4.7 Article

Exploring the Benefits of Resource Disaggregation for Service Reliability in Data Centers

Journal

IEEE TRANSACTIONS ON CLOUD COMPUTING
Volume 11, Issue 2, Pages 1651-1666

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCC.2022.3151923

Keywords

Data center; reliability; resource disaggregation; ILP

Ask authors/readers for more resources

Resource disaggregation in data centers can improve resource utilization and offer a more cost-efficient approach for upgrade and expansion. This paper investigates the potential benefits of resource disaggregation from the aspect of reliability, which has not been considered before. The study shows that resource disaggregation can significantly improve service reliability.
By overcoming the server box barrier, resource disaggregation in data centers (DCs) can significantly improve resource utilization. This may then provide a more cost-efficient approach for resource upgrade and expansion. The advantages of resource disaggregation have been explored in earlier research to improve the efficiency of resource usage. This paper investigates the potential benefits of resource disaggregation from the aspect of reliability, which has not been considered before. Resource disaggregation gives rise to a new failure pattern. For example, in a conventional server, the failure of one type of resource leads to the failure of the entire server, so that other types of resources in the same server also become unavailable. After disaggregating, the failure of different types of resources becomes more isolated so that other resources are still available. In this paper, we model the reliability of a resource allocation request in a server-based or disaggregated DC based on whether the request is allocated with only working resources or is also provisioned with backup resources. We then consider a resource allocation problem to maximize the number of requests accepted with guaranteed reliability. This is formulated as an integer linear programming (ILP) problem, and a more straightforward heuristic approach is also proposed. Our numerical studies demonstrate that it may be possible to significantly improve service reliability with this resource disaggregation approach.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available