Expectations of the High Performance Computing Cluster File System Selection

被引:0
作者
Aladyshev, O. S. [1 ]
Shabanov, B. M. [1 ]
Zakharchenko, A. V. [1 ]
机构
[1] Russian Acad Sci, Joint Supercomp Ctr, Sci Res Inst Syst Anal, Moscow 119334, Russia
关键词
parallel file systems; supercomputers; high performance computing; distributed locking; I/O operations;
D O I
10.1134/S1995080223120041
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
When constructing a high-performance computing cluster, one of the most pressing issues is ensuring efficient organization of the external storage systems. Such systems consist of both hardware and software components. The software component is a parallel file system, and consists of server and client parts. The article explores the principles of operating parallel file systems: mechanisms of data sharing between clients; metadata and data maintenance methods; as well as aspects of selecting a parallel file system for a high performance cluster computing cluster. We have had the opportunity to test some solutions on the large supercomputers of Joint Supercomputer Center of the Russian Academy of Sciences (JSCC RAS) and develop a basic model for file data flow in HPC cluster.
引用
收藏
页码:5132 / 5147
页数:16
相关论文
共 17 条
[1]   Influence of External Memory Characteristics of Supercomputer Complexes on Parallel Programs Execution [J].
Aladyshev, O. S. ;
Kiselev, E. A. ;
Zakharchenko, A. V. ;
Shabanov, B. M. ;
Savin, G. I. .
LOBACHEVSKII JOURNAL OF MATHEMATICS, 2021, 42 (11) :2493-2502
[2]  
[Anonymous], 2000, VERITAS SANPoint Direct File Access, Whitepaper
[3]  
Barry A. P., 2000, P 17 IEEE S MASS STO
[4]  
Brooks Ch., 2001, Patent No. 246146
[5]  
Choi S., 2010, P 10 IEEE INT C COMP
[6]  
Hildebrand D., 2014, CITI Tech. Report No. 06-06
[7]  
Lad S. S., 2015, Int. J. Sci. Eng. Appl. Sci.
[8]   Petal: Distributed virtual disks [J].
Lee, EK ;
Thekkath, CA .
ACM SIGPLAN NOTICES, 1996, 31 (09) :84-92
[9]  
Preslan K. W., 1999, P 16 IEEE MASS STORA
[10]  
Schmuck F., 2002, P C FILE STORAGE TEC