Grant: Discovery Grants Program - Individual
McGill University
$29,000.00
Data management in the cloud
FY 2014-15
Summary
Cloud computing has become a quickly evolving new computing paradigm. A cloud computing infrastructure can consist of hundreds to many thousands of compute nodes whose computational power is offered to customers through a pay-per-use model. Additionally, cloud providers often provide a whole range of software services that customers can use to facilitate their software development. Resource management becomes a crucial task in such a complex application hosting environment. On the one hand, it makes sense to physically collocate small-scale applications as it allows the provider to exploit the full computational capacity of each machine. Such approach, however, requires dynamic allocation of computational and memory resources depending on workload patterns. It might also require the dynamic migration of applications between machines. On the other hand, there is an increasing number of large-scale applications, whose data might need to be distributed and replicated across tens to hundreds of nodes, and whose workload will demand many compute nodes. In this case, coordination, distribution and provisioning are crucial but difficult tasks. Database systems (DBS) present particular challenges in such cloud environment. This is especially true for online transaction processing applications (OLTP) that exhibit a high volume of short transactions with high update rates, as they require complex storage and memory management, and sophisticated consistency protocols. Current DBS are difficult to deploy and maintain in the cloud. In our research, we will develop DBS technology that is better suitable for cloud environments. One research direction will develop solutions that make DBS better candidates in resource-sharing environments targeting small-scale applications. This includes efficient and flexible migration mechanisms as well as performance models that allow for dynamic resource management. A second direction will develop a database management stack that provides the scalability, high throughput, high consistency and fast response times that are needed by large-scale applications with OLTP flavor.
Program
Discovery Grants Program - Individual
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
239106-2011
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
2014
Competition year année de concours
2011
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
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
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
6
Application title
Data management in the cloud
Keyword
NSERC
Application summary
Cloud computing has become a quickly evolving new computing paradigm. A cloud computing infrastructure can consist of hundreds to many thousands of compute nodes whose computational power is offered to customers through a pay-per-use model. Additionally, cloud providers often provide a whole range of software services that customers can use to facilitate their software development. Resource management becomes a crucial task in such a complex application hosting environment. On the one hand, it makes sense to physically collocate small-scale applications as it allows the provider to exploit the full computational capacity of each machine. Such approach, however, requires dynamic allocation of computational and memory resources depending on workload patterns. It might also require the dynamic migration of applications between machines. On the other hand, there is an increasing number of large-scale applications, whose data might need to be distributed and replicated across tens to hundreds of nodes, and whose workload will demand many compute nodes. In this case, coordination, distribution and provisioning are crucial but difficult tasks. Database systems (DBS) present particular challenges in such cloud environment. This is especially true for online transaction processing applications (OLTP) that exhibit a high volume of short transactions with high update rates, as they require complex storage and memory management, and sophisticated consistency protocols. Current DBS are difficult to deploy and maintain in the cloud. In our research, we will develop DBS technology that is better suitable for cloud environments. One research direction will develop solutions that make DBS better candidates in resource-sharing environments targeting small-scale applications. This includes efficient and flexible migration mechanisms as well as performance models that allow for dynamic resource management. A second direction will develop a database management stack that provides the scalability, high throughput, high consistency and fast response times that are needed by large-scale applications with OLTP flavor.