A Self-regulating System for Resource Sharing in Multi-site Grid Environments

We describe a self-adaptive and self-regulating system for fair sharing of resources in a multi-site grid environment. In such an environment, each site has a set of resources and has internal demand which it manages using internal policies and rules. To manage periodic fluctuations in the local demand and potential shortfall of resources to meet the local demand, the participants borrow and lend resources to one another. This resource sharing among the participants is regulated by a distributed, peer-to-peer resource brokering algorithmthat is scalable and fair in its allocation of the shared resources. The self-regulatingmechanism enables discovery of shared resources and the possible extent of the donated or borrowed resources. The regulating mechanism automatically clusters participants with similar borrowing and donating properties. We present both analytical and empirical evidence to prove the properties of such a system. In particular, we prove that the system is fair – that is, participants who contribute more resources to the shared pool get to borrow proportionately more resources from others. Such a resource brokering mechanism allows participants in a multi-site grid environment to meet their peak demands by provisioning resources only for average demand.

By: Pawel Garbacki; Vijay K. Naik

Published in: RC24208 in 2007


This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.


Questions about this service can be mailed to reports@us.ibm.com .