{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:22:54Z","timestamp":1742916174264,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Singapore","isbn-type":[{"type":"print","value":"9789811636363"},{"type":"electronic","value":"9789811636370"}],"license":[{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,10,2]],"date-time":"2021-10-02T00:00:00Z","timestamp":1633132800000},"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":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-981-16-3637-0_56","type":"book-chapter","created":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T11:58:23Z","timestamp":1633089503000},"page":"795-811","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Data Processing on Distributed Systems Storage Challenges"],"prefix":"10.1007","author":[{"given":"Mohamed","family":"Eddoujaji","sequence":"first","affiliation":[]},{"given":"Hassan","family":"Samadi","sequence":"additional","affiliation":[]},{"given":"Mohamed","family":"Bohorma","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,10,2]]},"reference":[{"key":"56_CR1","unstructured":"Hadoop official site. http:\/\/hadoop.apache.org\/"},{"key":"56_CR2","unstructured":"https:\/\/www.lebigdata.fr\/hadoop"},{"key":"56_CR3","unstructured":"Achandair, O., Elmahouti, M., Khoulji, S., Kerkeb, M.L.: Improving Small File Management in Hadoop, pp. 1\u201314 (2017)."},{"key":"56_CR4","doi-asserted-by":"crossref","unstructured":"Bende, S., Shedge, R.: Dealing with Small files problem in hadoop distributed file system. Procedia Comput. Sci. 79, 1001\u20131012 (December 2016)","DOI":"10.1016\/j.procs.2016.03.127"},{"key":"56_CR5","doi-asserted-by":"crossref","unstructured":"Cai, X., Chen, C., Liang, Y.: An optimization strategy of massive small files storage based on HDFS. In: 2018 Joint International Advanced Engineering and Technology Research Conference (JIAET 2018) (2018)","DOI":"10.2991\/jiaet-18.2018.40"},{"key":"56_CR6","doi-asserted-by":"crossref","unstructured":"Niazi, S., Ronstr\u00f6m, M., Haridi, S., Dowling, J.: Size Matters: Improving the Performance of Small Files in Hadoop. Middleware\u201918. ACM, Rennes, France (2018)","DOI":"10.1145\/3274808.3274811"},{"key":"56_CR7","unstructured":"Mir, M.A., Ahmed, J.: An Optimal Solution for Small File Problem in Hadoop. Int. J. Adv. Res. Comput. Sci. (2017)"},{"key":"56_CR8","doi-asserted-by":"crossref","unstructured":"Alange, N., Mathur, A.: Small sized file storage problems in hadoop distributed file system. In: Second International Conference on Smart Systems and Inventive Technology (ICSSIT 2019), IEEE Xplore (2019)","DOI":"10.1109\/ICSSIT46314.2019.8987739"},{"key":"56_CR9","unstructured":"Archid, A.S., Mangala, C.N.: Improving Hadoop Performance in Handling Small Files. Int. J. Eng. Res. Technol. (IJERT) (2016)"},{"key":"56_CR10","doi-asserted-by":"crossref","unstructured":"Ahada, M.A., Biswasa, R.: Architecture for Efficiently Storing Small Size Files in Hadoop. Procedia Comput. Sci. 132, 1626\u20131635 (2018)","DOI":"10.1016\/j.procs.2018.05.128"},{"key":"56_CR11","doi-asserted-by":"crossref","unstructured":"Vorapongkitipun, C., Nupairoj, N.: Improving performance of small\u00adfile accessing in hadoop. In: IEEE International Conference on Computer Science and Software Engineering (JCSSE), pp. 200\u2013205 (2014)","DOI":"10.1109\/JCSSE.2014.6841867"},{"key":"56_CR12","unstructured":"Sheoran, S., Sethia, D., Saran, H.: Optimized MapFile based storage of small files in hadoop. In: ACM International Symposium on Cluster, Cloud and Grid Computing"},{"key":"56_CR13","unstructured":"https:\/\/searchstorage.techtarget.com\/definition\/parallel-file-system"},{"key":"56_CR14","unstructured":"Carns, P.H., Ligon III, W.B., Ross, R.B., Thakur, R.: Pvfs: A parallel file system for linux clusters. In: Proceedings of the 4th Annual Linux Showcase and Conference, pp. 317\u2013327. USENIX Association."},{"key":"56_CR15","doi-asserted-by":"crossref","unstructured":"Alange, N., Mathur, A.: Small sized file storage problems in hadoop distributed file system. In: 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT). IEEE (2019)","DOI":"10.1109\/ICSSIT46314.2019.8987739"},{"key":"56_CR16","unstructured":"https:\/\/dataottam.com\/2016\/09\/09\/3-solutions-for-big-datas-small-files-problem\/"},{"key":"56_CR17","doi-asserted-by":"crossref","unstructured":"Bende, S., Shedge, R.: Dealing with small files problem in hadoop distributed file system. In: 7th International Conference on Communication, Computing and Virtualization (2016)","DOI":"10.1016\/j.procs.2016.03.127"},{"key":"56_CR18","unstructured":"Implementing WebGIS on Hadoop: A Case Study of Improving Small File I\/O Performance on HDFS"},{"key":"56_CR19","doi-asserted-by":"crossref","unstructured":"Wang, K., Yang, Y., Qiu, X., Gao, Z.: MOSM: An approach for efficient string massive small files on Hadoop. In: International Conference on Big Data Analysis (ICBDA), IEEE (2017)","DOI":"10.1109\/ICBDA.2017.8078848"},{"key":"56_CR20","doi-asserted-by":"crossref","unstructured":"Huang, L., Liu, J., Meng, W.: A review of various optimization schemes of small files storage on Hadoop. In: Joint International Advanced Engineering and Technology Research Conference (JIAET 2018) (2018)","DOI":"10.23919\/ChiCC.2018.8483588"},{"key":"56_CR21","unstructured":"Tchaye-Kondi, J., Zhai, Y., Lin K.J., Tao, W., Yang, K.: Hadoop perfect file: a fast access container for small files with direct in disc metadata access. IEEE"},{"key":"56_CR22","doi-asserted-by":"crossref","unstructured":"Ciritoglu, H.E., Saber, T., Buda, T.S., Murphy, J., Thorpe, C.: Towardsa better replica management for hadoop distributed file system. IEEE Big Data Congress \u201818At: San Francisco (2018)","DOI":"10.1109\/BigDataCongress.2018.00021"},{"key":"56_CR23","unstructured":"Cheng, W., Zhou, M., Tong, B., Zhu, J.: Optimizing Small File Storage Process of the HDFS Which Based on the Indexing Mechanism. In: 2nd IEEE International Conference on Cloud Computing and Big Data Analysis (2017)"},{"key":"56_CR24","doi-asserted-by":"crossref","unstructured":"Venkataramanachary, V., Reveron, E., Shi, W.: Storage and rack sensitive replica placement algorithm for distributed platform with data as files. In: 2020 12th International Conference on Communication Systems & Networks (COMSNETS) (2020)","DOI":"10.1109\/COMSNETS48256.2020.9027494"},{"key":"56_CR25","doi-asserted-by":"crossref","unstructured":"Rattanaopas, K., Kaewkeeree, S.: Improving Hadoop MapReduce Performance with Data Compression: A Study Using Wordcount Job. IEEE (2017)","DOI":"10.1109\/ECTICon.2017.8096300"},{"key":"56_CR26","doi-asserted-by":"crossref","unstructured":"El-Sayed, T., Badawy, M., El-Sayed, A.: SFSAN approach for solving the problem of small files in Hadoop. In: 2018 13th International Conference on Computer Engineering and Systems (ICCES) (2018)","DOI":"10.1109\/ICCES.2018.8639479"},{"key":"56_CR27","unstructured":"Niazi, S., Ronstr\u00f6m, M.: Size Matters: Improving the Performance of Small Files in Hadoop. In: The 19th International Middleware Conference"},{"key":"56_CR28","unstructured":"Climate Data Online, available from National Centers for Environmental Information at https:\/\/www.ncdc.noaa.gov\/cdo-web\/datasets"},{"key":"56_CR29","unstructured":"Merla, P.R., Liang, Y.: Data analysis using hadoop MapReduce environment. IEEE"},{"key":"56_CR30","unstructured":"Tao, W., Zhai, Y., Tchaye-Kondi, J.: LHF: A New Archive based Approach to Acclerate Massive Small Files Access Performance in HDFS. EasyChair Preprint n\u00b0. 773 (2017)"},{"key":"56_CR31","unstructured":"Shah, A., Padole, M.: Optimization of hadoop MapReduce model in cloud computing environment. IEEE (2019)"},{"key":"56_CR32","doi-asserted-by":"crossref","unstructured":"Zheng, T., Guo, W., Fan, G.: A method to improve the performance for storing massive small files in Hadoop. In: The 7th International Conference on Computer Engineering and Networks (CENet2017) Shanghai (2017)","DOI":"10.22323\/1.299.0022"},{"key":"56_CR33","unstructured":"https:\/\/arxiv.org\/ftp\/arxiv\/papers\/1904\/1904.03997.pdf"}],"container-title":["Smart Innovation, Systems and Technologies","Networking, Intelligent Systems and Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-16-3637-0_56","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T12:47:38Z","timestamp":1633092458000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-16-3637-0_56"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,2]]},"ISBN":["9789811636363","9789811636370"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-16-3637-0_56","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2021,10,2]]},"assertion":[{"value":"2 October 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}