Parallel I/O
Parallel I/O, in the context of a computer, means the performance of multiple input/output operations at the same time, for instance simultaneously outputs to storage devices and display devices.[1] It is a fundamental feature of operating systems.[2]
One particular instance is parallel writing of data to disk; when file data is spread across multiple disks, for example in a RAID array, one can store multiple parts of the data at the same time, thereby achieving higher write speeds than with a single device.[3][4]
Other ways of parallel access to data include: Parallel Virtual File System, Lustre, GFS etc.
Features
Scientific computing
It is used for scientific computing and not for databases. It break up support into multiple layers including High level I/O library, Middleware layer and Parallel file system.[5] Parallel File System manages the single view, maintains logical space and provides access to data files.[6]
Storage
A single file may be stripped across one or more object storage target, which increases the bandwidth while accessing the file and available disk space.[7] The caches are larger in Parallel I/O and shared through distributed memory systems.[8]
Breakthroughs
Companies have been running Parallel I/O on their servers to achieve results with regard to price and performance. Datacore’s SANsymphony system recorded $0.08/IOPS on a system, which was lesser than the competitors.[9]
See also
References
- ^ "Parallel I/O" (PDF). Johns Hopkins University.
- ^ "Introduction to Parallel I/O" (PDF). Oak Ridge National Laboratory.
- ^ "Introduction: The Parallel I/O Stack" (PDF). Cornell University.
- ^ "Introduction to Parallel I/O". The University of Texas at Austin.
- ^ "Parallel I/O". Scientific Computing Department.
- ^ "A Comprehensive Look at High Performance Parallel I/O". Berkeley Lab.
- ^ John Webster (9 December 2015). "The Rebirth of Parallel I/O". Forbes.
- ^ "The significance of parallel I/O in data storage". Techtarget.
- ^ "DataCore pushing parallel IO, and puts the cores to work". The Register. 27 October 2015.
 | This computing article is a stub. You can help Wikipedia by expanding it. |