Kconfig.iosched 3.3 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117
  1. if BLOCK
  2. menu "IO Schedulers"
  3. config IOSCHED_NOOP
  4. bool
  5. default y
  6. ---help---
  7. The no-op I/O scheduler is a minimal scheduler that does basic merging
  8. and sorting. Its main uses include non-disk based block devices like
  9. memory devices, and specialised software or hardware environments
  10. that do their own scheduling and require only minimal assistance from
  11. the kernel.
  12. config IOSCHED_TEST
  13. tristate "Test I/O scheduler"
  14. depends on DEBUG_FS
  15. default m
  16. ---help---
  17. The test I/O scheduler is a duplicate of the noop scheduler with
  18. addition of test utlity.
  19. It allows testing a block device by dispatching specific requests
  20. according to the test case and declare PASS/FAIL according to the
  21. requests completion error code.
  22. config IOSCHED_DEADLINE
  23. tristate "Deadline I/O scheduler"
  24. default y
  25. ---help---
  26. The deadline I/O scheduler is simple and compact. It will provide
  27. CSCAN service with FIFO expiration of requests, switching to
  28. a new point in the service tree and doing a batch of IO from there
  29. in case of expiry.
  30. config IOSCHED_CFQ
  31. tristate "CFQ I/O scheduler"
  32. # If BLK_CGROUP is a module, CFQ has to be built as module.
  33. depends on (BLK_CGROUP=m && m) || !BLK_CGROUP || BLK_CGROUP=y
  34. default y
  35. ---help---
  36. The CFQ I/O scheduler tries to distribute bandwidth equally
  37. among all processes in the system. It should provide a fair
  38. and low latency working environment, suitable for both desktop
  39. and server systems.
  40. This is the default I/O scheduler.
  41. Note: If BLK_CGROUP=m, then CFQ can be built only as module.
  42. config CFQ_GROUP_IOSCHED
  43. bool "CFQ Group Scheduling support"
  44. depends on IOSCHED_CFQ && BLK_CGROUP
  45. default n
  46. ---help---
  47. Enable group IO scheduling in CFQ.
  48. config IOSCHED_BFQ
  49. tristate "BFQ I/O scheduler"
  50. depends on EXPERIMENTAL
  51. default n
  52. ---help---
  53. The BFQ I/O scheduler tries to distribute bandwidth among
  54. all processes according to their weights.
  55. It aims at distributing the bandwidth as desired, independently of
  56. the disk parameters and with any workload. It also tries to
  57. guarantee low latency to interactive and soft real-time
  58. applications. If compiled built-in (saying Y here), BFQ can
  59. be configured to support hierarchical scheduling.
  60. config CGROUP_BFQIO
  61. bool "BFQ hierarchical scheduling support"
  62. depends on CGROUPS && IOSCHED_BFQ=y
  63. default n
  64. ---help---
  65. Enable hierarchical scheduling in BFQ, using the cgroups
  66. filesystem interface. The name of the subsystem will be
  67. bfqio.
  68. choice
  69. prompt "Default I/O scheduler"
  70. default DEFAULT_CFQ
  71. help
  72. Select the I/O scheduler which will be used by default for all
  73. block devices.
  74. config DEFAULT_DEADLINE
  75. bool "Deadline" if IOSCHED_DEADLINE=y
  76. config DEFAULT_CFQ
  77. bool "CFQ" if IOSCHED_CFQ=y
  78. config DEFAULT_BFQ
  79. bool "BFQ" if IOSCHED_BFQ=y
  80. help
  81. Selects BFQ as the default I/O scheduler which will be
  82. used by default for all block devices.
  83. The BFQ I/O scheduler aims at distributing the bandwidth
  84. as desired, independently of the disk parameters and with
  85. any workload. It also tries to guarantee low latency to
  86. interactive and soft real-time applications.
  87. config DEFAULT_NOOP
  88. bool "No-op"
  89. endchoice
  90. config DEFAULT_IOSCHED
  91. string
  92. default "deadline" if DEFAULT_DEADLINE
  93. default "cfq" if DEFAULT_CFQ
  94. default "bfq" if DEFAULT_BFQ
  95. default "noop" if DEFAULT_NOOP
  96. endmenu
  97. endif