Summary: 1
A Quantitative Analysis of Cache Policies for Scalable Network File Systems
Michael D. Dahlin, Clifford J. Mather, Randolph Y. Wang,
Thomas E. Anderson, and David A. Patterson
Computer Science Division, University of California at Berkeley
{dahlin, cjmather, rywang, tea, pattrsn}@cs.berkeley.edu
This work is supported in part by the Advanced Research Projects
Agency (N00600­93­C­2481), the National Science Foundation
(CDA 8722788), California MICRO, Digital Equipment Corporation, the
AT&T Foundation, Xerox Corporation, and Siemens Corporation. Dahlin
was also supported under a National Science Foundation Graduate
Research Fellowship. Anderson was also supported by a National Science
Foundation Young Investigator Award.
more than commodity workstations, even for the server. In
reality, the widely used SUN Network File System, NFS
[Sand85], has spawned a new industry dedicated to building
the high­performance multiprocessor systems needed to
scale NFS to more than a few dozen clients. The Andrew
File System, AFS [Howa88], was designed to reduce server
load relative to NFS in the interest of scalability, but its ulti­

Source: Anderson, Tom - Department of Computer Science and Engineering, University of Washington at Seattle
Dahlin, Michael D. - Department of Computer Sciences, University of Texas at Austin

Collections: Computer Technologies and Information Sciences