Estimating Unseen Deduplication— from Theory to Practice

This paper is included in the Proceedings of the 14th USENIX Conference on File and Storage Technologies (FAST 16).February 22 25, 2016 Santa Clara, CA, USAISB N 978 -1- 931971-28 -7 Open access to the Proceedings of the 14th USENIX Conference on File and Storage Technologies is sponsored by USENIXE stimating Unseen deduplication from Theory to PracticeDanny Harnik, Ety Khaitzin, and Dmitry Sotnikov, IBM Research Association 14th USENIX Conference on File and Storage Technologies (FAST 16) 277 EstimatingUnseenDeduplication fromTheorytoPracticeDannyHarnik,EtyKhait zinandDmitrySotnikovIBMR esearch Howtoestimatethededuplicationbenefitsofa givendataset? , , ,therearethe-oreticalproofsthatthisprobl emishard[12]andmoreprecisely, ,compressionisalocalprocedureandtherefor ethecompressionestimationproblemcanbesol vedveryefficiently[11].Asaresult, :VirtualDesktopInfrastructure(VDI)enviro nmentswerereported( [1]) (a1:6reduc-tion).Howeverinreality,depend ingonthespecificenvironment, (between1:2and1:50).

ment depends on the data itself and on the storage media that it resides on. The technique is based ... deduplication and data reduction in general, makes more sense than ever. Combined with the popularity of modern ... Understanding the estimation accuracy. The proofs of accuracy of the Unseen algorithm are the-

Tags:

  Data, Understanding, Deduplication

Information

Related search queries