Grant: Discovery Grants Program - Individual
University of Waterloo
$55,000.00
Dynamic Data Systems
FY 2024-25
Summary
Data systems store and manage application data collected in almost every sector of science and society. With data coming from a vast number of sources, well-designed systems are required for data management and analysis. Effective use of system resources such as memory to perform computation efficiently becomes increasingly important. As the price-performance ratio of main memory continues to improve, it is advantageous to perform in-memory computing on data. If these data are retained in the buffer pool memory of data systems, it allows low-latency in-memory computation that can greatly improve system performance. Thus, how buffer pool is managed as a resource and how memory elasticity is supported become important in the design of efficient data systems. With the ubiquity of Cloud computing, users are increasingly relying on its services to support and run their data-intensive jobs. Effective and efficient system resource management are key to the design, use and deployment of large-scale data systems that deliver performant data services.
The goals of the proposed research are to develop techniques for the design of data systems that can perform dynamic resource management and provide dynamic composable data system services at scale. This research program will achieve these goals through the following set of challenging objectives. First, efficient techniques for resource management will be developed that will predictively fetch and retain required data in the system buffer pool to optimize for future accesses and reduce transaction latencies through in-memory processing. Second, techniques for disaggregating the buffer pool over multiple machines will enable the data system to scale with respect to both resources and performance. Third, the ability to offer data services that can be composed to deliver the different functionalities of a data system through well-defined application programming interfaces will be developed. Fourth, these data services will be configured with resources to deliver efficient systems given a user's resource budget. Leveraging benefits of serverless computing such as elastic scaling, pay-as-you-go and management-free services, these objectives will revolutionize the data management landscape for the better. Combining dynamic allocation and management of resources with elastic data service composability will lead to the goal of delivering performant data systems. Realizing this goal will drive advancement and use of large-scale systems that store, manage and process data while generating socio-economic benefits such as knowledge sharing, community development, and enhanced technology adoption.
Program
Discovery Grants Program - Individual
Recipient
Location
Ontario, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
RGPIN-2024-04657
Name nom
Daudjee, Khuzaima
Department département
Computer Science, David R. Cheriton School of - 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
2024
Competition year année de concours
2024
Award amount
55000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1507
Committee name en
Computer Science
Committee name fr
Sciences informatiques
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
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
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Dynamic Data Systems
Keywords
dynamic data management systems; database system resource management; database workloads; distributed database systems; scalability; transaction processing
Application summary
Data systems store and manage application data collected in almost every sector of science and society. With data coming from a vast number of sources, well-designed systems are required for data management and analysis. Effective use of system resources such as memory to perform computation efficiently becomes increasingly important. As the price-performance ratio of main memory continues to improve, it is advantageous to perform in-memory computing on data. If these data are retained in the buffer pool memory of data systems, it allows low-latency in-memory computation that can greatly improve system performance. Thus, how buffer pool is managed as a resource and how memory elasticity is supported become important in the design of efficient data systems. With the ubiquity of Cloud computing, users are increasingly relying on its services to support and run their data-intensive jobs. Effective and efficient system resource management are key to the design, use and deployment of large-scale data systems that deliver performant data services.
The goals of the proposed research are to develop techniques for the design of data systems that can perform dynamic resource management and provide dynamic composable data system services at scale. This research program will achieve these goals through the following set of challenging objectives. First, efficient techniques for resource management will be developed that will predictively fetch and retain required data in the system buffer pool to optimize for future accesses and reduce transaction latencies through in-memory processing. Second, techniques for disaggregating the buffer pool over multiple machines will enable the data system to scale with respect to both resources and performance. Third, the ability to offer data services that can be composed to deliver the different functionalities of a data system through well-defined application programming interfaces will be developed. Fourth, these data services will be configured with resources to deliver efficient systems given a user's resource budget. Leveraging benefits of serverless computing such as elastic scaling, pay-as-you-go and management-free services, these objectives will revolutionize the data management landscape for the better. Combining dynamic allocation and management of resources with elastic data service composability will lead to the goal of delivering performant data systems. Realizing this goal will drive advancement and use of large-scale systems that store, manage and process data while generating socio-economic benefits such as knowledge sharing, community development, and enhanced technology adoption.