R. Malpani, J. Lorch, and D. Berger, "Making World Wide Web Caching Servers Cooperate," Proc. Fourth Int'l World Wide Web Conf., Dec. 1995.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Hence there is a need to develop scalable and efficient solutions for cache consistency to deal with such growths. While studies have addressed viable CDN architectures [48, 8, 4, 33, 12, 43, 37, 16] the role of a proxy in a CDN [32] cooperative caching to improve hit ratio and response times [44, 5, 11, 43, 12, 17, 28, 34, 38, 49], load balancing amongst proxies [23, 24, 33] redirection schemes and other performance issues [21, 20, 31] object replication strategies in such networks [22] and how prefetching affects performance in CDNs [42] very few have addressed consistency issues in CDNs. 47, 46, 48, 45, 33] are few ....

....hit ratios and user response times but at the cost of increased network bandwidth usage. Cooperation between proxies generates network traffic as it necessitates communication between the proxies for locating an object requested. Several such techniques have been developed and studied in detail [43, 12, 17, 28, 34, 38, 49]. While this is orthogonal to the goal of maintaining consistency, the trade off of potentially achieving better user response times versus higher network bandwidth usage has to be addressed. Propagation of updates and or invalidates: When an object changes at the server, for server based ....

Radhika Malpani, Jacob Lorch, and David Berger. Making World Wide Web caching servers cooperate. In 4th international WWW conference, Boston, MA, 1995.

....and the receivers. Although a cache hierarchy mimics reliable multicast, it does not perform a perfect multicast as within an ISP the same version of the same document can be sent over a link multiple times. However, there are a number of proposals to have caches communicate via multicast [26] [16]) Thus, CMP is an attractive scheme to deliver hot changing documents. However, multicast distribution of Web documents on the Internet is still in its infancy as a viable service; in fact, very few network providers offer it as a service [11] In particular, a continuous multicast distribution ....

R. Malpani, J. Lorch, and D. Berger, "Making World Wide Web Caching Servers Cooperate", In Fourth International WWW Conference, Boston, Dec 1995.

....web traffic in a network. It tries to satisfy requests with a cached copy; failing this, it forwards the request to the home server. The dilemma in this scheme is that there is more benefit if more users share the same cache, but then the cache itself is liable to get swamped. Malpani et al. [7] work around this problem by making a group of caches function as one. A page request is served locally if it is cached in any of the caches. The disadvantage of this approach is that it leads to a lot of communication between the caches thus making it unsuitable for large networks. Chankhunthod ....

....have proxy support built in. However, the size of the network containing the proxy should not be too large; otherwise the proxy itself could get swamped with requests. This limits the benefit a popular server can derive from the use of proxy caches. 1.2. 2 Co operative Caching Malpani et al. [7] tried to make a group of caches function as one. A user s request for a page is directed to an arbitrary cache. If the page is stored there, it is returned to the user. Otherwise, the cache forwards the request to all other caches via a special protocol called IP Multicast [5] Multicast is a ....

Radhika Malpani, Jacob Lorch and David Berger. Making World Wide Web Caching Servers Cooperate. In Proceedings of World Wide Web Conference, 1996.

....(CDNs) such as Akamai [1] handle high demand for data by distributing replicas on multiple servers. CDNs are typically managed by a central entity, while CFS is built from resources shared and owned by a cooperative group of users. There are several proposed scalable cooperative Web caches [3, 8, 10, 15]. To locate data, these systems either multicast queries or require that some or all servers know about all other servers. As a result, none of the proposed methods is both highly scalable and robust. In addition, load balance is hard to achieve as the content of each cache depends heavily on the ....

MALPANI, R., LORCH, J., AND BERGER, D. Making world wide web caching servers cooperate. In Fourth International World Wide Web Conference (1995), pp. 107--110.

....documents. However, the mechanisms used in summary caching for sharing directory information can also be used in informing the client about the availability of documents in the reference point cache of a server. System of Caching Proxies: Harvest [13] Cachemesh [18] Cooperating Web Caches [19], and Adaptive Web Caching [20] are all proposed caching schemes that involve a hierarchy of caches that cooperate. However, they all follow the current model of proxy caching, that is each client goes thorugh exactly one proxy and the proxies fetch and deliver all documents. They all differ among ....

R. Malpani, J. Lorch, and D. Berger, "Making world wide web caching servers cooperate," in In 4th International World Wide Web Conference, December 1995, pp. 107--117.

....(CDNs) such as Akamai [1] handle high demand for data by distributing replicas on multiple servers. CDNs are typically managed by a central entity, while CFS is built from resources shared and owned by a cooperative group of users. There are several proposed scalable cooperative Web caches [3, 8, 10, 15]. To locate data, these systems either multicast queries or require that some or all servers know about all other servers. As a result, none of the proposed methods is both highly scalable and robust. In addition, load balance is hard to achieve as the content of each cache depends heavily on the ....

MALPANI, R., LORCH, J., AND BERGER, D. Making world wide web caching servers cooperate. In Fourth International World Wide Web Conference (1995), pp. 107--110.

....(CDNs) such as Akamai [1] handle high demand for data by distributing replicas on multiple servers. CDNs are typically managed by a central entity, while CFS is built from resources shared and owned by a cooperative group of users. There are several proposed scalable cooperative Web caches [3, 9, 11, 18]. To locate data, these systems either multicast queries or require that some or all servers know about all other servers. As a result, none of the proposed methods is both highly scalable and robust. In addition, load balance is hard to achieve as the content of each cache depends heavily on the ....

Radhika Malpani, Jacob Lorch, and David Berger. Making world wide web caching servers cooperate. In Fourth International World Wide Web Conference, pages 107{ 110, 1995.

....the method to ameliorate the situation caused by the mentioned problems. A lot of research has been done based on using a proxy cache to save bandwidth and reduce latency and congestion in the Internet. However, as researchers have found out there are certain limitations in using a single proxy [6, 14]. The single proxy can be a bottleneck. It is also dicult to scale with a single cache server architecture. As the client population 1 Web server Web server Proxy Proxy clients clients clients cooperation Figure 1: A general caching architecture increases, it produces a lot of load on the ....

....among a rapidly evolving set of popular objects. This was pointed out by the Harvest study [6] one of the pioneering works on hierarchical caching. Researchers, in the mean time, had established the usefulness of caching in the Internet [8] Cooperative caching also received attention soon [8, 7, 14]. Along with the idea of cooperative cache, came the issues of cache to cache communication and other protocol issues. With the explosion of the World Wide Web, large scalable cache architecture became a focus of attention both in the academia and in the industry. 3 Cooperative Caching in File ....

[Article contains additional citation context not shown here]

Radhika Malpani, Jacob Lorch, and David Berger. Making world wide web caching servers cooperate. In Fourth International World Wide Web Conference, December 1995.

....Thus, for a local cache miss, only 2 requests (central mapping server interrogation and response) are needed to localize an object. Other work on the improvement of cooperative caching aims at reducing the memory consumption of caches by limiting object replication among the cooperating caches [134, 156]. Solutions to minimizing the number of messages exchanged among sibling caches without using a centralized server have been proposed in the RELAIS project at INRIA Rocquencourt [90] and in later similar yet enhanced protocols [67, 138] 9.3 Architectures for the Next Generation Web Two ....

R. Malpani, J. Lorch, and D. Berger. Making World Wide Web Caching Servers Cooperate. In 4th International World-Wide Web Conference, 1995.

.... are at the edge of networks in the form of browser and proxy caches, the ends of high latency links, or as part of cache hierarchies [CDN 96, Squ] Signi cant research has gone into optimizing cache performance [CDN 96, WAS 96, NLA] co operation among several caches [CDN 96, KS97, MLB95, GRC97] and cache hierarchies [Squ, CDN 96, NL] Web servers are also replicated to achieve load balancing. An important method that is gaining momentum is caching inside the network [ZFJ97, DHS93, HM97] Danzig et al. DHS93] had observed the advantage of placing caches inside the ....

R. Malpani, J. Lorch, and D. Berger. Making world wide web caching servers cooperate. In Proceedings of the Fourth International World Wide Web Conference, December 1995.

....the bandwidth available for competing requests, and thus increasing latencies for other users. In order to reduce access latencies, it is desirable to store copies of popular objects closer to the user. Consequently, Web caching has become an increasingly important topic [1] 8] 14] 18] [19], 22] Caching can be implemented at various points in the network. On one end of the spectrum, there is typically a cache in the Web server itself. Further, it is increasingly common for a university or corporation to implement specialized servers in the network called caching proxies. Such ....

# R. Malpani, J. Lorch, and D. Berger, "Making World Wide Web Caching Servers Cooperate," Proc. Fourth Int'l World-Wide Web Conf., pp. 107-117, Boston, 1995.

.... for large scale distributed file systems [7] This approach essentially involves contacting the server directly or contacting nearby replicas which are known to have a copy the performance is usually unacceptable if the replica being contacted doesn t have a copy and needs to contact the server [24]. Consequently, in order to simultaneously have low response time and access to fresh data, it is desirable that the server transmit the updates to the replicas as soon as the updates occur. We believe that reliable multicast could be an efficient way to disseminate the updates. Another important ....

R. Malpani, J. Lorch, and D. Berger. Making World Wide Web Caching Servers Cooperate. In Proceedings of World Wide Web Conference, 1996.

....on the network side will reflect the access pattern of a group of users who share the cache. The e#ectiveness of the network cache can increase by placing it where we know that a group of users has a high degree of similarity of interest (or locality of reference) and by implementing multiple [MLB95] or hierarchical proxy caching. Multiple proxy caching is when many clients share many caches and a cache that misses can query other caches. In two level caching we have several network caches connected to another parent or first level network cache with a larger cache size. If the document is ....

....rate 8796 b sec. The value for r s was chosen by noticing that most Web users are happy when they get a transfer rate of 5 KB sec. The value for the proxy cache hit rate was measured from our log files, ranging between 30 60 [AWA 95] Similar numbers have been reported in the literature [MLB95] In this chapter we use the value 40 for the network cache hit rate. The value for the client hit rate cr also was measured by examining the caches on several clients in one of our labs, and the Network Tra#c is not the Sum of its Components 92 Table 7.1: Factors and their values for the base ....

R. Malpani, J. Lorch, and D. Berger. Making World Wide Web caching servers cooperate. In 4th International World-wide Web Conference, pages 107--117, Boston, December 1995.

....guarantee transactional semantics. E. Pitoura Summer School on Mobile Computing, Jyvaskyla, 1998 14 DO in Web Based Systems Cache management to meet the needs of wired users where ad hoc browsing is common and cache methods can trade inexpensive network bandwidth for reducing storage [9, 54, 20]. Mostly used for browsing, no updates (vs files) Which Pages to Prefetch Hoard Prefetch based on the user s surfing history list. Studies [41] indicate 2 usability of the prefetched objects. To support disconnected operation, this policy can be extended by fetching all documents of pages ....

R. Malpani, J. Lorch, and D. Berger. Making World Wide Web Caching Servers Cooperate. In Proceedings of the 4th International World Wide Web Conference, Boston, MA, December 1995.

....and the receivers. Although a cache hierarchy mimics reliable multicast, it does not perform a perfect multicast as within an ISP the same version of the same document can be sent over a link multiple times. However, there are a number of proposals to have caches communicate via multicast [26] [16]) Thus, CMP is an attractive scheme to deliver hot changing documents. However, multicast distribution of Web documents on the Internet is still in its infancy as a viable service; in fact, very few network providers offer it as a service [11] In particular, a continuous multicast distribution ....

R. Malpani, J. Lorch, and D. Berger, "Making World Wide Web Caching Servers Cooperate", In Fourth International WWW Conference, Boston, Dec 1995.

.... the popular locations for caches are at the edge of networks in the form of browser and proxy caches, the ends of high latency links, or as part of cache hierarchies [8, 31] Significant research has gone into optimizing cache performance [8, 33, 29, 10] co operation among several caches [8, 23, 26, 17, 15], and cache hierarchies [31, 8, 28] Web servers are also replicated to achieve load balancing. Placing caches inside the network is becoming more popular [34, 35, 13, 20] Danzig et al. 13] had observed the advantage of placing caches inside the backbone rather than at its edges. They showed ....

R. Malpani, J. Lorch, and D. Berger. Making world wide web caching servers cooperate. In Proceedings of the Fourth International World Wide Web Conference, Dec. 1995.

....proposed to address this problem [10] but none of them guarantees to deliver a hit if the requested object is present in the system. Other work on the improvement of cooperative caching aims at reducing the memory consumption of caches by limiting object replication among the cooperating caches [15, 21]. However, they do not solve the problem of the resulting cache and network load. A solution to minimizing the number of messages exchanged among sibling caches without using a centralized server has been proposed in the Relais project [22] It lies in the local knowledge of the state of the ....

R. Malpani, J. Lorch, and D. Berger. Making World Wide Web Caching Servers Cooperate. Proceedings of the 4th International World-Wide Web Conference. 1995.

....Methods to co operate and manage this co operation introduce complexity into the system; caches should co operate only if there is a performance gain from it. The question of how to reduce the time taken for servicing requests by a co operating proxy has been studied by other researchers [1, 3, 4]; we do not tackle that issue here. The Harvest 1 object cache [1] was the first system designed to operate in concert with other instances of itself. It used unicasting for achieving co operation. Malpani et al. 4] have presented a multicasting based technique to reduce the time it takes for ....

....requests by a co operating proxy has been studied by other researchers [1, 3, 4] we do not tackle that issue here. The Harvest 1 object cache [1] was the first system designed to operate in concert with other instances of itself. It used unicasting for achieving co operation. Malpani et al. [4] have presented a multicasting based technique to reduce the time it takes for communication between caching proxies. Gadde et al. 3] consider an approach of maintaining a centralized database of pages existing in various caches. Our goal in this paper is orthogonal to the issue of getting to a ....

R. Malpani, J. Lorch, D. Berger. "Making World Wide Web Caching Servers Cooperate," in Proceedings of the Fourth International World Wide Web Conference, December 1995.

No context found.

R. Malpani, J. Lorch, and D. Berger, "Making World Wide Web Caching Servers Cooperate," Proc. Fourth Int'l World Wide Web Conf., Dec. 1995.

No context found.

R. Malpani, J. Lorch, and D. Berger. Making world wide web caching servers cooperate. In WWW, Apr 1995.

No context found.

R. Malpani, J. Lorch, and D. Berger. Making world wide web caching servers cooperate. In WWW, Apr 1995.

No context found.

R. Malpani, J. Lorch, and D. Berger. Making world wide web caching servers cooperate. In WWW, Apr 1995.

No context found.

R. Malpani, J. Lorch, and D. Berger, "Making world wide web caching servers cooperate," in Proc. 4th Int. World Wide Web Conf., Dec. 1995.

No context found.

R. Malpani,J. Lorch,and D. Berger,"Making World Wide Web caching servers cooperate," The Fou([ International

No context found.

Radhika Malpani, Jacob Lorch and David Berger, "Making World Wide Web Caching Servers Cooperate", Proceedings of the Fourth International World Wide Web Conference, Boston, December 1995.

First 50 documents  Next 50

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