{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:49:58Z","timestamp":1729619398389,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1109\/msst.2016.7897082","type":"proceedings-article","created":{"date-parts":[[2017,4,13]],"date-time":"2017-04-13T16:45:41Z","timestamp":1492101941000},"page":"1-14","source":"Crossref","is-referenced-by-count":7,"title":["Sorted deduplication: How to process thousands of backup streams"],"prefix":"10.1109","author":[{"given":"Jurgen","family":"Kaiser","sequence":"first","affiliation":[]},{"given":"Tim","family":"Suss","sequence":"additional","affiliation":[]},{"given":"Lars","family":"Nagel","sequence":"additional","affiliation":[]},{"given":"Andre","family":"Brinkmann","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","first-page":"21","article-title":"On the resemblance and containment of documents","author":"broder","year":"1997","journal-title":"Proceedings of the Conference on Compression and Complexity of Sequences"},{"key":"ref10","first-page":"183","article-title":"Improving restore speed for backup systems that use inline chunk-based deduplication","author":"lillibridge","year":"2013","journal-title":"Proceedings of the 11th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref11","first-page":"181","article-title":"Accelerating restore and garbage collection in deduplication-based backup systems via exploiting historical information","author":"fu","year":"2014","journal-title":"Proceedings of the USENIX Annual Technical Conference (ATC)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2078861.2078864"},{"key":"ref13","article-title":"Fingerprinting by random polynomials","author":"rabin","year":"1981","journal-title":"Center for Research in Computing Technology Harvard University Tech Rep"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2485732.2485748"},{"key":"ref16","first-page":"175","article-title":"File recipe compression in data deduplication systems","author":"meister","year":"2013","journal-title":"Proceedings of 11th USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref17","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","volume":"1518","author":"raab","year":"1998","journal-title":"Proceedings of the 2nd International Workshop on Randomization and Approximation Techniques in Computer Science (RANDOM'98) ser LNCS"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511814075"},{"key":"ref19","first-page":"215","article-title":"On a classical problem of probability theory","author":"erd\u00f3s","year":"1961","journal-title":"Magyar Tudományos Akadémia Matematikai Kutató Intézetének Közleményei 6 MR 0150807"},{"key":"ref28","article-title":"Content-aware load balancing for distributed backup","author":"douglis","year":"2011","journal-title":"Proc of Large Installation System Administration Conference (LISA) 2004"},{"key":"ref4","first-page":"89","article-title":"Venti: a new approach to archival storage","author":"quinlan","year":"2002","journal-title":"Proceedings of the 1st USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2010.187"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"ref6","article-title":"Deriving and Comparing Deduplication Techniques Using a Model-Based Classification","author":"kaiser","year":"2015","journal-title":"Proceedings of the 10th European Conference on ComputerSystems (EuroSys)"},{"key":"ref29","article-title":"Optimizing file replication over limited bandwidth networks using remote differential compression","author":"teodosiu","year":"2006","journal-title":"Microsoft Research TR-2006–157"},{"key":"ref5","article-title":"SiLo: A Similarity-Locality based Near-Exact Deduplication Scheme with low RAM Overhead and High Throughput","author":"xia","year":"2011","journal-title":"Proceedings of the USENIX Annual Technical Conference (ATC)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s002360050048"},{"key":"ref7","first-page":"151","article-title":"Identifying trends in enterprise data protection systems","author":"amvrosiadis","year":"2015","journal-title":"Proceedings of the USENIX Annual Technical Conference (ATC)"},{"key":"ref2","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)"},{"year":"2012","key":"ref9","article-title":"Data domain boost software"},{"key":"ref1","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":"ref20","first-page":"1","article-title":"MAD 2: A scalable high-throughput exact deduplication approach for network backup services","author":"wei","year":"2010","journal-title":"Proceedings of the 26th IEEE Conference on Mass Storage Systems and Technologies (MSST)"},{"key":"ref22","first-page":"25","article-title":"Building a highperformance deduplication system","author":"guo","year":"2011","journal-title":"Proceedings of the USENIX Annual Technical Conference (ATC)"},{"key":"ref21","article-title":"Fast, inexpensive content-addressed storage in Foundation","author":"rhea","year":"2008","journal-title":"Proceedings of the USENIX 2008 Annual Technical Conference (ATC)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.76"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2485732.2485753"},{"key":"ref26","article-title":"Patent No.: US 7, 930,559 B1","author":"beaverson","year":"2011","journal-title":"EMC Corporation"},{"key":"ref25","article-title":"De-centralized deduplication in san cluster file systems","author":"clements","year":"2009","journal-title":"Proceedings of the ser USENIX'09"}],"event":{"name":"2016 32nd Symposium on Mass Storage Systems and Technologies (MSST)","start":{"date-parts":[[2016,5,2]]},"location":"Santa Clara, CA","end":{"date-parts":[[2016,5,6]]}},"container-title":["2016 32nd Symposium on Mass Storage Systems and Technologies (MSST)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7893520\/7897073\/07897082.pdf?arnumber=7897082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T22:06:44Z","timestamp":1569017204000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7897082\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/msst.2016.7897082","relation":{},"subject":[],"published":{"date-parts":[[2016]]}}}