a symmetric load balancing algorithm

3
A Symmetric Load Balancing Algorithm with A Symmetric Load Balancing Algorithm with Performance Guarantees for Distributed Hash Performance Guarantees for Distributed Hash Tables Tables Abstract— Abstract— Peers participating in a distributed hash table (DHT) Peers participating in a distributed hash table (DHT) may host different numbers of virtual servers and are may host different numbers of virtual servers and are enabled to balance their loads in the reallocation of enabled to balance their loads in the reallocation of virtual servers. Most decentralized load balance virtual servers. Most decentralized load balance algorithms designed for DHTs based on virtual servers algorithms designed for DHTs based on virtual servers require the participating peers to be asymmetric, where require the participating peers to be asymmetric, where some serve as the rendezvous nodes to pair virtual some serve as the rendezvous nodes to pair virtual servers and participating peers, thereby introducing servers and participating peers, thereby introducing another load imbalance problem.While state-of-the-art another load imbalance problem.While state-of-the-art studies intend to present symmetric load balancing studies intend to present symmetric load balancing algorithms, they introduce significant algorithmic algorithms, they introduce significant algorithmic overheads and guarantee no rigorous performance overheads and guarantee no rigorous performance metrics. In this paper, a novel symmetric load metrics. In this paper, a novel symmetric load balancing algorithm for DHTs is presented by having the balancing algorithm for DHTs is presented by having the participating peers approximate the system state with participating peers approximate the system state with histograms and cooperatively implement a global index. histograms and cooperatively implement a global index. Each peer independently reallocates in our proposal its Each peer independently reallocates in our proposal its

Upload: impulsetechnology

Post on 28-Apr-2015

36 views

Category:

Documents


3 download

TRANSCRIPT

Page 1: A Symmetric Load Balancing Algorithm

A Symmetric Load Balancing Algorithm with PerformanceA Symmetric Load Balancing Algorithm with Performance

Guarantees for Distributed Hash TablesGuarantees for Distributed Hash Tables

Abstract—Abstract—

Peers participating in a distributed hash table (DHT) may host different numbers ofPeers participating in a distributed hash table (DHT) may host different numbers of

virtual servers and are enabled to balance their loads in the reallocation of virtualvirtual servers and are enabled to balance their loads in the reallocation of virtual

servers. Most decentralized load balance algorithms designed for DHTs based onservers. Most decentralized load balance algorithms designed for DHTs based on

virtual servers require the participating peers to be asymmetric, where some servevirtual servers require the participating peers to be asymmetric, where some serve

as the rendezvous nodes to pair virtual servers and participating peers, therebyas the rendezvous nodes to pair virtual servers and participating peers, thereby

introducing another load imbalance problem.While state-of-the-art studies intendintroducing another load imbalance problem.While state-of-the-art studies intend

to present symmetric load balancing algorithms, they introduce significantto present symmetric load balancing algorithms, they introduce significant

algorithmic overheads and guarantee no rigorous performance metrics. In thisalgorithmic overheads and guarantee no rigorous performance metrics. In this

paper, a novel symmetric load balancing algorithm for DHTs is presented bypaper, a novel symmetric load balancing algorithm for DHTs is presented by

having the participating peers approximate the system state with histograms andhaving the participating peers approximate the system state with histograms and

cooperatively implement a global index. Each peer independently reallocates in ourcooperatively implement a global index. Each peer independently reallocates in our

proposal its locally hosted virtual servers by publishing and inquiring the globalproposal its locally hosted virtual servers by publishing and inquiring the global

index based on their histograms. Unlike competitive algorithms, our proposalindex based on their histograms. Unlike competitive algorithms, our proposal

exhibits analytical performance guarantees in terms of the load balance factor andexhibits analytical performance guarantees in terms of the load balance factor and

the algorithmic convergence rate, and introduces no load imbalance problem due tothe algorithmic convergence rate, and introduces no load imbalance problem due to

the algorithmic workload.the algorithmic workload.

Existing system :Existing system :

To tackle the load imbalance problem in DHTs, prior proposals have presentedTo tackle the load imbalance problem in DHTs, prior proposals have presented

centralized algorithms that rely on a few rendezvous nodes to balance the loads ofcentralized algorithms that rely on a few rendezvous nodes to balance the loads of

peers in a DHT.peers in a DHT.

In contrast to the centralized approach, some studies, e.g., [9], [10], suggest In contrast to the centralized approach, some studies, e.g., [9], [10], suggest

organizing rendezvous nodes in a hierarchical manner. Virtual servers are firstorganizing rendezvous nodes in a hierarchical manner. Virtual servers are first

Page 2: A Symmetric Load Balancing Algorithm

matched with peers through the rendezvous nodes in the lower layer of thematched with peers through the rendezvous nodes in the lower layer of the

hierarchy; for unpaired virtual servers, the rendezvous peers relay them to thehierarchy; for unpaired virtual servers, the rendezvous peers relay them to the

rendezvous in the upper layer to seek reallocation. This process repeats iterativelyrendezvous in the upper layer to seek reallocation. This process repeats iteratively

until an unpaired virtual server reaches a rendezvous in the highest layer.until an unpaired virtual server reaches a rendezvous in the highest layer.

Demerits :Demerits :

considering large-scale and dynamic DHT networks, the centralized algorithmsconsidering large-scale and dynamic DHT networks, the centralized algorithms

may introduce the performance bottleneck and the single point of failure.may introduce the performance bottleneck and the single point of failure.

Consequently, the rendezvous nodes may experience skewed workloads,Consequently, the rendezvous nodes may experience skewed workloads,

introducing another load imbalance problem. They may also become theintroducing another load imbalance problem. They may also become the

performance bottleneck and the single point of failure. Moreover, the hierarchicalperformance bottleneck and the single point of failure. Moreover, the hierarchical

networks (e.g., the tree-shaped network in ) facilitating the load balancingnetworks (e.g., the tree-shaped network in ) facilitating the load balancing

algorithms are prone to node/communication failure, thus demanding sophisticatedalgorithms are prone to node/communication failure, thus demanding sophisticated

maintenance for the networks.maintenance for the networks.

Proposed system :Proposed system :

In this paper, we present a fully decentralized load balancing algorithm for DHTs.In this paper, we present a fully decentralized load balancing algorithm for DHTs.

Our proposal, is essentially different from the previous rendezvous-based solutionsOur proposal, is essentially different from the previous rendezvous-based solutions

in that each peer estimates and represents the system state with histograms. Basedin that each peer estimates and represents the system state with histograms. Based

on the histograms, each peer reallocates its load independently without introducingon the histograms, each peer reallocates its load independently without introducing

an asymmetric rendezvous in collecting the system state as well as matchingan asymmetric rendezvous in collecting the system state as well as matching

virtual servers and participating peers. virtual servers and participating peers.