National Laboratory for Applied Network Research (NLANR), "Global caching hierarchy," http://www.nlanr.net/. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
An Empirical Evaluation of Client-side Server Selection.. - Dykes, Robbins, Jeffery (2000) (32 citations) (Correct)
....selection, Web I. INTRODUCTION Distributed systems rely on replicated objects and services to improve performance and reliability. For example, popular World Wide Web sites are often replicated at multiple locations, and systems are being designed to share cached objects across the Internet [1][2][3] 4] When objects are replicated or cached on multiple servers, the client would like to select a server that offers fast response time. However, fluctuations in network congestion and server load make it difficult to predict response times, especially during busy times of day when network load ....
....selection meth TABLE I CLASSIFI CATION AND EXAMPLES OF SERVER SELECTION METHODS. RTT IS NETWORK ROUND TRIP TIME, BW AND LATENCY ARE STATISTICAL ESTIMATORS DERIVED FROM HISTORIC DATA Category Selection metrics Example Ref. Client side geography, hops Push caching [15] RTT ICP, NLANR [2][16] BW SPAND [17] random, server load Smart Client [18] prior response time empirical study [19] hops, RTT, BW simulation study [20] 21] hops, RTT, latency empirical study [9] RTT, BW, latency empirical study this work Server side server load HTTP Redirect [8] IP address rewrite [14] DNS ....
National Laboratory for Applied Network Research (NLANR), "Global caching hierarchy," http://www.nlanr.net/.
An Empirical Evaluation of Client-side Server Selection.. - Dykes, Robbins, Jeffery (2000) (32 citations) (Correct)
....selection, Web I. INTRODUCTION Distributed systems rely on replicated objects and services to improve performance and reliability. For example, popular World Wide Web sites are often replicated at multiple locations, and systems are being designed to share cached objects across the Internet [1][2][3] 4] When objects are replicated or cached on multiple servers, the client would like to select a server that offers fast response time. However, fluctuations in network congestion and server load make it difficult to predict response times, especially during busy times of day when network load ....
....selection meth TABLE I CLASSIFICATION AND EXAMPLES OF SERVER SELECTION METHODS. RTT IS NETWORK ROUND TRIP TIME, BW AND LATENCY ARE STATISTICAL ESTIMATORS DERIVED FROM HISTORIC DATA Category Selection metrics Example Ref. Client side geography, hops Push caching [15] RTT ICP, NLANR [2][16] BW SPAND [17] random, server load Smart Client [18] prior response time empirical study [19] hops, RTT, BW simulation study [20] 21] hops, RTT, latency empirical study [9] RTT, BW, latency empirical study this work Server side server load HTTP Redirect [8] IP address rewrite [14] DNS ....
National Laboratory for Applied Network Research (NLANR), "Global caching hierarchy," http://www.nlanr.net/.
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