( 您好!臺灣時間:2019/10/23 10:52
字體大小: 字級放大   字級縮小   預設字形  


研究生(外文):Wei-xiang Kang
論文名稱(外文):Adaptive Computing for Large-Scale Dynamic Distributed Systems
指導教授(外文):Wei-Jen Wang
外文關鍵詞:cyber organismgrid computingcloud computingautomatic computingself-provisionself-adaptation
  • 被引用被引用:0
  • 點閱點閱:179
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
在資料量以及運算量需求大量增加的現今,單一電腦已難應付各種計算需求,因此各種大型運算架構紛紛被提出,例如計算網格 (Computational Grid) 以及雲端運算 (Cloud Computing)。這些系統通常採用分散式的架構,內部的組成單元也多是異質性的計算資源,因此在系統管理上與資源使用上往往會遇到很多困難。對程式設計師來說,這些計算資源的差異與系統的使用規則會造成程式設計上的困擾,並難以對程式效能做最佳化。目前這方面的研究大多是以達成整體系統效能最佳化為目的,如Condor、Globus Toolkit、IOS等,所以在多程式的執行環境中無法針對所有的應用程式進行個別的效能最佳化。
因此,本研究提出了網路有機體 (Cyber Organism)的計算模式,希望能讓個別應用程式能夠像有機體的自我調適一般以適應各種不同的情況,讓程式顯得更加的聰明。在這個計算模式之下,個別應用程式具有內部溝通能力、環境感測的能力、自我調適的能力。而計算環境應該提供資訊讓個別應用程式感測環境的變化。依據這個計算模式,本研究採用Message Passing Interface (MPI)函式庫發展出一個擁有自我調適功能的系統,並提供許多介面讓應用程式呼叫,以利動態偵測系統環境並進行調節的工作。
The demand for computing power continues growing year by year. Meanwhile, sequential processing techniques are becoming insufficient for many complex problems. As a result, large-scale computing frameworks, such as cloud computing and grid computing, become necessary to fulfill the computing needs. A large-scale computing framework is usually comprised of distributed and heterogeneous computing resources.
The distributed and heterogeneous properties intricate system management, and may impose additional rules and restrictions on the environment while using it. The rules and restrictions are very likely to puzzle application developers and make application optimization difficult to achieve. Most systems in literature aim to optimize the throughput of the entire system, such as Condor, Globus Toolkit, and IOS. Those systems ignore individual application performance in most cases, and thus may not be fare to all users. Furthermore, they cannot handle the environment change seamlessly.
This research proposes an alternative computing model relating to cyber organisms, aiming to make applications smarter and more adaptive to environment changes. In this model, the computing environment is not responsible for application optimization and reconfiguration. Instead, it provides necessary information for each individual application through a standard interface. Each application consists of several processes to cooperate some given tasks. The sub-components are able to communicate with each other, sense the change of the environment, and react accordingly. Based on the proposed model, we implement a prototype using Message Passing Interface (MPI).
The major contribution of the proposed system is that the applications are self-manageable and self-provisioning. In other words, it can automatically add new processes to a right computing host, delete old processes from a wrong computing host, and move data to balance workload between hosts when the environment changes. Therefore, different applications can be optimized for different purposes. The experimental results confirm that our system can effectively adapt to the change of the environment and automatically improve application performance.
摘 要 i
Abstract ii
目 錄 iv
圖目錄 vi
表目錄 vii
1. 緒論 - 1 -
1-1. 無縫網際空間概念 - 2 -
1-2. 環境與生物特性 - 3 -
1-3. 網路生物體 - 5 -
1-4. 研究目標 - 7 -
1-5. 研究貢獻 - 9 -
1-6. 論文架構 - 10 -
2. 相關研究 - 11 -
2-1. 中央式管理方法的工具 - 11 -
2-2. SALSA(Simple Actor Language System and Architecture) - 13 -
2-3. 資料搬移的工具與方法 - 14 -
2-4. 行程搬移與IOS - 16 -
2-5. MPI (Message Passing Interface) - 19 -
3. 系統架構 - 21 -
3-1. 程式核心架構 - 21 -
3-2. 程式提供之介面 - 24 -
3-3. 程式執行流程與實作說明 - 27 -
4. 實驗結果 - 31 -
4-1. 實驗環境與實驗工具 - 31 -
4-2. 實驗結果與分析 - 33 -
4-2-1. 階層式主從式架構與動態資料配置 - 33 -
4-2-2. 行程新增 - 39 -
4-2-3. 行程終止 - 43 -
5. 結論 - 45 -
6. 未來展望 - 46 -
參考文獻 - 47 -
[1]M. Weiser, “Some computer science issues in ubiquitous computing,” Communications of the ACM, vol. 36, 1993, pp. 75–84.
[2]u-Taiwan - http://www.utaiwan.nat.gov.tw/index.php.
[3]I. Foster, “The anatomy of the grid: Enabling scalable virtual organizations,” Euro-Par 2001 Parallel Processing, pp. 1–4.
[4]M. Armbrust, A. Fox, R. Griffith, A.D. Joseph, R.H. Katz, A. Konwinski, G. Lee, D.A. Patterson, A. Rabkin, I. Stoica, and others, “Above the clouds: A berkeley view of cloud computing,” EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2009-28, 2009.
[5]G. Agha, “Computing in pervasive cyberspace,” Communications of the ACM, vol. 51, 2008, pp. 68–70.
[6]G.A. Agha, “Actors: a model of concurrent computation in distributed systems,” AITR-844, 1985.
[7]K. Schmidt-Nielsen,“Animal physiology adaptation and environment, ” Cambridge [u.a.]: Cambridge Univ. Press, 1997.
[8]A.S. Tanenbaum and M.V. Steen, “Distributed systems”, Citeseer, 2002.
[9]W.J. Wang, K. El Maghraoui, J. Cummings, J. Napolitano, B.K. Szymanski, and C.A. Varela, “A middleware framework for maximum likelihood evaluation over dynamic grids,” Second IEEE International Conference on e-Science and Grid Computing, 2006. e-Science''06, 2006, pp. 105–105.
[10]T. Desell, N. Cole, M. Magdon-Ismail, H. Newberg, B. Szymanski, and C. Varela, “Distributed and generic maximum likelihood evaluation,” 3rd IEEE International Conference on e-Science and Grid Computing (eScience2007), page 8pp, Bangalore, India, 2007.
[11]C. Wu, “A Dynamic Load-Balancing Maximum Likelihood Evaluation Framework,” 2009.
[12]Condor Project Homepage - http://www.cs.wisc.edu/condor/.
[13]D. Thain, T. Tannenbaum, and M. Livny, “Distributed computing in practice: The Condor experience,” Concurrency and Computation Practice and Experience, vol. 17, 2005, pp. 323–356.
[14]The Globus Alliance - http://www.globus.org/.
[15]C. Varela and G. Agha, “Programming dynamically reconfigurable open systems with SALSA,” ACM SIGPLAN Notices, vol. 36, 2001, pp. 34.
[16]SALSA Programming Language - http://wcl.cs.rpi.edu/salsa/.
[17]Welcome to Apache Hadoop! - http://hadoop.apache.org/.
[18]J. Dean and S. Ghemawat, “Map Reduce: Simplified data processing on large clusters,” Communications of the ACM-Association for Computing Machinery-CACM, vol. 51, 2008, pp. 107–114.
[19]D. Borthakur, “The hadoop distributed file system: Architecture and design,” Hadoop Project Website, 2007.
[20]S. Ghemawat, H. Gobioff, and S.T. Leung, “The Google file system,” ACM SIGOPS Operating Systems Review, vol. 37, 2003, pp. 43.
[21]A. Mahanti and D.L. Eager, “Adaptive data parallel computing on workstation clusters,” Journal of Parallel and Distributed Computing, vol. 64, 2004, pp. 1241-1255.
[22]M. Kaddoura, S. Ranka, and A. Wang, “Array decompositions for nonuniform computational environments,” Journal of Parallel and Distributed Computing, vol. 36, 1996, pp. 91–105.
[23]K.E. Maghraoui, T.J. Desell, B.K. Szymanski, and C.A. Varela, “The internet operating system: Middleware for adaptive distributed computing,” International Journal of High Performance Computing Applications, vol. 20, 2006, pp. 467.
[24]S. Shen, “Runtime Reconfiguration Using I/O and CPU Profiler over Dynamic P2P Systems,” 2009.
[25]“MPI: A Message-Passing Interface Standard Version 2.1,” Message Passing Interface Forum, 9月. 2008.
[26]MPICH2 : High-performance and Widely Portable MPI - http://www.mcs.anl.gov/research/projects/mpich2/.
[27]Open MPI: Open Source High Performance Computing - http://www.open-mpi.org/.
[28]LAM/MPI Parallel Computing - http://www.lam-mpi.org/.
[29]R. Bündgen, M. Göbel, and W. Küchlin, “A master-slave approach to parallel term rewriting on a hierarchical multiprocessor,” Design and Implementation of Symbolic Computation Systems, 1996, pp. 183-194.
第一頁 上一頁 下一頁 最後一頁 top
1. 林素娟,2005,〈先秦至漢代禮俗中有關厲鬼的觀念及其因應之道〉,《成大中文學報》13:90。
2. 林富士,1998,〈臺灣的義民廟與義民爺〉,《文化視窗》5:12-19。
3. 簡翠貞,2008,〈《左傳》引諺探微〉。《新竹教育大學人文社會學報--文學與思想專刊(一)》1.2:17。
4. 林美容,1994,〈鬼的民俗學〉。《臺灣文藝》,3.143:59-64。
5. 林翎,1988,〈中國巫術與中國社會〉。《歷史月刊》6:27。
6. 林金郎,2009,〈宗教與民俗中的鬼神觀〉。《歷史月刊》257:27、28、32。
7. 林金郎,2008,〈道的信仰與神明概念〉。《歷史月刊》246:25-26。
8. 王志宇,2003,〈台灣的無祀孤魂信仰新論---以竹山地區祠廟為中心的探討〉。《逢甲人文社會學報》6: 182-210。
9. 王志宇,2003,〈台灣民間信仰的鬼神觀---以聖賢堂系列鸞書為中心的探討〉。《逢甲人文社會學報》7: 130-131。
10. 鄧榮坤著,2005,《生趣客家話》。(台北:武陵出版社)。
11. 黃瑩,2008,〈淺析受楚文化影響的客家文化的鬼神觀念〉。《歷史月刊》244:77-78。
12. 黃蘭翔,1999,〈風水中的宗族脈絡與其對生活環境經理的影響〉。《臺灣史研究》,4.2:57-88。
13. 馮輝岳著,2002,《客家童謠大家唸書》。(台北:武陵出版社)。
14. 洪維晟,2006,〈評介江志宏著 《臺灣傳統常民社會的明幽二元思維:普渡、祭厲與善書》〉。《史匯》(10:381)。
系統版面圖檔 系統版面圖檔