Differential time-shared virtual machine multiplexing for handling QoS variation in clouds

  • Authors:
  • Md. Mahfuzur Rahman;Ruppa Thulasiram;Peter Graham

  • Affiliations:
  • University of Manitoba, Winnipeg, Canada;University of Manitoba, Winnipeg, Canada;University of Manitoba, Winnipeg, Canada

  • Venue:
  • Proceedings of the 1st ACM multimedia international workshop on Cloud-based multimedia applications and services for e-health
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Multi-media applications (including those arising in E-health scenarios) can cause temporally varying resource demands in cloud environments. As a result, flexible resource provisioning becomes a key requirement. Cloud computing achieves "provisioning elasticity" by using virtual machine (VM) based resource provisioning. Normal, static VM provisioning has no runtime overhead but fails to deal with unanticipated changes in resource demands. Dynamic provisioning overcomes this problem using live migration of VMs but introduces runtime overhead. To reduce unnecessary VM migration, we propose Differential Time shared VM Multiplexing (DTVM) to help support load adaptability while ensuring efficient resource utilization in cloud datacenters. DTVM looks at possible local (i.e. in the same physical machine) solutions to limit VM migration by providing more resources to high demand VMs obtained from low demand VMs. DTVM effectively allows cloud providers to prioritize among the end-users (i.e. virtual machines). DTVM also allows the end-users to prioritize their tasks in their VMs to finish important tasks at the earliest time. In this paper, we introduce DTVM for cloud environments and assess its potential benefits using CloudSim [6]. The results obtained from our simulation experiments suggest that this approach is both feasible and would be effective for interactive multi-media workloads in cloud environments.