-
This site is deprecated and will be decommissioned shortly. For current information regarding HPC visit our new site: hpc.njit.edu
Difference between revisions of "ParallelFileSystem"
(Importing text file) |
(Importing text file) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 3: | Line 3: | ||
designed to store data across multiple networked servers. | designed to store data across multiple networked servers. | ||
| − | + | A PFS provides cluster nodes shared access to data in parallel. It enables | |
high performance by allowing system architects to use various storage technologies and high-speed | high performance by allowing system architects to use various storage technologies and high-speed | ||
interconnects. PFS also can scale well as storage needs grow. | interconnects. PFS also can scale well as storage needs grow. | ||
| Line 9: | Line 9: | ||
A PFS provides for concurrent access by multiple tasks of a parallel application to facilitate | A PFS provides for concurrent access by multiple tasks of a parallel application to facilitate | ||
high-performance access through simultaneous, coordinated input/output operations | high-performance access through simultaneous, coordinated input/output operations | ||
| − | between compute nodes and storage | + | between compute nodes and storage. |
A PFS breaks up a data set and distributes, or stripes, the blocks to multiple storage drives. Users | A PFS breaks up a data set and distributes, or stripes, the blocks to multiple storage drives. Users | ||
do not need to know the physical location of the data blocks to retrieve a file. The system uses a | do not need to know the physical location of the data blocks to retrieve a file. The system uses a | ||
global namespace to facilitate data access. | global namespace to facilitate data access. | ||
Latest revision as of 16:29, 12 September 2021
A parallel file system (PFS), also known as a clustered file system, is a type of storage system designed to store data across multiple networked servers.
A PFS provides cluster nodes shared access to data in parallel. It enables high performance by allowing system architects to use various storage technologies and high-speed interconnects. PFS also can scale well as storage needs grow.
A PFS provides for concurrent access by multiple tasks of a parallel application to facilitate high-performance access through simultaneous, coordinated input/output operations between compute nodes and storage.
A PFS breaks up a data set and distributes, or stripes, the blocks to multiple storage drives. Users do not need to know the physical location of the data blocks to retrieve a file. The system uses a global namespace to facilitate data access.
