A scalable monitoring strategy for highly dynamic systems

This paper presents an autonomic monitoring strategy for highly-dynamic systems based on DiVHA - the distributed virtual hypercube algorithm. Hypercubes are scalable by definition, presenting several advantageous properties such as symmetry and logarithmic diameter. A system based on DiVHA keeps the hypercube properties even when the number of nodes is not a power of two, or under a dynamic fault situation, in which nodes fail and recover continuously, leaving and joining the system. In particular, the paper describes a strategy for dealing with unstable nodes, which also allows the discovery of nodes that present a more predictable behaviour. The system was implemented in PlanetLab, a highly-dynamic large scale environment that spans the globe, and and experimental results are presented.