Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0719113-162126 Statistics This thesis had been viewed 1507 times. Download 338 times. Author Cheng-Sin Guo Author's Email Address No Public. Department Computer Science and Enginerring Year 2012 Semester 2 Degree Master Type of Document Master's Thesis Language zh-TW.Big5 Chinese Page Count 40 Title Dynamic Placement Strategy for Virtual Machine in Virtual Cluster Environment Keyword OpenNEbula Virtual Cluster Virtualization Dynamic Placement Strategy Dynamic Placement Strategy Virtualization Virtual Cluster OpenNEbula Abstract Virtualization technology is a facility that allows multiple operating systems to share same physical resource, the benefits of virtualization are improved the resource utilization and energy-efficient, therefore, the cloud computing relies on virtualization technology, however, due to the abstraction of cloud computing environment, how to allocate hardware resources to the virtual machine will directly affect the system performance.
OpenNEbula(ONE) is an open-source virtual infrastructure , Aims to provide rich functionality, flexible approach and better interoperability and scalability to simplify the management of large data centers and existing virtual infrastructure. Thus cloud service providers can build their own cloud easily. ONE also supports most of hypervisors. However, three default placement policies which ONE provides do not have dynamic placement when server is overloaded, resulting in considerable waste of resources. Therefore, we provide dynamic placement policy to improve this problem, using the built-in attributes by ONE to filter high load node so as not to continue into the virtual machine scheduling. Also adding a dynamic monitoring mechanism in ONE system, make each nodes’ CPU usage in a reasonable range to maintain stable services. Whenever a node’s CPU usage is overloaded, using the virtual machine live migration techniques to alleviate the burden of high load node, makes cloud service more stable.
Advisor Committee Chia-Ying Tseng - advisor
Liang-Teh Lee - co-chair
Trong-Yen Lee - co-chair
Files Date of Defense 2013-07-04 Date of Submission 2013-07-22