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
|
#ifndef _BCACHE_H
#define _BCACHE_H
/*
* SOME HIGH LEVEL CODE DOCUMENTATION:
*
* Bcache mostly works with cache sets, cache devices, and backing devices.
*
* Support for multiple cache devices hasn't quite been finished off yet, but
* it's about 95% plumbed through. A cache set and its cache devices is sort of
* like a md raid array and its component devices. Most of the code doesn't care
* about individual cache devices, the main abstraction is the cache set.
*
* Multiple cache devices is intended to give us the ability to mirror dirty
* cached data and metadata, without mirroring clean cached data.
*
* Backing devices are different, in that they have a lifetime independent of a
* cache set. When you register a newly formatted backing device it'll come up
* in passthrough mode, and then you can attach and detach a backing device from
* a cache set at runtime - while it's mounted and in use. Detaching implicitly
* invalidates any cached data for that backing device.
*
* A cache set can have multiple (many) backing devices attached to it.
*
* There's also flash only volumes - this is the reason for the distinction
* between struct cached_dev and struct bcache_device. A flash only volume
* works much like a bcache device that has a backing device, except the
* "cached" data is always dirty. The end result is that we get thin
* provisioning with very little additional code.
*
* Flash only volumes work but they're not production ready because the moving
* garbage collector needs more work. More on that later.
*
* BUCKETS/ALLOCATION:
*
* Bcache is primarily designed for caching, which means that in normal
* operation all of our available space will be allocated. Thus, we need an
* efficient way of deleting things from the cache so we can write new things to
* it.
*
* To do this, we first divide the cache device up into buckets. A bucket is the
* unit of allocation; they're typically around 1 mb - anywhere from 128k to 2M+
* works efficiently.
*
* Each bucket has a 16 bit priority, and an 8 bit generation associated with
* it. The gens and priorities for all the buckets are stored contiguously and
* packed on disk (in a linked list of buckets - aside from the superblock, all
* of bcache's metadata is stored in buckets).
*
* The priority is used to implement an LRU. We reset a bucket's priority when
* we allocate it or on cache it, and every so often we decrement the priority
* of each bucket. It could be used to implement something more sophisticated,
* if anyone ever gets around to it.
*
* The generation is used for invalidating buckets. Each pointer also has an 8
* bit generation embedded in it; for a pointer to be considered valid, its gen
* must match the gen of the bucket it points into. Thus, to reuse a bucket all
* we have to do is increment its gen (and write its new gen to disk; we batch
* this up).
*
* Bcache is entirely COW - we never write twice to a bucket, even buckets that
* contain metadata (including btree nodes).
*
* THE BTREE:
*
* Bcache is in large part design around the btree.
*
* At a high level, the btree is just an index of key -> ptr tuples.
*
* Keys represent extents, and thus have a size field. Keys also have a variable
* number of pointers attached to them (potentially zero, which is handy for
* invalidating the cache).
*
* The key itself is an inode:offset pair. The inode number corresponds to a
* backing device or a flash only volume. The offset is the ending offset of the
* extent within the inode - not the starting offset; this makes lookups
* slightly more convenient.
*
* Pointers contain the cache device id, the offset on that device, and an 8 bit
* generation number. More on the gen later.
*
* Index lookups are not fully abstracted - cache lookups in particular are
* still somewhat mixed in with the btree code, but things are headed in that
* direction.
*
* Updates are fairly well abstracted, though. There are two different ways of
* updating the btree; insert and replace.
*
* BTREE_INSERT will just take a list of keys and insert them into the btree -
* overwriting (possibly only partially) any extents they overlap with. This is
* used to update the index after a write.
*
* BTREE_REPLACE is really cmpxchg(); it inserts a key into the btree iff it is
* overwriting a key that matches another given key. This is used for inserting
* data into the cache after a cache miss, and for background writeback, and for
* the moving garbage collector.
*
* There is no "delete" operation; deleting things from the index is
* accomplished by either by invalidating pointers (by incrementing a bucket's
* gen) or by inserting a key with 0 pointers - which will overwrite anything
* previously present at that location in the index.
*
* This means that there are always stale/invalid keys in the btree. They're
* filtered out by the code that iterates through a btree node, and removed when
* a btree node is rewritten.
*
* BTREE NODES:
*
* Our unit of allocation is a bucket, and we we can't arbitrarily allocate and
* free smaller than a bucket - so, that's how big our btree nodes are.
*
* (If buckets are really big we'll only use part of the bucket for a btree node
* - no less than 1/4th - but a bucket still contains no more than a single
* btree node. I'd actually like to change this, but for now we rely on the
* bucket's gen for deleting btree nodes when we rewrite/split a node.)
*
* Anyways, btree nodes are big - big enough to be inefficient with a textbook
* btree implementation.
*
* The way this is solved is that btree nodes are internally log structured; we
* can append new keys to an existing btree node without rewriting it. This
* means each set of keys we write is sorted, but the node is not.
*
* We maintain this log structure in memory - keeping 1Mb of keys sorted would
* be expensive, and we have to distinguish between the keys we have written and
* the keys we haven't. So to do a lookup in a btree node, we have to search
* each sorted set. But we do merge written sets together lazily, so the cost of
* these extra searches is quite low (normally most of the keys in a btree node
* will be in one big set, and then there'll be one or two sets that are much
* smaller).
*
* This log structure makes bcache's btree more of a hybrid between a
* conventional btree and a compacting data structure, with some of the
* advantages of both.
*
* GARBAGE COLLECTION:
*
* We can't just invalidate any bucket - it might contain dirty data or
* metadata. If it once contained dirty data, other writes might overwrite it
* later, leaving no valid pointers into that bucket in the index.
*
* Thus, the primary purpose of garbage collection is to find buckets to reuse.
* It also counts how much valid data it each bucket currently contains, so that
* allocation can reuse buckets sooner when they've been mostly overwritten.
*
* It also does some things that are really internal to the btree
* implementation. If a btree node contains pointers that are stale by more than
* some threshold, it rewrites the btree node to avoid the bucket's generation
* wrapping around. It also merges adjacent btree nodes if they're empty enough.
*
* THE JOURNAL:
*
* Bcache's journal is not necessary for consistency; we always strictly
* order metadata writes so that the btree and everything else is consistent on
* disk in the event of an unclean shutdown, and in fact bcache had writeback
* caching (with recovery from unclean shutdown) before journalling was
* implemented.
*
* Rather, the journal is purely a performance optimization; we can't complete a
* write until we've updated the index on disk, otherwise the cache would be
* inconsistent in the event of an unclean shutdown. This means that without the
* journal, on random write workloads we constantly have to update all the leaf
* nodes in the btree, and those writes will be mostly empty (appending at most
* a few keys each) - highly inefficient in terms of amount of metadata writes,
* and it puts more strain on the various btree resorting/compacting code.
*
* The journal is just a log of keys we've inserted; on startup we just reinsert
* all the keys in the open journal entries. That means that when we're updating
* a node in the btree, we can wait until a 4k block of keys fills up before
* writing them out.
*
* For simplicity, we only journal updates to leaf nodes; updates to parent
* nodes are rare enough (since our leaf nodes are huge) that it wasn't worth
* the complexity to deal with journalling them (in particular, journal replay)
* - updates to non leaf nodes just happen synchronously (see btree_split()).
*/
#define pr_fmt(fmt) "bcache: %s() " fmt "\n", __func__
#include <linux/bcache.h>
#include <linux/bio.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/rbtree.h>
#include <linux/rwsem.h>
#include <linux/types.h>
#include <linux/workqueue.h>
#include "bset.h"
#include "util.h"
#include "closure.h"
struct bucket {
atomic_t pin;
uint16_t prio;
uint8_t gen;
uint8_t last_gc; /* Most out of date gen in the btree */
uint16_t gc_mark; /* Bitfield used by GC. See below for field */
};
/*
* I'd use bitfields for these, but I don't trust the compiler not to screw me
* as multiple threads touch struct bucket without locking
*/
BITMASK(GC_MARK, struct bucket, gc_mark, 0, 2);
#define GC_MARK_RECLAIMABLE 1
#define GC_MARK_DIRTY 2
#define GC_MARK_METADATA 3
#define GC_SECTORS_USED_SIZE 13
#define MAX_GC_SECTORS_USED (~(~0ULL << GC_SECTORS_USED_SIZE))
BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, GC_SECTORS_USED_SIZE);
BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1);
#include "journal.h"
#include "stats.h"
struct search;
struct btree;
struct keybuf;
struct keybuf_key {
struct rb_node node;
BKEY_PADDED(key);
void *private;
};
struct keybuf {
struct bkey last_scanned;
spinlock_t lock;
/*
* Beginning and end of range in rb tree - so that we can skip taking
* lock and checking the rb tree when we need to check for overlapping
* keys.
*/
struct bkey start;
struct bkey end;
struct rb_root keys;
#define KEYBUF_NR 500
DECLARE_ARRAY_ALLOCATOR(struct keybuf_key, freelist, KEYBUF_NR);
};
struct bcache_device {
struct closure cl;
struct kobject kobj;
struct cache_set *c;
unsigned id;
#define BCACHEDEVNAME_SIZE 12
char name[BCACHEDEVNAME_SIZE];
struct gendisk *disk;
unsigned long flags;
#define BCACHE_DEV_CLOSING 0
#define BCACHE_DEV_DETACHING 1
#define BCACHE_DEV_UNLINK_DONE 2
unsigned nr_stripes;
unsigned stripe_size;
atomic_t *stripe_sectors_dirty;
unsigned long *full_dirty_stripes;
unsigned long sectors_dirty_last;
long sectors_dirty_derivative;
struct bio_set *bio_split;
unsigned data_csum:1;
int (*cache_miss)(struct btree *, struct search *,
struct bio *, unsigned);
int (*ioctl) (struct bcache_device *, fmode_t, unsigned, unsigned long);
};
struct io {
/* Used to track sequential IO so it can be skipped */
struct hlist_node hash;
struct
|