Effect of heterogeneity on static load balance algorithm performance in DHT systems
Kun‐Cheng Tsai, Chyouhwa Chen · Journal of the Chinese Institute of Engineers · 2008
Application layer peer to peer (P2P) network technology is widely regarded as the most important development for next generation Internet infra‐structure. For these systems to be effective, load balancing among the peers is critical. Early structured P2P systems rely on the randomness of object ID generated with a dynamic hash function to avoid the load imbalance issue. This has been known to result in an imbalance factor of O (log N) in the number of items stored at a node. This paper makes two contributions. First, based on previous work, we propose a simple yet extremely effective extension. We demonstrate the superior performance of our proposal and also explore other important issues vital to the performance for the virtual server framework, such as the effect of the number of directories employed in the system, and the performance ramification of user registration strategies. Secondly, and more significantly, we characterize systematically the effect of heterogeneity on load balancing algorithm performance, and the conditions in which heterogeneity may be easy or hard to deal with. We show how previous results may be valid only in the simpler settings.