forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathspace-info.c
1115 lines (989 loc) · 31.7 KB
/
space-info.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
// SPDX-License-Identifier: GPL-2.0
#include "misc.h"
#include "ctree.h"
#include "space-info.h"
#include "sysfs.h"
#include "volumes.h"
#include "free-space-cache.h"
#include "ordered-data.h"
#include "transaction.h"
#include "block-group.h"
u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info,
bool may_use_included)
{
ASSERT(s_info);
return s_info->bytes_used + s_info->bytes_reserved +
s_info->bytes_pinned + s_info->bytes_readonly +
(may_use_included ? s_info->bytes_may_use : 0);
}
/*
* after adding space to the filesystem, we need to clear the full flags
* on all the space infos.
*/
void btrfs_clear_space_info_full(struct btrfs_fs_info *info)
{
struct list_head *head = &info->space_info;
struct btrfs_space_info *found;
rcu_read_lock();
list_for_each_entry_rcu(found, head, list)
found->full = 0;
rcu_read_unlock();
}
static int create_space_info(struct btrfs_fs_info *info, u64 flags)
{
struct btrfs_space_info *space_info;
int i;
int ret;
space_info = kzalloc(sizeof(*space_info), GFP_NOFS);
if (!space_info)
return -ENOMEM;
ret = percpu_counter_init(&space_info->total_bytes_pinned, 0,
GFP_KERNEL);
if (ret) {
kfree(space_info);
return ret;
}
for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
INIT_LIST_HEAD(&space_info->block_groups[i]);
init_rwsem(&space_info->groups_sem);
spin_lock_init(&space_info->lock);
space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
INIT_LIST_HEAD(&space_info->ro_bgs);
INIT_LIST_HEAD(&space_info->tickets);
INIT_LIST_HEAD(&space_info->priority_tickets);
ret = btrfs_sysfs_add_space_info_type(info, space_info);
if (ret)
return ret;
list_add_rcu(&space_info->list, &info->space_info);
if (flags & BTRFS_BLOCK_GROUP_DATA)
info->data_sinfo = space_info;
return ret;
}
int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
{
struct btrfs_super_block *disk_super;
u64 features;
u64 flags;
int mixed = 0;
int ret;
disk_super = fs_info->super_copy;
if (!btrfs_super_root(disk_super))
return -EINVAL;
features = btrfs_super_incompat_flags(disk_super);
if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
mixed = 1;
flags = BTRFS_BLOCK_GROUP_SYSTEM;
ret = create_space_info(fs_info, flags);
if (ret)
goto out;
if (mixed) {
flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
ret = create_space_info(fs_info, flags);
} else {
flags = BTRFS_BLOCK_GROUP_METADATA;
ret = create_space_info(fs_info, flags);
if (ret)
goto out;
flags = BTRFS_BLOCK_GROUP_DATA;
ret = create_space_info(fs_info, flags);
}
out:
return ret;
}
void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags,
u64 total_bytes, u64 bytes_used,
u64 bytes_readonly,
struct btrfs_space_info **space_info)
{
struct btrfs_space_info *found;
int factor;
factor = btrfs_bg_type_to_factor(flags);
found = btrfs_find_space_info(info, flags);
ASSERT(found);
spin_lock(&found->lock);
found->total_bytes += total_bytes;
found->disk_total += total_bytes * factor;
found->bytes_used += bytes_used;
found->disk_used += bytes_used * factor;
found->bytes_readonly += bytes_readonly;
if (total_bytes > 0)
found->full = 0;
btrfs_try_granting_tickets(info, found);
spin_unlock(&found->lock);
*space_info = found;
}
struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info,
u64 flags)
{
struct list_head *head = &info->space_info;
struct btrfs_space_info *found;
flags &= BTRFS_BLOCK_GROUP_TYPE_MASK;
rcu_read_lock();
list_for_each_entry_rcu(found, head, list) {
if (found->flags & flags) {
rcu_read_unlock();
return found;
}
}
rcu_read_unlock();
return NULL;
}
static inline u64 calc_global_rsv_need_space(struct btrfs_block_rsv *global)
{
return (global->size << 1);
}
static int can_overcommit(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info, u64 bytes,
enum btrfs_reserve_flush_enum flush,
bool system_chunk)
{
u64 profile;
u64 avail;
u64 used;
int factor;
/* Don't overcommit when in mixed mode. */
if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
return 0;
if (system_chunk)
profile = btrfs_system_alloc_profile(fs_info);
else
profile = btrfs_metadata_alloc_profile(fs_info);
used = btrfs_space_info_used(space_info, true);
avail = atomic64_read(&fs_info->free_chunk_space);
/*
* If we have dup, raid1 or raid10 then only half of the free
* space is actually usable. For raid56, the space info used
* doesn't include the parity drive, so we don't have to
* change the math
*/
factor = btrfs_bg_type_to_factor(profile);
avail = div_u64(avail, factor);
/*
* If we aren't flushing all things, let us overcommit up to
* 1/2th of the space. If we can flush, don't let us overcommit
* too much, let it overcommit up to 1/8 of the space.
*/
if (flush == BTRFS_RESERVE_FLUSH_ALL)
avail >>= 3;
else
avail >>= 1;
if (used + bytes < space_info->total_bytes + avail)
return 1;
return 0;
}
/*
* This is for space we already have accounted in space_info->bytes_may_use, so
* basically when we're returning space from block_rsv's.
*/
void btrfs_try_granting_tickets(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info)
{
struct list_head *head;
enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_NO_FLUSH;
lockdep_assert_held(&space_info->lock);
head = &space_info->priority_tickets;
again:
while (!list_empty(head)) {
struct reserve_ticket *ticket;
u64 used = btrfs_space_info_used(space_info, true);
ticket = list_first_entry(head, struct reserve_ticket, list);
/* Check and see if our ticket can be satisified now. */
if ((used + ticket->bytes <= space_info->total_bytes) ||
can_overcommit(fs_info, space_info, ticket->bytes, flush,
false)) {
btrfs_space_info_update_bytes_may_use(fs_info,
space_info,
ticket->bytes);
list_del_init(&ticket->list);
ticket->bytes = 0;
space_info->tickets_id++;
wake_up(&ticket->wait);
} else {
break;
}
}
if (head == &space_info->priority_tickets) {
head = &space_info->tickets;
flush = BTRFS_RESERVE_FLUSH_ALL;
goto again;
}
}
#define DUMP_BLOCK_RSV(fs_info, rsv_name) \
do { \
struct btrfs_block_rsv *__rsv = &(fs_info)->rsv_name; \
spin_lock(&__rsv->lock); \
btrfs_info(fs_info, #rsv_name ": size %llu reserved %llu", \
__rsv->size, __rsv->reserved); \
spin_unlock(&__rsv->lock); \
} while (0)
static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *info)
{
lockdep_assert_held(&info->lock);
btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull",
info->flags,
info->total_bytes - btrfs_space_info_used(info, true),
info->full ? "" : "not ");
btrfs_info(fs_info,
"space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu",
info->total_bytes, info->bytes_used, info->bytes_pinned,
info->bytes_reserved, info->bytes_may_use,
info->bytes_readonly);
DUMP_BLOCK_RSV(fs_info, global_block_rsv);
DUMP_BLOCK_RSV(fs_info, trans_block_rsv);
DUMP_BLOCK_RSV(fs_info, chunk_block_rsv);
DUMP_BLOCK_RSV(fs_info, delayed_block_rsv);
DUMP_BLOCK_RSV(fs_info, delayed_refs_rsv);
}
void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *info, u64 bytes,
int dump_block_groups)
{
struct btrfs_block_group *cache;
int index = 0;
spin_lock(&info->lock);
__btrfs_dump_space_info(fs_info, info);
spin_unlock(&info->lock);
if (!dump_block_groups)
return;
down_read(&info->groups_sem);
again:
list_for_each_entry(cache, &info->block_groups[index], list) {
spin_lock(&cache->lock);
btrfs_info(fs_info,
"block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s",
cache->start, cache->length, cache->used, cache->pinned,
cache->reserved, cache->ro ? "[readonly]" : "");
btrfs_dump_free_space(cache, bytes);
spin_unlock(&cache->lock);
}
if (++index < BTRFS_NR_RAID_TYPES)
goto again;
up_read(&info->groups_sem);
}
static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
unsigned long nr_pages, int nr_items)
{
struct super_block *sb = fs_info->sb;
if (down_read_trylock(&sb->s_umount)) {
writeback_inodes_sb_nr(sb, nr_pages, WB_REASON_FS_FREE_SPACE);
up_read(&sb->s_umount);
} else {
/*
* We needn't worry the filesystem going from r/w to r/o though
* we don't acquire ->s_umount mutex, because the filesystem
* should guarantee the delalloc inodes list be empty after
* the filesystem is readonly(all dirty pages are written to
* the disk).
*/
btrfs_start_delalloc_roots(fs_info, nr_items);
if (!current->journal_info)
btrfs_wait_ordered_roots(fs_info, nr_items, 0, (u64)-1);
}
}
static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
u64 to_reclaim)
{
u64 bytes;
u64 nr;
bytes = btrfs_calc_insert_metadata_size(fs_info, 1);
nr = div64_u64(to_reclaim, bytes);
if (!nr)
nr = 1;
return nr;
}
#define EXTENT_SIZE_PER_ITEM SZ_256K
/*
* shrink metadata reservation for delalloc
*/
static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
u64 orig, bool wait_ordered)
{
struct btrfs_space_info *space_info;
struct btrfs_trans_handle *trans;
u64 delalloc_bytes;
u64 dio_bytes;
u64 async_pages;
u64 items;
long time_left;
unsigned long nr_pages;
int loops;
/* Calc the number of the pages we need flush for space reservation */
items = calc_reclaim_items_nr(fs_info, to_reclaim);
to_reclaim = items * EXTENT_SIZE_PER_ITEM;
trans = (struct btrfs_trans_handle *)current->journal_info;
space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
if (delalloc_bytes == 0 && dio_bytes == 0) {
if (trans)
return;
if (wait_ordered)
btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
return;
}
/*
* If we are doing more ordered than delalloc we need to just wait on
* ordered extents, otherwise we'll waste time trying to flush delalloc
* that likely won't give us the space back we need.
*/
if (dio_bytes > delalloc_bytes)
wait_ordered = true;
loops = 0;
while ((delalloc_bytes || dio_bytes) && loops < 3) {
nr_pages = min(delalloc_bytes, to_reclaim) >> PAGE_SHIFT;
/*
* Triggers inode writeback for up to nr_pages. This will invoke
* ->writepages callback and trigger delalloc filling
* (btrfs_run_delalloc_range()).
*/
btrfs_writeback_inodes_sb_nr(fs_info, nr_pages, items);
/*
* We need to wait for the compressed pages to start before
* we continue.
*/
async_pages = atomic_read(&fs_info->async_delalloc_pages);
if (!async_pages)
goto skip_async;
/*
* Calculate how many compressed pages we want to be written
* before we continue. I.e if there are more async pages than we
* require wait_event will wait until nr_pages are written.
*/
if (async_pages <= nr_pages)
async_pages = 0;
else
async_pages -= nr_pages;
wait_event(fs_info->async_submit_wait,
atomic_read(&fs_info->async_delalloc_pages) <=
(int)async_pages);
skip_async:
spin_lock(&space_info->lock);
if (list_empty(&space_info->tickets) &&
list_empty(&space_info->priority_tickets)) {
spin_unlock(&space_info->lock);
break;
}
spin_unlock(&space_info->lock);
loops++;
if (wait_ordered && !trans) {
btrfs_wait_ordered_roots(fs_info, items, 0, (u64)-1);
} else {
time_left = schedule_timeout_killable(1);
if (time_left)
break;
}
delalloc_bytes = percpu_counter_sum_positive(
&fs_info->delalloc_bytes);
dio_bytes = percpu_counter_sum_positive(&fs_info->dio_bytes);
}
}
/**
* maybe_commit_transaction - possibly commit the transaction if its ok to
* @root - the root we're allocating for
* @bytes - the number of bytes we want to reserve
* @force - force the commit
*
* This will check to make sure that committing the transaction will actually
* get us somewhere and then commit the transaction if it does. Otherwise it
* will return -ENOSPC.
*/
static int may_commit_transaction(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info)
{
struct reserve_ticket *ticket = NULL;
struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
struct btrfs_block_rsv *delayed_refs_rsv = &fs_info->delayed_refs_rsv;
struct btrfs_trans_handle *trans;
u64 bytes_needed;
u64 reclaim_bytes = 0;
u64 cur_free_bytes = 0;
trans = (struct btrfs_trans_handle *)current->journal_info;
if (trans)
return -EAGAIN;
spin_lock(&space_info->lock);
cur_free_bytes = btrfs_space_info_used(space_info, true);
if (cur_free_bytes < space_info->total_bytes)
cur_free_bytes = space_info->total_bytes - cur_free_bytes;
else
cur_free_bytes = 0;
if (!list_empty(&space_info->priority_tickets))
ticket = list_first_entry(&space_info->priority_tickets,
struct reserve_ticket, list);
else if (!list_empty(&space_info->tickets))
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
bytes_needed = (ticket) ? ticket->bytes : 0;
if (bytes_needed > cur_free_bytes)
bytes_needed -= cur_free_bytes;
else
bytes_needed = 0;
spin_unlock(&space_info->lock);
if (!bytes_needed)
return 0;
trans = btrfs_join_transaction(fs_info->extent_root);
if (IS_ERR(trans))
return PTR_ERR(trans);
/*
* See if there is enough pinned space to make this reservation, or if
* we have block groups that are going to be freed, allowing us to
* possibly do a chunk allocation the next loop through.
*/
if (test_bit(BTRFS_TRANS_HAVE_FREE_BGS, &trans->transaction->flags) ||
__percpu_counter_compare(&space_info->total_bytes_pinned,
bytes_needed,
BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
goto commit;
/*
* See if there is some space in the delayed insertion reservation for
* this reservation.
*/
if (space_info != delayed_rsv->space_info)
goto enospc;
spin_lock(&delayed_rsv->lock);
reclaim_bytes += delayed_rsv->reserved;
spin_unlock(&delayed_rsv->lock);
spin_lock(&delayed_refs_rsv->lock);
reclaim_bytes += delayed_refs_rsv->reserved;
spin_unlock(&delayed_refs_rsv->lock);
if (reclaim_bytes >= bytes_needed)
goto commit;
bytes_needed -= reclaim_bytes;
if (__percpu_counter_compare(&space_info->total_bytes_pinned,
bytes_needed,
BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0)
goto enospc;
commit:
return btrfs_commit_transaction(trans);
enospc:
btrfs_end_transaction(trans);
return -ENOSPC;
}
/*
* Try to flush some data based on policy set by @state. This is only advisory
* and may fail for various reasons. The caller is supposed to examine the
* state of @space_info to detect the outcome.
*/
static void flush_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info, u64 num_bytes,
int state)
{
struct btrfs_root *root = fs_info->extent_root;
struct btrfs_trans_handle *trans;
int nr;
int ret = 0;
switch (state) {
case FLUSH_DELAYED_ITEMS_NR:
case FLUSH_DELAYED_ITEMS:
if (state == FLUSH_DELAYED_ITEMS_NR)
nr = calc_reclaim_items_nr(fs_info, num_bytes) * 2;
else
nr = -1;
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
ret = btrfs_run_delayed_items_nr(trans, nr);
btrfs_end_transaction(trans);
break;
case FLUSH_DELALLOC:
case FLUSH_DELALLOC_WAIT:
shrink_delalloc(fs_info, num_bytes * 2, num_bytes,
state == FLUSH_DELALLOC_WAIT);
break;
case FLUSH_DELAYED_REFS_NR:
case FLUSH_DELAYED_REFS:
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
if (state == FLUSH_DELAYED_REFS_NR)
nr = calc_reclaim_items_nr(fs_info, num_bytes);
else
nr = 0;
btrfs_run_delayed_refs(trans, nr);
btrfs_end_transaction(trans);
break;
case ALLOC_CHUNK:
case ALLOC_CHUNK_FORCE:
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
break;
}
ret = btrfs_chunk_alloc(trans,
btrfs_metadata_alloc_profile(fs_info),
(state == ALLOC_CHUNK) ? CHUNK_ALLOC_NO_FORCE :
CHUNK_ALLOC_FORCE);
btrfs_end_transaction(trans);
if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
case RUN_DELAYED_IPUTS:
/*
* If we have pending delayed iputs then we could free up a
* bunch of pinned space, so make sure we run the iputs before
* we do our pinned bytes check below.
*/
btrfs_run_delayed_iputs(fs_info);
btrfs_wait_on_delayed_iputs(fs_info);
break;
case COMMIT_TRANS:
ret = may_commit_transaction(fs_info, space_info);
break;
default:
ret = -ENOSPC;
break;
}
trace_btrfs_flush_space(fs_info, space_info->flags, num_bytes, state,
ret);
return;
}
static inline u64
btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
bool system_chunk)
{
struct reserve_ticket *ticket;
u64 used;
u64 expected;
u64 to_reclaim = 0;
list_for_each_entry(ticket, &space_info->tickets, list)
to_reclaim += ticket->bytes;
list_for_each_entry(ticket, &space_info->priority_tickets, list)
to_reclaim += ticket->bytes;
if (to_reclaim)
return to_reclaim;
to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
if (can_overcommit(fs_info, space_info, to_reclaim,
BTRFS_RESERVE_FLUSH_ALL, system_chunk))
return 0;
used = btrfs_space_info_used(space_info, true);
if (can_overcommit(fs_info, space_info, SZ_1M,
BTRFS_RESERVE_FLUSH_ALL, system_chunk))
expected = div_factor_fine(space_info->total_bytes, 95);
else
expected = div_factor_fine(space_info->total_bytes, 90);
if (used > expected)
to_reclaim = used - expected;
else
to_reclaim = 0;
to_reclaim = min(to_reclaim, space_info->bytes_may_use +
space_info->bytes_reserved);
return to_reclaim;
}
static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 used, bool system_chunk)
{
u64 thresh = div_factor_fine(space_info->total_bytes, 98);
/* If we're just plain full then async reclaim just slows us down. */
if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
return 0;
if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
system_chunk))
return 0;
return (used >= thresh && !btrfs_fs_closing(fs_info) &&
!test_bit(BTRFS_FS_STATE_REMOUNTING, &fs_info->fs_state));
}
/*
* maybe_fail_all_tickets - we've exhausted our flushing, start failing tickets
* @fs_info - fs_info for this fs
* @space_info - the space info we were flushing
*
* We call this when we've exhausted our flushing ability and haven't made
* progress in satisfying tickets. The reservation code handles tickets in
* order, so if there is a large ticket first and then smaller ones we could
* very well satisfy the smaller tickets. This will attempt to wake up any
* tickets in the list to catch this case.
*
* This function returns true if it was able to make progress by clearing out
* other tickets, or if it stumbles across a ticket that was smaller than the
* first ticket.
*/
static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info)
{
struct reserve_ticket *ticket;
u64 tickets_id = space_info->tickets_id;
u64 first_ticket_bytes = 0;
if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) {
btrfs_info(fs_info, "cannot satisfy tickets, dumping space info");
__btrfs_dump_space_info(fs_info, space_info);
}
while (!list_empty(&space_info->tickets) &&
tickets_id == space_info->tickets_id) {
ticket = list_first_entry(&space_info->tickets,
struct reserve_ticket, list);
/*
* may_commit_transaction will avoid committing the transaction
* if it doesn't feel like the space reclaimed by the commit
* would result in the ticket succeeding. However if we have a
* smaller ticket in the queue it may be small enough to be
* satisified by committing the transaction, so if any
* subsequent ticket is smaller than the first ticket go ahead
* and send us back for another loop through the enospc flushing
* code.
*/
if (first_ticket_bytes == 0)
first_ticket_bytes = ticket->bytes;
else if (first_ticket_bytes > ticket->bytes)
return true;
if (btrfs_test_opt(fs_info, ENOSPC_DEBUG))
btrfs_info(fs_info, "failing ticket with %llu bytes",
ticket->bytes);
list_del_init(&ticket->list);
ticket->error = -ENOSPC;
wake_up(&ticket->wait);
/*
* We're just throwing tickets away, so more flushing may not
* trip over btrfs_try_granting_tickets, so we need to call it
* here to see if we can make progress with the next ticket in
* the list.
*/
btrfs_try_granting_tickets(fs_info, space_info);
}
return (tickets_id != space_info->tickets_id);
}
/*
* This is for normal flushers, we can wait all goddamned day if we want to. We
* will loop and continuously try to flush as long as we are making progress.
* We count progress as clearing off tickets each time we have to loop.
*/
static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
{
struct btrfs_fs_info *fs_info;
struct btrfs_space_info *space_info;
u64 to_reclaim;
int flush_state;
int commit_cycles = 0;
u64 last_tickets_id;
fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work);
space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
false);
if (!to_reclaim) {
space_info->flush = 0;
spin_unlock(&space_info->lock);
return;
}
last_tickets_id = space_info->tickets_id;
spin_unlock(&space_info->lock);
flush_state = FLUSH_DELAYED_ITEMS_NR;
do {
flush_space(fs_info, space_info, to_reclaim, flush_state);
spin_lock(&space_info->lock);
if (list_empty(&space_info->tickets)) {
space_info->flush = 0;
spin_unlock(&space_info->lock);
return;
}
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
space_info,
false);
if (last_tickets_id == space_info->tickets_id) {
flush_state++;
} else {
last_tickets_id = space_info->tickets_id;
flush_state = FLUSH_DELAYED_ITEMS_NR;
if (commit_cycles)
commit_cycles--;
}
/*
* We don't want to force a chunk allocation until we've tried
* pretty hard to reclaim space. Think of the case where we
* freed up a bunch of space and so have a lot of pinned space
* to reclaim. We would rather use that than possibly create a
* underutilized metadata chunk. So if this is our first run
* through the flushing state machine skip ALLOC_CHUNK_FORCE and
* commit the transaction. If nothing has changed the next go
* around then we can force a chunk allocation.
*/
if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles)
flush_state++;
if (flush_state > COMMIT_TRANS) {
commit_cycles++;
if (commit_cycles > 2) {
if (maybe_fail_all_tickets(fs_info, space_info)) {
flush_state = FLUSH_DELAYED_ITEMS_NR;
commit_cycles--;
} else {
space_info->flush = 0;
}
} else {
flush_state = FLUSH_DELAYED_ITEMS_NR;
}
}
spin_unlock(&space_info->lock);
} while (flush_state <= COMMIT_TRANS);
}
void btrfs_init_async_reclaim_work(struct work_struct *work)
{
INIT_WORK(work, btrfs_async_reclaim_metadata_space);
}
static const enum btrfs_flush_state priority_flush_states[] = {
FLUSH_DELAYED_ITEMS_NR,
FLUSH_DELAYED_ITEMS,
ALLOC_CHUNK,
};
static const enum btrfs_flush_state evict_flush_states[] = {
FLUSH_DELAYED_ITEMS_NR,
FLUSH_DELAYED_ITEMS,
FLUSH_DELAYED_REFS_NR,
FLUSH_DELAYED_REFS,
FLUSH_DELALLOC,
FLUSH_DELALLOC_WAIT,
ALLOC_CHUNK,
COMMIT_TRANS,
};
static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket,
const enum btrfs_flush_state *states,
int states_nr)
{
u64 to_reclaim;
int flush_state;
spin_lock(&space_info->lock);
to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
false);
if (!to_reclaim) {
spin_unlock(&space_info->lock);
return;
}
spin_unlock(&space_info->lock);
flush_state = 0;
do {
flush_space(fs_info, space_info, to_reclaim, states[flush_state]);
flush_state++;
spin_lock(&space_info->lock);
if (ticket->bytes == 0) {
spin_unlock(&space_info->lock);
return;
}
spin_unlock(&space_info->lock);
} while (flush_state < states_nr);
}
static void wait_reserve_ticket(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket)
{
DEFINE_WAIT(wait);
int ret = 0;
spin_lock(&space_info->lock);
while (ticket->bytes > 0 && ticket->error == 0) {
ret = prepare_to_wait_event(&ticket->wait, &wait, TASK_KILLABLE);
if (ret) {
/*
* Delete us from the list. After we unlock the space
* info, we don't want the async reclaim job to reserve
* space for this ticket. If that would happen, then the
* ticket's task would not known that space was reserved
* despite getting an error, resulting in a space leak
* (bytes_may_use counter of our space_info).
*/
list_del_init(&ticket->list);
ticket->error = -EINTR;
break;
}
spin_unlock(&space_info->lock);
schedule();
finish_wait(&ticket->wait, &wait);
spin_lock(&space_info->lock);
}
spin_unlock(&space_info->lock);
}
/**
* handle_reserve_ticket - do the appropriate flushing and waiting for a ticket
* @fs_info - the fs
* @space_info - the space_info for the reservation
* @ticket - the ticket for the reservation
* @flush - how much we can flush
*
* This does the work of figuring out how to flush for the ticket, waiting for
* the reservation, and returning the appropriate error if there is one.
*/
static int handle_reserve_ticket(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
struct reserve_ticket *ticket,
enum btrfs_reserve_flush_enum flush)
{
int ret;
switch (flush) {
case BTRFS_RESERVE_FLUSH_ALL:
wait_reserve_ticket(fs_info, space_info, ticket);
break;
case BTRFS_RESERVE_FLUSH_LIMIT:
priority_reclaim_metadata_space(fs_info, space_info, ticket,
priority_flush_states,
ARRAY_SIZE(priority_flush_states));
break;
case BTRFS_RESERVE_FLUSH_EVICT:
priority_reclaim_metadata_space(fs_info, space_info, ticket,
evict_flush_states,
ARRAY_SIZE(evict_flush_states));
break;
default:
ASSERT(0);
break;
}
spin_lock(&space_info->lock);
ret = ticket->error;
if (ticket->bytes || ticket->error) {
/*
* Need to delete here for priority tickets. For regular tickets
* either the async reclaim job deletes the ticket from the list
* or we delete it ourselves at wait_reserve_ticket().
*/
list_del_init(&ticket->list);
if (!ret)
ret = -ENOSPC;
}
spin_unlock(&space_info->lock);
ASSERT(list_empty(&ticket->list));
/*
* Check that we can't have an error set if the reservation succeeded,
* as that would confuse tasks and lead them to error out without
* releasing reserved space (if an error happens the expectation is that
* space wasn't reserved at all).
*/
ASSERT(!(ticket->bytes == 0 && ticket->error));
return ret;
}
/**
* reserve_metadata_bytes - try to reserve bytes from the block_rsv's space
* @root - the root we're allocating for
* @space_info - the space info we want to allocate from
* @orig_bytes - the number of bytes we want
* @flush - whether or not we can flush to make our reservation
*
* This will reserve orig_bytes number of bytes from the space info associated
* with the block_rsv. If there is not enough space it will make an attempt to
* flush out space to make room. It will do this by flushing delalloc if
* possible or committing the transaction. If flush is 0 then no attempts to
* regain reservations will be made and this will fail if there is not enough
* space already.
*/
static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
struct btrfs_space_info *space_info,
u64 orig_bytes,
enum btrfs_reserve_flush_enum flush,
bool system_chunk)
{
struct reserve_ticket ticket;
u64 used;
int ret = 0;
bool pending_tickets;