CMS multicore scheduling strategy

20th International Conference on Computing in High Energy and Nuclear Physics

物理学;计算机科学

Yzquierdo, Antonio Pérez-Calero^1,2 ; Hernández, Jose^2 ; Holzman, Burt^3 ; Majewski, Krista^3 ; McCrea, Alison^4

Port d'Informació Científica (PIC), Universität Autónoma de Barcelona, Bellaterra (Barcelona), Spain^1

Centro de Investigaciones Energéticas, Medioambientales y Tecnológicas, CIEMAT, Madrid, Spain^2

Fermi National Accelerator Laboratory, United States^3

University of California San Diego, United States^4

关键词: Dynamic partitioning;    Further development;    Memory requirements;    Memory-sharing;    Node scheduling;    Parallelizing;    Processor architectures;    Scheduling strategies;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/513/3/032074/pdf
DOI  :  10.1088/1742-6596/513/3/032074

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

In the next years, processor architectures based on much larger numbers of cores will be most likely the model to continue Moore's Law style throughput gains. This not only results in many more jobs in parallel running the LHC Run 1 era monolithic applications, but also the memory requirements of these processes push the workernode architectures to the limit. One solution is parallelizing the application itself, through forking and memory sharing or through threaded frameworks. CMS is following all of these approaches and has a comprehensive strategy to schedule multicore jobs on the GRID based on the glideinWMS submission infrastructure. The main component of the scheduling strategy, a pilot-based model with dynamic partitioning of resources that allows the transition to multicore or whole-node scheduling without disallowing the use of single-core jobs, is described. This contribution also presents the experiences made with the proposed multicore scheduling schema and gives an outlook of further developments working towards the restart of the LHC in 2015.