@device(postscript)
@libraryfile(Mathematics10)
@libraryfile(Accents)
@style(fontfamily=timesroman,fontscale=11)
@pagefooting(immediate, left "@c<Technical Report 1996>",
center "@c<Computer Science>",
right "@c<Carnegie Mellon>")
@heading(Exploiting Weak Connectivity in a Distributed File System)
@heading(CMU-CS-96-195)
@center(@b(Lily B. Mummert))
@center(December 1996 - Ph.D. Thesis)
@center(FTP: CMU-CS-96-195.ps)
@blankspace(1)
@begin(text,spacing=1)

@i(Weak connectivity),  in the form of intermittent, low-bandwidth,
or expensive networks is a fact of life in mobile computing.  For the
foreseeable future, access to cheap, high-performance, reliable
networks, or @i{strong connectivity} will be limited to a few oases,
such as work or home, in a vast desert of weak connectivity.  The
design of distributed file systems has traditionally been based on an
assumption of strong connectivity.  Yet, to provide ubiquitous data
access, it is vital that distributed file systems make effective use
of weak connectivity.

This dissertation describes the design, implementation, and evaluation
of weakly connected operation in the Coda File System.  The starting
point of this work is @i{disconnected operation}, in which a file
system client operates using data in its cache during server or
network failures.  Disconnected clients suffer from many limitations:
@i{updates are not visible} to other clients, @i{cache misses} may
impede progress, @i{updates are at risk} from client loss or damage,
and the danger of @i{update conflicts} increases as disconnections
are prolonged.  Weak connectivity provides an opportunity to alleviate
these limitations.

Coda's strategy for weakly connected operation is best characterized
as @i{application-transparent adaptation}.  The system bears full
responsibility for coping with the demands of weak connectivity.  This
approach preserves upward compatibility by allowing applications to
run unchanged.  Coda provides several mechanisms for weakly connected
operation motivated by actual experience.  The foundation of
adaptivity in this system is the @i{communications layer}, which
derives and supplies information on network conditions to higher
system layers.  The @i{rapid cache validation} mechanism enables the
system to recover quickly in intermittent environments.  The {@i{trickle
reintegration} mechanism insulates the user from poor network
performance by propagating updates to servers asynchronously.  The
@i{cache miss handling} mechanism alerts the user to potentially
lengthy service times and provides opportunities for intervention.

A quantitative evaluation of these mechanisms, based on controlled
experimentation and empirical data gathered from the deployed system
in everyday use, shows that Coda is able to provide good performance
even when network bandwidth varies over four orders of magnitude @y(M)
from modem speeds to LAN speeds.

@blankspace(2line)
@begin(transparent,size=10)
@b(Keywords:@ )@c<Distributed file systems, weak connectivity, high
availability, mobile computing, Coda, reintegration, application-transparent
adaptation, UNIX>
@end(transparent)
@blankspace(1line)
@end(text)
@flushright(@b[(148 pages)])