Locality-aware request distribution in cluster-based network servers

Pai, Vijay S.; Aron, Mohit; Banga, Gaurov; Svendsen, Michael; Druschel, Peter; Zwaenepoel, Willy; Nahum, Erich

doi:10.1145/384265.291048

Cited by 93 publications

(128 citation statements)

References 10 publications

(3 reference statements)

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…In this section, we describe and analyse the most recent architectures that implement content-aware load balancing. Some works prove that by using the content of requests and loading information from the servers, more flexible and intelligent distributing algorithms can be developed [1,3,11,14,18,49,60,62,74].…”

Section: Content-aware Load Balancing Architecturesmentioning

confidence: 99%

“…Hence, the same ISS and IRS numbers have to be used in both connections. Pai et al in [60] introduce some modifications to Hunt's Hand-off and apply it to their request distribution algorithm (Locality-Aware Request Distribution (LARD)) that is covered in Section 6.1. Aron et al include some modifications to the TCP Hand-off mechanism to permit a granularity of individual requests when using HTTP/1.1 persistent connections in [3].…”

Section: Tcp Hand-offmentioning

confidence: 99%

See 1 more Smart Citation

An up-to-date survey in web load balancing

2010

View full text Add to dashboard Cite

This survey is an up-to-date state-of-the-art in Web load balancing mechanisms that includes all the possible classifications and focuses on the advantages of using load balancing solutions to increase the performance of the Web system. A general description of the Web load balancing solutions is included and organised by differentiating the OSI protocol stack layer the load balancing is based on. The most important request distributing polices that are proposed in the literature are also included. This article summarises all previous surveys on the Web load balancing subject and updates the state-of-the-art with the most recent load balancing proposals.

show abstract

Section: Content-aware Load Balancing Architecturesmentioning

confidence: 99%

Section: Tcp Hand-offmentioning

confidence: 99%

An up-to-date survey in web load balancing

2010

View full text Add to dashboard Cite

show abstract

“…Since no service time information was recorded, the simulation estimated the service time as the sum of the (constant) time to establish and close a connection, and the (variable, size-dependent) time required to retrieve and transfer a file. The justification for this estimation method may be found in [17,19,23]. The selection of the particular data trace was motivated by the fact that it exhibits arrival-rate fluctuations corresponding to light, medium and heavy loadings in this temporal order, as evidenced by figures 3 and 4.…”

Section: Multi-threaded Back-end Serversmentioning

confidence: 99%

“…The dispatcher receives incoming requests and then decides how to assign them to back-end servers, which in turn serve the requests according to some discipline. The dispatcher is also responsible for passing incoming data pertaining to a job from a client to a back-end server, so that, for each job in progress at a back-end server there is an open connection between the dispatcher and that server [17,23].…”

Section: Introductionmentioning

confidence: 99%

Deferred Assignment Scheduling in Cluster-Based Servers

et al. 2006

View full text Add to dashboard Cite

This paper proposes a new scheduling policy for cluster-based servers called DAS (Deferred Assignment Scheduling). The main idea in DAS is to defer scheduling as much as possible in order to make better use of the accumulated information on job sizes. In broad outline, DAS operates as follows: (1) incoming jobs are held by the dispatcher in a buffer; (2) the dispatcher monitors the number of jobs being processed by each server; (3) when the number of jobs at a server queue drops below a prescribed threshold, the dispatcher sends to it the shortest job in its buffer.To gauge the efficacy of DAS, the paper presents simulation studies, using various data traces. The studies collected response times and slowdowns for two cluster configurations under multi-threaded and multi-process back-end server architectures. The experimental results show that in both architectures, DAS outperforms the Round-Robin policy in all traffic regimes, and the JSQ (Join Shortest Queue) policy in medium and heavy traffic regimes.

show abstract

“…For example, the selected server may not have sufficient disk bandwidth to admit a new multimedia presentation along with other requests being served. Content-based routing techniques have been proposed in [15,17]. However, these techniques merely …”

Section: Introductionmentioning

confidence: 99%

Retrieval scheduling for collaborative multimedia presentations

Bai

Srinivasan

Prabhakaran³

2000

Multimedia Systems

View full text Add to dashboard Cite

The single-system approach is no longer sufficient to handle the load on popular Internet servers, especially for those offering extensive multimedia content. Such services have to be replicated to enhance their availability, performance, and reliability. In a highly replicated and available environment, server selection is an important issue. In this paper, we propose an application-layer broker (ALB) for this purpose. ALB employs a content-based, client-centric approach to negotiate with the servers and to identify the best server for the requested objects. ALB aims to maximize client buffer utilization in order to efficiently handle dynamic user interactions such as skip, reverse presentation, go back in time. We also present details of a collaborative multimedia presentation platform that we have developed based on ALB.

show abstract

Locality-aware request distribution in cluster-based network servers

Abstract: We consider cluster-based network servers in which a front-end directs incoming requests to one of a number of back-ends. Specifically, we consider content-based request distribution:

Cited by 93 publications

References 10 publications

An up-to-date survey in web load balancing

An up-to-date survey in web load balancing

Deferred Assignment Scheduling in Cluster-Based Servers

Retrieval scheduling for collaborative multimedia presentations

Contact Info

Product

Resources

About