近年來，隨著網際網路的迅速發展，使用者為尋求低成本、高運算能力和高效能的網路運算環境，基於目前現有網路技術發展，進而衍生出雲端運算(Cloud Computing)的網路架構。雲端運算利用網際網路，提供使用者豐富的軟體、應用程式與虛擬化資源，且毋須考量複雜與昂貴的硬體設備問題，可滿足絕大部份使用者的需求，其系統涵蓋架構即服務(Infrastructure as a Service, IaaS)、平台即服務(Platform as a Service, PaaS)與軟體即服務(Software as a Service, SaaS)三個層級。

隨著雲端運算技術蓬勃發展，許多使用者透過雲端取得各種應用服務、存取私人資料與架設伺服器，其考量雲端虛擬機器效能與可靠度問題，本研究提出EuQoS系統以降低雲端虛擬機器運作負載程度，可有利於分析大量資料時，分散雲端虛擬機器之負載，提高服務效率與加強虛擬機器可靠度。

本論文提出之系統架構包含：運用Eucalyptus建置雲端基礎環境，並使用統一介面管理虛擬機器以及支援Amazon EC2/S3的功能函式。並結合Hadoop分散式運算技術與管理者介面，即時觀察服務運作情況，輔以本研究所提出之QoS機制，達到負載均衡之目的。本實驗情境係利用分析大量資料服務記錄，測量CPU、記憶體與網路流量。根據實驗模擬結果顯示，本研究所提出的負載平衡機制，可將執行時間降低1.91秒；CPU負載減少12.92%；記憶體負載改善5.99%；整體雲端系統之網路流量改善6.94%，由以上數據可驗證本研究所提出之EuQoS系統，可有效降低雲端虛擬機器之負載，達到提升雲端運算系統之效能。

The Internet technologies have developed rapidly in recent years. The computing environment with the advantages of cost saving, high computing capability and performance is among the favorable technology for users. Based on aforementioned background, Cloud Computing technology is proposed, it uses Internet as communication medium to provide rich software, applications and virtualization resources. Because of its three levels division of infrastructure: Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (SaaS). Cloud computing technology meets the needs of user on their consideration of hardware complexity and cost.

Services, private data, and servers in the cloud provide users’ access which lead to the virtual machines’ performance and reliability issues. This study investigates the load balancing issue of virtual machines in cloud computing environments. This study also distributes the virtual machines’ loading to improve performance and enhance its reliability through analyzing large data in cloud computing.

This study proposes QoS system that uses Eucalyptus as the basic infrastructure. It has a uniform interface to manage virtual machines and supports EC2/S3 APIs compatibility. The EuQoS system is combined with Hadoop technology to provide the management interface allowing real-time services load balancing observation. The experimental scenario uses large log processing service to measure CPU, memory and throughput. Experimental results indicate that the proposed Eucalyptus QoS system decreases service execution time to 1.91 seconds, reduces 12.92% CPU loading, reduces 5.99% memory loading, improves 6.94% system throughput.

[1] S. Zhang, S. Zhang, X. Chen and X. Huo, “Cloud Computing Research and Development Trend,” Proceedings of IEEE Second International Conference on Future Networks, pp. 93-97, 2010.
[2] J. Peng, X. Zhang, Z. Lei, B. Zhang, Z. Wu and Q. Li, “Comparison of Several Cloud Computing Platforms,” Proceedings of Second International Symposium on Information Science and Engineering, pp. 23-27, 2009.
[3] S. Zhang, S. Zhang, X. Chen and S. Wu, “Analysis and Research of Cloud Computing System Instance,” Proceedings of Second International Conference on Future Networks, pp. 88-92, 2010.
[4] S. Zhang, X. Chen, S. Zhang and X. Huo, “The comparison between cloud computing and grid computing,” Proceedings of International Conference on Computer Application and System Modeling, pp. 22-24, 2010.
[5] L.J. Zhang and Q. Zhou, “CCOA: Cloud Computing Open Architecture,” Proceedings of IEEE International Conference on Web Services, pp.607-616, 2009.
[6] D. Nurmi, R. Wolski, C. Grzegorczyk, G. Obertelli, S. Soman, L. Youseff and D. Zagorodnov, “The Eucalyptus Open-Source Cloud-Computing System,” Proceedings of IEEE/ACM International Symposium on Cluster Computing and the Grid, pp.124-131, 2009.
[7] E. Caron, F. Desprez, D. Loureiro and A. Muresan, “Cloud Computing Resource Management through a Grid Middleware: A Case Study with DIET and Eucalyptus,” Proceedings of IEEE Conference on Cloud Computing, pp.151-154, 2009.
[8] B. Takayuki, K. Hitoshi, K. Ryo, I. Takayuki, H. Toshihiro and S. Mitsuhisa, “D-Cloud: Design of a Software Testing Environment for Reliable Distributed Systems Using Cloud Computing Technology,” Proceedings of IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, pp.631-636, 2010.
[9] B. Takayuki, K. Hitoshi, K. Ryo, I. Takayuki, H. Toshihiro and S. Mitsuhisa, “D-Cloud: Design of a Software Testing Environment for Reliable Distributed Systems Using Cloud Computing Technology,” Proceedings of IEEE/ACM International Conference on Cluster, Cloud and Grid Computing, pp.631-636, 2010.
[10] P. Sempolinski and D. Thain, “A Comparison and Critique of Eucalyptus, OpenNebula and Nimbus,” Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, pp.417-426, 2010.
[11] C. Vazquez, E. Huedo, R.S. Montero, I.M. Llorente, “Dynamic Provision of Computing Resources from Grid Infrastructures and Cloud Providers,” Workshops at the Grid and Pervasive Computing Conference, pp.113-120, 2009.
[12] P. Sempolinski and D. Thain, “A Comparison and Critique of Eucalyptus, OpenNebula and Nimbus,” Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, pp.417-426, 2010.
[13] R.T. Kaushik, M. Bhandarkar and K. Nahrstedt,“Evaluation and Analysis of GreenHDFS: A Self-Adaptive, Energy-Conserving Variant of the Hadoop Distributed File System,” Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, pp.274-287, 2010.
[14] X. Liu; J. Han; Y. Zhong; C. Han and X. He, “Implementing WebGIS on Hadoop: A case study of improving small file I/O performance on HDFS,” Proceedings of IEEE International Conference on Cluster Computing and Workshops, pp.1-8, 2009.
[15] T. Jiaqi, S. Kavulya, T. Gandhi and P. Narasimhan, “Visual, Log-Based Causal Tracing for Performance Debugging of MapReduce Systems,“ Proceedings of IEEE 30th International Conference on Distributed Computing Systems, pp.795-806, 2010.
[16] S. Sathya and M. Victor Jose, “Application of Hadoop MapReduce technique to Virtual Database system design,” Proceedings of IEEE Conference on Emerging Trends in Electrical and Computer Technology, pp.892-896, 2011.
[17] C. Zhang and H.D. Sterck, “CloudBATCH: A Batch Job Queuing System on Clouds with Hadoop and HBase,” Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, pp.368-375, 2010.
[18] C. Zhang and H.D. Sterck, “Supporting multi-row distributed transactions with global snapshot isolation using bare-bones HBase,” Proceedings of IEEE/ACM International Conference on Grid Computing, pp.177-184, 2010.
[19] L. Fagui, Z. Hao and Z. Haiyan,“A Xen-Based Secure Virtual Disk Access-Control Method,” Proceedings of International Conference on Multimedia Information Networking and Security, pp.375-378, 2010.
[20] S.B. Nigmandjanovich and C.W. Ahn, “Policy-based dynamic resource allocation for virtual machines on Xen-enabled virtualization environment,” Proceedings of IEEE 2nd International Conference on Advanced Computer Control, pp.353-355, 2010.
[21] M. Eto and H. Umeno, “Design and implementation of content based page sharing method in Xen,” Proceedings of International Conference on Control, Automation and Systems, pp.2919-2922, 2008.
[22] J. Che, Q. He, Q. Gao and D. Huang, “Performance Measuring and Comparing of Virtual Machine Monitors,” Proceedings of IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, pp.381-386, 2008.
[23] W. Jiang, Y. Zhou, Y. Cui, W. Feng, Y. Chen, Y. Shi and Q. Wu, “CFS Optimizations to KVM Threads on Multi-Core Environment,” Proceedings of IEEE International Conference on Parallel and Distributed Systems, pp.348-354, 2009.
[24] Q. Liu, C. Weng, M. Li and Y. Luo, “An In-VM Measuring Framework for Increasing Virtual Machine Security in Clouds,” Proceedings of IEEE Conference on Security & Privacy, pp.56-62, 2010.
[25] Y. Gao, X. Li and Y. Che, “New Architecture and Algorithm for Webserver Cluster Based on Linux Virtual Server,” Proceedings of IEEE International Symposiums on Information Processing, pp.520-524, 2008.
[26] Y. Xu, X. Xie and D. Xia, “Research and design on LVS cluster system,” Proceedings of IEEE International Workshop on Open-source Software for Scientific Computation, pp.68-72, 2009.
[27] B. Chen and N. Xiao, “High Scalable and Available Server Environment Based on Virtual Machine,” Proceedings of International Conference on Hybrid Information Technology, pp.362-371, 2006.
[28] Y. Liu and Y. Fang, “Optimizing WLC scheduling algorithm of LVS,” Proceedings of International Conference on Computer Application and System Modeling, pp.V6-585-V6-588, 2010.
[29] H. Lan, X. Wang, Y. Zhai and Y. Bin, “Extraction of User Profile Based on the Hadoop Framework,” Proceedings of IEEE International Conference on Wireless Communications, Networking and Mobile Computing, pp.1-6, 2009.
[30] J. Ekanayake, S. Pallickara and G. Fox, “MapReduce for Data Intensive Scientific Analyses,” Proceedings of IEEE Fourth International Conference on eScience, pp. 277-284, 2008.
[31] G. Mackey, S. Sehrish, J. Bent, J. Lopez, S. Habib and J. Wang, “Introducing MapReduce to High End Computing,” Proceedings of IEEE Petascale Data Storage Workshop, pp.1-6, 2008.
[32] G. Mackey, S. Sehrish and J. Wang, “Improving Metadata Management for Small Files in HDFS,” Proceedings of IEEE International Conference on Cluster Computing and Workshops, pp. 1-4, 2009.
[33] J. Shafer, S. Rixner and L. Alan, “The Hadoop Distributed Filesystem: Balancing Portability and Performance,” Proceedings of IEEE International Symposium on Performance Analysis of Systems & Software, pp.122-133, 2010.
[34] L. Jiang, B. Li and M. Song, “THE optimization of HDFS based on small files,” Proceedings of 3rd IEEE International Conference on Broadband Network and Multimedia Technology, pp.912-915, 2010.
[35] Z. Chen and H. Sterck, “CloudBATCH: A Batch Job Queuing System on Clouds with Hadoop and HBase,” Proceedings of IEEE Second International Conference on Cloud Computing Technology and Science, pp.368-375, 2010.
[36] W. Zhou, G. Pierre and C. Chi, “CloudTPS: Scalable Transactions for Web Applications in the Cloud,” Proceedings of IEEE Transactions on Services Computing, pp.1, 2011.
[37] J. Sun and Q. Jin, “Scalable RDF store based on HBase and MapReduce,” Proceedings of IEEE 3rd International Conference on Advanced Computer Theory and Engineering, pp. 20-22, 2010.