{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T10:28:52Z","timestamp":1761992932953,"version":"build-2065373602"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"HTRDP","award":["2012AA012602"],"award-info":[{"award-number":["2012AA012602"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2017,3,1]]},"DOI":"10.1109\/tpds.2016.2594070","type":"journal-article","created":{"date-parts":[[2016,7,26]],"date-time":"2016-07-26T18:21:03Z","timestamp":1469557263000},"page":"863-876","source":"Crossref","is-referenced-by-count":9,"title":["PDFS: Partially Dedupped File System for Primary Workloads"],"prefix":"10.1109","volume":"28","author":[{"given":"Hongliang","family":"Yu","sequence":"first","affiliation":[]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Wei","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Weimin","family":"Zheng","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"518","article-title":"Similarity\n search in high dimensions via hashing","author":"gionis","year":"1999","journal-title":"Proc 5th Int Conf Very Large Data Bases"},{"key":"ref38","first-page":"26","article-title":"SiLo: A similarity-locality based near-exact\n deduplication scheme with low RAM overhead and high throughput","author":"xia","year":"2011","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"key":"ref33","article-title":"Bloom filters via d-left hashing and dynamic bit reassignment\n extended abstract","author":"bonomi","year":"2006","journal-title":"Proc 44th Annu Allerton Conf"},{"key":"ref32","first-page":"47","article-title":"Finding a needle in haystack: Facebook's photo storage","author":"beaver","year":"2010","journal-title":"Proc 9th USENIX Conf Operating Syst Des Implementation"},{"key":"ref31","first-page":"13","article-title":"Scale and concurrency of GIGA+: File system directories with millions of files","author":"patil","year":"2011","journal-title":"Proc 9th USENIX Conf File stroage Technol"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1837915.1837921"},{"key":"ref37","article-title":"On the resemblance and containment of documents","author":"broder","year":"1997","journal-title":"Proc Compression Complexity Sequences"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"ref35","first-page":"3","article-title":"End-to-end data\n integrity for file systems: A ZFS case study","author":"zhang","year":"2010","journal-title":"Proc 8th USENIX Conf File Storage Technol"},{"key":"ref34","first-page":"684","article-title":"An improved construction for counting bloom filters","author":"bonomi","year":"2006","journal-title":"Proc 14th Conf Annu Eur Symp"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.14"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860869-6\/50037-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2011.5937237"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.84"},{"year":"0","key":"ref13"},{"key":"ref14","first-page":"24","article-title":"iDedup: Latency-aware, inline data\n deduplication for primary storage","author":"srinivasan","year":"2012","journal-title":"Proc 10th USENIX Conf File Storage Technol"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2013.6544846"},{"key":"ref16","article-title":"Getting The hang of IOPS: An Introduction to disk performance","author":"atkin","year":"2012","journal-title":"Symantec Connect Whitepaper"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/2611778"},{"key":"ref18","first-page":"331","article-title":"Design tradeoffs for data deduplication performance in backup\n workloads","author":"fu","year":"2015","journal-title":"Proc USENIX Conf File Storage Technol"},{"key":"ref19","first-page":"13","article-title":"Single instance storage in Windows\n 2000&#x00AE;","author":"bolosky","year":"2000","journal-title":"Proc 4th Usenix Windows Systems Symp"},{"key":"ref28","first-page":"25","article-title":"An empirical study of memory sharing\n in virtual machines","author":"barker","year":"2012","journal-title":"Proc USENIX Conf Annu Tech Conf"},{"key":"ref4","first-page":"111","article-title":"Sparse indexing: Large scale, inline deduplication using sampling and locality","author":"lillibridge","year":"2009","journal-title":"Proc 7th Conf File Storage Technol"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ISPA.2011.31"},{"key":"ref3","first-page":"8","article-title":"Decentralized deduplication in\n SAN cluster file systems","author":"clements","year":"2009","journal-title":"Proc Conf USENIX Annu Tech Conf"},{"key":"ref6","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2287076.2287081"},{"key":"ref5","first-page":"16","article-title":"ChunkStash:\n Speeding up inline storage deduplication using flash memory","author":"debnath","year":"2010","journal-title":"Proc USENIX Conf USENIX Annu Tech Conf"},{"year":"0","key":"ref8"},{"key":"ref7","first-page":"183","article-title":"Improving\n restore speed for backup systems that use inline chunk-based deduplication","author":"lillibridge","year":"2013","journal-title":"Proc USENIX Conf File Storage Technol"},{"key":"ref2","article-title":"Avoiding the disk\n bottleneck in the data domain deduplication file system","author":"zhu","year":"2008","journal-title":"Proc 6th USENIX Conf File Storage Technol"},{"key":"ref9","first-page":"81","article-title":"Memory efficient sanitization of a\n deduplicated storage system","author":"botelho","year":"2013","journal-title":"Proc 11th USENIX Conf File Storage Technol"},{"key":"ref1","article-title":"The digital universe in 2020: Big data, bigger digital shadows, and biggest growth in the far\n east","author":"gantz","year":"2012","journal-title":"IDC White Paper"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33615-7_9"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-25821-3_5"},{"year":"0","key":"ref45"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/276698.276876"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"year":"0","key":"ref42"},{"key":"ref24","first-page":"3","article-title":"Similarity based deduplication with small data chunks","author":"aronovich","year":"2012","journal-title":"Proc Prague Stringology Conf"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/997817.997857"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534539"},{"key":"ref44","first-page":"1","article-title":"A study of practical deduplication","author":"meyer","year":"2011","journal-title":"Proc 9th USENIX Conf File stroage Technol"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1508293.1508299"},{"year":"0","key":"ref43"},{"key":"ref25","article-title":"Difference engine: Harnessing memory redundancy in virtual\n machines","author":"gupta","year":"2008","journal-title":"Proc OSDI"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/7851095\/07522088.pdf?arnumber=7522088","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:42:31Z","timestamp":1642005751000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7522088\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,1]]},"references-count":46,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2016.2594070","relation":{},"ISSN":["1045-9219"],"issn-type":[{"type":"print","value":"1045-9219"}],"subject":[],"published":{"date-parts":[[2017,3,1]]}}}