Optimised Migrate Virtual Machine RejuvenationReportar como inadecuado

Optimised Migrate Virtual Machine Rejuvenation - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

Server virtualization is an essentialcomponent in virtualized software infrastructure such as cloud computing.Virtual machines are generated through a software called virtual machinemonitor VMM running on physical servers. The risks of software aging causedby aging-related bugs affect both VM and VMM. As a result, service reliabilitydegrades may generate huge financial losses to companies. This paper presentsan analytic model using stochastic reward nets for time-based rejuvenationtechniques of VMM and VM. We propose to manipulate the VM behavior while theVMM rejuvenation is according to the load on the system. Using a previous Petrinet model of virtualized server, we performed an algorithm in order to optimizerejuvenation technique and achieve high availability. So we perform Migrate-VMrejuvenation or Warm-VM rejuvenation while there are current jobs in thesystem. Although Migrate-VM rejuvenation is better than Warm-VM rejuvenation insteady state availability, it can’t be always performed as it depends on thecapacity of the other host. When the queue is empty and the virtual machine hasno current jobs to serve, we propose to combine both VMM rejuvenation and VMrejuvenation. We show that the proposed technique can enhance the availabilityof VMs.


Component, Component, Availability, Data Center, Rejuvenation, Virtual Machine, Petri Net

Cite this paper

Manel, S. , Ridha, A. and Alia, M. 2015 Optimised Migrate Virtual Machine Rejuvenation. Journal of Computer and Communications, 3, 33-40. doi: 10.4236-jcc.2015.38004.

Autor: Sanheji Manel1, Azizi Ridha2, Maaloul Alia1

Fuente: http://www.scirp.org/


Documentos relacionados