{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:46:00Z","timestamp":1773153960039,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016]]},"DOI":"10.1109\/msst.2016.7897080","type":"proceedings-article","created":{"date-parts":[[2017,4,13]],"date-time":"2017-04-13T20:45:41Z","timestamp":1492116341000},"page":"1-7","source":"Crossref","is-referenced-by-count":26,"title":["A long-term user-centric analysis of deduplication patterns"],"prefix":"10.1109","author":[{"given":"Zhen","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoff","family":"Kuenning","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sonam","family":"Mandal","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip","family":"Shilane","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vasily","family":"Tarasov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"kand Erez","family":"Zadok","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","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"},{"key":"ref32","article-title":"Characteristics of backup workloads in production systems","author":"wallace","year":"2012","journal-title":"Proceedings of the Tenth USENIX Conference on File and Storage Technologies (FAST ‘12)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2015.40"},{"key":"ref30","article-title":"HydraFS: a high-throughput file system for the HYDRAstor content-addressable storage system","author":"ungureanu","year":"2010","journal-title":"Proc USENIX Conf File and Storage Technologies (FAST '10)"},{"key":"ref35","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"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2015.7208297"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35170-9_18"},{"key":"ref11","article-title":"DedupT: Deduplication for tape systems. Technical report","author":"gharaibeh","year":"2014","journal-title":"IBM"},{"key":"ref12","article-title":"The digital universe decade - are you ready? IDC White Paper","author":"gratz","year":"2010"},{"key":"ref13","article-title":"Building a high-performance deduplication system","author":"guo","year":"2011","journal-title":"Proceedings of the USENIX Annual Technical Conference"},{"key":"ref14","article-title":"A deduplication-based data archiving system","author":"jianting","year":"2012","journal-title":"Proceedings of the International Conference on Image Vision and Computing (ICIVC)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534540"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/1837915.1837921"},{"key":"ref17","article-title":"Cdstore: Toward reliable, secure, and cost efficient cloud storage via convergent dispersal","author":"li","year":"2015","journal-title":"USENIX Annual Technical Conference"},{"key":"ref18","article-title":"Improving restore speed for backup systems that use inline chunk-based deduplication","author":"lillibridge","year":"2013","journal-title":"Proceedings of the Eleventh USENIX Conference on File and Storage Technologies (FAST ‘13)"},{"key":"ref19","article-title":"Sparse indexing: Large scale, inline deduplication using sampling and locality","author":"lillibridge","year":"2009","journal-title":"In Proceedings of the Seventh USENIX Conference on File and Storage Technologies (FAST)"},{"key":"ref28","article-title":"Big data: What it is and why you should care","author":"olofson","year":"2011","journal-title":"White Paper from AWR"},{"key":"ref4","article-title":"Content-aware load balancing for distributed backup","author":"douglis","year":"2011","journal-title":"Proc Usenix Large Installation System Administration Conf"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2010.5650369"},{"key":"ref3","article-title":"Tradeoffs in scalable data routing for deduplication clusters","author":"dong","year":"2011","journal-title":"Proc of USENIX Conference on File and Storage Technologies (FAST '11)"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391246"},{"key":"ref29","article-title":"Generating realistic datasets for deduplication analysis","author":"tarasov","year":"2012","journal-title":"Proceedings of the USENIX Annual Technical Conference"},{"key":"ref5","article-title":"Primary data deduplication-large scale study and system design","author":"ei-shimi","year":"2012","journal-title":"Proceedings of the USENIX Annual Technical Conference"},{"key":"ref8","article-title":"Accelerating restore and garbage collection in deduplication-based backup systems via exploiting history information","author":"fu","year":"2014","journal-title":"Proceedings of Annual Technical Conference"},{"key":"ref7","article-title":"FSL. Fslhomes data set and tools","year":"0","journal-title":"tracer filesystems org"},{"key":"ref2","article-title":"ChunkStash: Speeding up inline storage deduplication using flash memory","author":"debnath","year":"2010","journal-title":"Proceedings of the USENIX Annual Technical Conference"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-013-1394-5"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"ref20","article-title":"Metadata considered harmful … to deduplication","author":"lin","year":"2015","journal-title":"HotStorage’ 15"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2367589.2367606"},{"key":"ref21","article-title":"Using deduplicating storage fot efficient disk image deployment","author":"lin","year":"2015","journal-title":"Proceedings International Conference on Software Testing Verification and Validation"},{"key":"ref24","article-title":"File recipe compression in data deduplication systems","author":"meister","year":"2013","journal-title":"Proceedings of the Eleventh USENIX Conference on File and Storage Technologies (FAST ‘13)"},{"key":"ref23","article-title":"dedupvl: Improving deduplication throughput using solid state drives (SSD)","author":"meister","year":"2010","journal-title":"Proceedings of the MSST Conference"},{"key":"ref26","article-title":"A study of practical deduplication","author":"meyer","year":"2011","journal-title":"Proc of USENIX Conference on File and Storage Technologies (FAST '11)"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.14"}],"event":{"name":"2016 32nd Symposium on Mass Storage Systems and Technologies (MSST)","location":"Santa Clara, CA","start":{"date-parts":[[2016,5,2]]},"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\/07897080.pdf?arnumber=7897080","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,8,30]],"date-time":"2018-08-30T21:56:36Z","timestamp":1535666196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7897080\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/msst.2016.7897080","relation":{},"subject":[],"published":{"date-parts":[[2016]]}}}