Empirical performance evaluation of schedulers for cluster of workstations
Empirical performance evaluation of schedulers for cluster of workstations
复制标题
工作站集群调度程序的实证性能评估
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
P. Manuel
中科院分区：
文献类型：
--
作者：
Kalim Qureshi;Syed Munir Hussain Shah;P. Manuel
集群计算作为高性能计算的一种选择，正受到指数级的欢迎。这主要得益于其有效的性价比。资源管理系统（RMS）是有效管理机群资源的关键部件，对分布式并行系统的性能有着至关重要的作用，其中作业调度模块尤为重要。在本文中，我们已经经验性地评估了四个资源管理系统（SGE，TORQUE，MAUI和SLURM），特别侧重于作业调度组件。我们对这些路由器进行了更全面的评估，如吞吐量、CPU、内存和网络利用率。在3个不同规模的测试平台上，采用FCFS、Backfilling、Fair share和SJF调度技术进行了实验，并对不同调度技术进行了头对头比较，突出了RMS对调度技术性能的影响。从结果中可以看出，调度技术的性能之间的相对差异高达63%。我们的结论是，从实验中，有没有单一的选择RMS可以被确定为最好的，但SLURM表现优于其他在大多数情况下。
Cluster computing is receiving exponential popularity as a choice for high performance computing. This is mainly due to its effective cost performance ratio. Resource management systems (RMS) are the key component to manage the resources of clusters efficiently and have a very vital role in the performance of distributed parallel systems especially a job scheduling module. In this paper, we have empirically evaluated four resource management systems (SGE, TORQUE, and MAUI Scheduler and SLURM) with special focus on job scheduler component. These schedulers have been evaluated on a more comprehensive set of metrics such as throughput, CPU, memory and network utilization. Experiments were carried out on three different size testbeds with a range of scheduler configurations such as FCFS, Backfilling, Fair share and SJF scheduling techniques.A head-to-head comparison of different scheduling techniques has also been presented which highlights the effect of RMS on the performance of scheduling techniques. It has been observed from results that relative difference among the performance of scheduling techniques reached up to 63%. We conclude from the experiments that there is no single choice of RMS which can be identified as the best but SLURM performs better than others in most of the cases.