Analysis of Web caching architectures: hierarchical and distributed caching

Rodríguez, P.; Spanner, Christian; Biersack, Ernst W.

doi:10.1109/90.944339

Cited by 196 publications

(155 citation statements)

References 14 publications

Supporting

Mentioning

151

Contrasting

Unclassified

Order By: Relevance

“…Regular Q-ary trees are commonly used for the derivation of numerical results for algorithms operating on trees [37,10]; it has also be seen that numerical results from regular tree topologies are in good accordance with experimental results from actual internet tree topologies [38]. The entire set of parameters (demand and topology) for each experiment is indicated in the title of the corresponding graph.…”

Section: Numerical Results Under Igreedymentioning

confidence: 57%

See 1 more Smart Citation

On the optimization of storage capacity allocation for content distribution

Laoutaris¹,

Zissimopoulos²,

Stavrakakis³

2005

Computer Networks

View full text Add to dashboard Cite

The addition of storage capacity in network nodes for the caching or replication of popular data objects results in reduced end-user delay, reduced network traffic, and improved scalability.The problem of allocating an available storage budget to the nodes of a hierarchical content distribution system is formulated; optimal algorithms, as well as fast/efficient heuristics, are developed for its solution. An innovative aspect of the presented approach is that it combines all relevant subproblems, concerning node locations, node sizes, and object placement, and solves them jointly in a single optimization step. The developed algorithms may be utilized in content distribution networks that employ either replication or caching/replacement. In addition to reducing the average fetch distance for the requested content, they also cater to load balancing and workload constraints on a given node. Strictly hierarchical, as well as hierarchical with peering, request routing models are considered.

show abstract

Section: Numerical Results Under Igreedymentioning

confidence: 57%

“…These percentages become much larger under unequal client request rates λ j . Table 3 presents some examples with λ j 's taken from a uniform distribution in [1,10]. A reduction as large as 40% over equal-share, and 42% over big-top, can be achieved by the allocation under iGreedy.…”

Section: Using Igreedy With Caching/replacementmentioning

confidence: 99%

On the optimization of storage capacity allocation for content distribution

Laoutaris¹,

Zissimopoulos²,

Stavrakakis³

2005

Computer Networks

View full text Add to dashboard Cite

show abstract

“…However, it is not scalable and has several drawbacks [17]. First, every hierarchy layer introduces additional delay; second, a lot of redundant document copies are stored at every hierarchy level, and third, higher level caches tend to become bottlenecks.…”

Section: Motivationsmentioning

confidence: 99%

Tulip: A New Hash Based Cooperative Web Caching Architecture

Bhuyan

2006

J Supercomput

View full text Add to dashboard Cite

Abstract.With the exponential growth of WWW traffic, web proxy caching becomes a critical technique for Internet web services. Well-organized proxy caching systems with multiple servers can greatly reduce the user perceived latency and decrease the network bandwidth consumption. Thus, many research papers focused on improving web caching performance with the efficient coordination algorithms among multiple servers. Hash based algorithm is the most widely used server coordination mechanism, however, there's still a lot of technical issues need to be addressed. In this paper, we propose a new hash based web caching architecture, Tulip. Tulip aggregates web objects that are likely to be accessed together into object clusters and uses object clusters as the primary access units. Tulip extends the locality-based algorithm in UCFS to hash based web proxy systems and proposes a simple algorithm to reduce the data grouping overhead. It takes into consideration the access speed dispatch between memory and disk and replaces expensive small disk I/O with less large ones. In case a client request cannot be fulfilled by the server in the memory, the system fetches the whole cluster which contains the required object into memory, the future requests for other objects in the same cluster can be satisfied directly from memory and slow disk I/Os are avoided. It also introduces a simple and efficient data dupllication algorithm, few maintenance work need to be done in case of server join/leave or server failure. Along with the local caching strategy, Tulip achieves better fault tolerance and load balance capability with the minimal cost. Our simulation results show Tulip has better performance than previous approaches.

show abstract

“…With this in mind, Krishnan et al (2000) imposed their so-called Full Independence Assumption under which a cache has an effective hit rate of zero after having encountered an equal sized cache previously. Rodriguez et al (2001) extended this to the case of two successive caches on a shortest path to the server having hit rates of α and β where β > α, the effective cache of the second (larger) cache now being β -α. To account for the case of a larger cache being encountered first we further extend this slightly by assigning an effective hit rate of…”

Section: Hierarchical Cache Locationmentioning

confidence: 99%

Web cache location

Boffey

Saeidi

2004

Pesqui. Oper.

View full text Add to dashboard Cite

Stress placed on network infrastructure by the popularity of the World Wide Web may be partially relieved by keeping multiple copies of Web documents at geographically dispersed locations. In particular, use of proxy caches and replication provide a means of storing information 'nearer to end users'. This paper concentrates on the locational aspects of Web caching giving both an overview, from an operational research point of view, of existing research and putting forward avenues for possible further research. This area of research is in its infancy and the emphasis will be on themes and trends rather than on algorithm construction. Finally, Web caching problems are briefly related to referral systems more generally.

show abstract

Analysis of Web caching architectures: hierarchical and distributed caching

Cited by 196 publications

References 14 publications

On the optimization of storage capacity allocation for content distribution

On the optimization of storage capacity allocation for content distribution

Tulip: A New Hash Based Cooperative Web Caching Architecture

Web cache location

Contact Info

Product

Resources

About