Exploiting in-kernel data paths to improve i/o throughput and cpu availability (1993) [51 citations — 4 self]
by Kevin Fall, Joseph Pasquale
In Proceedings of the Winter 1993 USENIX Conference
http://digitalassets.lib.berkeley.edu/techreports/ucb/text/S2K-92-17.ps
Add To MetaCart
Abstract:
We present the motivation, design, implementation, and performance evaluation of a UNIX kernel mechanism capable of establishing fast in-kernel data pathways between I/O objects. A new system call, splice() moves data asynchronously and without user-process intervention to and from I/O objects specified by file descriptors. Performance measurements indicate improved I/O throughput and increased CPU availability attributable to reduce context switch and data copying overhead.
Citations
| 217 | A Stream Input-Output System – Ritchie - 1984 |
| 204 | Inside Windows NT – Custer - 1993 |
| 125 | Scheduling and IPC mechanisms for continuous media – Govindan, Anderson - 1991 |
| 31 | An I/O System for Mach 3.0 – Forin, Golub, et al. - 1991 |
| 9 | I/O System Design for Intensive Multimedia I/O – Pasquale - 1992 |
| 7 | Distributed multimedia: How can the necessary data rates be supported – Pasieka, Crumley, et al. - 1991 |
| 2 | Interprocess Communication in the 8th Edition Unix System – Presotto, Ritchie - 1985 |
| 1 | DECStation 5000/200 KN02 System Module Functional Specification – Corporation - 1990 |

