Integrating Theory and Practice in Parallel File Systems

Dartmouth Technical Report PCS-TR93-188

	Thomas H. Cormen
	David Kotz

Date:  1993

URL (compressed postscript): <http://www.cs.dartmouth.edu/reports/TR93-188-update.ps.Z> (72KB)

URL (PDF): <http://www.cs.dartmouth.edu/reports/TR93-188-update.pdf> (192KB)

Abstract:
 	Several algorithms for parallel disk systems have appeared in
 the literature recently, and they are asymptotically optimal in terms
 of the number of disk accesses.  Scalable systems with parallel disks
 must be able to run these algorithms.  We present a list of
 capabilities that must be provided by the system to support these
 optimal algorithms: control over declustering, querying about the
 configuration, independent I/O, turning off file caching and
 prefetching, and bypassing parity.  We summarize recent theoretical
 and empirical work that justifies the need for these capabilities.

Note:
 The original 1993 tech report was superceded by the 
 <A HREF= "http://www.cs.dartmouth.edu/~dfk/papers/dags.html">
 conference version. </A>  The paper has since been revised,
 re-issued on 9/20/94 as an updated technical report.