main.c 3.9 KB

123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139
  1. /*
  2. * CFQ, or complete fairness queueing, disk scheduler.
  3. *
  4. * Based on ideas from a previously unfinished io
  5. * scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
  6. *
  7. * Copyright (C) 2003 Jens Axboe <axboe@kernel.dk>
  8. */
  9. #include <linux/module.h>
  10. #include <linux/slab.h>
  11. #include <linux/blkdev.h>
  12. #include <linux/elevator.h>
  13. #include <linux/jiffies.h>
  14. #include <linux/rbtree.h>
  15. #include <linux/ioprio.h>
  16. #include <linux/blktrace_api.h>
  17. #include "blk.h"
  18. #include "blk-cgroup.h"
  19. /*
  20. * tunables
  21. */
  22. /* max queue in one round of service */
  23. static const int cfq_quantum = 8;
  24. static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
  25. /* maximum backwards seek, in KiB */
  26. static const int cfq_back_max = 16 * 1024;
  27. /* penalty of a backwards seek */
  28. static const int cfq_back_penalty = 2;
  29. static const int cfq_slice_sync = HZ / 10;
  30. static int cfq_slice_async = HZ / 25;
  31. static const int cfq_slice_async_rq = 2;
  32. static int cfq_slice_idle = HZ / 125;
  33. static int cfq_group_idle = HZ / 125;
  34. static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
  35. static const int cfq_hist_divisor = 4;
  36. /*
  37. * offset from end of service tree
  38. */
  39. #define CFQ_IDLE_DELAY (HZ / 5)
  40. /*
  41. * below this threshold, we consider thinktime immediate
  42. */
  43. #define CFQ_MIN_TT (2)
  44. #define CFQ_SLICE_SCALE (5)
  45. #define CFQ_HW_QUEUE_MIN (5)
  46. #define CFQ_SERVICE_SHIFT 12
  47. #define CFQQ_SEEK_THR (sector_t)(8 * 100)
  48. #define CFQQ_CLOSE_THR (sector_t)(8 * 1024)
  49. #define CFQQ_SECT_THR_NONROT (sector_t)(2 * 32)
  50. #define CFQQ_SEEKY(cfqq) (hweight32(cfqq->seek_history) > 32/8)
  51. #define RQ_CIC(rq) icq_to_cic((rq)->elv.icq)
  52. #define RQ_CFQQ(rq) (struct cfq_queue *) ((rq)->elv.priv[0])
  53. #define RQ_CFQG(rq) (struct cfq_group *) ((rq)->elv.priv[1])
  54. static struct kmem_cache *cfq_pool;
  55. #define CFQ_PRIO_LISTS IOPRIO_BE_NR
  56. #define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
  57. #define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
  58. #define sample_valid(samples) ((samples) > 80)
  59. #define rb_entry_cfqg(node) rb_entry((node), struct cfq_group, rb_node)
  60. struct cfq_ttime {
  61. unsigned long last_end_request;
  62. unsigned long ttime_total;
  63. unsigned long ttime_samples;
  64. unsigned long ttime_mean;
  65. };
  66. /*
  67. * Most of our rbtree usage is for sorting with min extraction, so
  68. * if we cache the leftmost node we don't have to walk down the tree
  69. * to find it. Idea borrowed from Ingo Molnars CFS scheduler. We should
  70. * move this into the elevator for the rq sorting as well.
  71. */
  72. struct cfq_rb_root {
  73. struct rb_root rb;
  74. struct rb_node *left;
  75. unsigned count;
  76. unsigned total_weight;
  77. u64 min_vdisktime;
  78. struct cfq_ttime ttime;
  79. };
  80. #define CFQ_RB_ROOT (struct cfq_rb_root) { .rb = RB_ROOT, \
  81. .ttime = {.last_end_request = jiffies,},}
  82. /*
  83. * Per process-grouping structure
  84. */
  85. struct cfq_queue {
  86. /* reference count */
  87. int ref;
  88. /* various state flags, see below */
  89. unsigned int flags;
  90. /* parent cfq_data */
  91. struct cfq_data *cfqd;
  92. /* service_tree member */
  93. struct rb_node rb_node;
  94. /* service_tree key */
  95. unsigned long rb_key;
  96. /* prio tree member */
  97. struct rb_node p_node;
  98. /* prio tree root we belong to, if any */
  99. struct rb_root *p_root;
  100. /* sorted list of pending requests */
  101. struct rb_root sort_list;
  102. /* if fifo isn't expired, next request to serve */
  103. struct request *next_rq;
  104. /* requests queued in sort_list */
  105. int queued[2];
  106. /* currently allocated requests */
  107. int allocated[2];
  108. /* fifo list of requests in sort_list */
  109. struct list_head fifo;
  110. /* time when queue got scheduled in to dispatch first request. */
  111. unsigned long dispatch_start;
  112. unsigned int allocated_slice;
  113. unsigned int slice_dispatch;
  114. /* time when first request from queue completed and slice started. */
  115. unsigned long slice_start;
  116. unsigned long slice_end;
  117. long slice_resid;
  118. /* pending priority requests */
  119. int prio_pending;
  120. /* number of requests that are on the dispatch list or inside driver */
  121. int dispatched;
  122. /* io prio of this group */
  123. unsigned short ioprio, org_ioprio;