forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathblk-throttle.c
2388 lines (2004 loc) · 64.2 KB
/
blk-throttle.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Interface for controlling IO bandwidth on a request queue
*
* Copyright (C) 2010 Vivek Goyal <[email protected]>
*/
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/blktrace_api.h>
#include <linux/blk-cgroup.h>
#include "blk.h"
/* Max dispatch from a group in 1 round */
static int throtl_grp_quantum = 8;
/* Total max dispatch from all groups in one round */
static int throtl_quantum = 32;
/* Throttling is performed over a slice and after that slice is renewed */
#define DFL_THROTL_SLICE_HD (HZ / 10)
#define DFL_THROTL_SLICE_SSD (HZ / 50)
#define MAX_THROTL_SLICE (HZ)
#define DFL_IDLE_THRESHOLD_SSD (1000L) /* 1 ms */
#define DFL_IDLE_THRESHOLD_HD (100L * 1000) /* 100 ms */
#define MAX_IDLE_TIME (5L * 1000 * 1000) /* 5 s */
/* default latency target is 0, eg, guarantee IO latency by default */
#define DFL_LATENCY_TARGET (0)
#define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
static struct blkcg_policy blkcg_policy_throtl;
/* A workqueue to queue throttle related work */
static struct workqueue_struct *kthrotld_workqueue;
/*
* To implement hierarchical throttling, throtl_grps form a tree and bios
* are dispatched upwards level by level until they reach the top and get
* issued. When dispatching bios from the children and local group at each
* level, if the bios are dispatched into a single bio_list, there's a risk
* of a local or child group which can queue many bios at once filling up
* the list starving others.
*
* To avoid such starvation, dispatched bios are queued separately
* according to where they came from. When they are again dispatched to
* the parent, they're popped in round-robin order so that no single source
* hogs the dispatch window.
*
* throtl_qnode is used to keep the queued bios separated by their sources.
* Bios are queued to throtl_qnode which in turn is queued to
* throtl_service_queue and then dispatched in round-robin order.
*
* It's also used to track the reference counts on blkg's. A qnode always
* belongs to a throtl_grp and gets queued on itself or the parent, so
* incrementing the reference of the associated throtl_grp when a qnode is
* queued and decrementing when dequeued is enough to keep the whole blkg
* tree pinned while bios are in flight.
*/
struct throtl_qnode {
struct list_head node; /* service_queue->queued[] */
struct bio_list bios; /* queued bios */
struct throtl_grp *tg; /* tg this qnode belongs to */
};
struct throtl_service_queue {
struct throtl_service_queue *parent_sq; /* the parent service_queue */
/*
* Bios queued directly to this service_queue or dispatched from
* children throtl_grp's.
*/
struct list_head queued[2]; /* throtl_qnode [READ/WRITE] */
unsigned int nr_queued[2]; /* number of queued bios */
/*
* RB tree of active children throtl_grp's, which are sorted by
* their ->disptime.
*/
struct rb_root pending_tree; /* RB tree of active tgs */
struct rb_node *first_pending; /* first node in the tree */
unsigned int nr_pending; /* # queued in the tree */
unsigned long first_pending_disptime; /* disptime of the first tg */
struct timer_list pending_timer; /* fires on first_pending_disptime */
};
enum tg_state_flags {
THROTL_TG_PENDING = 1 << 0, /* on parent's pending tree */
THROTL_TG_WAS_EMPTY = 1 << 1, /* bio_lists[] became non-empty */
};
#define rb_entry_tg(node) rb_entry((node), struct throtl_grp, rb_node)
enum {
LIMIT_LOW,
LIMIT_MAX,
LIMIT_CNT,
};
struct throtl_grp {
/* must be the first member */
struct blkg_policy_data pd;
/* active throtl group service_queue member */
struct rb_node rb_node;
/* throtl_data this group belongs to */
struct throtl_data *td;
/* this group's service queue */
struct throtl_service_queue service_queue;
/*
* qnode_on_self is used when bios are directly queued to this
* throtl_grp so that local bios compete fairly with bios
* dispatched from children. qnode_on_parent is used when bios are
* dispatched from this throtl_grp into its parent and will compete
* with the sibling qnode_on_parents and the parent's
* qnode_on_self.
*/
struct throtl_qnode qnode_on_self[2];
struct throtl_qnode qnode_on_parent[2];
/*
* Dispatch time in jiffies. This is the estimated time when group
* will unthrottle and is ready to dispatch more bio. It is used as
* key to sort active groups in service tree.
*/
unsigned long disptime;
unsigned int flags;
/* are there any throtl rules between this group and td? */
bool has_rules[2];
/* internally used bytes per second rate limits */
uint64_t bps[2][LIMIT_CNT];
/* user configured bps limits */
uint64_t bps_conf[2][LIMIT_CNT];
/* internally used IOPS limits */
unsigned int iops[2][LIMIT_CNT];
/* user configured IOPS limits */
unsigned int iops_conf[2][LIMIT_CNT];
/* Number of bytes disptached in current slice */
uint64_t bytes_disp[2];
/* Number of bio's dispatched in current slice */
unsigned int io_disp[2];
unsigned long last_low_overflow_time[2];
uint64_t last_bytes_disp[2];
unsigned int last_io_disp[2];
unsigned long last_check_time;
unsigned long latency_target; /* us */
/* When did we start a new slice */
unsigned long slice_start[2];
unsigned long slice_end[2];
unsigned long last_finish_time; /* ns / 1024 */
unsigned long checked_last_finish_time; /* ns / 1024 */
unsigned long avg_idletime; /* ns / 1024 */
unsigned long idletime_threshold; /* us */
};
/* We measure latency for request size from <= 4k to >= 1M */
#define LATENCY_BUCKET_SIZE 9
struct latency_bucket {
unsigned long total_latency; /* ns / 1024 */
int samples;
};
struct avg_latency_bucket {
unsigned long latency; /* ns / 1024 */
bool valid;
};
struct throtl_data
{
/* service tree for active throtl groups */
struct throtl_service_queue service_queue;
struct request_queue *queue;
/* Total Number of queued bios on READ and WRITE lists */
unsigned int nr_queued[2];
unsigned int throtl_slice;
/* Work for dispatching throttled bios */
struct work_struct dispatch_work;
unsigned int limit_index;
bool limit_valid[LIMIT_CNT];
unsigned long dft_idletime_threshold; /* us */
unsigned long low_upgrade_time;
unsigned long low_downgrade_time;
unsigned int scale;
struct latency_bucket tmp_buckets[LATENCY_BUCKET_SIZE];
struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
struct latency_bucket __percpu *latency_buckets;
unsigned long last_calculate_time;
bool track_bio_latency;
};
static void throtl_pending_timer_fn(unsigned long arg);
static inline struct throtl_grp *pd_to_tg(struct blkg_policy_data *pd)
{
return pd ? container_of(pd, struct throtl_grp, pd) : NULL;
}
static inline struct throtl_grp *blkg_to_tg(struct blkcg_gq *blkg)
{
return pd_to_tg(blkg_to_pd(blkg, &blkcg_policy_throtl));
}
static inline struct blkcg_gq *tg_to_blkg(struct throtl_grp *tg)
{
return pd_to_blkg(&tg->pd);
}
/**
* sq_to_tg - return the throl_grp the specified service queue belongs to
* @sq: the throtl_service_queue of interest
*
* Return the throtl_grp @sq belongs to. If @sq is the top-level one
* embedded in throtl_data, %NULL is returned.
*/
static struct throtl_grp *sq_to_tg(struct throtl_service_queue *sq)
{
if (sq && sq->parent_sq)
return container_of(sq, struct throtl_grp, service_queue);
else
return NULL;
}
/**
* sq_to_td - return throtl_data the specified service queue belongs to
* @sq: the throtl_service_queue of interest
*
* A service_queue can be embedded in either a throtl_grp or throtl_data.
* Determine the associated throtl_data accordingly and return it.
*/
static struct throtl_data *sq_to_td(struct throtl_service_queue *sq)
{
struct throtl_grp *tg = sq_to_tg(sq);
if (tg)
return tg->td;
else
return container_of(sq, struct throtl_data, service_queue);
}
/*
* cgroup's limit in LIMIT_MAX is scaled if low limit is set. This scale is to
* make the IO dispatch more smooth.
* Scale up: linearly scale up according to lapsed time since upgrade. For
* every throtl_slice, the limit scales up 1/2 .low limit till the
* limit hits .max limit
* Scale down: exponentially scale down if a cgroup doesn't hit its .low limit
*/
static uint64_t throtl_adjusted_limit(uint64_t low, struct throtl_data *td)
{
/* arbitrary value to avoid too big scale */
if (td->scale < 4096 && time_after_eq(jiffies,
td->low_upgrade_time + td->scale * td->throtl_slice))
td->scale = (jiffies - td->low_upgrade_time) / td->throtl_slice;
return low + (low >> 1) * td->scale;
}
static uint64_t tg_bps_limit(struct throtl_grp *tg, int rw)
{
struct blkcg_gq *blkg = tg_to_blkg(tg);
struct throtl_data *td;
uint64_t ret;
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return U64_MAX;
td = tg->td;
ret = tg->bps[rw][td->limit_index];
if (ret == 0 && td->limit_index == LIMIT_LOW)
return tg->bps[rw][LIMIT_MAX];
if (td->limit_index == LIMIT_MAX && tg->bps[rw][LIMIT_LOW] &&
tg->bps[rw][LIMIT_LOW] != tg->bps[rw][LIMIT_MAX]) {
uint64_t adjusted;
adjusted = throtl_adjusted_limit(tg->bps[rw][LIMIT_LOW], td);
ret = min(tg->bps[rw][LIMIT_MAX], adjusted);
}
return ret;
}
static unsigned int tg_iops_limit(struct throtl_grp *tg, int rw)
{
struct blkcg_gq *blkg = tg_to_blkg(tg);
struct throtl_data *td;
unsigned int ret;
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && !blkg->parent)
return UINT_MAX;
td = tg->td;
ret = tg->iops[rw][td->limit_index];
if (ret == 0 && tg->td->limit_index == LIMIT_LOW)
return tg->iops[rw][LIMIT_MAX];
if (td->limit_index == LIMIT_MAX && tg->iops[rw][LIMIT_LOW] &&
tg->iops[rw][LIMIT_LOW] != tg->iops[rw][LIMIT_MAX]) {
uint64_t adjusted;
adjusted = throtl_adjusted_limit(tg->iops[rw][LIMIT_LOW], td);
if (adjusted > UINT_MAX)
adjusted = UINT_MAX;
ret = min_t(unsigned int, tg->iops[rw][LIMIT_MAX], adjusted);
}
return ret;
}
#define request_bucket_index(sectors) \
clamp_t(int, order_base_2(sectors) - 3, 0, LATENCY_BUCKET_SIZE - 1)
/**
* throtl_log - log debug message via blktrace
* @sq: the service_queue being reported
* @fmt: printf format string
* @args: printf args
*
* The messages are prefixed with "throtl BLKG_NAME" if @sq belongs to a
* throtl_grp; otherwise, just "throtl".
*/
#define throtl_log(sq, fmt, args...) do { \
struct throtl_grp *__tg = sq_to_tg((sq)); \
struct throtl_data *__td = sq_to_td((sq)); \
\
(void)__td; \
if (likely(!blk_trace_note_message_enabled(__td->queue))) \
break; \
if ((__tg)) { \
char __pbuf[128]; \
\
blkg_path(tg_to_blkg(__tg), __pbuf, sizeof(__pbuf)); \
blk_add_trace_msg(__td->queue, "throtl %s " fmt, __pbuf, ##args); \
} else { \
blk_add_trace_msg(__td->queue, "throtl " fmt, ##args); \
} \
} while (0)
static void throtl_qnode_init(struct throtl_qnode *qn, struct throtl_grp *tg)
{
INIT_LIST_HEAD(&qn->node);
bio_list_init(&qn->bios);
qn->tg = tg;
}
/**
* throtl_qnode_add_bio - add a bio to a throtl_qnode and activate it
* @bio: bio being added
* @qn: qnode to add bio to
* @queued: the service_queue->queued[] list @qn belongs to
*
* Add @bio to @qn and put @qn on @queued if it's not already on.
* @qn->tg's reference count is bumped when @qn is activated. See the
* comment on top of throtl_qnode definition for details.
*/
static void throtl_qnode_add_bio(struct bio *bio, struct throtl_qnode *qn,
struct list_head *queued)
{
bio_list_add(&qn->bios, bio);
if (list_empty(&qn->node)) {
list_add_tail(&qn->node, queued);
blkg_get(tg_to_blkg(qn->tg));
}
}
/**
* throtl_peek_queued - peek the first bio on a qnode list
* @queued: the qnode list to peek
*/
static struct bio *throtl_peek_queued(struct list_head *queued)
{
struct throtl_qnode *qn = list_first_entry(queued, struct throtl_qnode, node);
struct bio *bio;
if (list_empty(queued))
return NULL;
bio = bio_list_peek(&qn->bios);
WARN_ON_ONCE(!bio);
return bio;
}
/**
* throtl_pop_queued - pop the first bio form a qnode list
* @queued: the qnode list to pop a bio from
* @tg_to_put: optional out argument for throtl_grp to put
*
* Pop the first bio from the qnode list @queued. After popping, the first
* qnode is removed from @queued if empty or moved to the end of @queued so
* that the popping order is round-robin.
*
* When the first qnode is removed, its associated throtl_grp should be put
* too. If @tg_to_put is NULL, this function automatically puts it;
* otherwise, *@tg_to_put is set to the throtl_grp to put and the caller is
* responsible for putting it.
*/
static struct bio *throtl_pop_queued(struct list_head *queued,
struct throtl_grp **tg_to_put)
{
struct throtl_qnode *qn = list_first_entry(queued, struct throtl_qnode, node);
struct bio *bio;
if (list_empty(queued))
return NULL;
bio = bio_list_pop(&qn->bios);
WARN_ON_ONCE(!bio);
if (bio_list_empty(&qn->bios)) {
list_del_init(&qn->node);
if (tg_to_put)
*tg_to_put = qn->tg;
else
blkg_put(tg_to_blkg(qn->tg));
} else {
list_move_tail(&qn->node, queued);
}
return bio;
}
/* init a service_queue, assumes the caller zeroed it */
static void throtl_service_queue_init(struct throtl_service_queue *sq)
{
INIT_LIST_HEAD(&sq->queued[0]);
INIT_LIST_HEAD(&sq->queued[1]);
sq->pending_tree = RB_ROOT;
setup_timer(&sq->pending_timer, throtl_pending_timer_fn,
(unsigned long)sq);
}
static struct blkg_policy_data *throtl_pd_alloc(gfp_t gfp, int node)
{
struct throtl_grp *tg;
int rw;
tg = kzalloc_node(sizeof(*tg), gfp, node);
if (!tg)
return NULL;
throtl_service_queue_init(&tg->service_queue);
for (rw = READ; rw <= WRITE; rw++) {
throtl_qnode_init(&tg->qnode_on_self[rw], tg);
throtl_qnode_init(&tg->qnode_on_parent[rw], tg);
}
RB_CLEAR_NODE(&tg->rb_node);
tg->bps[READ][LIMIT_MAX] = U64_MAX;
tg->bps[WRITE][LIMIT_MAX] = U64_MAX;
tg->iops[READ][LIMIT_MAX] = UINT_MAX;
tg->iops[WRITE][LIMIT_MAX] = UINT_MAX;
tg->bps_conf[READ][LIMIT_MAX] = U64_MAX;
tg->bps_conf[WRITE][LIMIT_MAX] = U64_MAX;
tg->iops_conf[READ][LIMIT_MAX] = UINT_MAX;
tg->iops_conf[WRITE][LIMIT_MAX] = UINT_MAX;
/* LIMIT_LOW will have default value 0 */
tg->latency_target = DFL_LATENCY_TARGET;
return &tg->pd;
}
static void throtl_pd_init(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
struct blkcg_gq *blkg = tg_to_blkg(tg);
struct throtl_data *td = blkg->q->td;
struct throtl_service_queue *sq = &tg->service_queue;
/*
* If on the default hierarchy, we switch to properly hierarchical
* behavior where limits on a given throtl_grp are applied to the
* whole subtree rather than just the group itself. e.g. If 16M
* read_bps limit is set on the root group, the whole system can't
* exceed 16M for the device.
*
* If not on the default hierarchy, the broken flat hierarchy
* behavior is retained where all throtl_grps are treated as if
* they're all separate root groups right below throtl_data.
* Limits of a group don't interact with limits of other groups
* regardless of the position of the group in the hierarchy.
*/
sq->parent_sq = &td->service_queue;
if (cgroup_subsys_on_dfl(io_cgrp_subsys) && blkg->parent)
sq->parent_sq = &blkg_to_tg(blkg->parent)->service_queue;
tg->td = td;
tg->idletime_threshold = td->dft_idletime_threshold;
}
/*
* Set has_rules[] if @tg or any of its parents have limits configured.
* This doesn't require walking up to the top of the hierarchy as the
* parent's has_rules[] is guaranteed to be correct.
*/
static void tg_update_has_rules(struct throtl_grp *tg)
{
struct throtl_grp *parent_tg = sq_to_tg(tg->service_queue.parent_sq);
struct throtl_data *td = tg->td;
int rw;
for (rw = READ; rw <= WRITE; rw++)
tg->has_rules[rw] = (parent_tg && parent_tg->has_rules[rw]) ||
(td->limit_valid[td->limit_index] &&
(tg_bps_limit(tg, rw) != U64_MAX ||
tg_iops_limit(tg, rw) != UINT_MAX));
}
static void throtl_pd_online(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
/*
* We don't want new groups to escape the limits of its ancestors.
* Update has_rules[] after a new group is brought online.
*/
tg_update_has_rules(tg);
}
static void blk_throtl_update_limit_valid(struct throtl_data *td)
{
struct cgroup_subsys_state *pos_css;
struct blkcg_gq *blkg;
bool low_valid = false;
rcu_read_lock();
blkg_for_each_descendant_post(blkg, pos_css, td->queue->root_blkg) {
struct throtl_grp *tg = blkg_to_tg(blkg);
if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
low_valid = true;
}
rcu_read_unlock();
td->limit_valid[LIMIT_LOW] = low_valid;
}
static void throtl_upgrade_state(struct throtl_data *td);
static void throtl_pd_offline(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
tg->bps[READ][LIMIT_LOW] = 0;
tg->bps[WRITE][LIMIT_LOW] = 0;
tg->iops[READ][LIMIT_LOW] = 0;
tg->iops[WRITE][LIMIT_LOW] = 0;
blk_throtl_update_limit_valid(tg->td);
if (!tg->td->limit_valid[tg->td->limit_index])
throtl_upgrade_state(tg->td);
}
static void throtl_pd_free(struct blkg_policy_data *pd)
{
struct throtl_grp *tg = pd_to_tg(pd);
del_timer_sync(&tg->service_queue.pending_timer);
kfree(tg);
}
static struct throtl_grp *
throtl_rb_first(struct throtl_service_queue *parent_sq)
{
/* Service tree is empty */
if (!parent_sq->nr_pending)
return NULL;
if (!parent_sq->first_pending)
parent_sq->first_pending = rb_first(&parent_sq->pending_tree);
if (parent_sq->first_pending)
return rb_entry_tg(parent_sq->first_pending);
return NULL;
}
static void rb_erase_init(struct rb_node *n, struct rb_root *root)
{
rb_erase(n, root);
RB_CLEAR_NODE(n);
}
static void throtl_rb_erase(struct rb_node *n,
struct throtl_service_queue *parent_sq)
{
if (parent_sq->first_pending == n)
parent_sq->first_pending = NULL;
rb_erase_init(n, &parent_sq->pending_tree);
--parent_sq->nr_pending;
}
static void update_min_dispatch_time(struct throtl_service_queue *parent_sq)
{
struct throtl_grp *tg;
tg = throtl_rb_first(parent_sq);
if (!tg)
return;
parent_sq->first_pending_disptime = tg->disptime;
}
static void tg_service_queue_add(struct throtl_grp *tg)
{
struct throtl_service_queue *parent_sq = tg->service_queue.parent_sq;
struct rb_node **node = &parent_sq->pending_tree.rb_node;
struct rb_node *parent = NULL;
struct throtl_grp *__tg;
unsigned long key = tg->disptime;
int left = 1;
while (*node != NULL) {
parent = *node;
__tg = rb_entry_tg(parent);
if (time_before(key, __tg->disptime))
node = &parent->rb_left;
else {
node = &parent->rb_right;
left = 0;
}
}
if (left)
parent_sq->first_pending = &tg->rb_node;
rb_link_node(&tg->rb_node, parent, node);
rb_insert_color(&tg->rb_node, &parent_sq->pending_tree);
}
static void __throtl_enqueue_tg(struct throtl_grp *tg)
{
tg_service_queue_add(tg);
tg->flags |= THROTL_TG_PENDING;
tg->service_queue.parent_sq->nr_pending++;
}
static void throtl_enqueue_tg(struct throtl_grp *tg)
{
if (!(tg->flags & THROTL_TG_PENDING))
__throtl_enqueue_tg(tg);
}
static void __throtl_dequeue_tg(struct throtl_grp *tg)
{
throtl_rb_erase(&tg->rb_node, tg->service_queue.parent_sq);
tg->flags &= ~THROTL_TG_PENDING;
}
static void throtl_dequeue_tg(struct throtl_grp *tg)
{
if (tg->flags & THROTL_TG_PENDING)
__throtl_dequeue_tg(tg);
}
/* Call with queue lock held */
static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
unsigned long expires)
{
unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
/*
* Since we are adjusting the throttle limit dynamically, the sleep
* time calculated according to previous limit might be invalid. It's
* possible the cgroup sleep time is very long and no other cgroups
* have IO running so notify the limit changes. Make sure the cgroup
* doesn't sleep too long to avoid the missed notification.
*/
if (time_after(expires, max_expire))
expires = max_expire;
mod_timer(&sq->pending_timer, expires);
throtl_log(sq, "schedule timer. delay=%lu jiffies=%lu",
expires - jiffies, jiffies);
}
/**
* throtl_schedule_next_dispatch - schedule the next dispatch cycle
* @sq: the service_queue to schedule dispatch for
* @force: force scheduling
*
* Arm @sq->pending_timer so that the next dispatch cycle starts on the
* dispatch time of the first pending child. Returns %true if either timer
* is armed or there's no pending child left. %false if the current
* dispatch window is still open and the caller should continue
* dispatching.
*
* If @force is %true, the dispatch timer is always scheduled and this
* function is guaranteed to return %true. This is to be used when the
* caller can't dispatch itself and needs to invoke pending_timer
* unconditionally. Note that forced scheduling is likely to induce short
* delay before dispatch starts even if @sq->first_pending_disptime is not
* in the future and thus shouldn't be used in hot paths.
*/
static bool throtl_schedule_next_dispatch(struct throtl_service_queue *sq,
bool force)
{
/* any pending children left? */
if (!sq->nr_pending)
return true;
update_min_dispatch_time(sq);
/* is the next dispatch time in the future? */
if (force || time_after(sq->first_pending_disptime, jiffies)) {
throtl_schedule_pending_timer(sq, sq->first_pending_disptime);
return true;
}
/* tell the caller to continue dispatching */
return false;
}
static inline void throtl_start_new_slice_with_credit(struct throtl_grp *tg,
bool rw, unsigned long start)
{
tg->bytes_disp[rw] = 0;
tg->io_disp[rw] = 0;
/*
* Previous slice has expired. We must have trimmed it after last
* bio dispatch. That means since start of last slice, we never used
* that bandwidth. Do try to make use of that bandwidth while giving
* credit.
*/
if (time_after_eq(start, tg->slice_start[rw]))
tg->slice_start[rw] = start;
tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice with credit start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
tg->slice_end[rw], jiffies);
}
static inline void throtl_start_new_slice(struct throtl_grp *tg, bool rw)
{
tg->bytes_disp[rw] = 0;
tg->io_disp[rw] = 0;
tg->slice_start[rw] = jiffies;
tg->slice_end[rw] = jiffies + tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] new slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
tg->slice_end[rw], jiffies);
}
static inline void throtl_set_slice_end(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
}
static inline void throtl_extend_slice(struct throtl_grp *tg, bool rw,
unsigned long jiffy_end)
{
tg->slice_end[rw] = roundup(jiffy_end, tg->td->throtl_slice);
throtl_log(&tg->service_queue,
"[%c] extend slice start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', tg->slice_start[rw],
tg->slice_end[rw], jiffies);
}
/* Determine if previously allocated or extended slice is complete or not */
static bool throtl_slice_used(struct throtl_grp *tg, bool rw)
{
if (time_in_range(jiffies, tg->slice_start[rw], tg->slice_end[rw]))
return false;
return 1;
}
/* Trim the used slices and adjust slice start accordingly */
static inline void throtl_trim_slice(struct throtl_grp *tg, bool rw)
{
unsigned long nr_slices, time_elapsed, io_trim;
u64 bytes_trim, tmp;
BUG_ON(time_before(tg->slice_end[rw], tg->slice_start[rw]));
/*
* If bps are unlimited (-1), then time slice don't get
* renewed. Don't try to trim the slice if slice is used. A new
* slice will start when appropriate.
*/
if (throtl_slice_used(tg, rw))
return;
/*
* A bio has been dispatched. Also adjust slice_end. It might happen
* that initially cgroup limit was very low resulting in high
* slice_end, but later limit was bumped up and bio was dispached
* sooner, then we need to reduce slice_end. A high bogus slice_end
* is bad because it does not allow new slice to start.
*/
throtl_set_slice_end(tg, rw, jiffies + tg->td->throtl_slice);
time_elapsed = jiffies - tg->slice_start[rw];
nr_slices = time_elapsed / tg->td->throtl_slice;
if (!nr_slices)
return;
tmp = tg_bps_limit(tg, rw) * tg->td->throtl_slice * nr_slices;
do_div(tmp, HZ);
bytes_trim = tmp;
io_trim = (tg_iops_limit(tg, rw) * tg->td->throtl_slice * nr_slices) /
HZ;
if (!bytes_trim && !io_trim)
return;
if (tg->bytes_disp[rw] >= bytes_trim)
tg->bytes_disp[rw] -= bytes_trim;
else
tg->bytes_disp[rw] = 0;
if (tg->io_disp[rw] >= io_trim)
tg->io_disp[rw] -= io_trim;
else
tg->io_disp[rw] = 0;
tg->slice_start[rw] += nr_slices * tg->td->throtl_slice;
throtl_log(&tg->service_queue,
"[%c] trim slice nr=%lu bytes=%llu io=%lu start=%lu end=%lu jiffies=%lu",
rw == READ ? 'R' : 'W', nr_slices, bytes_trim, io_trim,
tg->slice_start[rw], tg->slice_end[rw], jiffies);
}
static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
unsigned long *wait)
{
bool rw = bio_data_dir(bio);
unsigned int io_allowed;
unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
u64 tmp;
jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
jiffy_elapsed_rnd = tg->td->throtl_slice;
jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
/*
* jiffy_elapsed_rnd should not be a big value as minimum iops can be
* 1 then at max jiffy elapsed should be equivalent of 1 second as we
* will allow dispatch after 1 second and after that slice should
* have been trimmed.
*/
tmp = (u64)tg_iops_limit(tg, rw) * jiffy_elapsed_rnd;
do_div(tmp, HZ);
if (tmp > UINT_MAX)
io_allowed = UINT_MAX;
else
io_allowed = tmp;
if (tg->io_disp[rw] + 1 <= io_allowed) {
if (wait)
*wait = 0;
return true;
}
/* Calc approx time to dispatch */
jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
if (jiffy_wait > jiffy_elapsed)
jiffy_wait = jiffy_wait - jiffy_elapsed;
else
jiffy_wait = 1;
if (wait)
*wait = jiffy_wait;
return 0;
}
static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio,
unsigned long *wait)
{
bool rw = bio_data_dir(bio);
u64 bytes_allowed, extra_bytes, tmp;
unsigned long jiffy_elapsed, jiffy_wait, jiffy_elapsed_rnd;
jiffy_elapsed = jiffy_elapsed_rnd = jiffies - tg->slice_start[rw];
/* Slice has just started. Consider one slice interval */
if (!jiffy_elapsed)
jiffy_elapsed_rnd = tg->td->throtl_slice;
jiffy_elapsed_rnd = roundup(jiffy_elapsed_rnd, tg->td->throtl_slice);
tmp = tg_bps_limit(tg, rw) * jiffy_elapsed_rnd;
do_div(tmp, HZ);
bytes_allowed = tmp;
if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) {
if (wait)
*wait = 0;
return true;
}
/* Calc approx time to dispatch */
extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed;
jiffy_wait = div64_u64(extra_bytes * HZ, tg_bps_limit(tg, rw));
if (!jiffy_wait)
jiffy_wait = 1;
/*
* This wait time is without taking into consideration the rounding
* up we did. Add that time also.
*/
jiffy_wait = jiffy_wait + (jiffy_elapsed_rnd - jiffy_elapsed);
if (wait)
*wait = jiffy_wait;
return 0;
}
/*
* Returns whether one can dispatch a bio or not. Also returns approx number
* of jiffies to wait before this bio is with-in IO rate and can be dispatched
*/
static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio,
unsigned long *wait)
{
bool rw = bio_data_dir(bio);
unsigned long bps_wait = 0, iops_wait = 0, max_wait = 0;
/*
* Currently whole state machine of group depends on first bio
* queued in the group bio list. So one should not be calling
* this function with a different bio if there are other bios
* queued.
*/
BUG_ON(tg->service_queue.nr_queued[rw] &&
bio != throtl_peek_queued(&tg->service_queue.queued[rw]));
/* If tg->bps = -1, then BW is unlimited */
if (tg_bps_limit(tg, rw) == U64_MAX &&
tg_iops_limit(tg, rw) == UINT_MAX) {
if (wait)
*wait = 0;
return true;
}
/*
* If previous slice expired, start a new one otherwise renew/extend
* existing slice to make sure it is at least throtl_slice interval
* long since now. New slice is started only for empty throttle group.
* If there is queued bio, that means there should be an active
* slice and it should be extended instead.
*/
if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw]))
throtl_start_new_slice(tg, rw);
else {
if (time_before(tg->slice_end[rw],
jiffies + tg->td->throtl_slice))
throtl_extend_slice(tg, rw,
jiffies + tg->td->throtl_slice);
}
if (tg_with_in_bps_limit(tg, bio, &bps_wait) &&
tg_with_in_iops_limit(tg, bio, &iops_wait)) {
if (wait)
*wait = 0;
return 1;
}
max_wait = max(bps_wait, iops_wait);
if (wait)
*wait = max_wait;