{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T14:46:10Z","timestamp":1773153970752,"version":"3.50.1"},"reference-count":52,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,11]]},"DOI":"10.1109\/sc.2012.14","type":"proceedings-article","created":{"date-parts":[[2013,3,2]],"date-time":"2013-03-02T07:39:24Z","timestamp":1362209964000},"page":"1-11","source":"Crossref","is-referenced-by-count":78,"title":["A study on data deduplication in HPC storage systems"],"prefix":"10.1109","author":[{"given":"Dirk","family":"Meister","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jurgen","family":"Kaiser","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andre","family":"Brinkmann","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Toni","family":"Cortes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Kuhn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julian","family":"Kunkel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"35","doi-asserted-by":"publisher","DOI":"10.1145\/319151.319158"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1145\/1288783.1288788"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1145\/1996130.1996139"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.1145\/301453.301480"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1006\/jmbi.1990.9999"},{"key":"37","article-title":"stdchk: A checkpoint storage system for desktop grid computing","author":"kiswany","year":"0","journal-title":"Proceedings of the 28th International Conference on Distributed Computing Systems (ICDCS) 2008"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1021\/ja055251s"},{"key":"43","article-title":"MapReduce: Simplified data processing on large clusters","author":"dean","year":"0","journal-title":"Proceedings of the 6th Symposium on Operating System Design and Implementation (OSDI) 2004"},{"key":"42","author":"meister","year":"2011","journal-title":"Fs-c File System Chunking Tool Suite Version 0 3 9"},{"key":"41","article-title":"On the viability of checkpoint compression for extreme scale fault tolerance","author":"ibtesham","year":"0","journal-title":"Proceedings of the Euro-Par 2011 Parallel Processing Workshops 2011"},{"key":"40","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/78\/1\/012022"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470468"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1145\/1462735.1462739"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534541"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1145\/2078861.2078864"},{"key":"26","article-title":"Characteristics of backup workloads in production systems","author":"wallace","year":"0","journal-title":"Proceedings of the 10th USENIX Conference on File and Storage Technologies (FAST) 2012"},{"key":"27","doi-asserted-by":"publisher","DOI":"10.1145\/2090181.2090187"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1145\/133057.133090"},{"key":"29","author":"dayal","year":"2008","journal-title":"Characterizing Hec Storage Systems at Rest"},{"key":"3","article-title":"Jumbo store: Providing efficient incremental upload and versioning for a utility rendering service","author":"eshghi","year":"0","journal-title":"Proceedings of the 5th USENIX Conference on File and Storage Technologies (FAST) 2007"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/2385603.2385606"},{"key":"1","article-title":"Avoiding the disk bottleneck in the Data Domain deduplication file system","author":"zhu","year":"0","journal-title":"Proceedings of the 6th USENIX Conference on File and Storage Technologies (FAST) 2008"},{"key":"7","first-page":"317","article-title":"PVFS: A parallel file system for linux clusters","author":"carns","year":"0","journal-title":"Proceedings of the 4th Annual Linux Showcase and Conference 2000"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/71.539739"},{"key":"6","article-title":"GPFS: A Shared-Disk File System for Large Computing Clusters","author":"schmuck","year":"0","journal-title":"Proceedings of the2002 Conference on File and Storage Technologies (FAST) 2002"},{"key":"5","author":"braam","year":"2002","journal-title":"Lustre A Scalable High Performance File System"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2008.4663778"},{"key":"4","article-title":"Decentralized deduplication in san cluster file systems","author":"clements","year":"0","journal-title":"Proceedings of the 2009 USENIX Annual Technical Conference 2009"},{"key":"31","doi-asserted-by":"publisher","DOI":"10.1145\/1374596.1374609"},{"key":"9","article-title":"Ceph: A scalable, high-performance distributed file system","author":"weil","year":"0","journal-title":"Proceedings of the 7th Symposium on Operating Systems Design and Implementation (OSDI) 2006"},{"key":"8","year":"0"},{"key":"19","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821916","author":"menezes","year":"1996","journal-title":"Handbook of Applied Cryptography"},{"key":"17","article-title":"Duplicate data elimination in a san file system","author":"hong","year":"0","journal-title":"Proceedings of the 21th IEEE \/ 12th NASA Goddard Conference on Mass Storage Systems and Technologies (MSST) 2004"},{"key":"18","article-title":"Compare-by-hash: A reasoned analysis","author":"black","year":"0","journal-title":"Proceedings of TheUSENIX Annual Technical Conference 2006"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232380"},{"key":"16","article-title":"An analysis of compare-by-hash","author":"henson","year":"0","journal-title":"Proceedings of the 9th Conference on Hot Topics in Operating Systems 2003"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/MASCOT.2009.5366623"},{"key":"14","article-title":"Venti: A new approach to archival storage","author":"quinlan","year":"0","journal-title":"Proceedings of the 1st USENIX Conference on File and Storage Technologies (FAST) 2002"},{"key":"11","author":"rabin","year":"1981","journal-title":"Fingerprinting by random polynomials"},{"key":"12","article-title":"HYDRAstor: A scalable secondary storage","author":"dubnicki","year":"0","journal-title":"Proceedings of the 7th USENIX Conference on File and Storage Technologies (FAST) 2009"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534539"},{"key":"20","author":"alvarez","year":"2009","journal-title":"Netapp Technical Report Netapp Deduplication for Fas and V-series Deployment and Implementation Guide"},{"key":"49","year":"2011","journal-title":"HDF5 User's Guide"},{"key":"48","year":"1994","journal-title":"Grib Format Edition 1"},{"key":"45","year":"0","journal-title":"Hadoop"},{"key":"44","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376726"},{"key":"47","year":"2012","journal-title":"The NetCDF Users Guide"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2012.6232381"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1145\/502034.502052"},{"key":"51","article-title":"Single instance storage in Windows 2000","author":"bolosky","year":"0","journal-title":"Proceedings of the 4th Conference on USENIX Windows Systems Symposium 2000"},{"key":"52","doi-asserted-by":"publisher","DOI":"10.1145\/1534530.1534540"},{"key":"50","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1977.1055714"}],"event":{"name":"2012 SC - International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Salt Lake City, UT","start":{"date-parts":[[2012,11,10]]},"end":{"date-parts":[[2012,11,16]]}},"container-title":["2012 International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6468170\/6468439\/06468447.pdf?arnumber=6468447","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T08:37:13Z","timestamp":1498034233000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6468447\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,11]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/sc.2012.14","relation":{},"subject":[],"published":{"date-parts":[[2012,11]]}}}