Server Load Balancing with Network Support: Active Anycast

Miura, Hiroyuki; Yamamoto, Masaaki; Nishimura, Kanehiro; Ikeda, Hiroki

doi:10.1007/3-540-40057-5_27

Cited by 11 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of leaving to the client the decision of which server to use, [10] proposes to restore it to the network, by using an active network. Active networks use routers capable of running user supplied code on each packet.…”

Section: Current Combined Anycast Load Balancing Methodsmentioning

confidence: 99%

Network Layer Implemented Anycast Load Balancing

Pereira

Vazão

2007

2007 IEEE Symposium on Computers and Communications

View full text Add to dashboard Cite

This paper presents a server selection method where the server selection is performed by the network, at the first routerfrom the client. This method, usable in networks under single administrative control, combines network metrics (such as traffic or latency) with common server load balancing metrics (such as load, CPU utilisation or response time), allowing network conditions to be taken into account when selecting the server which will handle the request.The performance of this technique was compared, by means ofsimulations, to that ofwidely used techniques such as random, round robin and least loaded server selection.

show abstract

Section: Current Combined Anycast Load Balancing Methodsmentioning

confidence: 99%

Network Layer Implemented Anycast Load Balancing

Pereira

Vazão

2007

2007 IEEE Symposium on Computers and Communications

View full text Add to dashboard Cite

show abstract

“…However, the advantages of this technique are worth the effort. Next to faster response times due to shorter network paths, anycasting can also be used for efficient load balancing [34] and the introduced redundancy ensures availability of the served data, even when one of the anycast nodes stops working. Anycasting is therefore also used in the DNS infrastructure [35,36,37].…”

Section: Anycastingmentioning

confidence: 99%

Resilience of the Domain Name System: A case study of the .nl-domain

2018

View full text Add to dashboard Cite

In this paper we analyse the resilience of the Domain Name System (DNS). We study the impact on the availability of DNS data of certain domains for the users of the Internet when parts of the DNS infrastructure become unavailable. We perform our analysis on the level of autonomous systems and hence we explore the impact when an autonomous system (and all the routers, name servers and resolvers located in it) fails or when interconnections between autonomous systems fail. We provide a generic method to carry out this resilience analysis, in which we first identify the domain names within the analysed domain, the autonomous systems where the name servers and resolvers for this domain reside, and the interconnections and relations between these autonomous systems. Next, we simulate failure scenarios to analyse the impact on the reachability of autonomous systems and the corresponding DNS data when autonomous systems or connections between them become unavailable. Our method can identify bottlenecks and single points of failure that should be mitigated in order to improve resilience. We demonstrate our method in a case study for the .nl-domain and its underlying second-level domains.

show abstract

“…As a request routing, we have proposed Active Anycast [13]. In Active Anycast, a router in the network autonomously distributes accesses from clients adequately to geographically dispersed servers.…”

Section: Active Anycastmentioning

confidence: 99%

“…To select the optimal server which gives the smallest response time, server load is also an important factor to be considered. As one of possible way to resolve these server selection problems, we have proposed "Active Anycast " [13]. In Active Anycast, when a user request arrives at an active router, this active router selects an adequate server and directs this request to the selected server.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of Integration Effect of Content Location and Request Routing in Content Distribution Networks

Miura

Yamamoto

Active Networks

Self Cite

View full text Add to dashboard Cite

Abstract.Recently the content distribution networks (CDNs) are highlighted as the new network paradigm which can improve latency for Web access. In CDNs, the content location strategy and request routing techniques are important technical issues. Both of them should be used in an integrated manner in general, but CDN performance applying both these technologies has not been evaluated in detail. In this paper, we investigate effect of integration of these techniques. For request routing, we focus on a request routing technique applied active network technology, Active Anycast, which improves both network delay and server processing delay. For content distribution technology, we propose a new strategy, Popularity-Probability, whose aim corresponds with that of Active Anycast. Performance evaluation results show that integration of Active Anycast and Popularity-Probability provides robust CDNs.

show abstract

Server Load Balancing with Network Support: Active Anycast

Cited by 11 publications

References 12 publications

Network Layer Implemented Anycast Load Balancing

Network Layer Implemented Anycast Load Balancing

Resilience of the Domain Name System: A case study of the .nl-domain

Evaluation of Integration Effect of Content Location and Request Routing in Content Distribution Networks

Contact Info

Product

Resources

About