{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:10Z","timestamp":1740169210645,"version":"3.37.3"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF), Korea government","doi-asserted-by":"publisher","award":["NRF-2018R1A1A1A05079398"],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Institute of Information and Communications Technology Planning and Evaluation (IITP), Korea government (MSIT)","award":["2020-0-00104"]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3039056","type":"journal-article","created":{"date-parts":[[2020,11,18]],"date-time":"2020-11-18T21:20:40Z","timestamp":1605734440000},"page":"209163-209180","source":"Crossref","is-referenced-by-count":12,"title":["A Content Fingerprint-Based Cluster-Wide Inline Deduplication for Shared-Nothing Storage Systems"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2603-3516","authenticated-orcid":false,"given":"Awais","family":"Khan","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1030-3844","authenticated-orcid":false,"given":"Prince","family":"Hamandawana","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8786-3850","authenticated-orcid":false,"given":"Youngjae","family":"Kim","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","first-page":"1","article-title":"Tagged consistency and garbage identification in deduplication-enabled storage systems","author":"khan","year":"2018","journal-title":"Proc 16th (WiP) USENIX FAST"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2016.7897080"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1837915.1837921"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2011.5937237"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2020.2972882"},{"key":"ref38","first-page":"29","article-title":"The logic of physical garbage collection in deduplicating storage","author":"douglis","year":"2017","journal-title":"Proc USENIX Conf File Storage Technol"},{"key":"ref33","first-page":"175","article-title":"File recipe compression in data deduplication systems","author":"meister","year":"2013","journal-title":"Proc 11th USENIX Conf File Storage Technol"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00106"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/NAS.2019.8834729"},{"key":"ref30","first-page":"1","article-title":"Metadata considered harmful…to deduplication","author":"lin","year":"2015","journal-title":"Proc of the USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage)"},{"key":"ref37","first-page":"291","article-title":"OrderMergeDedup: Efficient, failure-consistent deduplication on flash","author":"chen","year":"2016","journal-title":"Proc USENIX Conf File Storage Technol"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOTS.2018.00016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CCGRID.2018.00036"},{"key":"ref34","first-page":"277","article-title":"Estimating unseen deduplication—From theory to practice","author":"harnik","year":"2016","journal-title":"Proc USENIX Conf File Storage Technol"},{"journal-title":"Clustered Data on Tap","year":"2020","key":"ref60"},{"key":"ref62","first-page":"195","article-title":"ProSy: A similarity based inline deduplication system for primary storage","author":"du","year":"2015","journal-title":"Proc IEEE Int Conf Netw Archit Storage (NAS)"},{"key":"ref61","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":"Proc USENIX Annu Tech Conf"},{"key":"ref63","first-page":"895","article-title":"DS-dedupe: A scalable, low network overhead data routing algorithm for inline cluster deduplication system","author":"sun","year":"2014","journal-title":"Proc Int Conf Comput Netw Commun (ICNC)"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2019.06.006"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/1288783.1288788"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126929"},{"key":"ref65","first-page":"285","article-title":"Primary data deduplication—Large scale study and system design","author":"el-shimi","year":"2012","journal-title":"Proc USENIX Conf Annu Tech Conf"},{"journal-title":"SQLite SQLite Home Page","year":"2020","key":"ref66"},{"key":"ref29","first-page":"2","article-title":"Tradeoffs in scalable data routing for deduplication clusters","author":"dong","year":"2011","journal-title":"Proc 9th USENIX Conf File stroage Technol"},{"journal-title":"Flexible I\/o Tester","year":"2020","author":"axboe","key":"ref67"},{"journal-title":"Ceph Architecture Scrubbing Documentation","year":"2020","key":"ref68"},{"key":"ref69","first-page":"1","article-title":"Chunkstash: Speeding up inline storage deduplication using flash memory","author":"debnath","year":"2010","journal-title":"Proc USENIX Annu Tech Conf"},{"journal-title":"Storage For Your Cloud Gluster","year":"2020","key":"ref2"},{"key":"ref1","first-page":"307","article-title":"Ceph: A Scalable, High-performance Distributed File System","author":"weil","year":"2006","journal-title":"Proc Symp Operating Syst Design Implementation"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"journal-title":"EMC data domain global deduplication array","year":"2020","key":"ref22"},{"key":"ref21","first-page":"197","article-title":"Hydrastor: A scalable secondary storage","author":"dubnicki","year":"2009","journal-title":"Proc 7th USENIX Conf File Storage Technol"},{"key":"ref24","first-page":"25","article-title":"Building a high-performance deduplication system","author":"guo","year":"2011","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCC.2015.2511752"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2017.2753258"},{"article-title":"Improving multi-node deduplication performance for interleaved data via sticky-auction routing","year":"2015","author":"eshghi","key":"ref25"},{"key":"ref50","first-page":"1","article-title":"A study of practical deduplication","author":"meyer","year":"2011","journal-title":"Proc 9th USENIX Conf File stroage Technol"},{"journal-title":"Introduction to the EMC XtremIO Storage Array (Ver 4 0)","year":"2018","key":"ref51"},{"journal-title":"How solidfire data efficiencies work","year":"2020","key":"ref59"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TST.2015.7040510"},{"journal-title":"HP 3PAR StoreServ Storage","year":"2020","author":"enterprise","key":"ref57"},{"key":"ref56","first-page":"257","article-title":"Extending the lifetime of flash-based storage through reducing write amplification from file systems","author":"lu","year":"2013","journal-title":"Proc 11th USENIX Conf File Storage Technol"},{"journal-title":"Permabit","year":"2020","author":"corporation","key":"ref55"},{"key":"ref54","first-page":"5","article-title":"Redundancy elimination within large collections of files","author":"kulkarni","year":"2004","journal-title":"Proc Annu Conf USENIX Annu Tech Conf"},{"journal-title":"btrfs wiki","year":"2018","key":"ref53"},{"journal-title":"The industry best data reduction hands down","year":"2020","key":"ref52"},{"key":"ref10","first-page":"101","article-title":"FastCDC: A fast and efficient content-defined chunking approach for data deduplication","author":"xia","year":"2016","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39637-3_14"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2011.78"},{"key":"ref12","first-page":"89","article-title":"Venti: A new approach to archival storage","author":"quinlan","year":"2002","journal-title":"Proc Conf File Storage Technol"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2391229.2391246"},{"key":"ref14","first-page":"18:1","article-title":"Avoiding the disk bottleneck in the data domain deduplication file system","author":"zhu","year":"2008","journal-title":"Proc 6th USENIX Conf File Storage Technol"},{"key":"ref15","first-page":"101","article-title":"Decentralized deduplication in san cluster file systems","author":"clements","year":"2009","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-35170-9_18"},{"key":"ref17","first-page":"26","article-title":"Silo: A similarity-locality based near-exact deduplication scheme with low ram overhead and high throughput","author":"xia","year":"2011","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232380"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2367589.2367606"},{"key":"ref4","article-title":"Big data gets bigger: What about data cleaning analytics as a storage service?","author":"fekry","year":"2017","journal-title":"Proc of the USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage)"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2004.9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.167"},{"key":"ref5","first-page":"26","article-title":"Primary data deduplication-large scale study and system design","author":"el-shimi","year":"2012","journal-title":"Proc USENIX Conf Annu Tech Conf"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2018.2852642"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.173"},{"key":"ref49","first-page":"1","article-title":"iDedup: Latency-aware, inline data deduplication for primary storage","author":"srinivasan","year":"2012","journal-title":"Proc 10th USENIX Conf File Storage Technol"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2016.7897082"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2571298"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359656"},{"key":"ref48","first-page":"501","article-title":"Nitro: A capacity-optimized SSD cache for primary storage","author":"li","year":"2014","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2016.7897081"},{"article-title":"Understanding lustre filesystem internals","year":"2009","author":"wang","key":"ref42"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1294261.1294281"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1188455.1188582"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2538542.2538562"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09262924.pdf?arnumber=9262924","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:56:57Z","timestamp":1642003017000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9262924\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3039056","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}