Preference Based and Fair Resources Selection in Grid VOs

Abstract

In this work, a preference-based resources allocation algorithm for a job-flow scheduling in Grid virtual organizations (VOs) is proposed and studied. Users’ and resource providers’ preferences, VOs internal policies, resources geographical distribution along with local private utilization impose specific requirements for efficient scheduling according to different, usually contradictive, criteria. The algorithm performs resources selection optimization according to a specified general criterion and may be used in a variety of scheduling procedures, such as Backfilling or First Fit. Fair scheduling policies in VOs assume resources distribution according to VO stakeholders individual preferences. For this purpose, we consider a target optimization criterion as a linear combination of global (group) and private (user) job scheduling criteria. The mutual importance factor between the private and the global criteria is introduced to achieve a balanced scheduling solution.