(3.236.222.124) 您好!臺灣時間:2021/05/10 17:03
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:::

我願授權國圖
: 
twitterline
研究生:陳勉志
研究生(外文):Mien-Chih Chen
論文名稱:一個在分散式網頁快取系統上的協調式的置換策略
論文名稱(外文):A Coordinated Replacement Policy On Distributed Web Caches
指導教授:陳添福陳添福引用關係
指導教授(外文):Tien-Fu Chen
學位類別:碩士
校院名稱:國立中正大學
系所名稱:資訊工程研究所
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:2001
畢業學年度:89
語文別:英文
論文頁數:51
中文關鍵詞:置換分散式網頁快取網頁快取伺服器複製
外文關鍵詞:replacementdistributed web cachesweb cachereplication
相關次數:
  • 被引用被引用:0
  • 點閱點閱:128
  • 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
近年來,全球資訊網的成長速度相當驚人。而此成長速度也帶來了可觀的網路流量。快取是一個經常被使用來加速瀏覽網頁的有效方法。因著快取伺服器的儲存空間有限,快取伺服器終究必須以比較有用的物件置換掉比較沒用的物件。在以前的研究中,有很多的置換方法都是為了有限的硬碟空間而設計。 然而,我們發現硬碟的成長速度比記憶體的成長速度要快的很多,而快取伺服器只能儲存有限數目的物件。因此,我們針對數目的限制提出一個新的置換方法,並且也針對數目的限制與硬碟空間的限制提出一個混合的置換方法。
然而,單一的網頁快取伺服器有其產量與效能的限制。快取伺服器之間的合作可以成為突破此限制的解決防法。在以前的研究之中,很少有人針對物件的放置與置換這個議題來討論,因此我們針對這個議題發展了一個估計模型,此模型可以幫助分散式快取系統作置換與複製的決策。

In recently years, the World Wide Web has experienced phenomenal growth. This growth also contributes significant network traffic of the Internet. A popular and effective technique for improving web performance is caching. As the web cache has limited resources, it is eventually necessary to replace less useful objects with more useful ones. Several replacement policy schemes have been proposed for dealing with limited storage capacity. However, we notice that the growth rate of disk is far larger than it of memory, which will raise the impact of another reason that causes replacement - entry-constraint. We therefore propose a new replacement to fit cache system with entry constraint and a hybrid method for both disk space constraint and entry constraint.
However, a single point of web cache server has limitation on throughput and performance. Cooperative caching can therefore be a solution for this limitation. There are less previous work address issues of object placement and replacements. Hence we develop a cost model for coordinated replacement policy and replicate decisions of distributed web cache system.

1 Introduction 1
1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . 1
1.2 Main Contribution. . . . . . . . . . . . . . . . . . . . . 2
1.3 Thesis Organization. . . . . . . . . . . . . . . . . . . . 3
2 Background and Related work 4
2.1 Web Cache. . . . . . . . . . . . . . . . . . . . . . . . . 4
2.2 Replacement Policies . . . . . . . . . . . . . . . . . . . 4
2.2.1 Basic Replacement Policies . . . . . . . . . . . . . . . 5
2.2.2 Greedy-Dual Family . . . . . . . . . . . . . . . . . . . 5
2.2.3 Other Replacement Policy . . . . . . . . . . . . . . . . 7
2.3 Cooperative Caches . . . . . . . . . . . . . . . . . . . . 8
2.3.1 Cooperative Caching Architectures. . . . . . . . . . . . 8
2.3.2 Cooperative Protocol. . . . . . . . . . . . . . . . . . 10
3 A Hybrid Replacement Policy For Web Caches 14
3.1 Motivation. . . . . . . . . . . . . . . . . . . . . . . . 14
3.2 GDSP Algorithm. . . . . . . . . . . . . . . . . . . . . . 15
3.2.1 Overview . . . . . . . . . . . . . . . . . . . . . . . 15
3.2.2 Capturing Object Popularity . . . . . . . . . . . . . . 16
3.3 Directory Entry Constraint/GD-entry policy. . . . . . . . 18
3.4 Hybrid Method . . . . . . . . . . . . . . . . . . . . . . 20
4 Coordinated Replacement Policy on Distributed Web Caches 23
4.1 Overview. . . . . . . . . . . . . . . . . . . . . . . . . 23
4.2 Model of Coordinated Replacement Policy . . . . . . . . . 24
4.3 Directory System Design . . . . . . . . . . . . . . . . . 26
4.3.1 Local Directory . . . . . . . . . . . . . . . . . . . . 26
4.3.2 Remote Hit Directory. . . . . . . . . . . . . . . . . . 28
4.4 Cooperative Protocol. . . . . . . . . . . . . . . . . . . 30
4.5 Decisions of Replacement and Replicate. . . . . . . . . . 32
4.5.1 Coordinated Replacement (Without Replicate Decision). . 33
4.5.2 Coordinated Replacement (With Replicate Decision) . . . 35
5 Performance Evaluation 38
5.1 Trace File Collection . . . . . . . . . . . . . . . . . . 38
5.1.1 Site of Trace File. . . . . . . . . . . . . . . . . . . 38
5.1.2 Trace File Collection . . . . . . . . . . . . . . . . . 38
5.1.3 Trace File Abstraction. . . . . . . . . . . . . . . . . 39
5.2 Performance of GD-Entry and hybrid method . . . . . . . . 39
5.3 Performance of Coordinated Replacement. . . . . . . . . . 42
5.4 Performance of Coordinated Replacement and Replicate. . . 43
5.5 Communication Messages Reduction. . . . . . . . . . . . . 43
6 Conclusions and Future work 47
6.1 Summary . . . . . . . . . . . . . . . . . . . . . . . . . 47
6.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . 48

[1] M. Arlitt, L. Cherkasova, J. Dilley, R. Friedrich, and T. Jin. Evaluating content man-agement techniques for web proxy caches. In the 2nd Workshop on Internet Server Performance, May 1999.
[2] Shudong Jin; Azer Bestavros. Popularity-aware greedydual-size web proxy caching al-gorithm. In 19th International Conference on Distributed Computing Systems, pages 254—261, 2000.
[3] Anawat Chankhunthod, Peter B. Danzig, Chuck Neerdaels, Michael F. Schwartz, and Kurt J. Worrel. A hierarchical internet object cache. In USENIX Technical Conference, January 1996.
[4] K.A. Dykes, S.G.; Robbins. A hierarchical internet object cache. In INFOCOM 2001. Proceedings. IEEE , Volume: 3, 2001.
[5] Li Fan, Pei Cao, Jussara Almeida, and Andrei Z. Broder. Summary cache: a scal-able wide-area web cache sharing protocol. IEEE/ACM Transactions on Networking,8(3):281—293, 2000.
[6] Syam Gadde, Micheal Rabinovich, and Jeff Chase. Reduce, reuse, recycle: An approach to building large internet caches. In In Workshop on Hot Topics in Operating Systems, May 1997.
[7] M. Korupolu, M.R.; Dahlin. Coordinated placement and replacement for large-scale distributed caches. In IEEE Workshop on Internet Applications, pages 62—71, 1999.
[8] B. Krishnamurthy and C. Wills. Proxy cache coherency and replacement─towards a more complete picture. In 19th International Conference on Distributed Computing Systems, June 1999.
[9] A. Mahanti, D. Eager, and C. Williamson. Temporal locality and its impact on web proxy cache performance, September 2000.
[10] Scott Michel, Khol Nguyen, Lixia Zhang, Adam Rosenstein, Lixia Zhang, Sally Floyd, and Van Jacobson. Adaptive web caching: Toward a new caching architecture. In 3rd international web caching conferenced, June 1998.
[11] N.Young. On-line caching as cache size varies. In Pro2nd Annual ACM-SIAM Symp. on Discrete Algorithms, pages 241—250, 1991.
[12] P.Cao and S.Irani. Cost-aware www proxy caching algorthms. In USENIX Symposium on Internet Technology and Systems, pages 241—250, 1997.
[13] Mohammad Salimullah Raunak. A survey of cooperative caching, December 1999.
[14] Luigi Rizzo and Lorenzo Vicisano. Replacement policies for a proxy cache. In Third International WWW Caching Workshop, June 1998.
[15] P. Rodriguez, C. Spanner, and E. Biersack. Web caching architectures: hierarchical and distributed caching. In Proceedings of WCW ’99, 1999.
[16] Alex Rousskov and Duane Wessels. Cache digests. Computer Networks and ISDN Systems, 30(22—23):2155—2168, 1998.
[17] V. Valloppillil and K. W. Ross. Cache array routing protocol, February 1998.
[18] P. A. Vixie. The hypertext caching protocol (htcp/0.0)., March 1998.
[19] D. Wessels and K. Claffy. Rfc:2186: Internet cache protocol(icp), verson2, September 1997.
[20] D. Wessels and K. Claffy. Rfc:2187: Application of internet cache protocol(icp), verson2, September 1997.
[21] Jiong Yang, Wei Wang, Ricahrd Muntz, and Jia Wang. Dynamic web caching. In Tech
Report, June 1998.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔