GekkoFS - A Temporary Distributed File System for HPC Applications
作者： Marc-Andre Vef , Nafiseh Moti , Tim SuB , Tommaso Tocci , Ramon Nou
DOI: 10.1109/CLUSTER.2018.00049
关键词: Scalability 、 Operating system 、 Metadata 、 Data structure 、 Computer science 、 File system 、 POSIX 、 Server 、 Throughput (business) 、 Distributed File System
摘要: We present GekkoFS, a temporary, highly-scalable burst buffer file system which has been specifically optimized for new access patterns of data-intensive High-Performance Computing (HPC) applications. The provides relaxed POSIX semantics, only offering features are actually required by most (not all) It is able to provide scalable I/O performance and reaches millions metadata operations already small number nodes, significantly outperforming the capabilities general-purpose parallel systems.
ieeecomputersociety.org参考文章(31)
Dennis Ritchie, Ken Thompson, The UNIX Time-Sharing System (Reprint). Communications of The ACM. ,vol. 26, pp. 84- 89 ,(1983)
Swapnil Patil, Garth Gibson, Scale and concurrency of GIGA+: file system directories with millions of files file and storage technologies. ,vol. 2011, pp. 13- 13 ,(2011) , 10.5555/1960475.1960488
Tony Hey, The Fourth Paradigm: Data-Intensive Scientific Discovery ,(2009)
Rob Latham, Rob Ross, Rajeev Thakur, The Impact of File Systems on MPI-IO Scalability Lecture Notes in Computer Science. pp. 87- 96 ,(2004) , 10.1007/978-3-540-30218-6_18
Jerome Soumagne, Dries Kimpe, Judicael Zounmevo, Mohamad Chaarawi, Quincey Koziol, Ahmad Afsahi, Robert Ross, Mercury: Enabling remote procedure call for high-performance computing international conference on cluster computing. pp. 1- 8 ,(2013) , 10.1109/CLUSTER.2013.6702617
Ning Liu, Jason Cope, Philip Carns, Christopher Carothers, Robert Ross, Gary Grider, Adam Crume, Carlos Maltzahn, On the role of burst buffers in leadership-class storage systems ieee conference on mass storage systems and technologies. pp. 1- 11 ,(2012) , 10.1109/MSST.2012.6232369
Robert Ross, Robert Latham, PVFS: a parallel file system conference on high performance computing (supercomputing). pp. 34- ,(2006) , 10.1145/1188455.1188490
Matthieu Dorier, Gabriel Antoniu, Rob Ross, Dries Kimpe, Shadi Ibrahim, CALCioM: Mitigating I/O Interference in HPC Systems through Cross-Application Coordination international parallel and distributed processing symposium. pp. 155- 164 ,(2014) , 10.1109/IPDPS.2014.27
Jay F. Lofstead, Scott Klasky, Karsten Schwan, Norbert Podhorszki, Chen Jin, Flexible IO and integration for scientific codes through the adaptable IO system (ADIOS) Proceedings of the 6th international workshop on Challenges of large applications in distributed environments - CLADE '08. pp. 15- 24 ,(2008) , 10.1145/1383529.1383533
Partho Nath, Anand Sivasubramaniam, Murali Vilayannur, Providing tunable consistency for a parallel file store file and storage technologies. pp. 2- 2 ,(2005) , 10.5555/1251028.1251030