An Extensible and Adaptive Framework for Load Balancing using multicasting
(2004)Abstract
Various load balancing solutions are available today. Most of these suffer
from several issues such as single point of failure or merely the high prices
that comes with specialised and proprietary solutions. We propose and im-
plement a framework for load balancing solutions that eliminates the single
point of failure. The framework is flexible and enables programmers to adapt
the load balancing to the exact requirements a such may have. The frame-
work enables the programmer to create single system image clusters, which
to the outside world looks like a single host. We use multicasting in or-
der to distribute the packets to al l cluster hosts. These are hereafter filtered
on each cluster such that only one host ends up receiving the packet. The
framework is tested and demonstrated using two example modules. The tests
performed proves the concept and shows a performance advantage of using
the framework.
Description
Sleipner is an extensible load-balancing framework using multicasting, developed for the Linux 2.4 kernel. It was written as a project at ITU with the purpose of studying decentralized (no single point of failure) load balancing technologies.