雲端運算是一種平行分散式的運算系統，在近幾年來越來越受歡迎。在雲端運算裡，MapReduce是一個很受歡迎的模組，同時Mapreduce對於大規模的資料平行應用也是一個重要的程式設計模組。Hadoop則是一個將MapReduce模型實作出來的平台，他是屬於開放原始碼的軟體，並且Hadoop經常被使用於資料密集的應用上，像是資料探勘以及網路索引。Hadoop在運行時會假設在叢集裡所有的機器節點都擁有相同的計算能力，並且每台節點執行工作所需的資料都是在本機上的，不需要進行資料的傳輸。然而，在一些私人的叢集或是計算中心並不會符合同質性，而在這樣的異質環境底下則可能會增加額外的開銷並且降低MapReduce的效能。因此在本篇論文中，我們設計了一個資料放置的演算法，用來解決節點會有工作量不平衡的問題。我們所提出的方法可以動態的調整以平衡在每台節點上資料的儲存，而調整的方式則是根據在異質環境的Hadoop叢集裡每台節點各自的運算能力來調配，這樣可以減少時間花在資料傳輸上，來達成改善Hadoop的效能。在實驗的結果顯示出，使用我們的演算法 - 動態資料放置策略在異質環境底下可以降低執行時間並且提升Hadoop的效能。

Cloud computing is one kind of parallel distributed computing system that becomes very popular computer application. MapReduce is popular model in cloud computing and also an important programming model for large-scale data-parallel application. Hadoop is an open-source implementation of MapReduce model, it is usually used for data-intensive application such as data mining and web indexing. The current Hadoop implementation assumes that every node in cluster have same computing capacity and task are data-local. However, there are not satisfied that homogeneity and data locality in private cluster and virtualized data centers, which may increase extra overhead and reduce MapReduce performance. In this paper, we propose a data placement algorithm to resolve the unbalanced node workload problem. The proposed method can dynamic adaptive balances data stored in each node based on computing capacity of each node in a heterogeneous Hadoop cluster. It could reduce data transfer time to achieve improved Hadoop performance. Experimental results show that dynamic data placement policy could decrease the time of execution and improve Hadoop performance in a heterogeneous cluster.

[1] Amazon Elastic Compute Cloud - http://aws.amazon.com/ec2/
[2] Amazon Elastic MapReduce
http://aws.amazon.com/elasticmapreduce/
[3] Apache
http://httpd.apache.org/
[4] AWS Elastic Beanstalk - http://aws.amazon.com/elasticbeanstalk/
[5] Cloud Foundry - http://www.cloudfoundry.com/
[6] Engine Yard https://www.engineyard.com/
[7] Force.com - http://www.force.com/
[8] Go Grid Cloud Servers - http://www.gogrid.com/products/infrastructure-cloud-servers
[9] Google App Engine - https://appengine.google.com/start
[10] Google Compute Engine - https://cloud.google.com/products/compute-engine
[11] Hadoop
http://hadoop.apache.org/
[12] Hadoop MapReduce
http://hadoop.apache.org/docs/stable/mapred tutorial.html
[13] Hadoop Distributed File System
http://hadoop.apache.org/docs/stable/hdfs design.html
[14] Hadoop Yahoo
http://www.ithome.com.tw/itadm/article.php?c=49410&s=4
[15] Heroku - https://www.heroku.com/
[16] HP Cloud Services - https://www.hpcloud.com/
[17] Jelastic - http://jelastic.com/
[18] Mendix - http://www.mendix.com/
[19] OpenShift - https://www.openshift.com/
[20] Oracle Infrastructure as a Service - http://www.oracle.com/us/products/engineered- systems/iaas/overview/index.html
[21] Orange Scape - http://www.orangescape.com/
[22] ReadySpace Cloud Services - http://www.readyspace.com/
[23] Secure Shell Script http://en.wikipedia.org/wiki/Secure Shell
[24] WhatIs.com CaaS - http://whatis.techtarget.com/de¯nition/Communications-as-a-
Service-CaaS
[25] Wikipedia Cloud Computing - https://en.wikipedia.org/wiki/Cloud computing
[26] Wikipedia Converged infrastructure - http://en.wikipedia.org/wiki/Converged infrastructure
[27] Windows Azure - http://www.windowsazure.com/en-us/
[28] WindowsAzureCloudServices - http://www.windowsazure.com/en-
us/documentation/services/cloud-services/?fb=zh-tw
[29] Amies, Alex; Sluiman, Harm; Tong, Qiang Guo; Liu, Guo Ning (July 2012). Infrastructure as a Service Cloud Concepts". Developing and Hosting Applications on the Cloud. IBM Press. ISBN 978-0-13-306684-5.
[30] D. Borthakur, K. Muthukkaruppan, K. Ranganathan, S. Rash, J.-S. Sarma, N. Spiegelberg, D. Molkov, R. Schmidt, J. Gray, H. Kuang, A. Menon, A. Aiyer,Apache Hadoop Goes Realtime at Facebook," In SIGMOD 11, June 12V16, 2011, Athens, Greece.
[31] F. Chang, J. Dean, S. Ghemawat, W.-C. Hsieh Bigtable: A Distributed Storage System for Structured Data," In TOCS 2008, 2008, 26.2: 4.
[32] Q. Chen, D. Zhang, M. Guo, Q. Deng and S. Guo, SAMR: A Self-Adaptive MapReduce Scheduling Algorithm in Heterogeneous Environment," . Computer and Information
Technology (CIT), 2010 IEEE 10th International Conference on. IEEE, 2010. p. 2736-2743.
[33] J. Dean, and S. Ghemawat MapReduce: Simpli¯ed Data Processing on Large Clusters," In OSDI '04, pp 137{150, Dec 2004.
[34] "Cloud Computing in Telecommunications". Ericsson. Retrieved 16 December 2012.
[35] S. Ghemawat, H. Gobio®, and S.-T. Leung The Google File System," In Proc. SOSP 2003, pages 29V43, 2003.
[36] B. He, W. Fang, Q. Luo, N. Govindaraju, and T. Wang Mars: A MapReduce Framework on Graphics Processors," In ACM, 2008., pages 260V269, 2008.
[37] "ITU-T NEWSLOG - CLOUD COMPUTING AND STANDARDIZATION: TECHNICAL REPORTS PUBLISHED." International Telecommunication Union (ITU), Retrieved 16 December 2012.
[38] "ITU Focus Group on Cloud Computing - Part 1." International Telecommunication Union (ITU) TELECOMMUNICATION STANDARDIZATION SECTOR OF ITU. Retrieved
16 December 2012.
[39] Metzler, Jim; Taylor, Steve. (2010-08-23) "Cloud computing: Reality vs. ¯ction," Network World.
[40] G. Lee, B. G. Chun and R. H Katz,. Heterogeneity-Aware Resource Allocation and Scheduling in the Cloud." Proceedings of the 3rd USENIX Workshop on Hot Topics in Cloud Computing, HotCloud. Vol. 11. 2011.
[41] National Institute of Standards and Technology The NIST De¯nition of Cloud Computing," September, 2011
[42] C. Tian, H. Zhou, Y. He and L. Zha, A Dynamic Mapreduce Scheduler for Heterogeneous Workloads." Grid and Cooperative Computing, 2009. GCC'09. Eighth International
Conference on. IEEE, 2009.
[43] Chou, Timothy. "Introduction to Cloud Computing: Business & Technology."
[44] M. Zaharia, A. Konwinski, A. D. Joseph, R. Katz, and I. Stoica Improving MapReduce Performance in Heterogeneous Environments," . In Proc. OSDI, pages 29V42, San Diego,
CA, December 2008.