{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T02:58:52Z","timestamp":1763348332483,"version":"3.37.3"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T00:00:00Z","timestamp":1609718400000},"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":["61872391"],"award-info":[{"award-number":["61872391"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Funds for Guangzhou Scientific and Technological Innovation and Development","award":["201802010011"],"award-info":[{"award-number":["201802010011"]}]},{"name":"Foundation for Young Talents in Higher Education of Guangdong, China","award":["2019KQNCX031"],"award-info":[{"award-number":["2019KQNCX031"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"published-print":{"date-parts":[[2021,7]]},"DOI":"10.1007\/s11227-020-03526-1","type":"journal-article","created":{"date-parts":[[2021,1,4]],"date-time":"2021-01-04T12:03:56Z","timestamp":1609761836000},"page":"7149-7170","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Enhancing HDFS with a full-text search system for massive small files"],"prefix":"10.1007","volume":"77","author":[{"given":"Wentao","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Lao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ge","family":"Nong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,1,4]]},"reference":[{"issue":"4","key":"3526_CR1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1145\/2810036","volume":"59","author":"A Apostolico","year":"2016","unstructured":"Apostolico A, Crochemore M, Farach-Colton M, Galil Z, Muthukrishnan S (2016) 40 years of suffix trees. Commun ACM 59(4):66\u201373","journal-title":"Commun ACM"},{"issue":"9","key":"3526_CR2","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/j.parco.2014.06.007","volume":"40","author":"D Arroyuelo","year":"2014","unstructured":"Arroyuelo D, Bonacic C, Gil-Costa V, Marin M, Navarro G (2014) Distributed text search using suffix arrays. Parallel Comput 40(9):471\u2013495","journal-title":"Parallel Comput"},{"key":"3526_CR3","doi-asserted-by":"crossref","unstructured":"Chandrasekar A, Chandrasekar K, Ramasatagopan H, Rafica AR, Balasubramaniyan J (2012) Classification based metadata management for HDFS. In: HPCC 2012 and ICESS 2012","DOI":"10.1109\/HPCC.2012.149"},{"issue":"6","key":"3526_CR4","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1109\/TKDE.2012.236","volume":"26","author":"G Chen","year":"2014","unstructured":"Chen G, Hu T, Jiang D, Lu P, Tan KL, Vo HT, Wu S (2014) BestPeer++: a peer-to-peer based large-scale data processing platform. IEEE Trans Knowl Data Eng 26(6):1316\u20131331","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"11","key":"3526_CR5","doi-asserted-by":"publisher","first-page":"3060","DOI":"10.1109\/TPDS.2017.2706686","volume":"28","author":"Y Chen","year":"2017","unstructured":"Chen Y, Zhou Y, Taneja S, Qin X, Huang J (2017) aHDFS: an erasure-coded data archival system for Hadoop clusters. IEEE Trans Parallel Distrib Syst 28(11):3060\u20133073","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"2","key":"3526_CR6","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s10479-016-2376-0","volume":"265","author":"C Choi","year":"2016","unstructured":"Choi C, Choi C, Choi J, Kim P (2016) Improved performance optimization for massive small files in cloud computing environment. Ann Oper Res 265(2):305\u2013317","journal-title":"Ann Oper Res"},{"key":"3526_CR7","unstructured":"Dhaliwal J, Puglisi SJ, Turpin A (2012) Trends in suffix sorting: a survey of low memory algorithms. In: Proceedings of the Thirty-Fifth Australasian Computer Science Conference-Volume, vol 122, pp 91\u201398"},{"issue":"2","key":"3526_CR8","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2009","unstructured":"Everingham M, Gool LV, Williams CKI, Winn J, Zisserman A (2009) The pascal visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"12","key":"3526_CR9","doi-asserted-by":"publisher","first-page":"3433","DOI":"10.1109\/TPDS.2014.2377720","volume":"26","author":"S Fu","year":"2015","unstructured":"Fu S, He L, Huang C, Liao X, Li K (2015) Performance optimization for managing massive numbers of small files in distributed file systems. IEEE Trans Parallel Distrib Syst 26(12):3433\u20133448","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"3526_CR10","doi-asserted-by":"crossref","unstructured":"Gao Z, Qin Y, Niu K (2016) An effective merge strategy based hierarchy for improving small file problem on HDFS. In: 2016 4th International Conference on Cloud Computing and Intelligence Systems","DOI":"10.1109\/CCIS.2016.7790278"},{"key":"3526_CR11","doi-asserted-by":"crossref","unstructured":"Gupta S, Yadav S, Prasad R (2018) Document retrieval using efficient indexing techniques. In: Information retrieval and management, pp 1745\u20131764","DOI":"10.4018\/978-1-5225-5191-1.ch079"},{"key":"3526_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102378","author":"LB Han","year":"2020","unstructured":"Han LB, Wu Y, Nong G (2020) Succinct suffix sorting in external memory. Inf Process Manag. https:\/\/doi.org\/10.1016\/j.ipm.2020.102378","journal-title":"Inf Process Manag"},{"issue":"10","key":"3526_CR13","doi-asserted-by":"publisher","first-page":"3696","DOI":"10.1007\/s11227-015-1462-4","volume":"72","author":"H He","year":"2015","unstructured":"He H, Du Z, Zhang W, Chen A (2015) Optimization strategy of Hadoop small file storage for big data in healthcare. J Supercomput 72(10):3696\u20133707","journal-title":"J Supercomput"},{"key":"3526_CR14","doi-asserted-by":"crossref","unstructured":"K\u00e4rkk\u00e4inen J, Kempa D, Puglisi SJ (2015) Parallel external memory suffix sorting. In: Proceedings of the 26th Annual Symposium on Combinatorial Pattern Matching, pp 329\u2013342","DOI":"10.1007\/978-3-319-19929-0_28"},{"key":"3526_CR15","doi-asserted-by":"crossref","unstructured":"Kim H, Yeom H (2017) Improving small file I\/O performance for massive digital archives. In: 2017 IEEE 13th International Conference on E-Science","DOI":"10.1109\/eScience.2017.39"},{"issue":"2","key":"3526_CR16","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1145\/1773912.1773922","volume":"44","author":"A Lakshman","year":"2010","unstructured":"Lakshman A, Malik P (2010) Cassandra: a decentralized structured storage system. ACM SIGOPS Oper Syst Rev 44(2):35\u201340","journal-title":"ACM SIGOPS Oper Syst Rev"},{"issue":"12","key":"3526_CR17","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1109\/TC.2018.2842050","volume":"67","author":"B Lao","year":"2018","unstructured":"Lao B, Nong G, Chan WH, Xie JY (2018) Fast in-place suffix sorting on a multicore computer. IEEE Trans Comput 67(12):1737\u20131749","journal-title":"IEEE Trans Comput"},{"key":"3526_CR18","doi-asserted-by":"crossref","unstructured":"Lin TY, Maire M, Belongie S, Hays J, Perona P, Ramanan D, Doll\u00e1r P, Zitnick CL (2014) Microsoft COCO: common objects in context. In: Computer Vision\u2014ECCV, pp 740\u2013755","DOI":"10.1007\/978-3-319-10602-1_48"},{"issue":"5","key":"3526_CR19","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1137\/0222058","volume":"22","author":"U Manber","year":"1993","unstructured":"Manber U, Myers G (1993) Suffix arrays: a new method for on-line string searches. SIAM J Comput 22(5):935\u2013948","journal-title":"SIAM J Comput"},{"key":"3526_CR20","doi-asserted-by":"crossref","unstructured":"Meng B, Bin Guo W, Sheng Fan G, Wu Qian N (2016) A novel approach for efficient accessing of small files in HDFS: TLB-MapFile. In: 17th IEEE\/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing","DOI":"10.1109\/SNPD.2016.7515978"},{"key":"3526_CR21","unstructured":"Mori Y Libdivsufsort, a software library that implements a lightweight suffix array construction algorithm. Available: https:\/\/github.com\/y-256\/libdivsufsort"},{"key":"3526_CR22","first-page":"1","volume":"2","author":"MC Nguyen","year":"2017","unstructured":"Nguyen MC, Won H, Son S, Gil MS, Moon YS (2017) Prefetching-based metadata management in advanced multitenant Hadoop. J Supercomput 2:1\u201321","journal-title":"J Supercomput"},{"issue":"3","key":"3526_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2493175.2493180","volume":"31","author":"G Nong","year":"2013","unstructured":"Nong G (2013) Practical linear-time O(1)-workspace suffix sorting for constant alphabets. ACM Trans Inf Syst 31(3):1\u201315","journal-title":"ACM Trans Inf Syst"},{"issue":"10","key":"3526_CR24","doi-asserted-by":"publisher","first-page":"1471","DOI":"10.1109\/TC.2010.188","volume":"60","author":"G Nong","year":"2011","unstructured":"Nong G, Zhang S, Chan WH (2011) Two efficient algorithms for linear time suffix array construction. IEEE Trans Comput 60(10):1471\u20131484","journal-title":"IEEE Trans Comput"},{"key":"3526_CR25","doi-asserted-by":"crossref","unstructured":"Parkhi O.M, Vedaldi A, Zisserman A, Jawahar CV (2012) Cats and dogs. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp 3498\u20133505","DOI":"10.1109\/CVPR.2012.6248092"},{"issue":"7","key":"3526_CR26","first-page":"278","volume":"3","author":"P Phakade","year":"2014","unstructured":"Phakade P, Raut S (2014) An innovative strategy for improved processing of small files in Hadoop. Int J Appl Innov Eng Manag 3(7):278\u2013280","journal-title":"Int J Appl Innov Eng Manag"},{"issue":"7","key":"3526_CR27","doi-asserted-by":"publisher","first-page":"1362","DOI":"10.1109\/TKDE.2019.2904056","volume":"32","author":"J Song","year":"2019","unstructured":"Song J, He H, Thomas R, Bao Y, Yu G (2019) Haery: a Hadoop based query system on accumulative and high-dimensional data model for big data. IEEE Trans Knowl Data Eng 32(7):1362\u20131377","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"3526_CR28","unstructured":"Tchaye-Kondi J, Zhai Y, Lin KJ, Tao W, Yang K (2019) Hadoop perfect file: a fast access container for small files with direct in disc metadata access. arXiv preprint arXiv:1903.05838"},{"issue":"1","key":"3526_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1877766.1877768","volume":"29","author":"F Transier","year":"2010","unstructured":"Transier F, Sanders P (2010) Engineering basic algorithms of an in-memory text search engine. ACM Trans Inf Syst 29(1):1\u201337","journal-title":"ACM Trans Inf Syst"},{"issue":"5","key":"3526_CR30","doi-asserted-by":"publisher","first-page":"1736","DOI":"10.1007\/s11227-014-1287-6","volume":"71","author":"Y Wang","year":"2014","unstructured":"Wang Y, Ma C, Wang W, Meng D (2014) An approach of fast data manipulation in HDFS with supplementary mechanisms. J Supercomput 71(5):1736\u20131753","journal-title":"J Supercomput"},{"issue":"12","key":"3526_CR31","doi-asserted-by":"publisher","first-page":"3304","DOI":"10.1109\/TKDE.2015.2453961","volume":"27","author":"S Wu","year":"2015","unstructured":"Wu S, Chen G, Chen K, Li F, Shou L (2015) HM: a column-oriented MapReduce system on hybrid storage. IEEE Trans Knowl Data Eng 27(12):3304\u20133317","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"9","key":"3526_CR32","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1109\/TC.2020.2972546","volume":"69","author":"JY Xie","year":"2020","unstructured":"Xie JY, Nong G, Lao B, Xu W (2020) Scalable suffix sorting on a multicore machine. IEEE Trans Comput 69(9):1364\u20131375","journal-title":"IEEE Trans Comput"},{"key":"3526_CR33","doi-asserted-by":"crossref","unstructured":"Zhang Y, Liu D (2012) Improving the efficiency of storing for small files in HDFS. In: 2012 International Conference on Computer Science and Service System","DOI":"10.1109\/CSSS.2012.556"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03526-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-020-03526-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-020-03526-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T10:33:38Z","timestamp":1624271618000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-020-03526-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,4]]},"references-count":33,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["3526"],"URL":"https:\/\/doi.org\/10.1007\/s11227-020-03526-1","relation":{},"ISSN":["0920-8542","1573-0484"],"issn-type":[{"type":"print","value":"0920-8542"},{"type":"electronic","value":"1573-0484"}],"subject":[],"published":{"date-parts":[[2021,1,4]]},"assertion":[{"value":"17 November 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}