在此篇論文中，我們提出一個可支援多核環境且具有任務感知及負載平衡能力之虛擬機器資源分配方法。所謂的任務感知是指任務執行的過程中，所量測的負載資訊來推論任務的特性，進而改進資源分配，達到負載平衡的目的。此資源分配方法可以達到 (1)針對在平台上的處理器資源提供負載平衡 (2)解決因為處理器資源以及週邊裝置被許多虛擬機器共享而導致的整體 I/O效能低落以及過長的回應時間等問題。詳細的資源分配器設計，包括系統架構、資源分配控制的策略、實驗結果分析將在論文中一一被呈現。首先我們提出一個佇列階層模型來描述虛擬機器在此即時資源分配器中的運作情況。我們可藉由此模型分析並預估虛擬機器在工作負載下的平均回應時間以及系統資源使用狀況。其次，我們設計此資源分配器的架構與演算法則，並且設計一系列實驗來驗證此資源分配器的效能。根據實驗結果顯示，我們可以有效平衡負載(處理器使用率平均化)以及提高整體 I/O效能(回應時間降低)。依據我們所提出的資源分配器可讓不同性質的虛擬機器同時運行時，能夠保障各系統所需的品質並提高的處理器資源使用率，使得未來虛擬機器性能更加穩健與高效率。

In this thesis, we propose a task-aware load-balanced resource allocation approach for virtual machines in multi-core environment. This proposed resource allocation approach achieves some objectives as follows: (1) To balance the load of various VMs on a physical platform; (2) To solve the problem of low I/O performance when the sharing between various virtual machines leads to long response time. The design of resource allocator includes system architecture and control strategy of resource allocation, we use the measurements to obtain the information of computing resource. The obtained information is used to determine the allocation of resources. The experimental results will be analyzed in this thesis. We propose a hierarchical queueing model to describe the operational situation by virtual machines in the real-time resource allocator. We utilize this model to estimate the average response time and the system utility of virtual machines.
In addition, we implement the resource allocator. And we design the experiments to verify the resource allocator performance. The results show that we can verify load balance (the average utilization of resource allocator) and I/O performance (decreasing the response time). The proposed load balance approach effectively support a variety of virtual machines simultaneously to meet the quality requirement of each individual system.
The proposed virtual machine resource allocation will guarantee the service quality of deployed virtual machine and improve the utilization of computing resource. That will benefit virtual machines with better robustness and higher efficiency in future.

[CHO09] Hyunsik Choi, Saeyoung Han, Sungyong Park, and Eunji Yang, “A CPU Provision Scheme Considering Virtual Machine Scheduling Delays in Xen Virtualized Environment”, In Proceedings of IEEE TENCON 2009, November 2009.
[CHE07] L. Cherkasova, D. Gupta, and A. Vahdat, “Comparison of the Three CPU Schedulers in Xen”, In Proceedings of the ACM SIGMETRICS Performance Evaluation Review, p.42-51, September 2007.
[DIW05] Gupta Diwaker, Gardner Rob, Cherkasova Ludmila, “XenMon: QoS Monitoring and Performance Profiling Tool”, Technical Report HPL-2005-187, HP Labs, 2005.
[DUD99] K. J. Duda , D. R. Cheriton, “Borrowed-Virtual-Time (BVT) scheduling: supporting latency-sensitive threads in a general-purpose scheduler”, In Proceedings of the 17th ACM Symposium on Operating Systems Principles, p.261-276, December 1999
[GOV07] Sriram Govindan , Arjun R. Nath , Amitayu Das , Bhuvan Urgaonkar , Anand Sivasubramaniam, “Xen and co.: communication-aware CPU scheduling for consolidated xen-based hosting platforms”, In Proceedings of the 3rd International Conference on Virtual execution environments, June 2007.
[GUO10] Y. Guo, X. Wang, W. Dong, G. Shi, Y. Li, “A cooperative model virtual-machine monitor based on multi-core platform”, In Proceedings of 2nd Future Computer and Communication, May 2010.
[HAY08] Brian Hay, Kara Nance, “Forensics examination of volatile system data using virtual introspection”, In Proceedings of ACM SIGOPS Operating Systems Review, p.74-82, April 2008.
[IDC11] International Data Corporation (IDC) Worldwide Quarterly Server Virtualization Tracker, http://www.idc.com/getdoc.jsp?containerId=IDC_P15379.
[JAC63] James R. Jackson, “Jobshop-like Queueing Systems”, Management Science, 1963.
[KIM08] Dongsung Kim , Hwanju Kim , Myeongjae Jeon , Euiseong Seo , Joonwon Lee, “Guest-Aware Priority-Based Virtual Machine Scheduling for Highly Consolidated Server”, In Proceedings of the 14th international Euro-Par Conference on Parallel Processing, August 2008.
[KIM09] Hwanju Kim , Hyeontaek Lim , Jinkyu Jeong , Heeseung Jo , Joonwon Lee, “Task-aware virtual machine scheduling for I/O performance”, In Proceedings of the 2009 ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, March 2009.
[KLE76] L. Kleinrock, Queueing Systems, Volume 2: Computer Applications, John Wiley and Sons, 1976.
[KUM07] S. Kumar, H. Raj, K. Schwan, and I. Ganev, “Re-architecting VMMs for Multicore Systems: The Sidecore Approach”, In Proceedings of the 2007 Workshop on the Interaction between Operating Systems and Computer Architecture, June 2007.
[LEE10] Min Lee, A S Krishnakumar, P. Krishnan, Navjot Singh, Shalini Yajnik, “Supporting Soft Real-Time Tasks in the Xen Hypervisor”, In Proceedings of the 6th ACM SIGPLAN/SIGOPS international conference on Virtual Execution Environments, 2010.
[LI09] L. Li, “An optimistic differentiated service job scheduling system for cloud computing service users and providers”, In Proceedings of the 2009 IEEE Third International Conference on Multimedia and Ubiquitous Engineering, Jun 2009.
[LIA08] Guangdeng Liao, Danhua Guo , Laxmi Bhuyan , Steve R King, “Software techniques to improve virtualized I/O performance on multi-core systems”, In Proceedings of ACM/IEEE Symposium on Architectures for Networking and Communications Systems, November 2008.
[MEN06] Aravind Menon , Alan L. Cox , Willy Zwaenepoel, “Optimizing network virtualization in Xen”, In Proceedings of the Annual Conference on USENIX '06 Annual Technical Conference, p.2-2, May 2006.
[ONG08] Diego Ongaro , Alan L. Cox , Scott Rixner, “Scheduling I/O in virtual machine monitors”, In Proceedings of the 4th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments, March 2008.
[SER11] G.Serazzi, “Java Modelling Tools”, http://jmt.sourceforge.net/.
[VMW10] VMware, “VMware® vSphere™: The CPU Scheduler in VMware ESX® 4.1”, VMware White Paper, 2010.
[WOO07] T. Wood, P. Shenoy, A. Venkataramani, and M. Yousif, “Black-box and gray-box strategies for virtual machine migration”, In Proceedings of 4th Symposium on Networked Systems Design and Implementation, April 2007.
[WUN06] B. Wun and P. Crowley, “Network I/O Acceleration in Heterogeneous Multicore Processors”, In Proceedings of 14th IEEE Symp. High-Performance Interconnects, pp. 9-14, 2006.
[XEN11] Xen, “Credit-Based CPU Scheduler”, http://wiki.xensource.com/xenwiki/CreditScheduler.