CIVSched: Communication-aware Inter-VM Scheduling in Virtual Machine Monitor Based on the Process

Author(s):  
Bei Guan ◽  
Yanjun Wu ◽  
Liping Ding ◽  
Yongji Wang
Author(s):  
Jan Stoess ◽  
Udo Steinberg ◽  
Volkmar Uhlig ◽  
Jens Kehne ◽  
Jonathan Appavoo ◽  
...  

2011 ◽  
Vol 19 ◽  
pp. 411-420 ◽  
Author(s):  
Megumi Ito ◽  
Shuichi Oikawa

Author(s):  
Pritam Patange

Abstract: Cloud computing has experienced significant growth in the recent years owing to the various advantages it provides such as 24/7 availability, quick provisioning of resources, easy scalability to name a few. Virtualization is the backbone of cloud computing. Virtual Machines (VMs) are created and executed by a software called Virtual Machine Monitor (VMM) or the hypervisor. It separates compute environments from the actual physical infrastructure. A disk image file representing a single virtual machine is created on the hypervisor’s file system. In this paper, we analysed the runtime performance of multiple different disk image file formats. The analysis comprises of four different parameters of performance namely- bandwidth, latency, input-output operations performed per second (IOPS) and power consumption. The impact of the hypervisor’s block and file sizes is also analysed for the different file formats. The paper aims to act as a reference for the reader in choosing the most appropriate disk file image format for their use case based on the performance comparisons made between different disk image file formats on two different hypervisors – KVM and VirtualBox. Keywords: Virtualization, Virtual disk formats, Cloud computing, fio, KVM, virt-manager, powerstat, VirtualBox.


2014 ◽  
Vol 24 (3) ◽  
pp. 535-550 ◽  
Author(s):  
Jiaqi Zhao ◽  
Yousri Mhedheb ◽  
Jie Tao ◽  
Foued Jrad ◽  
Qinghuai Liu ◽  
...  

Abstract Scheduling virtual machines is a major research topic for cloud computing, because it directly influences the performance, the operation cost and the quality of services. A large cloud center is normally equipped with several hundred thousand physical machines. The mission of the scheduler is to select the best one to host a virtual machine. This is an NPhard global optimization problem with grand challenges for researchers. This work studies the Virtual Machine (VM) scheduling problem on the cloud. Our primary concern with VM scheduling is the energy consumption, because the largest part of a cloud center operation cost goes to the kilowatts used. We designed a scheduling algorithm that allocates an incoming virtual machine instance on the host machine, which results in the lowest energy consumption of the entire system. More specifically, we developed a new algorithm, called vision cognition, to solve the global optimization problem. This algorithm is inspired by the observation of how human eyes see directly the smallest/largest item without comparing them pairwisely. We theoretically proved that the algorithm works correctly and converges fast. Practically, we validated the novel algorithm, together with the scheduling concept, using a simulation approach. The adopted cloud simulator models different cloud infrastructures with various properties and detailed runtime information that can usually not be acquired from real clouds. The experimental results demonstrate the benefit of our approach in terms of reducing the cloud center energy consumption


2015 ◽  
Vol 23 (5) ◽  
pp. 673-682 ◽  
Author(s):  
Masaya Sato ◽  
Toshihiro Yamauchi ◽  
Hideo Taniguchi

Sign in / Sign up

Export Citation Format

Share Document