A COMPARISON OF RECEIVER-INITIATED AND SENDER-INITIATED ADAPTIVE LOAD SHARING

Load sharing in a locally distributed system is the process of transparently distributing work submitted to the system by its users. By directing work away from nodes that are heavily loaded to nodes that are lightly loaded, system performance can be improved substantially. Adaptive load sharing policies make transfer decisions using information about the current system state. Control over the maintenance of this information and the initiation of load sharing actions may be centralized in a 'server' node or distributed among the system nodes participating in load sharing. The goal of this paper is to compare two strategies for adaptive load sharing with distributed control. In sender-initiated strategies, congested nodes search for lightly loaded nodes to which work may be transferred. In receiver-initiated strategies, the situation is reversed: lightly loaded notes search for congested nodes from which work may be transferred. We show that sender-initiated strategies outperform receiver-initiated strategies at light to moderate system loads, and that receiver-initiated strategies are preferable at high system loads only if the cost of task transfer under the two strategies are comparable. (There are reasons to believe that the costs will be greater under receiver-initiated strategies, making sender-initiated strategies uniformly preferable. )