BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20111116T003000Z
DTEND:20111116T004500Z
LOCATION:TCC LL1
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: Job scheduling is essential on large-scale computing systems. While numerous research has been focused on improving job scheduling theoretically, our work is motivated by practical issues observed in current production supercomputers, caused by reasons such as user behaviors, emerging system architecture, and new workload characteristics. Further, several challenges are identified in building extreme scale supercomputers, such as reliability, I/O performance, and energy efficiency, which arguably can be mitigated by appropriate job scheduling strategies. In this study, we proposed an integrated job scheduling framework, aiming at addressing the issues and challenges in resource management for large-scale production supercomputers. We designed a set of new schemes and implemented it in a production resource manager. We conducted simulation-based evaluation using real job traces from production supercomputers. Experimental results show our schemes can effectively improve job scheduling regarding both user satisfaction and system utilization.
SUMMARY:An Integrated Job Scheduling Framework for Production Supercomputers
PRIORITY:3
END:VEVENT
END:VCALENDAR