透過您的圖書館登入
IP:216.73.216.134
  • 學位論文

使用DWRR排程演算法之高效率Xen vCPU排程器

Efficient Xen vCPU scheduler Using Distribute Weighted Round-Robin Scheduling Algorithm

指導教授 : 曾嘉影
若您是本文的作者,可授權文章由華藝線上圖書館中協助推廣。

摘要


虛擬化技術可以讓一台實體機器,同時模擬出多個系統。此技術擁有提高系統使用率、節能、資源量化、簡化管理的優點。因此,虛擬化技術成為支撐雲端運算的主要技術。隨著電腦硬體工業持續推動多核心處理器系統,虛擬系統如何分配硬體資源給虛擬機器,將成為影響整體系統效能的關鍵。 Credit Scheduler為Xen所使用的虛擬CPU排程器,擁有全域工作負載平衡的能力,在多核心系統上,有較好的公平性。但是Credit Scheduler對於延遲敏感的工作負載,效能低落。本論文將針對上述問題,使用Distribute Weighted Round-Robin(DWRR)排程演算法作為解決方案。DWRR對於延遲敏感的工作負載,有較短的回應時間,並保有Credit Scheduler的高公平性。如此,可以在延遲敏感的應用上,提升Xen虛擬系統20%~33%的效能。

並列摘要


Virtualization can let one physical machine to simulate multiple virtual machines simultaneously, and it has many advantages such as better system utilization, energy conservation, resource quantification, and more easily to manage system. With these advantages, virtualization become the technology which is widely used to support cloud computing. With the computer hardware industry promote multi-core system continuously, how to allocate hardware resources to the virtual machine between physical CPUs becomes the key issue of which affects the overall system performance. Credit Scheduler is Xen default virtual CPU scheduler, having better fairness for multi-core systems with global load balancing, but bad performance for latency-sensitive workloads. In order to solve this problem, this paper proposed the Distribute Weighted Round-Robin scheduling algorithm using on Xen virtual CPU scheduler, it can get less response time for latency-sensitive workloads, also have good fairness, so that enhance 20% to 33% of the performance of the Xen virtualization system.

並列關鍵字

Xen Virtual Machine Virtualization Scheduling SMP

參考文獻


[8] Tong Li. Dan Baumberger and Scott Hahn. "Efficient and Scalable Multiprocessor Fair Scheduling Using Distributed Weighted Round-Robin". Proceedings of the 14th ACM SIGPLAN symposium on Principles and Practice of Parallel Programming, pp.65-74, 2009.
[9] J. B. Nagle. On packet switches with infinite storage. IEEE Transactions on Communications, 35(4):435–438, Apr. 1987.
[11] Xu, X. H., Shan, P. P., Wan, J. and Jiang Y. C. 2008 Performance Evaluation of the CPU Scheduler in XEN, Proceedings of International Symposium on Information Science and Engineering, 68-72, Shanghai, Dec 20-22 2008.
[12] S. Govindan, A. Nath, A. Das, B. Urgaonkar, and A. Sivasubramaniam. Xen and Co.: Communication-aware cpu scheduling for consolidated Xen-based hosting platforms. Proceedings of the 3rd international conference on Virtual execution environments (VEE), 2007, pages 126-136.
[15] J. Liu, W. Huang, B. Abali, and DK Panda, “High Performance VMM-Bypass I/O in Virtual Machines,” USENIX Annual Technical Conference, June 2006.

延伸閱讀