M/G/1/MLPS compared to M/G/1/PS |
| |
Authors: | Samuli Aalto Urtzi Ayesta |
| |
Institution: | a Networking Laboratory, Helsinki University of Technology, P.O. Box 3000, FIN-02015 HUT, Helsinki, Finland b France Telecom R & D and INRIA Sophia Antipolis, France |
| |
Abstract: | Multilevel processor sharing scheduling disciplines have recently been resurrected in papers that focus on the differentiation between short and long TCP flows in the Internet. We prove that, for M/G/1 queues, such disciplines are better than the processor sharing discipline with respect to the mean delay whenever the hazard rate of the service time distribution is decreasing. |
| |
Keywords: | Scheduling Multilevel processor sharing Mean delay Unfinished truncated work M/G/1 |
本文献已被 ScienceDirect 等数据库收录! |