Measuring the cost of online load-balancing in distributed range-queriable systems

Konstantinou, I; Tsoumakos, D; Koziris, N

dc.contributor.author	Konstantinou, I	en
dc.contributor.author	Tsoumakos, D	en
dc.contributor.author	Koziris, N	en
dc.date.accessioned	2014-03-01T02:46:13Z
dc.date.available	2014-03-01T02:46:13Z
dc.date.issued	2009	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/32610
dc.subject	Case Study	en
dc.subject	Cost Effectiveness	en
dc.subject	Distributed System	en
dc.subject	Experimental Analysis	en
dc.subject	Hybrid Method	en
dc.subject	Load Balance	en
dc.subject	Range Query	en
dc.subject.other	Bandwidth efficient	en
dc.subject.other	Distributed systems	en
dc.subject.other	Experimental analysis	en
dc.subject.other	Hybrid method	en
dc.subject.other	Load allocation	en
dc.subject.other	Load-Balancing	en
dc.subject.other	Peer-to-peer overlays	en
dc.subject.other	Range query	en
dc.subject.other	Re-distribution	en
dc.subject.other	Skip-graphs	en
dc.subject.other	Hybrid sensors	en
dc.subject.other	Online systems	en
dc.subject.other	Cost benefit analysis	en
dc.title	Measuring the cost of online load-balancing in distributed range-queriable systems	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/P2P.2009.5284544	en
heal.identifier.secondary	http://dx.doi.org/10.1109/P2P.2009.5284544	en
heal.identifier.secondary	5284544	en
heal.publicationDate	2009	en
heal.abstract	Distributed systems such as Peer-to-Peer overlays have been shown to efficiently support the processing of range queries over large numbers of participating hosts. In such systems, uneven load allocation has to be effectively tackled in order to minimize overloaded peers and optimize their performance. In this work, we detect and analyze the two basic methodologies used to achieve load-balancing: Iterative key re-distribution between neighbors and node migration. Based on this analysis, we propose a hybrid method that adaptively utilizes these two extremes to achieve both fast and cost-effective load-balancing in distributed systems that support range queries. As a case study, we offer an implementation on top of a Skip Graph, where we validate our findings in a variety of workloads. Our experimental analysis shows that the hybrid method converges 10% faster than simple neighbor item exchanges and is more than 70% bandwidth efficient compared to simple node migrations. © 2009 IEEE.	en
heal.journalName	IEEE P2P'09 - 9th International Conference on Peer-to-Peer Computing	en
dc.identifier.doi	10.1109/P2P.2009.5284544	en
dc.identifier.spage	135	en
dc.identifier.epage	138	en