International Journal of Innovation and Applied Studies ISSN 2028-9324 Vol. 8 No. 4 Oct. 2014, pp. 1504-1516 © 2014 Innovative Space of Scientific Research Journals http://www.ijias.issr-journals.org/ Corresponding Author: Amany Abdelsamea 1504 Virtual Machine Consolidation Challenges: A Review Amany Abdelsamea 1 , Elsayed E. Hemayed 2 , Hesham Eldeeb 1 , and Hanan Elazhary 1 1 Computers & Systems Department, Electronics Research Institute, Giza, Egypt 2 Computer Engineering Department, Faculty of Engineering, Cairo University, Giza, Egypt Copyright © 2014 ISSR Journals. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. ABSTRACT: Virtualization is a powerful technology that facilitates better use of the available data center resources using a technique called Virtual Machine (VM) consolidation which involves gathering of several virtual machines into a single physical server. To address the problem of high energy usage, it is necessary to eliminate inefficiencies and waste in the way electricity is delivered to computing resources, and in the way these resources are utilized to serve application workloads. This can be done by improving the physical infrastructure of data centers as well as resource allocation and management algorithms. VM consolidation involves live migration, which is the capability of transferring a VM between physical servers with a close to zero down time is an effective way to improve the utilization of resources and energy efficiency in cloud data centers. VM placement and VM migration act as a backbone to the VM consolidation process. Issues such as heterogeneity and scalability of physical resources, volatile workloads and migration cost make the VM consolidation process difficult. This paper presents a comprehensive survey of different VM consolidation challenges such as host underload detection, host overload detection, VM selection, VM live migration and VM placement algorithms. The paper discusses these VM consolidation challenges and presents a comparison between different state-of-the-art VM consolidations algorithms. KEYWORDS: Cloud computing, Hypervisor, Virtualization, VM selection, VM live migration, VM placement. 1 INTRODUCTION Cloud computing is defined by NIST [1] as a model for enabling convenient, on demand network access to a shared pool of configurable computing resources that can be rapidly provisioned and released with minimum management effort or service provider interaction. Several other definitions have been proposed for cloud computing [2], but they all imply the existence of a shared pool of computing resources. Virtualization plays a vital role in managing and coordinating access to the resource pool via a software layer called Virtual Machine Monitor (VMM) or hypervisor. It hides the details of the physical resources and provides virtualized resources for high level applications. Moreover, it virtualizes all of the resources of a given physical machine (PM) allowing several virtual machines (VM) to share its resources [3]. It should be noted that an essential characteristic of a virtual machine is that the software running on it is limited to the resources and abstractions provided by the virtual machine. Virtualization also allows gathering several virtual machines into a single physical server using a technique called VM consolidation. VM consolidation can provide significant benefits to cloud computing by facilitating better use of the available data center resources. It can be performed either statically or dynamically. In static VM consolidation, the VMM allocates the physical resources to the VMs based on peak load demand (overprovision). This leads to resource wastage because the workloads are not always at peak. On the other hand, in case of dynamic VM consolidation, the VMM changes the VM capacities according to the current workload demands (resizing). This helps in utilizing the data centers resources efficiently.