| Linus Torvalds | 1da177e | 2005-04-16 15:20:36 -0700 | [diff] [blame^] | 1 | |
| 2 | menu "IO Schedulers" |
| 3 | |
| 4 | config IOSCHED_NOOP |
| 5 | bool |
| 6 | default y |
| 7 | ---help--- |
| 8 | The no-op I/O scheduler is a minimal scheduler that does basic merging |
| 9 | and sorting. Its main uses include non-disk based block devices like |
| 10 | memory devices, and specialised software or hardware environments |
| 11 | that do their own scheduling and require only minimal assistance from |
| 12 | the kernel. |
| 13 | |
| 14 | config IOSCHED_AS |
| 15 | tristate "Anticipatory I/O scheduler" |
| 16 | default y |
| 17 | ---help--- |
| 18 | The anticipatory I/O scheduler is the default disk scheduler. It is |
| 19 | generally a good choice for most environments, but is quite large and |
| 20 | complex when compared to the deadline I/O scheduler, it can also be |
| 21 | slower in some cases especially some database loads. |
| 22 | |
| 23 | config IOSCHED_DEADLINE |
| 24 | tristate "Deadline I/O scheduler" |
| 25 | default y |
| 26 | ---help--- |
| 27 | The deadline I/O scheduler is simple and compact, and is often as |
| 28 | good as the anticipatory I/O scheduler, and in some database |
| 29 | workloads, better. In the case of a single process performing I/O to |
| 30 | a disk at any one time, its behaviour is almost identical to the |
| 31 | anticipatory I/O scheduler and so is a good choice. |
| 32 | |
| 33 | config IOSCHED_CFQ |
| 34 | tristate "CFQ I/O scheduler" |
| 35 | default y |
| 36 | ---help--- |
| 37 | The CFQ I/O scheduler tries to distribute bandwidth equally |
| 38 | among all processes in the system. It should provide a fair |
| 39 | working environment, suitable for desktop systems. |
| 40 | |
| 41 | endmenu |