{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T22:30:41Z","timestamp":1757457041434,"version":"3.37.3"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,7,25]],"date-time":"2016-07-25T00:00:00Z","timestamp":1469404800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61202121","61300218"],"award-info":[{"award-number":["61202121","61300218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National High Technology Research and Development","award":["2015AA015305"],"award-info":[{"award-number":["2015AA015305"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Parallel Prog"],"published-print":{"date-parts":[[2017,8]]},"DOI":"10.1007\/s10766-016-0450-5","type":"journal-article","created":{"date-parts":[[2016,7,25]],"date-time":"2016-07-25T15:07:22Z","timestamp":1469459242000},"page":"946-964","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["GLE-Dedup: A Globally\u2013Locally Even Deduplication by Request-Aware Placement for Better Read Performance"],"prefix":"10.1007","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2389-7845","authenticated-orcid":false,"given":"Mingzhu","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songping","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,7,25]]},"reference":[{"issue":"4","key":"450_CR1","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1145\/1210596.1210599","volume":"2","author":"DR Bobbarjung","year":"2006","unstructured":"Bobbarjung, D.R., Jagannathan, S., Dubnicki, C.: Improving duplicate elimination in storage systems. ACM Trans. Storage (TOS) 2(4), 424\u2013448 (2006)","journal-title":"ACM Trans. Storage (TOS)"},{"key":"450_CR2","unstructured":"Bolosky, W.J., Corbin, S., Goebel, D., Douceur, J.R.: Single instance storage in windows 2000. In Proceedings of the 4th USENIX Windows Systems Symposium, pp. 13\u201324. Seattle, WA (2000)"},{"key":"450_CR3","doi-asserted-by":"crossref","unstructured":"Calder, B., Wang, J., Ogus, A., Nilakantan, N., Skjolsvold, A., McKelvie, S., Xu, Y., Srivastav, S., Wu, J., Simitci, H., et al.: Windows azure storage: a highly available cloud storage service with strong consistency. In Proceedings of the Twenty-Third ACM Symposium on Operating Systems Principles, pp. 143\u2013157. ACM (2011)","DOI":"10.1145\/2043556.2043571"},{"key":"450_CR4","unstructured":"Chen, F., Luo, T., Zhang, X.: Caftl: a content-aware flash translation layer enhancing the lifespan of flash memory based solid state drives. In FAST, vol. 11 (2011)"},{"issue":"2","key":"450_CR5","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1145\/176979.176981","volume":"26","author":"PM Chen","year":"1994","unstructured":"Chen, P.M., Lee, E.K., Gibson, G.A., Katz, R.H., Patterson, D.A.: Raid: high-performance, reliable secondary storage. ACM Comput. Surv. (CSUR) 26(2), 145\u2013185 (1994)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"450_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Chen, Z., Xiao, N., Liu, F.: Nf-dedupe: a novel no-fingerprint deduplication scheme for flash-based ssds. In 2015 IEEE Symposium on Computers and Communication (ISCC), pp. 588\u2013594. IEEE (2015)","DOI":"10.1109\/ISCC.2015.7405578"},{"key":"450_CR7","unstructured":"Debnath, B.K., Sengupta, S., Li, J.: Chunkstash: speeding up inline storage deduplication using flash memory. In USENIX annual technical conference (2010)"},{"key":"450_CR8","doi-asserted-by":"crossref","unstructured":"Du, Y., Zhang, Y., Xiao, N.: R-dedup: content aware redundancy management for ssd-based raid systems. In Parallel Processing (ICPP), 2014 43rd International Conference on, pp. 111\u2013120. IEEE (2014)","DOI":"10.1109\/ICPP.2014.20"},{"key":"450_CR9","unstructured":"El-Shimi, A., Kalach, R., Kumar, A., Ottean, A., Li, J., Sengupta, S.: Primary data deduplicationlarge scale study and system design. In Presented as part of the 2012 USENIX Annual Technical Conference (USENIX ATC 12), pp. 285\u2013296. (2012)"},{"key":"450_CR10","unstructured":"Fu, M., Feng, D., Hua, Y., He, X., Chen, Z., Xia, W., Huang, F., Liu, Q.: Accelerating restore and garbage collection in deduplication-based backup systems via exploiting historical information. In 2014 USENIX Annual Technical Conference (USENIX ATC 14), pp. 181\u2013192. (2014)"},{"key":"450_CR11","unstructured":"Fu, M., Feng, D., Hua, Y., He, X., Chen, Z., Xia, W., Zhang, Y., Tan, Y.: Design tradeoffs for data deduplication performance in backup workloads. In 13th USENIX Conference on File and Storage Technologies (FAST 15), pp. 331\u2013344. (2015)"},{"key":"450_CR12","doi-asserted-by":"crossref","unstructured":"Fu, Y., Jian, H., Xiao, N., Tian, L., Liu, F.: Aa-dedupe: an application-aware source deduplication approach for cloud backup services in the personal computing environment. In Cluster Computing (CLUSTER), 2011 IEEE International Conference on, pp. 112\u2013120. IEEE (2011)","DOI":"10.1109\/CLUSTER.2011.20"},{"key":"450_CR13","doi-asserted-by":"crossref","unstructured":"Ghemawat, S., Gobioff, H., Leung, S.T.: The google file system. In ACM SIGOPS operating systems review, vol. 37, pp. 29\u201343. ACM (2003)","DOI":"10.1145\/945445.945450"},{"key":"450_CR14","unstructured":"Guo, F., Efstathopoulos, P.: Building a high-performance deduplication system. In USENIX Annual Technical Conference (2011)"},{"issue":"35","key":"450_CR15","doi-asserted-by":"crossref","first-page":"5066","DOI":"10.1007\/s11434-014-0645-3","volume":"59","author":"H Guo","year":"2014","unstructured":"Guo, H., Wang, L., Chen, F., Liang, D.: Scientific big data and digital earth. Chin. Sci. Bull. 59(35), 5066\u20135073 (2014)","journal-title":"Chin. Sci. Bull."},{"key":"450_CR16","doi-asserted-by":"crossref","unstructured":"He, W., Xiao, N., Liu, F., Chen, Z., Fu, Y.: Dl-dedupe: dual-level deduplication scheme for flash-based ssds. In Web-Age Information Management, pp. 4\u201315. Springer (2013)","DOI":"10.1007\/978-3-642-39527-7_3"},{"issue":"3","key":"450_CR17","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1007\/BF01266332","volume":"2","author":"M Holland","year":"1994","unstructured":"Holland, M., Gibson, G.A., Siewiorek, D.P.: Architectures and algorithms for on-line failure recovery in redundant disk arrays. Distrib. Parallel Database 2(3), 295\u2013335 (1994)","journal-title":"Distrib. Parallel Database"},{"key":"450_CR18","doi-asserted-by":"crossref","unstructured":"Hu, Y., Jiang, H., Feng, D., Tian, L., Luo, H., Zhang, S.: Performance impact and interplay of ssd parallelism through advanced commands, allocation strategy and data granularity. In Proceedings of the international conference on Supercomputing, pp. 96\u2013107. ACM (2011)","DOI":"10.1145\/1995896.1995912"},{"key":"450_CR19","doi-asserted-by":"crossref","unstructured":"Kaczmarczyk, M., Barczynski, M., Kilian, W., Dubnicki, C.: Reducing impact of data fragmentation caused by in-line deduplication. In Proceedings of the 5th Annual International Systems and Storage Conference, p. 15. ACM (2012)","DOI":"10.1145\/2367589.2367600"},{"key":"450_CR20","doi-asserted-by":"crossref","unstructured":"Kim, Y., Tauras, B., Gupta, A., Urgaonkar, B.: Flashsim: A simulator for nand flash-based solid-state drives. In Advances in System Simulation, 2009. SIMUL\u201909. First International Conference on, pp. 125\u2013131. IEEE (2009)","DOI":"10.1109\/SIMUL.2009.17"},{"issue":"3","key":"450_CR21","first-page":"13","volume":"6","author":"R Koller","year":"2010","unstructured":"Koller, R., Rangaswami, R.: I\/o deduplication: utilizing content similarity to improve i\/o performance. ACM Trans. Storage (TOS) 6(3), 13 (2010)","journal-title":"ACM Trans. Storage (TOS)"},{"key":"450_CR22","unstructured":"Lillibridge, M., Eshghi, K., Bhagwat, D.: Improving restore speed for backup systems that use inline chunk-based deduplication. In Presented as part of the 11th USENIX Conference on File and Storage Technologies (FAST 13), pp. 183\u2013197. (2013)"},{"key":"450_CR23","unstructured":"Lillibridge, M., Eshghi, K., Bhagwat, D., Deolalikar, V., Trezis, G., Camble, P.: Sparse indexing: Large scale, inline deduplication using sampling and locality. In Fast, vol. 9, pp. 111\u2013123. (2009)"},{"key":"450_CR24","unstructured":"McKnight, J., Asaro, T., Babineau, B.: Digital archiving: end-user survey and market forecast 2006\u20132010. The Enterprise Strategy Group (2006)"},{"key":"450_CR25","doi-asserted-by":"crossref","unstructured":"Meister, D., Brinkmann, A.: Dedupv1: improving deduplication throughput using solid state drives (ssd). In Mass Storage Systems and Technologies (MSST), 2010 IEEE 26th Symposium on, pp. 1\u20136. IEEE (2010)","DOI":"10.1109\/MSST.2010.5496992"},{"key":"450_CR26","doi-asserted-by":"crossref","unstructured":"Meister, D., Kaiser, J., Brinkmann, A., Cortes, T., Kuhn, M., Kunkel, J.: A study on data deduplication in hpc storage systems. In Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, p. 7. IEEE Computer Society Press (2012)","DOI":"10.1109\/SC.2012.14"},{"issue":"4","key":"450_CR27","first-page":"14","volume":"7","author":"DT Meyer","year":"2012","unstructured":"Meyer, D.T., Bolosky, W.J.: A study of practical deduplication. ACM Trans. Storage (TOS) 7(4), 14 (2012)","journal-title":"ACM Trans. Storage (TOS)"},{"issue":"6","key":"450_CR28","doi-asserted-by":"crossref","first-page":"824","DOI":"10.1109\/TC.2010.263","volume":"60","author":"J Min","year":"2011","unstructured":"Min, J., Yoon, D., Won, Y.: Efficient deduplication techniques for modern backup operation. Comput. IEEE Trans. 60(6), 824\u2013840 (2011)","journal-title":"Comput. IEEE Trans."},{"key":"450_CR29","doi-asserted-by":"crossref","unstructured":"Nam, Y.J., Park, D., Du, D.H.: Assuring demanded read performance of data deduplication storage with backup datasets. In Modeling, Analysis & Simulation of Computer and Telecommunication Systems (MASCOTS), 2012 IEEE 20th International Symposium on, pp. 201\u2013208. IEEE (2012)","DOI":"10.1109\/MASCOTS.2012.32"},{"key":"450_CR30","doi-asserted-by":"crossref","unstructured":"Ng, C.H., Lee, P.P.: Revdedup: A reverse deduplication storage system optimized for reads to latest backups. In Proceedings of the 4th Asia-Pacific Workshop on Systems, p. 15. ACM (2013)","DOI":"10.1145\/2500727.2500731"},{"key":"450_CR31","doi-asserted-by":"crossref","unstructured":"Park, N., Lilja, D.J.: Characterizing datasets for data deduplication in backup applications. In Workload Characterization (IISWC), 2010 IEEE International Symposium on, pp. 1\u201310. IEEE (2010)","DOI":"10.1109\/IISWC.2010.5650369"},{"key":"450_CR32","unstructured":"Prabhakaran, V., Wobber, T.: SSD extension for disksim simulation environment. Microsoft Reseach. (2009)"},{"key":"450_CR33","volume-title":"Data compression: The Complete Reference","author":"D Salomon","year":"2004","unstructured":"Salomon, D.: Data compression: The Complete Reference. Springer, New York (2004)"},{"key":"450_CR34","doi-asserted-by":"crossref","unstructured":"Shvachko, K., Kuang, H., Radia, S., Chansler, R.: The hadoop distributed file system. In Mass Storage Systems and Technologies (MSST), 2010 IEEE 26th Symposium on, pp. 1\u201310. IEEE (2010)","DOI":"10.1109\/MSST.2010.5496972"},{"key":"450_CR35","unstructured":"Sun, Z., Kuenning, G., Mandal, S., Shilane, P., Tarasov, V., Xiao, N., Zadok, E.: A long-term user-centric analysis of deduplication patterns"},{"key":"450_CR36","doi-asserted-by":"crossref","unstructured":"Tan, Y., Yan, Z., Feng, D., Sha, E.H., Ge, X.: Reducing the de-linearization of data placement to improve deduplication performance. In High Performance Computing, Networking, Storage and Analysis (SCC), 2012 SC Companion:, pp. 796\u2013800. IEEE (2012)","DOI":"10.1109\/SC.Companion.2012.110"},{"key":"450_CR37","unstructured":"Wallace, G., Douglis, F., Qian, H., Shilane, P., Smaldone, S., Chamness, M., Hsu, W.: Characteristics of backup workloads in production systems. In FAST, vol. 4, p. 500. (2012)"},{"key":"450_CR38","unstructured":"Xia, W., Jiang, H., Feng, D., Hua, Y.: Silo: A similarity-locality based near-exact deduplication scheme with low ram overhead and high throughput. In USENIX Annual Technical Conference (2011)"},{"key":"450_CR39","doi-asserted-by":"crossref","unstructured":"Xia, W., Jiang, H., Feng, D., Tian, L., Fu, M., Wang, Z.: P-dedupe: exploiting parallelism in data deduplication system. In Networking, Architecture and Storage (NAS), 2012 IEEE 7th International Conference on, pp. 338\u2013347. IEEE (2012)","DOI":"10.1109\/NAS.2012.46"},{"key":"450_CR40","unstructured":"Xiao, M., Hassan, M.A., Xiao, W., Wei, Q., Chen, S.: Codeplugin: plugging deduplication into erasure coding for cloud storage. In 7th USENIX Workshop on Hot Topics in Cloud Computing (HotCloud 15) (2015)"},{"key":"450_CR41","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhu, Y., Lee, P.P., Xu, Y.: Even data placement for load balance in reliable distributed deduplication storage systems. In Quality of Service (IWQoS), 2015 IEEE 23rd International Symposium on, pp. 349\u2013358. IEEE (2015)","DOI":"10.1109\/IWQoS.2015.7404754"},{"key":"450_CR42","unstructured":"Zaharia, M., Chowdhury, M., Franklin, M.J., Shenker, S., Stoica, I.: Spark: cluster computing with working sets. In Proceedings of the 2nd USENIX conference on Hot topics in cloud computing, vol. 10, p. 10. (2010)"},{"key":"450_CR43","doi-asserted-by":"crossref","unstructured":"Zhengda, Z., Jingli, Z.: A novel data redundancy scheme for de-duplication storage system. In Knowledge Acquisition and Modeling (KAM), 2010 3rd International Symposium on, pp. 293\u2013296. IEEE (2010)","DOI":"10.1109\/KAM.2010.5646152"},{"key":"450_CR44","unstructured":"Zhu, B., Li, K., Patterson, R.H.: Avoiding the disk bottleneck in the data domain deduplication file system. In Fast, vol. 8, pp. 1\u201314. (2008)"}],"container-title":["International Journal of Parallel Programming"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10766-016-0450-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0450-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0450-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10766-016-0450-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,11]],"date-time":"2019-09-11T13:34:26Z","timestamp":1568208866000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10766-016-0450-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7,25]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,8]]}},"alternative-id":["450"],"URL":"https:\/\/doi.org\/10.1007\/s10766-016-0450-5","relation":{},"ISSN":["0885-7458","1573-7640"],"issn-type":[{"type":"print","value":"0885-7458"},{"type":"electronic","value":"1573-7640"}],"subject":[],"published":{"date-parts":[[2016,7,25]]}}}