{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:13:39Z","timestamp":1787012019478,"version":"build-2736575974"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T00:00:00Z","timestamp":1671235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,12,17]]},"DOI":"10.1109\/bigdata55660.2022.10020871","type":"proceedings-article","created":{"date-parts":[[2023,1,26]],"date-time":"2023-01-26T14:35:23Z","timestamp":1674743723000},"page":"319-328","source":"Crossref","is-referenced-by-count":4,"title":["Predicting Deduplication Performance: An Analytical Model and Empirical Evaluation"],"prefix":"10.1109","author":[{"given":"Owen","family":"Randall","sequence":"first","affiliation":[{"name":"University of Alberta,Edmonton"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Lu","sequence":"additional","affiliation":[{"name":"University of Alberta,Edmonton"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"HYDRAstor: A scalable secondary storage","volume-title":"7th USENIX Conference on File and Storage Technologies (FAST 09)","author":"Dubnicki"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2010.263"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2011.5937237"},{"key":"ref4","first-page":"24","article-title":"Idedup: Latency-aware, inline data deduplication for primary storage","volume-title":"Proceedings of the 10th USENIX Conference on File and Storage Technologies","author":"Srinivasan"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/502059.502052"},{"key":"ref6","first-page":"2","article-title":"Single instance storage in windows\u00ae 2000","volume-title":"Proceedings of the 4th Conference on USENIX Windows Systems Symposium - Volume 4","author":"Bolosky"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3233\/ica-120418"},{"key":"ref8","article-title":"Venti: A new approach to archival data storage","volume-title":"Conference on File and Storage Technologies (FAST 02)","author":"Quinlan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/378993.379239"},{"key":"ref10","article-title":"Avoiding the disk bottleneck in the data domain deduplication file system","volume-title":"Proceedings of the 6th USENIX Conference on File and Storage Technologies","author":"Zhu"},{"key":"ref11","first-page":"18","article-title":"Bimodal content defined chunking for backup streams","volume-title":"Proceedings of the 8th USENIX Conference on File and Storage Technologies","author":"Kruus"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2014.07.016"},{"key":"ref13","first-page":"101","article-title":"Fastcdc: A fast and efficient content-defined chunking approach for data deduplication","volume-title":"2016 USENIX Annual Technical Conference (USENIX ATC 16)","author":"Xia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/1987816.1987837"},{"key":"ref15","article-title":"Sparse indexing: Large scale, inline deduplication using sampling and locality","volume-title":"Proceedings of the 7th USENIX Conference on File and Storage Technologies (FAST 09)","author":"Lillibridge"},{"key":"ref16","first-page":"16","article-title":"Chunkstash: Speeding up inline storage deduplication using flash memory","volume-title":"Proceedings of the 2010 USENIX Conference on USENIX Annual Technical Conference","author":"Debnath"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/sym8070069"},{"key":"ref18","article-title":"Evaluation of efficient archival storage techniques","author":"You","year":"2004","journal-title":"MSST"},{"key":"ref19","article-title":"Fingerprinting by random polynomials","volume-title":"Center for Research in Computing Technology","author":"Rabin","year":"1981"},{"key":"ref20","article-title":"CORD-19: The COVID-19 open research dataset","volume-title":"Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020","author":"Wang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1462735.1462739"},{"key":"ref22","first-page":"331","article-title":"Design tradeoffs for data deduplication performance in backup workloads","volume-title":"13th USENIX Conference on File and Storage Technologies (FAST 15)","author":"Fu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2078861.2078864"},{"key":"ref24","first-page":"4","article-title":"Characteristics of backup workloads in production systems","volume-title":"Proceedings of the 10th USENIX Conference on File and Storage Technologies","author":"Wallace"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1147\/rd.312.0249"}],"event":{"name":"2022 IEEE International Conference on Big Data (Big Data)","location":"Osaka, Japan","start":{"date-parts":[[2022,12,17]]},"end":{"date-parts":[[2022,12,20]]}},"container-title":["2022 IEEE International Conference on Big Data (Big Data)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10020192\/10020156\/10020871.pdf?arnumber=10020871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,13]],"date-time":"2024-02-13T01:42:58Z","timestamp":1707788578000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10020871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,17]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/bigdata55660.2022.10020871","relation":{},"subject":[],"published":{"date-parts":[[2022,12,17]]}}}