Exploiting process lifetime distributions for dynamic load balancing
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Exploiting process lifetime distributions for dynamic load balancing
ACM Transactions on Computer Systems (TOCS)
| Hi-index | 0.01 |
Based on analysis and simulation with synthetic workloads, Eager, Lazowska and Zahorjan [ELZ88] claim that ``there are likely no conditions under which migration could yield major performance improvements beyond those offered by non-migratory load sharing...'''' [ELZ88]''s system model is intended to be conservative in the sense that it overestimates the benefits of migration of active processes and underestimates the benefits of non-migratory load-sharing. In this note we point out that there are, in fact, several ways in which the [ELZ88] analysis and workload model understate the benefits of migrating active processes. We also discuss their system model and its applicability to current systems. We conclude that the general result of [ELZ88] does not apply to current systems. Elsewhere ([HBD95]) we use a trace-driven simulation to show a wide range of conditions in which preemptive migration provides significant performance benefit. Based on these results, and similar results from simulations and implemented systems, we feel that the benefits of preemptive migration in current systems should be reexamined. [ELZ88] Derek L. Eager, Edward D. Lazowska and John Zahorjan. "The limited performance benefits of migrating active processes for load sharing." In SIGMETRICS 1988, pp. 662-675, May 1988. [HDB95] Mor Harchol-Balter and Allen B. Downey, "Exploiting Process Lifetime Distributions for Dynamic Load Balancing." Tech report UCB//CSD-95-887.