Fairness and classifications
- 1 March 2007
- journal article
- Published by Association for Computing Machinery (ACM) in ACM SIGMETRICS Performance Evaluation Review
- Vol. 34 (4) , 4-12
- https://doi.org/10.1145/1243401.1243405
Abstract
The growing trend in computer systems towards using scheduling policies that prioritize jobs with small service requirements has resulted in a new focus on the fairness of such policies. In particular, researchers have been interested in whether prioritizing small job sizes results in large jobs being treated "unfairly." However, fairness is an amorphous concept and thus difficult to define and study. This article provides a short survey of recent work in this area.Keywords
This publication has 32 references indexed in Scilit:
- QUANTIFYING FAIRNESS IN QUEUING SYSTEMSProbability in the Engineering and Informational Sciences, 2008
- Comparing FB and PS scheduling policiesACM SIGMETRICS Performance Evaluation Review, 2006
- On measuring fairness in queuesAdvances in Applied Probability, 2004
- Enhancing Both Network and User Performance for Networks Supporting Best Effort TrafficIEEE/ACM Transactions on Networking, 2004
- The impact of the service discipline on delay asymptoticsPerformance Evaluation, 2003
- Size-based scheduling to improve web performanceACM Transactions on Computer Systems, 2003
- Asymptotic convergence of scheduling policies with respect to slowdownPerformance Evaluation, 2002
- Exploiting process lifetime distributions for dynamic load balancingACM Transactions on Computer Systems, 1997
- Heavy-traffic asymptotic expansions for the asymptotic decay rates in theBMAP/G/1 queueCommunications in Statistics. Stochastic Models, 1994
- On extremal service disciplines in single-stage queueing systemsJournal of Applied Probability, 1990