虛擬化對資源管理有很多好處,像是高資源使用量、低效能耗損、快速失誤復原和彈性的資源配置等。因此,我們觀察到有越來越多資 料中心和私有叢集電腦應用虛擬機器的趨勢。然而,虛擬化也帶來很 多新的挑戰,尤其是對有複雜運算行為和高效能資源需求的科學運算 軟體來說更甚。
在此篇論文中,我們以實際應用的科學運算軟體和效能評估軟體 分析自行建立的私有虛擬叢集電腦的運算效能。我們發現透過適當的 虛擬環境設定和infiniBand的硬體支援(SR-IOV),虛擬化的效能耗損 可以降至極少量。但是,運算效能仍舊難以建模或預測。最後,我們 提出一套自動調校系統,以便找到虛擬環境中,最佳表現和價格的資 源配置。相較於測試所有可能的資源配置,我們證實自動調校系統能 夠快速地找出接近最佳解的答案。

Virtualization can provide many benefits for managing resources, including higher resource utilization, lower energy cost, faster fault recovery and more flexible re- source provisioning, etc. Hence, we have seen an increasing trend for adapting virtual machine in both datacenters and in-house clusters. However, virtualization also brings several new challenges, especially for scientific applications which have more complex runtime behavior and higher performance demand. In this work, we use real scientific applications and performance benchmarking tools to analyze the application performance of our in-house virtualized cluster. We found the perfor- mance degradation could be minimized with proper virtual machine configuration and the support of hardware virtualized InfiniBand, but the performance is still difficult to be modeled or predicted. Therefore, we developed an auto-tuning tool for finding the best resource provisioning in terms of both time and cost, and show that we can find close to optimal resource provisioning setting in much shorter time than searching though all possible settings.

[1] A. Beloglazov, R. Buyya, Y. C. Lee, and A. Zomaya. A taxonomy and survey of energy-efficient data centers and cloud computing systems. International Journal of Advanced Research in Computer and Communication Engineering (IJARCCE), Oct. 2013.
[2] J. Delgado, S. M. Sadjadi, M. Bright, and H. A. Duran-Limon. Performance Prediction of Weather Forecasting Software on Multicore Systems. IEEE IPDPSW, 2010.
[3] P. Gschwandtner, T. Fahringer, and R. Prodan. Performance Analysis and Benchmarking of the Intel SCC. CLUSTER, 2011.
[4] A. Iosup, S. Ostermann, N. Yigitbasi, R. Prodan, T. Fahringer, and D. H. Epema. Performance Analysis of Cloud Computing Services for Many-Tasks Scientific Computing. IEEE TPDS, 2011.
[5] H. Jordan, P. Thoman, J. J. Durillo, S. P. P. Gschwandtner, T. Fahringer, and H. Moritsch. A Multi-Objective Auto-Tuning Framework for Parallel Codes. IEEE/ACM SC, 2012.
[6] Y. Kessaci, N. Melab, and E.-G. Talbi. A Pareto-based GA for Scheduling HPC Applications on Distributed Cloud Infrastructures. IEEE HPCS, 2011.
[7] J. Liu. Evaluating Standard-Based Self-Virtualizing Devices: A Performance Study on 10 GbE NICs with SR-IOV Support. Parallel and Distributed Com- puting, Applications and Technologies (PDCAT), 2012.
[8] Y.-M. Ma, C.-R. Lee, and Y.-C. Chung. InfiniBand Virtualization on KVM. IEEE CloudCom, 2012.
[9] S. Ostermann, A. Iosup, N. Yigitbasi, R. Prodan, T. Fahringer, and D. Epema. A Performance Analysis of EC2 Cloud Computing Services for Scientific Com- puting. ICST International Conference on Cloud Computing, 2009.
[10] C. Pizzuti. A Multi-Objective Genetic Algorithm for Community Detection in Networks. Tools with Artificial Intelligence (ICTAI), 2009.
[11] N. Regola and J.-C. Ducom. Recommendations for Virtualization Technologies in High Performance Computing. IEEE CloudCom, 2010.
[12] H. Song, H. Jin, J. He, X.-H. Sun, and R. Thakur. A Server-Level Adap- tive Data Layout Strategy for Parallel File Systems. Parallel and Distributed Processing Symposium Workshops & PhD Forum (IPDPSW), 2012.
[13] A. Thammano and A. Phu-ang. A hybrid evolutionary algorithm for the resource-constrained project scheduling problem. Artif Life Robotics, 2012.
[14] Z. Xiao, W. Song, and Q. Chen. Dynamic resource allocation using virtual machines for cloud computing environment. IEEE TPDS, 24(6):1107–1117, June 2013.
[15] K. Yelick, S. Coghlan, B. Draney, and R. S. Canon. ”the magellan report on cloud computing for science”, Dec. 2011.
[16] A. J. Younge, R. Henschel, J. T. Brown, G. von Laszewski, J. Qiu, and G. C. Fox. Analysis of Virtualization Technologies for High Performance Computing Environments. CLOUD, 2011.
[17] W. Zhengying, S. Bingxin, and Z. Erdun. Bandwidth-delay-constrained least- cost multicast routing based on heuristic genetic algorithm. Computer Com- munications, 2001.