Pascale Minet ; Steven Martin ; Leila Azouz Saidane ; Skander Azzaz - FP/FIFO scheduling: coexistence of deterministic and probabilistic QoS guarantees

dmtcs:407 - Discrete Mathematics & Theoretical Computer Science, January 1, 2007, Vol. 9 no. 1 - https://doi.org/10.46298/dmtcs.407
FP/FIFO scheduling: coexistence of deterministic and probabilistic QoS guaranteesArticle

Authors: Pascale Minet ORCID1; Steven Martin 2; Leila Azouz Saidane 3; Skander Azzaz 3

  • 1 High performance communication
  • 2 Laboratoire de Recherche en Informatique
  • 3 Centre de Recherche Réseau Image SysTème Architecture et MuLtimédia

In this paper, we focus on applications having quantitative QoS (Quality of Service) requirements on their end-to-end response time (or jitter). We propose a solution allowing the coexistence of two types of quantitative QoS garantees, deterministic and probabilistic, while providing a high resource utilization. Our solution combines the advantages of the deterministic approach and the probabilistic one. The deterministic approach is based on a worst case analysis. The probabilistic approach uses a mathematical model to obtain the probability that the response time exceeds a given value. We assume that flows are scheduled according to non-preemptive FP/FIFO. The packet with the highest fixed priority is scheduled first. If two packets share the same priority, the packet arrived first is scheduled first. We make no particular assumption concerning the flow priority and the nature of the QoS guarantee requested by the flow. An admission control derived from these results is then proposed, allowing each flow to receive a quantitative QoS guarantee adapted to its QoS requirements. An example illustrates the merits of the coexistence of deterministic and probabilistic QoS guarantees.


Volume: Vol. 9 no. 1
Section: Distributed Computing and Networking
Published on: January 1, 2007
Imported on: March 26, 2015
Keywords: [INFO.INFO-DM] Computer Science [cs]/Discrete Mathematics [cs.DM]

Consultation statistics

This page has been seen 520 times.
This article's PDF has been downloaded 680 times.