Canada Spends Logo

Explore our Budget 2026 analysis

Grant: Collaborative Research and Development Grants

McGill University

$56,100.00

Scalable Caching for Clustered Servers

FY 2011-12

Summary
Multi-tier architectures are the main building block of modern information systems and are used across many application domains such as e-commerce, life-sciences, and banking. The different tasks an information system has to perform are split across several server tiers. For instance, web-based requests are first processed by the web-server tier, then they are forwarded to the application server tier that implements the business logical and finally they call a database backend tier that manages the business critical data. The application server tier is often clustered, i.e., consists of several servers, in order to provide fault-tolerance and load-distribution. Furthermore, each server usually caches data it receives from the database system in main-memory in order to be able to serve further requests locally. In this research, we develop a novel collaborative caching infrastructure that takes advantage of the full capacity of the caches of individual application server replicas in order to provide increased scalability over existing solutions. Instead of each application server replica only caching data that it needs locally, the different caches will work together to avoid caching the same data items multiple times thus allowing a larger percentage of the database to be cached. Our research addresses some of the fundamental challenges associated with such a distributed caching architecture, such as the development of a scalable cache directory structure, a distributed query engine that can access local and remote caches, cache consistency mechanisms that reflect application needs, and the consideration of new hardware advances such as multi-core architectures and remote direct memory access. This research will make important advances in the field of scalable middleware infrastructure, a field in which our industry partner provides several products. Customers that use such advanced infrastructure, many of them Canadian companies, will benefit from improved performance without additional hardware costs. Furthermore, this project will train several highly qualified personnel in an extremely relevant IT area.
Program
Collaborative Research and Development Grants
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data

As published

Application id
389308-2009
Name nom
Kemme, Bettina
Department département
Computer Science, School of
Organization id
61
Institution établissement
McGill University
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2011
Competition year année de concours
2009
Award amount
56100
Program id
CRDPJ
Program nane en
Collaborative Research and Development Grants
Program name fr
Subventions de recherche et développement coopérative
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
800
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 and communication services
Area of application fr
Services d'information et de télécommunications
Research subject code
2704
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Distributed and parallel processing
Research subject fr
Traitement réparti et simultané
Partie
2
Nb partie
2
Application title
Scalable Caching for Clustered Servers
Keyword
NSERC
Application summary
Multi-tier architectures are the main building block of modern information systems and are used across many application domains such as e-commerce, life-sciences, and banking. The different tasks an information system has to perform are split across several server tiers. For instance, web-based requests are first processed by the web-server tier, then they are forwarded to the application server tier that implements the business logical and finally they call a database backend tier that manages the business critical data. The application server tier is often clustered, i.e., consists of several servers, in order to provide fault-tolerance and load-distribution. Furthermore, each server usually caches data it receives from the database system in main-memory in order to be able to serve further requests locally. In this research, we develop a novel collaborative caching infrastructure that takes advantage of the full capacity of the caches of individual application server replicas in order to provide increased scalability over existing solutions. Instead of each application server replica only caching data that it needs locally, the different caches will work together to avoid caching the same data items multiple times thus allowing a larger percentage of the database to be cached. Our research addresses some of the fundamental challenges associated with such a distributed caching architecture, such as the development of a scalable cache directory structure, a distributed query engine that can access local and remote caches, cache consistency mechanisms that reflect application needs, and the consideration of new hardware advances such as multi-core architectures and remote direct memory access. This research will make important advances in the field of scalable middleware infrastructure, a field in which our industry partner provides several products. Customers that use such advanced infrastructure, many of them Canadian companies, will benefit from improved performance without additional hardware costs. Furthermore, this project will train several highly qualified personnel in an extremely relevant IT area.