多集群并行作业的性能监测及分析  

Performance Monitoring and Analysis on Multi-cluster Parallel Jobs

作　　者：陈诗然[1] 胡凯[1] 张伟[1] 张璐[1] 

机构地区：[1]北京航空航天大学计算机学院,北京100083

出　　处：《计算机工程》2008年第13期75-77,共3页Computer Engineering

摘　　要：介绍一种多集群计算模式,在分析了多集群系统结构灵活、具有可重组性等特点的基础上,研究适用于该模式的并行作业性能监测分析方法与技术,设计和实现了一个并行作业性能监测分析工具。它采用动态性能分析方法,遵循分布式软件设计架构,具有高内聚、低耦合的模块组织结构,运行验证表明其能够在多集群计算模式下有效工作。A multi-cluster computing model is introduced. In the analysis on the basis of the multi-cluster system features, which include flexible architecture and reconfigurability, the methods and technologies of performance monitoring and analysis, which is applicable to this model, are researched. A performance monitoring and analysis tool of parallel jobs is designed and implemented. In this tool, dynamic performance analysis method is used, distributed software design framework is followed, a high cohesion and low coupling structure is designed. Operation results show it can work effectively in the multi-cluster computing model.

关 键 词：多集群 并行作业 性能监测 性能分析 插桩 

分 类 号：TP311[自动化与计算机技术—计算机软件与理论]