{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:45:59Z","timestamp":1773153959983,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":39,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T00:00:00Z","timestamp":1733097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,2]]},"DOI":"10.1145\/3652892.3700766","type":"proceedings-article","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:36:13Z","timestamp":1732736173000},"page":"292-298","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SeqCDC: Hashless Content-Defined Chunking for Data Deduplication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0804-1600","authenticated-orcid":false,"given":"Sreeharsha","family":"Udayashankar","sequence":"first","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3283-3846","authenticated-orcid":false,"given":"Abdelrahman","family":"Baba","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6429-9983","authenticated-orcid":false,"given":"Samer","family":"Al-Kiswany","sequence":"additional","affiliation":[{"name":"University of Waterloo, Waterloo, Canada"}]}],"member":"320","published-online":{"date-parts":[[2024,12,2]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Statista","author":"Holst Arne","year":"2021","unstructured":"Arne Holst. Volume of data\/information created, captured, copied, and consumed worldwide from 2010 to 2025. Statista, June, 2021."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1165389.945450"},{"key":"e_1_3_2_1_3_1","first-page":"1","volume-title":"Robert Chansler. The Hadoop Distributed File System. In 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST)","author":"Shvachko Konstantin","year":"2010","unstructured":"Konstantin Shvachko, Hairong Kuang, Sanjay Radia, and Robert Chansler. The Hadoop Distributed File System. In 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST), pages 1--10, 2010."},{"key":"e_1_3_2_1_4_1","volume-title":"High-performance, reliable secondary storage. ACM Computing Surveys (CSUR), 26(2):145--185","author":"Chen Peter M","year":"1994","unstructured":"Peter M Chen, Edward K Lee, Garth A Gibson, Randy H Katz, and David A Patterson. RAID: High-performance, reliable secondary storage. ACM Computing Surveys (CSUR), 26(2):145--185, 1994."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/353360.353362"},{"key":"e_1_3_2_1_6_1","volume-title":"Data compression. ACM Computing Surveys (CSUR), 19(3):261--296","author":"Lelewer Debra A","year":"1987","unstructured":"Debra A Lelewer and Daniel S Hirschberg. Data compression. ACM Computing Surveys (CSUR), 19(3):261--296, 1987."},{"key":"e_1_3_2_1_7_1","volume-title":"Data compression","author":"Salomon David","year":"2002","unstructured":"David Salomon. Data compression. Springer, 2002."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2571298"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1462735.1462739"},{"key":"e_1_3_2_1_10_1","volume-title":"A study of practical deduplication. ACM Transactions on Storage (ToS), 7(4):1--20","author":"Meyer Dutch T","year":"2012","unstructured":"Dutch T Meyer and William J Bolosky. A study of practical deduplication. ACM Transactions on Storage (ToS), 7(4):1--20, 2012."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/2208461.2208465"},{"key":"e_1_3_2_1_12_1","volume-title":"IBM Redbooks","author":"Coyne Larry","year":"2012","unstructured":"Larry Coyne, Sandra Moulton, and Carlos Alvarez. IBM System Storage N Series Data Compression and Deduplication: Data ONTAP 8.1 Operating in 7-mode. IBM Redbooks, 2012."},{"key":"e_1_3_2_1_13_1","volume-title":"Conference on File and Storage Technologies (FAST 02)","author":"Quinlan Sean","year":"2002","unstructured":"Sean Quinlan and Sean Dorward. Venti: A New Approach to Archival Data Storage. In Conference on File and Storage Technologies (FAST 02), Monterey, CA, January 2002. USENIX Association."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","first-page":"430","DOI":"10.1109\/FITME.2010.5656539","volume-title":"2010 international conference on future information technology and management engineering","volume":"1","author":"He Qinlu","year":"2010","unstructured":"Qinlu He, Zhanhuai Li, and Xiao Zhang. Data deduplication techniques. In 2010 international conference on future information technology and management engineering, volume 1, pages 430--433. IEEE, 2010."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2015.7218510"},{"key":"e_1_3_2_1_17_1","first-page":"101","volume-title":"2016 USENIX Annual Technical Conference (USENIX ATC 16)","author":"Xia Wen","year":"2016","unstructured":"Wen Xia, Yukun Zhou, Hong Jiang, Dan Feng, Yu Hua, Yuchong Hu, Qing Liu, and Yucheng Zhang. FastCDC: A fast and efficient content-defined chunking approach for data deduplication. In 2016 USENIX Annual Technical Conference (USENIX ATC 16), pages 101--114, 2016."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.peva.2014.07.016"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.02.013"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2009.06.004"},{"key":"e_1_3_2_1_22_1","volume-title":"Verification of a cryptographic primitive: Sha-256. ACM Transactions on Programming Languages and Systems (TOPLAS), 37(2):1--31","author":"Appel Andrew W","year":"2015","unstructured":"Andrew W Appel. Verification of a cryptographic primitive: Sha-256. ACM Transactions on Programming Languages and Systems (TOPLAS), 37(2):1--31, 2015."},{"key":"e_1_3_2_1_23_1","first-page":"469","volume-title":"Samer Al-Kiswany. Dedupbench: A Benchmarking Tool for Data Chunking Techniques. In 2023 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)","author":"Liu Alan","year":"2023","unstructured":"Alan Liu, Abdelrahman Baba, Sreeharsha Udayashankar, and Samer Al-Kiswany. Dedupbench: A Benchmarking Tool for Data Chunking Techniques. In 2023 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), pages 469--474, 2023."},{"key":"e_1_3_2_1_24_1","volume-title":"The MD5 message-digest algorithm. Technical report","author":"Rivest Ronald","year":"1992","unstructured":"Ronald Rivest. The MD5 message-digest algorithm. Technical report, 1992."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD62652.2024.00025"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1900008.1900101"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.4135\/9781412985116"},{"key":"e_1_3_2_1_28_1","first-page":"1","volume-title":"Prabodh Mishra. The Design and Operation of CloudLab. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Duplyakin Dmitry","year":"2019","unstructured":"Dmitry Duplyakin, Robert Ricci, Aleksander Maricq, Gary Wong, Jonathon Duerig, Eric Eide, Leigh Stoller, Mike Hibler, David Johnson, Kirk Webb, Aditya Akella, Kuangching Wang, Glenn Ricart, Larry Landweber, Chip Elliott, Michael Zink, Emmanuel Cecchet, Snigdhaswin Kar, and Prabodh Mishra. The Design and Operation of CloudLab. In 2019 USENIX Annual Technical Conference (USENIX ATC 19), pages 1--14, Renton, WA, July 2019. USENIX Association."},{"key":"e_1_3_2_1_29_1","volume-title":"VMWare marketplace. https:\/\/marketplace.cloud.vmware.com\/services","year":"2023","unstructured":"VMWare. VMWare marketplace. https:\/\/marketplace.cloud.vmware.com\/services, 2023."},{"key":"e_1_3_2_1_30_1","volume-title":"GitHub - rust-lang\/rust: Empowering everyone to build reliable and efficient software. https:\/\/github.com\/rust-lang\/rust","year":"2023","unstructured":"Rust. GitHub - rust-lang\/rust: Empowering everyone to build reliable and efficient software. https:\/\/github.com\/rust-lang\/rust, 2023."},{"key":"e_1_3_2_1_31_1","volume-title":"The Linux Kernel Archives. https:\/\/www.kernel.org\/","year":"2023","unstructured":"Linux. The Linux Kernel Archives. https:\/\/www.kernel.org\/, 2023."},{"key":"e_1_3_2_1_32_1","volume-title":"https:\/\/redis.io\/","year":"2023","unstructured":"Redis. Redis. https:\/\/redis.io\/, 2023."},{"key":"e_1_3_2_1_33_1","volume-title":"https:\/\/www.mysql.com\/","author":"SQL.","year":"2023","unstructured":"MySQL. MySQL. https:\/\/www.mysql.com\/, 2023."},{"key":"e_1_3_2_1_34_1","volume-title":"https:\/\/www.tpc.org\/tpcc\/detail5.asp","author":"Transaction Processing Council","year":"2023","unstructured":"Transaction Processing Council. TPC-C Overview. https:\/\/www.tpc.org\/tpcc\/detail5.asp, 2023."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/1383422.1383443"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2308181"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357223.3362731"},{"key":"e_1_3_2_1_38_1","first-page":"288","volume-title":"Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom)","author":"Xu Zhen","year":"2021","unstructured":"Zhen Xu and Wenbo Zhang. QuickCDC: A Quick Content Defined Chunking Algorithm Based on Jumping and Dynamically Adjusting Mask Bits. In 2021 IEEE Intl Conf on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking (ISPA\/BDCloud\/SocialCom\/SustainCom), pages 288--299, 2021."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2014.2322600"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926195"}],"event":{"name":"Middleware '24: 25th International Middleware Conference","location":"Hong Kong Hong Kong","acronym":"Middleware '24","sponsor":["IFIP","Usenix"]},"container-title":["Proceedings of the 25th International Middleware Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652892.3700766","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3652892.3700766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T22:53:57Z","timestamp":1750287237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3652892.3700766"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,2]]},"references-count":39,"alternative-id":["10.1145\/3652892.3700766","10.1145\/3652892"],"URL":"https:\/\/doi.org\/10.1145\/3652892.3700766","relation":{},"subject":[],"published":{"date-parts":[[2024,12,2]]},"assertion":[{"value":"2024-12-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}