{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T11:49:21Z","timestamp":1773834561771,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010,5]]},"DOI":"10.1109\/msst.2010.5496987","type":"proceedings-article","created":{"date-parts":[[2010,7,6]],"date-time":"2010-07-06T18:06:33Z","timestamp":1278439593000},"page":"1-14","source":"Crossref","is-referenced-by-count":57,"title":["MAD2: A scalable high-throughput exact deduplication approach for network backup services"],"prefix":"10.1109","author":[{"given":"Jiansheng","family":"Wei","sequence":"first","affiliation":[]},{"given":"Hong","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Dan","family":"Feng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Replication Under Scalable Hashing: A Family of Algorithms for Scalable Decentralized Data Distribution","author":"honicky","year":"2004","journal-title":"Proceedings of the 18th International Parallel and Distributed Processing Symposium (IPDPS)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534541"},{"key":"ref33","first-page":"1","article-title":"Finding similar files in a large file system","author":"manber","year":"1994","journal-title":"Proceedings of the winter 1994 USENIX Technical Conference"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-9323-8_11"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2006.44"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1060289.1060324"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534540"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2008.32"},{"key":"ref35","first-page":"165","article-title":"Hierarchical Bloom Filter Arrays (HBA): A Novel, Scalable Metadata Management System for Large Cluster-based Storage","author":"zhu","year":"2004","journal-title":"the proceedings of IEEE International Conference on Cluster Computing (Cluster"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/1081870.1081916"},{"key":"ref10","article-title":"Redundancy Elimination Within Large Collections of Files","author":"kulkarni","year":"2004","journal-title":"Proceedings of the 2004 USENIX Annual Technical Conference"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/383059.383072"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/SEQUEN.1997.666900"},{"key":"ref12","author":"rabin","year":"1981","journal-title":"Fingerprinting by random polynomials"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/362686.362692"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1080\/15427951.2004.10129096"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1288783.1288788"},{"key":"ref17","first-page":"143","article-title":"Fast, Inexpensive Content-Addressed Storage in Foundation","author":"rhea","year":"2008","journal-title":"Proceedings of the 2008 USENIX Annual Technical Conference"},{"key":"ref18","article-title":"Decentralized Deduplication in SAN Cluster File Systems","author":"clements","year":"2009","journal-title":"Proceedings of the 2009 USENIX Annual Technical Conference"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1060289.1060291"},{"key":"ref28","first-page":"43","article-title":"Design, Implementation, and Evaluation of Duplicate Transfer Detection in HTTP","author":"mogul","year":"2004","journal-title":"Proceedings of the 1st Symposium on Networked Systems Design and Implementation (NSDI)"},{"key":"ref4","article-title":"HYDRAstor: a Scalable Secondary Storage","author":"dubnicki","year":"2009","journal-title":"Proceedings of the 7th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref27","article-title":"Exploiting Similarity for Multi-Source Downloads Using File Handprints","author":"pucha","year":"2007","journal-title":"Proceedings of the 4th Symposium on Networked System Design and Implementation (NSDI)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2005.47"},{"key":"ref6","first-page":"111","article-title":"Sparse Indexing: Large Scale, Inline Deduplication Using Sampling and Locality","author":"lillibridge","year":"2009","journal-title":"Proceedings of the 7th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/775152.775239"},{"key":"ref5","first-page":"269","article-title":"Avoiding the Disk Bottleneck in the Data Domain Deduplication File System","author":"zhu","year":"2008","journal-title":"Proceedings of the 6th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref8","article-title":"Alternatives for Detecting Redundancy in Storage Systems Data","author":"policroniades","year":"2004","journal-title":"Proceedings of the 2004 USENIX Annual Technical Conference"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"ref2","first-page":"89","article-title":"Venti: a new approach to archival storage","author":"quinlan","year":"2002","journal-title":"Proceedings of the USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref1","first-page":"29","article-title":"A Cooperative Internet Backup Scheme","author":"lillibridge","year":"2003","journal-title":"Proceedings of the 2003 USENIX Annual Technical Conference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2003.818784"},{"key":"ref20","year":"0","journal-title":"EMC Centera Content addressed storage system"},{"key":"ref45","first-page":"329","article-title":"Pastry: Scalable, decentralized object location and routing for large-scale peer-to-peer systems","author":"rowstron","year":"2001","journal-title":"Proceedings of the 18th IFIP\/ACM International Conference on Distributed Systems Platforms (Middleware)"},{"key":"ref22","first-page":"123","article-title":"Jumbo Store: Providing Efficient Incremental Upload and Versioning for a Utility Rendering Service","author":"eshghi","year":"2007","journal-title":"Proceedings of the 5th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1060289.1060316"},{"key":"ref42","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1007\/3-540-49543-6_13","article-title":"Balls into Bins - A Simple and Tight Analysis","author":"raab","year":"1998","journal-title":"Proc 7th Int Workshop on Randomization and Approximation Techniques in Computer Science (RANDOM)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/347059.347408"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/236711.236713"},{"key":"ref23","article-title":"Evaluation of Efficient Archival Storage Techniques","author":"you","year":"2004","journal-title":"Proceedings of the 21st IEEE\/12th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST)"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/383059.383071"},{"key":"ref26","article-title":"TAPER: Tiered Approach for Eliminating Redundancy in Replica Synchronization","author":"jain","year":"2005","journal-title":"Proc 4th USENIX Conference on File and Storage Technologies"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2005.46"},{"key":"ref25","first-page":"127","article-title":"Opportunistic Use of Content Addressable Storage for Distributed File Systems","author":"tolia","year":"2003","journal-title":"Proceedings of the 2003 USENIX Annual Technical Conference"}],"event":{"name":"2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","location":"Incline Village, NV, USA","start":{"date-parts":[[2010,5,3]]},"end":{"date-parts":[[2010,5,7]]}},"container-title":["2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5488875\/5496967\/05496987.pdf?arnumber=5496987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,19]],"date-time":"2017-06-19T10:25:30Z","timestamp":1497867930000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5496987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010,5]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/msst.2010.5496987","relation":{},"subject":[],"published":{"date-parts":[[2010,5]]}}}