cluster. Concurr. Comput. Pract. Exp. 29, 8 (2017)","journal-title":"Concurrency and Computation: Practice and Experience"},{"key":"97_CR12","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1049\/iet-sen.2016.0289","volume":"11","author":"S Rashmi","year":"2017","unstructured":"Rashmi, S., Basu, A.: Resource optimised workflow scheduling in Hadoop using stochastic hill climbing technique. IET Softw. 11, 239\u2013244 (2017)","journal-title":"IET Softw."},{"key":"97_CR13","doi-asserted-by":"crossref","unstructured":"Song, G.H., Chuai, J.N., Yang, B.W., et al.: QDFS: a quality-aware distributed file storage service based on HDFS. In: IEEE International Conference on Computer Science and Automation Engineering, pp. 203\u2013207. IEEE (2011)","DOI":"10.1109\/CSAE.2011.5952454"},{"key":"97_CR14","doi-asserted-by":"crossref","unstructured":"Lin, C.Y., Lin, Y.C.: A load-balancing algorithm for hadoop distributed file system. In: International Conference on Network-Based Information Systems, pp. 173\u2013179. IEEE (2015)","DOI":"10.1109\/NBiS.2015.30"},{"key":"97_CR15","doi-asserted-by":"crossref","unstructured":"Oriani, A., Garcia, I.C.: From backup to hot standby: high availability for HDFS. In: Reliable Distributed Systems, pp. 131\u2013140. IEEE (2013)","DOI":"10.1109\/SRDS.2012.33"},{"key":"97_CR16","doi-asserted-by":"crossref","unstructured":"Aishwarya, K., Arvind, R.A., Sreevatson, M.C., et al.: Efficient prefetching technique for storage of heterogeneous small files in Hadoop Distributed File System Federation. In: Fifth International Conference on Advanced Computing, pp. 523\u2013530. IEEE (2014)","DOI":"10.1109\/ICoAC.2013.6922006"},{"key":"97_CR17","doi-asserted-by":"crossref","unstructured":"Lin, X., Wang, P., Wu, B.: Log analysis in cloud computing environment with Hadoop and Spark. In: IEEE International Conference on Broadband Network & Multimedia Technology, pp. 273\u2013276. IEEE (2014)","DOI":"10.1109\/ICBNMT.2013.6823956"},{"key":"97_CR18","doi-asserted-by":"crossref","unstructured":"Zhou, S., Li, X., Matsui, T., et al.: Visualization and diagnosis of earth science data through Hadoop and Spark. In: IEEE International Conference on Big Data, pp. 2974\u20132980. IEEE (2017)","DOI":"10.1109\/BigData.2016.7840949"},{"key":"97_CR19","doi-asserted-by":"crossref","unstructured":"Islam, N.S., Wasi-Ur-Rahman, M., Lu, X., et al.: Efficient data access strategies for Hadoop and Spark on HPC cluster with heterogeneous storage. In: IEEE International Conference on Big Data, pp. 223\u2013232. IEEE (2017)","DOI":"10.1109\/BigData.2016.7840608"},{"key":"97_CR20","doi-asserted-by":"publisher","unstructured":"Fan, W., Han, Z., Wang, R.: An evaluation model and benchmark for parallel computing frameworks. Mob. Inf. Syst. 2018, Article ID 3890341 (2018). https:\/\/doi.org\/10.1155\/2018\/3890341","DOI":"10.1155\/2018\/3890341"}],"container-title":["Advances in Intelligent Systems and Computing","Complex, Intelligent, and Software Intensive Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-93659-8_97","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,3]],"date-time":"2023-09-03T06:56:26Z","timestamp":1693724186000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-93659-8_97"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6,19]]},"ISBN":["9783319936581","9783319936598"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-93659-8_97","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2018,6,19]]}}}