Mahanti, A.: Web Proxy Workload Characterisation And Modelling. M.Sc. Thesis, Department of Computer Science, University of Saskatchewan (1999).  Home/Search   Document Details and Download   Summary   Related Articles   Check

....to fit all client requests. Whereas this approach fully benefits from sharing, it might undermine the cache memory efficiency. This is due to the fact that generic documents are potentially larger than adapted documents. Accordingly, fewer documents fit in the cache. Cache performance studies [11] suggest that increasing the cache size by a magnitude of 4 may increase the document hit ratio by up to about 25 and the byte hit ratio by up to about 35 . Reducing the size of the documents in the cache by adaptation will gain similar improvements in cache hits. Besides, even higher compression ....

....policy is subject to ongoing research. 5 Related Research Related research to our work actually spans different research areas. On the one hand this is web proxy caching research. This research area has been investigated for quite a long time and many aspects have been deeply examined [6, 7, 10, 11, 14, 17, 18, 19, 20, 21]. The idea of proxy caching goes back to the CERN proxy [17] It was further developed in the Harvest project [6] which also created the concepts of hierarchical caching, the basis of our system scenario. The subsequent open source project Squid [7] has further developed the Harvest ideas and ....

Mahanti, A.: Web Proxy Workload Characterisation And Modelling. M.Sc. Thesis, Department of Computer Science, University of Saskatchewan (1999).

....images for different devices may experience document sizes differing by three orders of magnitude. Accordingly, caching of images should benefit significantly from the adaptation aware caching scheme. If we take into account that about 78 of all requests issued by the clients are image requests [13], our approach benefits from the majority of requests. Furthermore, our approach depends on a fair amount of homogeneity in the client population of the particular proxies. A proxy with a very diverse client population has to store a document in a representation that can be adapted to a variety ....

....1 bit (b w) WBMP 1KB WAP phone (Siemens S35i) 5. RELATED RESEARCH Related research to our work actually spans different research areas. On the one hand this is web proxy caching research. This research area has been investigated for quite a long time and many aspects have been deeply examined [3, 4, 5, 7, 13, 15, 16, 17, 18, 19]. The idea of proxy caching goes back to the CERN proxy [15] It was further developed in the Harvest project [4] which also created the concepts of hierarchical caching, the basis of our system scenario. The subsequent open source project Squid [3] has further developed the Harvest ideas and ....

A. Mahanti, "Web Proxy Workload Characterisation And Modelling", M.Sc. Thesis, Department of Computer Science, University of Saskatchewan, Sep 1999.

.... [HSY98] HK97] HJWC98] IKY97] IST98] JC98] JDB96] JK97] JK98] Kah97] KKO98] WMS98a] KS98a] KW97a] KW97b] KW98] KMK99] KR99] KW99] KA99] KS98b] KLM97] KSW98b] KSW98a] LG98] LHC 98] LSCH98] LWS 99] LD99] LAJF98] Liu98] LC97] LC98] TB97] LOG96] LA94] Luo98] Mah99] MWE00] MEW00] MLB95] MR97] MS97] MSC98] Mar96] MC98] Mar99] MR98] WMFMA98] Mel96] MBV97] MA98] Mog95] Mog96] MDFK97a] MDFK97b] MJ98] MAWM98] Nau98] NLN98] Pad95] PM96] Par96] Pet98] PR94] PK96] Pit97] Pit98] RCG98] RSGR00] RF98b] RF98a] RV98] RBR98] RS98] ....

Anirban Mahanti. Web Proxy Workload Characterisation and Modelling. Master's thesis, Department of Computer Science, University of Saskatchewan, September 1999.

....of documents smaller than 10,000 bytes account for only 27 of the total bytes transferred by the proxy to the clients. The tail of the distribution (transfers over 100,000 bytes) accounts for a signi cant 30 of the total bytes transferred. Similar observations can be made for the other data sets [25]. Therefore, caching smaller documents can increase the hit ratio at the cost of more bytes transferred over the network. To reduce the network trac volume, proxies can cache larger documents, thus sacri cing the cache hit ratio. 0 0.2 0.4 0.6 0.8 1 1 100 10,000 1,000,000 1e08 Cumulative ....

....The frequency versus rank plot for the USask data set (on a log log scale) appear in Figure 4. Visual inspection of the graph suggests that the distribution follows Zipf s law, albeit not as strictly as has been observed for Web servers. Similar observations can be made for the other two data sets [25]. There appears to be some attening at the most popular end and the least popular end of the plots. This might indicate caching of the frequently requested hot documents at browsers and lower level caches. The middle portion appears to follow the Zipf distribution more accurately. Similar ....

A. Mahanti, Web Proxy Workload Characterisation and Modelling, M.Sc. Thesis, Department of Computer Science, University of Saskatchewan, September 1999. Available at URL: ftp://ftp.cs.usask.ca/pub/discus/thesis-mahanti.ps.Z

.... advent of distributed systems consisting of workstations and shared le servers resulted in much research on locality characteristics and their impact on caching at client [3] and le server caches [26] Many recent studies have focussed on the characteristics of Web trac at clients [5] proxies [16, 28], and servers [1, 2, 6] Almeida et al. 1] used the LRUSM model to measure temporal locality in Web server access logs. Cao et al. 9] analyzed document inter reference times to establish the presence of temporal locality in Web proxy access logs. Others have used trace driven caching simulations ....

....the document being accessed from the origin server in the absence of intermediate proxies. Therefore, only requests with the 200 (OK) and 206 (Partial Content) status codes are considered. The next step in the data reduction process was to discard requests for dy 1 Larger data sets were used in [16]. However, the results presented here are for a more recent trace, and are consistent with the observations made in [16] 4 namic documents, since these documents are typically not cached at proxies. We assumed that all documents with a cgi bin or in the URL string represent dynamic ....

[Article contains additional citation context not shown here]

A. Mahanti, Web Proxy Workload Characterisation and Modelling, M.Sc. Thesis, Department of Computer Science, University of Saskatchewan, September 1999, available at URL ftp://ftp.cs.usask.ca/pub/discus/thesis-mahanti.ps.Z.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC