본문 바로가기
  • Home

Real-Time Job Scheduling Strategy for Grid Computing

  • Journal of The Korea Society of Computer and Information
  • Abbr : JKSCI
  • 2010, 15(2), pp.1-8
  • Publisher : The Korean Society Of Computer And Information
  • Research Area : Engineering > Computer Science

최준영 1 Won Joo Lee 2 Chang Ho Jeon 3

1삼성전자
2인하공업전문대학
3한양대학교

Accredited

ABSTRACT

In this paper, we propose a scheduling strategy for grid environment that reduces resource cost. This strategy considers resource cost and job failure rate to efficiently allocate local computing resources. The key idea of our strategy is that we use two-level scheduling using remote and local scheduler. The remote scheduler determines the expected total execution times of jobs using the current network and local system status maintained in its resource database and allocates jobs with minimum total execution time to local systems. The local scheduler recalculates the waiting time and execution time of allocated job and uses it to determine whether the job can be processed within the specified deadline. If it cannot finish in time, the job is migrated other local systems. Through simulation, we show that it is more effective to reduce the resource cost than the previous Greedy strategy. We also show that the proposed strategy improves the performance compared to previous Greedy strategy.

Citation status

* References for papers published after 2022 are currently being built.