Copyright © 2005 Elsevier Ltd All rights reserved.
Design and analysis of a class-aware recursive loop scheduler for class-based scheduling
Received 8 November 2004;
Abstract
In this paper, we consider the problem of devising a loop scheduler that allocates slots to users according to their relative weights as smoothly as possible. Instead of the existing notion of smoothness based on balancedness, we propose a variance-based metric which is more intuitive and easier to compute.
We propose a recursive loop scheduler for a class-based scheduling scenario based on an optimal weighted round-robin scheduler. We show that it achieves very good allocation smoothness with almost no degradation in intra-class fairness. In addition, we also demonstrate the equivalence between our proposed metric and the balancedness-based metric.
Keywords: Loop scheduler; Smoothness; Recursive; Class-aware scheduling
Article Outline
- 1. Introduction
- 1.1. Perfectly-fair loop schedulers
- 1.2. Class-based scheduling scenario
- 1.3. Contribution of this paper
- 2. Problem definition
- 2.1. Smoothness metrics
- 2.1.1. Variance-based metric
- 2.1.2. m-balancedness
- 2.1.3. Comparison between
and
- 2.2. Intra-class unfairness metric
- 2.3. Problem formulation
- 3. Description of K-flow loop schedulers
- 3.1. K-flow deficit round-robin scheduler
- 3.2. K-flow credit round-robin scheduler
- 3.3. K-flow smoothed round-robin scheduler
- 3.4. K-flow weighted round robin with WFQ-like spreading scheduler
- 3.5. K-flow golden ratio
scheduler
- 3.6. K-flow short-term fair scheduler
- 3.7. K-flow m-balanced scheduler
- 3.8. K-flow random
scheduler
- 4. Design of class-aware loop scheduler
- 4.1. An optimal two-class loop scheduler (C=2)
- 4.2. A recursive class-aware loop scheduler for multi-class scenario (C>2)
- 4.3. Variants of recursive class-aware loop schedulers
- 5. Numerical results
- 5.1. Performance of variants of recursive class-aware loop schedulers
- 5.2. Performance comparison between class-aware and class-unaware loop schedulers
- 5.2.1. Allocation smoothness
- 5.2.2. Unfairness
- 5.3. Performance comparison with GPS and PGPS schedulers
- 6. Conclusions
- References
- Vitae






E-mail Article
Add to my Quick Links

Cited By in Scopus (0)







