그리드 컴퓨팅의 다중 큐 하이브리드 작업스케줄링 기법 = Multi-queue Hybrid Job Scheduling Mechanismin Grid Computing

다국어 초록 (Multilingual Abstract)

computing is a service that share geographically distributed computing resources through high speed network. In this paper, we propose hybrid scheduling scheme which considers not only meta-scheduling scheme to distribute the job between the nodes of grid computing system but also the job scheduling to distribute the job within the local nodes.According to the number of processors needed and expected execution time, the job with high priority is allocated to job queue while the one with low priority and remote job are allocated to backfill queue.We evaluate the proposing scheme through the various experiments and the results show that the utilization of grid computing system increases and the job slowdown decreases.

국문 초록 (Abstract)

컴퓨팅은 지리적으로 분산된 컴퓨팅 자원들을 네트워크로 연동시켜 서로 공유 될 수 있도록 해주는 서비스이다. 본 논문에서는 그리드 컴퓨팅 시스템을 구성하는 전체 노드를 대상으로 작업을 분배하는 메타 스케줄링 정책과 특정 한 개의 노드 내에서 작업을 분배하는 작업 스케줄링을 동시에 고려하는 하이브리드 스케줄링 기법을 제안한다. 그리드 컴퓨팅 노드로 제출된 작업을 필요 프로세서 수와 예상 작업수행 시간에 따라 구분하여 우선순위가 높은 작업은 작업 큐(Job Queue)로, 우선순위가 낮은 작업과 원거리 작업은 백필 큐(Backfill Queue)로 할당시킴으로써, 그리드 컴퓨팅 시스템의 성능을 높이는 방법을 연구한다. 다양한 실험을 통하여 제안된 기법들의 성능을 평가하며, 그리드 컴퓨팅 시스템의 이용률이 높아지고, 작업 지연시간이 감소됨을 확인한다.

참고문헌 (Reference)

1 "http://www.legion.org"

2 A. Mualem, "Utilization, Predictability, Workloads and User Run time Estimates in Scheduling the IBM SP2 with Backfilling" 12 (12): 529-543, 2001

3 D. G. Feitelson, "Theory and Practice in Parallel Job Schedulin" 1291 : 1-34, 1997

4 B. Bode, "The Portable Batch Scheduler and the MauiScheduler on Linux Clusters" 2000

5 D. Talby, "Supporting Priorities and Improving Utilization of the IBM SP2 Scheduler Using Slack-based Backfilling" 513-517, 1999

6 W. A. Ward Jr, "Scheduling Jobs on Parallel Systems Using a Relaxed Backfill Strategy" 88-102, 2002

7 B. Lawson, "Multiple-queue Backfilling Scheduling with Priorities and Reservations for Parallel Systems" 72-87, 2002

8 D. Feitelson, "Logs of Real Parallel Workloads from Production Systems"

9 D. Zotkin, "Job-Length Estimation and Performance in Backfilling Schedulers" 1999

10 H. Shan, "Job Superscheduler Architecture and Performance in Computational Grid Environments" 2003

11 K. Li, "Job Scheduling for Grid Computing on Metacomputers" 2005

12 D. G. Feitelson, "Improved Utilization and Responsiveness with Gang Scheduling" 1291 : 238-261, 1997

13 O. H. Ibarra,et al, "Heuristic Algorithm for Scheduling Independent Tasks on Nonidentical Processors" 24 no. 2 : 280-289, apr.1977.

14 I. Foster, "Grid Services for Distributed System Integration" 35 (35): 37-46, 2002

15 I. Foster, "Globus: A Metacomputing Infrastructure Toolkit" 11 (11): 115-128, 1997

16 V. Hamscher, "Evaluation of Job-Scheduling Strategies for Grid Computing" 1971 : 191-202, 2000

17 V. Subramani, "Distributed Job Scheduling on Computational Grids Using Multiple Simultaneous Requests" 359-368, 2002

18 Q. Wang, "De-centralized Job Scheduling on Computational Grids Using Distributed Backfilling" 3251 : 285-292, 2004

19 S. Srinivasan, "Characterization of Backfilling Strategies for Parallel Jobs Scheduling" 514-522, 2002

20 K. Krauter, "A Taxonomy and Survey of Grid Resource Management Systems for Distributed Computing" 32 (32): 135-164, 2002

21 R. McCann,et al, "A Dynamic Processor Allocation Policy for Multiprogrammed Sharedmemory Multiprocessors" 11 no. 2 : 146-178, 1993.05