Abstract:

With the expansion of the scale of high performance computer systems, job launch consumes more and more time, and the task start time gradually becomes an important factor affecting system scalability. Meanwhile, the rapid increase of the number of components brings failures more frequently, resulting in repeated submission of parallel applications before their completion. Therefore, the task start efficiency has a direct impact on the effective utilization of computing resources and user experience. A hierarchical parallel job launch model is designed and its performance under different job scales is tested, analyzed and optimized. After optimization, the proposed model can support a large-scale system with tasks start and control efficiently and have good scalability.

Key words: job task launch;hierarchical management;virtualization;network data optimization;scalability