An approximate analysis of waiting time in multi-class M/G/1/./EDF queues

Authors:
Ken Chen;Laurent Decreusefond
Affiliations:
Network Department, ENST, 46 rue Barrault, 75634 Paris cedex 13, France;Network Department, ENST, 46 rue Barrault, 75634 Paris cedex 13, France
Venue:
Proceedings of the 1996 ACM SIGMETRICS international conference on Measurement and modeling of computer systems
Year:
1996

Citing 6
Cited 1

Optimal scheduling policies for a class of queues with customer deadlines to the beginning of service

Journal of the ACM (JACM)
A Performance Analysis of Minimum Laxity and Earliest Deadline Scheduling in a Real-Time System

IEEE Transactions on Computers
Virtual clock: a new traffic control algorithm for packet switching networks

SIGCOMM '90 Proceedings of the ACM symposium on Communications architectures & protocols
Comparison of Hybrid Minimum Laxity/First-In-First-Out Scheduling Policies for Real-Time Multiprocessors

IEEE Transactions on Computers
Scheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment

Journal of the ACM (JACM)
Providing Quality of Service Packet Switched Networks

Performance Evaluation of Computer and Communication Systems, Joint Tutorial Papers of Performance '93 and Sigmetrics '93

Scheduling and memory requirements analysis with AADL

Proceedings of the 2005 annual ACM SIGAda international conference on Ada: The Engineering of Correct and Reliable Software for Real-Time & Distributed Systems using Ada and Related Technologies

Quantified Score

Hi-index	0.00

Visualization

Abstract

The Earliest-Deadline-First (EDF) queueing discipline is being more and more widely used for handling time-sensitive applications in computer systems and networks. In this paper, we consider an arbitrary number of traffic classes with class-specific soft-deadline. A soft-deadline is a target waiting-time limit that can be missed. EDF queueing has been proved to minimize the maximum delay overflow related to this limit. We propose a quantitative analysis, through the metric of mean waiting time, on the behavior of EDF queueing. This analysis gives also insight on the correlation between traffic classes with different time-constraints. Technically speaking, we have proven that the mean waiting times for an arbitrary set of N classes of traffic streams with soft deadlines are the unique solution of a system of non-linear equations under the constraint of the Kleinrock's conservation law. We then provide an O (N2) algorithm to get the solution. Simulation suggests that the theoretical approximation we made is quite acceptable.