Communications of the ACM
Understanding Performance Interference of I/O Workload in Virtualized Cloud Environments
CLOUD '10 Proceedings of the 2010 IEEE 3rd International Conference on Cloud Computing
A Mathematical Programming Approach for Server Consolidation Problems in Virtualized Data Centers
IEEE Transactions on Services Computing
How a consumer can measure elasticity for cloud platforms
ICPE '12 Proceedings of the 3rd ACM/SPEC International Conference on Performance Engineering
Hi-index | 0.00 |
Dynamic migration of virtual machines (VMs) across physical servers has the potential to increase the utilization of the servers and hence drive down the data center costs. However, IT practitioners are leery of using this capability for increasing resource utilization due to concerns about the impact of such migrations on the performance of the applications, particularly the response times seen by the users of the applications. The relative newness to the industry of many of the tools used to automate VM migrations for resource utilization; data from researchers; as well as the recommendations from some analysts justify such caution and warrant quantifying the risks as well as potential rewards before deciding how aggressively this capability should be adopted. This paper will discuss the requirements for a benchmark to be used for such quantification. We will also discuss adaptations to SPECvirt_sc2010, originally developed as a single server benchmark, to meet these requirements. We will also present risk-reward quantifications obtained using this benchmark for a simple case and the broader use of the benchmark for other cases.