Improving the Efficiency of Deploying Virtual Machines in a Cloud Environment

Abstract

Flexible allocation of resources is one of the main benefits of cloud computing. Virtualization is used to achieve this flexibility: one or more virtual machines run on a single physical machine. These virtual machines can be deployed and destroyed as needed. One obstacle to flexibility in current cloud systems is that deploying multiple virtual machines simultaneously on multiple physical machines is slow due to the inefficient usage of available resources.We implemented and evaluated three methods of transferring virtual machine images for the OpenNebula cloud middleware. One of the implementations was based on BitTorrent and the other two were based on multicast. Our evaluation results showed that the implemented methods were significantly more scalable than the default methods available in OpenNebula when tens of virtual machines were deployed simultaneously. However, the implemented methods were slightly slower than the old ones for deploying only one or a few virtual machines at a time due to overhead related to managing the transfer process.We also evaluated the performance of different virtual machine disk formats, as this choice also affects the deployment time of the machine. Raw images, QCOW2 images and logical volumes were evaluated. Logical volumes were fastest overall in sequential disk I/O performance. With sequential reads and writes, raw images could provide at best approximately 88% of the write performance and 95% of the read performance of logical volumes. The corresponding numbers for QCOW2 were 86% write and 74% read performance. Random access performance between QCOW2 and raw images was nearly identical, but LVM random access performance in our specific benchmark was significantly worse.If the usage pattern of the cloud is such that deploying large batches of virtual machines at once is common, using the new transfer methods will significantly speed up the deployment process and reduce its resource usage. The disk access method should be chosen based on what provides acceptable performance for the task being executed and provides the fastest deployment times.

Controlling Multiple Virtual Machines in Computer Classrooms

“…The BitTorrent or the UDPcast suit this purpose best. The diff erences between these two ways are negligible; however, the BitTorrent is little bit faster as shown by Laurikainen (2012).…”

Assessment of In-Cloud Enterprise Resource Planning System Performed in a Virtual Cluster

“…According to the functional mean time in average functional access time for each ERP application platform on (1), we derived the respective each platform mean time equation (2). After that a performance index is defined on (3) and sequentially normalized to be a value ranging from 0 to 1 on (4), where we refer to this as a normalized performance index corresponding to each ERP application platform.…”

“…Therefore, in this paper, we introduce a novel approach of high reliability for the task transfer between hosts, that is, a high-performed high-availability in-cloud enterprise resources planning (incloud ERP) which has deployed in the virtual machine cluster for tackling the above-mentioned crucial problem. Here, this paper gives a scheme, taking advantage of virtual machine cluster [1][2][3] to deal with the failover problem as well. The proposed approach has built in-cloud ERP [4,5] in the virtual environment so that the client is able to use mobile devices wirelessly and easily to access in-cloud services via Wi-Fi/3G, but identity verification must be carried out through access control authentication [6] in the cloud.…”

An in-cloud enterprise resource planning system with high availability and access control authentication

“…Traditionally a real host is difficult to transfer everything to another host timely and then resume its task as usual, and further data cannot be updated to the latest ones. In this paper we introduce high availability architecture to build an in-cloud services solution to the above-mentioned crucial problem to prevent data loss and system termination, as well as make good use of virtual machine cluster [1] [2] [3] approach to resolve the failover problem. This paper introduces in-cloud Enterprise Resources Planning (ERP) [4] [5] in virtual environment, and mobile devices users can easily access in-cloud services via Wi-Fi/3G, as shown in Figs.…”