跳到主要內容

臺灣博碩士論文加值系統

(52.203.18.65) 您好!臺灣時間:2022/01/19 16:17
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:文成康
研究生(外文):Cheng-Kang Wen
論文名稱:可擴展性伺服器設計之研究
論文名稱(外文):A Study on the Design of Scalable Servers
指導教授:蔡尚榮蔡尚榮引用關係
指導教授(外文):Shang-Rong Tsai
學位類別:博士
校院名稱:國立成功大學
系所名稱:電機工程學系碩博士班
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2002
畢業學年度:90
語文別:英文
論文頁數:105
中文關鍵詞:分散式系統可擴展性伺服器
外文關鍵詞:Distributed SystemsScalable Servers
相關次數:
  • 被引用被引用:0
  • 點閱點閱:373
  • 評分評分:
  • 下載下載:58
  • 收藏至我的研究室書目清單書目收藏:0
網際網路上多數的服務是建構在客戶端/伺服器的模式下來運作。網際網路的使用者及各類不同應用的快速成長使得伺服器的工作能力受到挑戰,因此帶來了伺服器的可擴展性的議題。面對日與俱增的使用者要求,單一伺服器在輸出入及計算的能力上已不堪負載了。因此,思考由一群伺服器共同來提供服務應可有效提昇服務品質與效能。並且要能夠增進容錯能力、具有負載平衡能力與提供單一伺服器的映象給使用者方使應用。然而,伺服器群組規模擴大後,伺服器的管理工作便顯得耗時費力。由此可知,可擴展性伺服器的設計議題是繁多而複雜的。
本論文對可擴展性伺服器進行分析,並提出一個一般性的可擴展性伺服器通用模型。此模型期望能用來簡化可擴展性伺服器的設計觀念,以及能為往後在設計可擴展性伺服器系統時的一個參考依據。這個模型可依要求分派器(Request Dispatcher)而細分為三種,即客戶端型、伺服端型、以及混合型。我們以各種不用的現有應用來評估與驗証此模型的可行性及有效性。我們也提出設計綱領以為日後建構可擴展性伺服器時的參考。最後,我們以實作的系統來展示及驗証此設計模型確實適用於設計大規的可擴展性伺服器。實作系統中包括一個利用SmartDNS建構的可擴展性代理伺服器,此系統符合本文所提模型的架構。另一實作系統是利用行動代理程式(Mobile Agents)技術在大規模可擴展性伺服器群組中進行軟體自動安裝及動態新增功能,以簡化伺服器群組的管理工作。
Most of Internet services are operating based on the client-server access model. The exponential growth in the number of Internet users and applications brings challenges of server scalability issues. Many innovatory companies set up their own WWW servers as alternative ways to provide online customer service and business transaction on the Internet. The solution of a single-machine server suffers from heavy load on I/O and computing capabilities. Therefore, we need new approaches which are supposed to be cost-effective and beneficial. A cluster of servers work together can provide good service quality and capacity. Internet services should be fault-tolerant and provide a single server image to users. The tasks of server management on large-scale server cluster are complex and time-consuming. The scalable server design consists of many issues including how a server group provides a single server image to their clients, how a clustered server achieves load balancing and supports fault tolerance.
In this dissertation, we focus on the modeling and analysis of scalable server design and server management to improve server scalability. We propose a generic model for scalable server design. The generic model intend for simplifying the abstraction of scalable server design and being a reference guidelines to design scalable server systems. The generic model is categorized into three application types based on the usage of the request dispatcher, namely, Client-Side Approach, Server-Side Approach, and Hybrid Approach. We evaluate the feasibility and effectiveness of the model with a variety of existing applications. We also provided design guidelines for future reference when building scalable server. Finally, we presented experimental examples to show the design model is feasible for large-scale Internet server systems. By applying mobile agent techniques, we can simplify server management tasks in a scalable server system. Our approach showed the abilities to remote installation and upgrading server software, to achieve code shipping in a server group, and to dynamically load functional modules into running servers without interrupting services. Another experimental example is the design of a scalable proxy server that supports document categorization. With the SmartDNS acting as a request dispatcher, the proxy server can logically ship partial data sets from a server cluster. In addition, the proxy server collects web documents based on similar topics and provides high cache hit ratio than general proxy servers.
Contents
Abstract…………………………………………………………v
Acknowledgements…..………………………………………viii
List of Figures……………………………………………...…xiii
Chapter 1……………………………………………………1
Introduction
1.1 Motivations…………………………………………………………………….1
1.2 What is a scalable server ?…………………………………………………….5
1.3 Why do wee need scalable servers ?.…………………………………………7
1.4 Related Work…………………………………………………………………..8
1.5 Dissertation Organization……………………………………………………15
Chapter 2……………………………………………………17
Design Model for Scalable Servers
2.1 The Generic Model…….……………………………………………………17
2.1.1 Server Load Collection and Monitoring……………………………18
2.1.2 Request Dispatcher………………………………………………….18
2.1.2.1 Symbolic Name Mapping……………………………………19
2.1.2.2 Connection Routing …………………………………………20
2.1.3 Server Cluster………………………………………………………21
2.2 The Applications of the Model………………………………………………22
2.2.1 Type I: Client-Side Approach…………………………………….22
2.2.2 Type II: Server-Side Approach……………………………………27
2.2.3 Type III: Hybrid Approach…………………………………………31
2.3 Taxonomy of Server Cluster…………………………………………………35
2.4 Design Issues…………………………………………………………………36
2.5 Design Guidelines……………………………………………………………39
2.5.1 An Application Example of Design Guidelines…………………..…40
2.6 Summary……………………………………………………………………...44
Chapter 3………………………………………………………46
A Scalable Proxy Server Supporting Document Categorization
3.1 Motivation…………………………………………………………………46
3.2 System Overview…………………………………………………………48
3.2.1 Design Concepts……………………………………………………48
3.2.2 Design Goals………………………………………………………51
3.3 System Architecture………………………………………………………51
3.3.1 System Components…………………………………………………51
3.3.2 System features………………………………………………………53
3.3.3 Proxy Management…………………………………………………54
3.3.4 Experimental Results………………………………………………55
3.4 Discussions…………………………………………………………………56
3.5 Summary……………………………………………………………………56
Chapter 4………………………………………………………58
Using Mobile Agent Technology to Build a Scalable Server
4.1 Introduction…………………………………………………………………58
4.2 Related work and background………………………………………………60
4.2.1 Scalable Service……………………………………………………..60
4.2.2 Mobile Agent………………………………………………………...62
4.3 System Design………………………………………………………………64
4.3.1 The System Framework……………………………………………64
4.3.1.1 Application…………………………………………………66
4.3.1.2 Functional Module…………………………………………66
4.3.1.3 Master Server………………………………………………66
4.3.1.4 Slave Server…………………………………………………67
4.3.1.5 Server Manager………………………………………………68
4.3.2 Maintenance of Server Group………………………………………68
4.3.2.1 Remote Application Installation……………………………68
4.3.2.2 Load Sharing and Fault Tolerant……………………………73
4.3.2.3 Server Topology……………………………………………76
4.3.3 The Advantages of the Server System………………………………77
4.4 An Application Example – A Scalable Entertainment Server Group………79
4.5 Summary……………………………………………………………………83
Chapter 5………………………………………………………84
A Server Broker Supporting Scalable and Load Balance Services
5.1 Introduction…………………………………………………………………84
5.2 General solutions……………………………………………………………85
5.3 System Design and Implementation………………………………………86
5.3.1 System Architecture…………………………………………………87
5.3.2 Address Translation…………………………………………………88
5.3.3 Modifications of FreeBSD…………………………………………90
5.3.4 Load Balancing and Fault Resiliency………………………………91
5.3.5 Data Consistency……………………………………………………92
5.4 Performance Evaluation……………………………………………………92
5.4.1 Experimental Environment…………………………………………93
5.4.2 Experimental Results………………………………………………94
5.5 Summary……………………………………………………………………97
Chapter 6………………………………………………………98
Conclusions
Bibliography………………………………………………....100
Autobiography
[1] Internet Software Consortium, http://www.isc.org.
[2] Netcraft Web Server Survey, http://www.netcraft.com.
[3] LaLiberte, D. and Braverman, A. 1995. “A Protocol for scalable group and public annotations”, Computer networks and ISDN systems: Proceedings of the 3rd International WWW Conference, v27, No. 6, P911-918.
[4] Sun Microsystems, “What Scalability Really Means?,” http://www.sun.com/ realitycheck/scalability.html, May 1995.
[5] Mari Korkea-aho, “Scalability in Distributed Multimedia System”, Master’s thesis, Helsinki University, November 5,1995.
[6] T. Berners-Lee, M. McCahill, “Uniform Resource Locators (URL)”, RFC 1738, December, 1994
[7] Chad Yoshikawa, Brent Chun, Paul Eastham, Amin Vahdat, Thomas Anderson, and David Culler, “Using Smart Clients to Build Scalable Services”, Computer Science Division University of California Berkeley, CA 94720
[8] D.Andersen, T.Yang, V.Holmedahl and O.Ibarra, “SWEB:Towards a Scalable WWW Server on MultiComputers,” Journal of Parallel and Distributed Computing, 1997.
[9] E.D.Katz, M.Butler, RMcGrath, ”A Scalable HTTP Server: The NCSA Prototype”, Computers networks and ISDN systems, Vol 27, 1994, pp.155-164
[10] T.T.Kwan, R.E.McGrath, D.A.Read, "NCSA's World Wide Web Server : Design and Performance", IEEE Computer, Nove, 1995, pp.68-74.
[11] S.Deering, “Host Extensions for IP Multicasting,” RFC 1054, Stanford University, May 1988.
[12] C.C.Chin and S.R. Tsai, “Transparency in a Replicated Network File system, “In Proceedings. 24th EUROMICRO conference, 1996.
[13] B. Liskov, S.Ghemawat, R.Gruber, P.Johnson, L.Shrira and M.Willianms, “Replication in the Harp File System,” Proc. 13th ACM Symposium on Operating System Principles, pp.226-238, 1991.
[14] B.Liskiv, R.Gruber, P.Johnson and L.Shrira, “A Replicated Unix File System,” ACM Operating System Review,” Vol.25,No.1,pp.60-64, Jan. 1991.
[15] N.Peyrouze and G.Muller,”FT-NFS: An Efficient Fault-Tolerant NFS Server Designed for Off-the-Shelf Workstations,” In Proceedings of the 26th International Symposium on Fault-Tolerant Computing, pp.64-73, 1996.
[16] J.H.Morris, M.Satyanarayanan, et al., "Andrew: A Distributed Personal Computing Environment", Commun. of the ACM, vol. 29, Mar 1986, pp. 184-201
[17] T. Brisco, RFC 1794, DNS Support for Load Balancing, April 1995.
[18] O. P. Damani, P. Y. Chung, Y. Huang, C. Kintala, and, Y. M. Wang, “ONE-IP: Techniques for Hosting a Service on a Cluster of Machines,” in Proc. The Sixth Int. World Wide Web Conference, April 1997.
[19] “How to Cost Effectively Scale Web Servers”, http://www.cisco.com/warp/public/784/5.html
[20] K. Egevang, P. Francis, "The IP Network Address Translator (NAT)", RFC1631.
[21] Steve Clarke, Port Forwarding, http://www.ox.compsoc.org.uk/~steve/portfowarding.html, October 2000.
[22] Chad Yoshikawa, Brent Chun, Paul Eastham, Amin Vahdat, Thomas Anderson, and David Culler, “Using Smart Clients to Build Scalable Services,” USENIX’97, :login Vol.22, No.2, April 1997.
[23] 文成康, 蔡尚榮, 宋豊旭, "一個支援文件分類之可擴展性代理伺服器," Parallel and Distributed Systems Workshop, Proceeding of National Computer Symposium 1999, pp. C370-C377, Taipei, Taiwan, December 1999.smart DNS.
[24] Cheng-Kang Wen, Shang Rong Tsai and Feng-Shiuh Song, "A Proxy Server Supporting Document Categorization," Proceeding of Parallel and Distributed Processing Techniques and Applications (PDPTA99), International Conference, Las Vegas, USA, June 1999.
[25] NetScape “proxy auto-config file,” March 1996 http://wp.netscape.com/eng/ mozilla/2.0/relnotes/demo/proxy-live.html.
[26] Charles C. Chin, Shang-Rong Tsai, "TOFF-2: A High-Performance Fault Tolerant File Service," , The Journal of Systems and Software, vol. 53 (2) pp. 173-182, 2000.
[27] Squid Proxy Server, http://squid.nlanr.net.
[28] Wensong Zhang; Shiyao Jin; and Quanyuan Wu, "Scaling Internet services by inuxDirector," High Performance Computing in the Asia-Pacific Region, 2000. Proceedings. The Fourth International Conference/Exhibition on , Vol. 1 , May 2000, Beijing, China.
[29] Wensong Zhang, "Linux Virtual Server for Scalable Network Services," Ottawa Linux Symposium 2000. http://www.linuxvirtualserver.org/ols/lvs.ps.gz
[30] Wensong Zhang, Shiyao Jin, Quanyuan Wu, "Creating Linux Virtual Servers," LinuxExpo 1999 Conference, http://www.linuxvirtualserver.org/linuxexpo.html.
[31] Foundry Networks White Paper, “Server Load Balancing in Today’s Web-enabled Enterprises,” April 2002.
[32] Foundry Networks Application Note, “ URL Switching with ServerIron,” April 2002.
[33]. Bieszczad,A., Pagurek,B, and White,T., “Mobile Agents for Network Management,” IEEE Communications Surveys, Vol.1, No.1, 1998.
[34]. Carzaniga,A.; Picco,G.; and Vigna,G.; “Designing Distributed Applications with a Mobile Code Paradigm,” in Proceed*ings of the 19th International Conference on Software Engineering, Boston, May 1997.
[35]. Raibulet,C. and Demartini,C., “Mobile Agent Technology for the Management of Distributed Systems – a Case Study,” Terena Networking Conference, Lisbon, May 2000.
[36]. Schutz,F., Gannoune,L., and Francioli,J., “Security Mechnisms for a Mobile Agent-Based Platform for Electronic Commerce of Internet Domain names,” INET 2000 Proceedings, Japan, July 2000.
[37]. Baldi,M.; Gai,S.; and Picco,G., “Exploiting Code Mobility in Decentralized and Flexible Network Management,” in Proceedings of the First International Workshop on Mobile Agents, Berlin, Germany, April 1997..
[38]. Harrison,C.G. , Chess, .M, Kershenbaum,A., "Mobile Agents: Are they a good idea? ", IBM T.J. Watson Research Center, March 28, 1995.
[39]. Concordia, URL: http://www.meitca.com/HSL/Projects/Concordia/ , 1997.
[40]. Voyager, "Voyager: Mobile Agent at Objectspace," http://www.objectspace.com/ products/voyager/, ObjectSpace Inc., 1999.
[41] Aglets, URL: http://www.trl.ibm.co.jp/aglets/, IBM, 1999.
[42] LaLiberte, D. and Braverman, A. 1995. “A Protocol for scalable group and public annotations”, Computer networks and ISDN systems: Proceedings of the 3rd International WWW Conference, v27, No. 6, P911-918.
[43] Mari Korkea-aho, “Scalability in Distributed Multimedia System”, Master’s thesis, Helsinki University, November 5,1995.
[44] Mario Baldi and Fulvio Risso, "Designing a Videconference System for Active Networks," Accepted for publication in Proceedings of the 2nd International Workshop on Mobile Agents, Stuttgart, September 1998.
[45] Alfonso Fuggetta and Giovanni Vigna, "Understanding Code Mobility," IEEE Transactions on Software Engineering, vol. 24, no. 5, pp. 342-361.
[46] "IBM Aglets Software Development Kit, "http://www.trl.ibm.co.jp/aglets/ .
[47] Danny Lange and Mitsuru Oshima, "Programming and Deploying Java Mobile Agents with Aglets"
[48] 文成康, 宋豐旭, 蔡尚榮, "支援 Scalable Server 的DNS設計," Proceedings of 1998 Workshop on Distributed System Technologies and Applications, pp.72-76, NCKU, Tainan, Taiwan, 1998.
[49] “A Dictionary of HTML META Tags”, http://vancouver-webpages.com/META/ metatags.detail.html, 1998.
[50] Paul Resnick, “Filtering Information on the Internet”, http://www.sciam.com/0397issue/0397resnick.html, 1997.
[51] Paul Resnick, James Miller, “PICS: Internet Access Controls Without Censorship”, http://www.w3.org/PICS/iacwcv2.htm, 1997.
[52] Venkata n. Padmanabhan, and Jeffrey C. Mogul, “Using Predictive Prefetching to Improve World-Wide Web Latency”, ACM SIGCOMM Computer Communication Review p22-36.
[53] Azer Bestavros, Robert L. Carter, Mark E. and Crovella, “Application Level Document Caching in the Internet”, ftp://ca-ftp.bu.edu/techreports/95-002-web-client-caching-ps.z, 1995.
[54] David P. Habib, and Robert L. Balliot, “How to Search the World Wide Web: A Tutorial and Guide for Beginners”, http://www.ultranet.com/~egrlib/totur.htm, 1998.
[55] Terry A.Gray, “How to Search the Web”, http://daphne.palomar.edu/TGSEARCH/, 1997.
[56] Jian Liu, “Guide to Meta-Search Engines”, http://www.indiana.edu/~librcsd/search/meta.html, 1998.
[57] A. Rijsinghani, “Computaion of the Internet Checksum via Incremental Update” RFC1624.
[58] C.C. Chin, “Design and Implementation of a Fault Tolerant Network File Service”, Master Dissertation, Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, June 1992.
[59] Ed Tittel , “Benchmarking The Web”, SunWorld Online Feature, September,1996.
[60] Gstone, See http://web66/coled.umn.edu/Gstone/.
[61] SPECweb96, See http://www.specbench.org/osg/web/.
[62] NetPerf, See http://www.netperf.org/.
[63] Webstone, See http://ipw.internet.com/analysis/internet_analysis/ 916160764.html.
[64] 文成康、蔡尚榮、吳重雄, “TANET上IP Multicast應用的管理,” TANET’95, pp.f191-f198, Chung-Li, Taiwan, December 1995.
[65] P.Srisuresh and M.Holdrege, “IP Network Address Translator(NAT) Terminology and Considerations,” RFC 2663, August 1999.
[66] Google Search Engine, http://www.google.com/, 2002.
[67] Google Press Release, “Google Launches World’s Largest Search Engine,” http://www.google.com/press/pressrel/pressrelease 26.html, June 26, 2000.
[68] Monika Henzinger, Google Inc., “Index the Web – A Challenge for Supercomputing,” Keynote Presentation, International Supercomputer Conference, Heidelberg, June 20, 2002.
[69] S. Brin and L. Page. “The anatomy of a large-scale hypertextual web search engine,” In Proceedings of the 7th International World Wide Web Conference, pages 107-117, Brisbane, Australia, April 1998. Elsevier Science.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top