@inproceedings{928e1632acdd4a50be1ff0180220f7a5,
title = "Controlling the chunk-size in deduplication systems",
abstract = "A special case of data compression in which repeated chunks of data are stored only once is known as deduplication. The input data is cut into chunks and a cryptographically strong hash value of each (different) chunk is stored. To restrict the influence of small inserts and deletes to local perturbations, the chunk boundaries are usually defined in a data dependent way, which implies that the chunks are of variable length. Usually, the chunk sizes may spread over a large range, which may have a negative impact on the storage performance. This may be dealt with by imposing artificial lower and upper bounds. This paper suggests an alternative by which the chunk size distribution is controlled in a natural way. Some analytical and experimental results are given.",
author = "Michael Hirsch and Klein, \{Shmuel T.\} and Dana Shapira and Yair Toaff",
note = "Publisher Copyright: {\textcopyright} Czech Technical University in Prague, Czech Republic.; 19th Prague Stringology Conference, PSC 2015 ; Conference date: 24-08-2015 Through 26-08-2015",
year = "2015",
language = "الإنجليزيّة",
series = "Proceedings of the Prague Stringology Conference 2015, PSC 2015",
pages = "78--89",
editor = "Jan Zd'arek and Jan Holub",
booktitle = "Proceedings of the Prague Stringology Conference 2015, PSC 2015",
}