EXPLOITING PROCESS LIFETIME DISTRIBUTIONS FOR DYNAMIC LOAD BALANCING

We consider policies for CPU load balancing in networks of workstation s. We address the question of whether preemptive migration (migrating active processes) is necessary, or whether remote execution (migrating processes only at the time of birth) is sufficient for load balancing . We show that resolving this issue is strongly tied to understanding the process lifetime distribution. Our measurements indicate that the distribution of lifetimes for a UNIX process is Pareto (heavy-tailed), with a consistent functional form over a variety of workloads. We sho w how to apply this distribution to derive a preemptive migration poli cy that requires no hand-tuned parameters. We used a trace-driven simu lation to show that our preemptive migration strategy is far more effe ctive than remote execution, even when the memory transfer cost is hig h.