ON JOB FAIRNESS IN NON-PREEMPTIVE PARALLEL JOB SCHEDULING

摘要

Fairness is an important issue for parallel job scheduling policies, but has been ignored in most of previous studies. In this paper, we consider two different styles of job fairness: FCFS and EQ. Commonly used summary statistics are applied to different job measures to evaluate the fairness under a wide range of non-preemptive parallel job scheduling policies, including priority backfill policies and goal-oriented scheduling policies. Guided by intuition, we study what fairness measures may be appropriate for characterizing the fairness considered. The impact of fairness on other scheduling performance is also studied.