@inproceedings{el-shimi2012primary,
author = {El-Shimi, Ahmed and Kalach, Ran and Kumar, Ankit and Oltean, Adi and Li, Jin and Sengupta, Sudipta},
title = {Primary Data Deduplication - Large Scale Study and System Design},
booktitle = {USENIX ATC'12 Proceedings of the 2012 USENIX conference on Annual Technical Conference},
year = {2012},
month = {June},
abstract = {We present a large scale study of primary data deduplication and use the findings to drive the design of a new primary data deduplication system implemented in the Windows Server 2012 operating system. File data was analyzed from 15 globally distributed file servers hosting data for over 2000 users in a large multinational corporation.

The findings are used to arrive at a chunking and compression approach which maximizes deduplication savings while minimizing the generated metadata and producing a uniform chunk size distribution. Scaling of deduplication processing with data size is achieved using a RAM frugal chunk hash index and data partitioning - so that memory, CPU, and disk seek resources remain available to fulfill the primary workload of serving IO.

We present the architecture of a new primary data deduplication system and evaluate the deduplication performance and chunking aspects of the system.},
url = {http://approjects.co.za/?big=en-us/research/publication/primary-data-deduplication-large-scale-study-system-design/},
pages = {26},
edition = {USENIX ATC'12 Proceedings of the 2012 USENIX conference on Annual Technical Conference},
}