期刊文献+

将参数扫描应用分布于网格的负载平衡方法

A Load Balancing Method for Distributing Parameter Sweep Applications on Grids
下载PDF
导出
摘要 为降低高性能计算网格中参数扫描应用的响应时间,基于负载平衡确定各网格节点分得任务的数目.用处理机需求与处理机数的比值表示网格节点的作业负载,用作业负载的均方差表示网格负载失衡度,并按降低网格负载失衡度确定参数扫描应用的任务分配.当参数应用的任务数不足以实现网格负载失衡时,选择作业负载较低的一组节点,并按负载平衡将该参数应用分布于这些节点.实验表明,基于负载平衡的调度可有效降低参数扫描应用的响应时间. To reduce the response time of a parameter sweep application on high-performance computational grids,the number of tasks allocated to each grid node is determined based on load balancing.Job load of each grid node is represented by the ratio of processor requirements to processor number,the grid load imbalance degree is represented by the mean square deviation of job loads,and the task allocations of a parameter sweep application are determined by reducing the grid load imbalance degree.When the task number of a parameter application is not adequate to implement the grid load balancing,a set of nodes with lower job loads are selected,and the parameter application will be distributed on these nodes according to load balancing.Experiments show the load balancing-based scheduling can effectively reduce the response time of parameter sweep applications.
出处 《电子学报》 EI CAS CSCD 北大核心 2007年第11期2211-2214,共4页 Acta Electronica Sinica
关键词 计算网格 参数扫描应用 作业负载 网格负载平衡 computational grid parameter sweep application job load grid load balancing
  • 相关文献

参考文献9

  • 1Abramson D, Sosic R, Giddy J, et al. Nimrod: a tool for performing parametised simulations using distributed workstations [A]. Proc of the 4th IEEE Symposium on High Performance Distributed Computing[ C]. Washington: IEEE Computer Society, 1995.112-121.
  • 2Buyya R, Abramson D,Giddy J.Nimrod/G: an architecture for a resource management and scheduling system in a global computalional grid[A]. Proc of the 4th International Conference/ Exhibition on High Performance Computing in the Asia-Pacific Region[C]. Washington: IEEE Computer Society, 2000 ( 1 ): 283-289.
  • 3Shava S, Walfredo C, Jaime F, et al. Combiniag workstations and supercomputers to support grid applications: The parallel tomography experience [ A ]. Proc of the 9th Heterogeneous Computing Workshop [C ]. Washington: IEEE Computer Society,2000.241-252.
  • 4Huedo E,Montero R S, Llorente I M. Experiences on adaptive grid scheduling of parameter sweep applications [ A ]. Proc of the 12th Euromicro Conference on Parallel, Distributed and Network-Based Processing [ C ]. Washington: IEEE Computer Society, 2004.28-33.
  • 5Casanova H, Legrand A, Zagorodnov D, et al. Heuristics for scheduling parameter sweep applications in grid environments [ A ]. Proc of the 9th Heterogeneous Computing Workshop [ C]. Washington: IEEE Computer Society,2000.349-363.
  • 6王庆江,桂小林,郑守淇.参数扫描应用的网格自适应调度[J].西安交通大学学报,2004,38(2):111-114. 被引量:1
  • 7Ememann C, Hamscher V,Schwiegelshohn U,et al. On advantages of grid computing for parallel job scheduling[A]. Proc of the 2nd IEEF/ACM International Symposium on Cluster Computing and the Grid[C]. Washington: IEEE Computer Society, 2002.31-38.
  • 8Bailey D,Barszcz E, Barton J,et al. The NAS Parallel Benchmarks [ R/OL ]. http://www. has. nasa. gov/News/Techreports/1994/PDF/RNR-94-007. pdf, 2006-04-12.
  • 9Mu' alem A W, Feitelson D G. Utilization,predictability, workloads, and user runtime estimates in scheduling the IBM SP2 with backfilling [ J ]. IEEE Transactions on Parallel and Distributed Systems, 2001,2(6) :529-543.

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部