Grant: Discovery Grants Program - Individual
University of Waterloo
$29,000.00
Data freshness in P2P replication
FY 2012-13
Summary
Peer-to-peer (P2P) systems often need to service data requests from telecommunications and web-based
clients around the globe. To boost performance and to increase data availability, unstructured P2P systems
employ replication to bring data closer to where it is needed, or to increase system or data resources. A
common replication strategy is to use result caching, which distributes replicas of query results in the
P2P system. This strategy, however, does not provide any data freshness guarantees since cached result
copies will become stale as the primary copy is updated. Thus, stale replicas or copies can preclude their
use by P2P applications that require fresh data.
A key goal of this proposal is to provide data freshness guarantees in P2P systems. There are several
problems with providing freshness guarantees that this proposal seeks to address. First, a replication strategy
that determines which peers in the system should cache the result is needed, keeping in mind that a large
number of choices exist. Second, an update propagation strategy needs to be designed that would determine
how, and which, replicas in the P2P system should be refreshed given that refreshing all replicas is likely to
be costly and unfeasible. Third, due to network churn and failure, peers may become unavailable or new
peers may join the system. Thus, techniques for supporting replication need to work gracefully in the face
of this potential dynamism in the P2P system. Another key goal of this research proposal is to design and
develop a set of techniques that can provide a spectrum of design choices that take data freshness and
performance into consideration. These techniques would quantify the trade-offs between freshness and
performance, given that providing fresher data is likely to be more costly but the storage and management
of available but undesired stale data is likely to waste system resources.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
371781-2009
Name nom
Daudjee, Khuzaima
Department département
Computer Science, David R. Cheriton School of
Organization id
33
Institution établissement
University of Waterloo
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2012
Competition year année de concours
2009
Award amount
29000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
Discovery grants programs
Group fr
Programmes de subventions à la découverte
Committee code
330
Committee name en
Computing and Information Sciences - A
Committee name fr
Informatique - A
Area of application code
802
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Information systems and technology
Area of application fr
Systèmes d'information et technologie de l'information
Research subject code
2711
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Database management
Research subject fr
Gestion de bases de données
Partie
4
Nb partie
5
Application title
Data freshness in P2P replication
Keyword
NSERC
Application summary
Peer-to-peer (P2P) systems often need to service data requests from telecommunications and web-based
clients around the globe. To boost performance and to increase data availability, unstructured P2P systems
employ replication to bring data closer to where it is needed, or to increase system or data resources. A
common replication strategy is to use result caching, which distributes replicas of query results in the
P2P system. This strategy, however, does not provide any data freshness guarantees since cached result
copies will become stale as the primary copy is updated. Thus, stale replicas or copies can preclude their
use by P2P applications that require fresh data.
A key goal of this proposal is to provide data freshness guarantees in P2P systems. There are several
problems with providing freshness guarantees that this proposal seeks to address. First, a replication strategy
that determines which peers in the system should cache the result is needed, keeping in mind that a large
number of choices exist. Second, an update propagation strategy needs to be designed that would determine
how, and which, replicas in the P2P system should be refreshed given that refreshing all replicas is likely to
be costly and unfeasible. Third, due to network churn and failure, peers may become unavailable or new
peers may join the system. Thus, techniques for supporting replication need to work gracefully in the face
of this potential dynamism in the P2P system. Another key goal of this research proposal is to design and
develop a set of techniques that can provide a spectrum of design choices that take data freshness and
performance into consideration. These techniques would quantify the trade-offs between freshness and
performance, given that providing fresher data is likely to be more costly but the storage and management
of available but undesired stale data is likely to waste system resources.