Dynamic load balancing in distributed systems

Load balancing algorithms for LANs vary in their complexity. D.L. Eager et al. (1986) claim that the optimal level of complexity falls in the simple dynamic range, but they do not explain why more complex algorithms fail to achieve improved performance. Even a perfect balancing algorithm does not show increased performance, due to a delayed information problem that increasingly affects the more complex algorithms. These results were obtained by constructing a simulation of a perfect balancing algorithm in which each node had immediate and free access to the states of all other nodes in the system. Even though each node could find the least-loaded node in the system immediately, the model performed no better than less complex models. The most significant parameter of the system was the cost of transferring a job from one node to another. This cost limits the dynamic algorithms because each node does not know how many jobs are on the way and therefore cannot send out precise information about its future state. Complex algorithms rely on this information, which is the reason why they fail