PLFS
Autor: | Gary Grider, Milo Polte, Ben McClelland, Meghan Wingate, James Nunez, John M. Bent, Paul Nowoczynski, Garth A. Gibson |
---|---|
Rok vydání: | 2009 |
Předmět: |
FOS: Computer and information sciences
File system Computer science Computer file Distributed computing Device file computer.file_format Everything is a file computer.software_genre Unix file types Virtual file system Torrent file File Control Block Self-certifying File System Journaling file system Data file Data_FILES Operating system Versioning file system 89999 Information and Computing Sciences not elsewhere classified Fork (file system) computer File system fragmentation |
Zdroj: | SC |
DOI: | 10.1145/1654059.1654081 |
Popis: | Parallel applications running across thousands of processors must protect themselves from inevitable system failures. Many applications insulate themselves from failures by checkpointing. For many applications, checkpointing into a shared single file is most convenient. With such an approach, the size of writes are often small and not aligned with file system boundaries. Unfortunately for these applications, this preferred data layout results in pathologically poor performance from the underlying file system which is optimized for large, aligned writes to non-shared files. To address this fundamental mismatch, we have developed a virtual parallel log structured file system, PLFS. PLFS remaps an application’s preferred data layout into one which is optimized for the underlying file system. Through testing on PanFS, Lustre, and GPFS, we have seen that this layer of indirection and reorganization can reduce checkpoint time by an order of magnitude for several important benchmarks and real applications without any application modification. |
Databáze: | OpenAIRE |
Externí odkaz: |