@inproceedings{douceur1999a,
author = {Douceur, John (JD) and Bolosky, Bill},
title = {A Large-Scale Study of File-System Contents},
booktitle = {Proceedings of the international conference on Measurement and modeling of computer systems (SIGMETRICS)},
year = {1999},
month = {January},
abstract = {We collect and analyze a snapshot of data from 10,568 file systems of 4801 Windows personal computers in a commercial environment. The file systems contain 140 million files totaling 10.5 TB of data. We develop analytical approximations for distributions of file size, file age, file functional lifetime, directory size, and directory depth, and we compare them to previously derived distributions. We find that file and directory sizes are fairly consistent across file systems, but file lifetimes vary widely and are significantly affected by the job function of the user. Larger files tend to be composed of blocks sized in powers of two, which noticeably affects their size distribution. File-name extensions are strongly correlated with file sizes, and extension popularity varies with user job function. On average, file systems are only half full.},
publisher = {Association for Computing Machinery, Inc.},
url = {http://approjects.co.za/?big=en-us/research/publication/a-large-scale-study-of-file-system-contents/},
edition = {Proceedings of the international conference on Measurement and modeling of computer systems (SIGMETRICS)},
}