summaryrefslogtreecommitdiff
path: root/drivers/md/bcache/bset.h
blob: a50dcfda656f5f9426eb66ac6620348aa23e2a0d (plain)
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHE_BSET_H
#define _BCACHE_BSET_H

#include <linux/bcache.h>
#include <linux/kernel.h>
#include <linux/types.h>

#include "util.h" /* for time_stats */

/*
 * BKEYS:
 *
 * A bkey contains a key, a size field, a variable number of pointers, and some
 * ancillary flag bits.
 *
 * We use two different functions for validating bkeys, bch_ptr_invalid and
 * bch_ptr_bad().
 *
 * bch_ptr_invalid() primarily filters out keys and pointers that would be
 * invalid due to some sort of bug, whereas bch_ptr_bad() filters out keys and
 * pointer that occur in normal practice but don't point to real data.
 *
 * The one exception to the rule that ptr_invalid() filters out invalid keys is
 * that it also filters out keys of size 0 - these are keys that have been
 * completely overwritten. It'd be safe to delete these in memory while leaving
 * them on disk, just unnecessary work - so we filter them out when resorting
 * instead.
 *
 * We can't filter out stale keys when we're resorting, because garbage
 * collection needs to find them to ensure bucket gens don't wrap around -
 * unless we're rewriting the btree node those stale keys still exist on disk.
 *
 * We also implement functions here for removing some number of sectors from the
 * front or the back of a bkey - this is mainly used for fixing overlapping
 * extents, by removing the overlapping sectors from the older key.
 *
 * BSETS:
 *
 * A bset is an array of bkeys laid out contiguously in memory in sorted order,
 * along with a header. A btree node is made up of a number of these, written at
 * different times.
 *
 * There could be many of them on disk, but we never allow there to be more than
 * 4 in memory - we lazily resort as needed.
 *
 * We implement code here for creating and maintaining auxiliary search trees
 * (described below) for searching an individial bset, and on top of that we
 * implement a btree iterator.
 *
 * BTREE ITERATOR:
 *
 * Most of the code in bcache doesn't care about an individual bset - it needs
 * to search entire btree nodes and iterate over them in sorted order.
 *
 * The btree iterator code serves both functions; it iterates through the keys
 * in a btree node in sorted order, starting from either keys after a specific
 * point (if you pass it a search key) or the start of the btree node.
 *
 * AUXILIARY SEARCH TREES:
 *
 * Since keys are variable length, we can't use a binary search on a bset - we
 * wouldn't be able to find the start of the next key. But binary searches are
 * slow anyways, due to terrible cache behaviour; bcache originally used binary
 * searches and that code topped out at under 50k lookups/second.
 *
 * So we need to construct some sort of lookup table. Since we only insert keys
 * into the last (unwritten) set, most of the keys within a given btree node are
 * usually in sets that are mostly constant. We use two different types of
 * lookup tables to take advantage of this.
 *
 * Both lookup tables share in common that they don't index every key in the
 * set; they index one key every BSET_CACHELINE bytes, and then a linear search
 * is used for the rest.
 *
 * For sets that have been written to disk and are no longer being inserted
 * into, we construct a binary search tree in an array - traversing a binary
 * search tree in an array gives excellent locality of reference and is very
 * fast, since both children of any node are adjacent to each other in memory
 * (and their grandchildren, and great grandchildren...) - this means
 * prefetching can be used to great effect.
 *
 * It's quite useful performance wise to keep these nodes small - not just
 * because they're more likely to be in L2, but also because we can prefetch
 * more nodes on a single cacheline and thus prefetch more iterations in advance
 * when traversing this tree.
 *
 * Nodes in the auxiliary search tree must contain both a key to compare against
 * (we don't want to fetch the key from the set, that would defeat the purpose),
 * and a pointer to the key. We use a few tricks to compress both of these.
 *
 * To compress the pointer, we take advantage of the fact that one node in the
 * search tree corresponds to precisely BSET_CACHELINE bytes in the set. We have
 * a function (to_inorder()) that takes the index of a node in a binary tree and
 * returns what its index would be in an inorder traversal, so we only have to
 * store the low bits of the offset.
 *
 * The key is 84 bits (KEY_DEV + key->key, the offset on the device). To
 * compress that,  we take advantage of the fact that when we're traversing the
 * search tree at every iteration we know that both our search key and the key
 * we're looking for lie within some range - bounded by our previous
 * comparisons. (We special case the start of a search so that this is true even
 * at the root of the tree).
 *
 * So we know the key we're looking for is between a and b, and a and b don't
 * differ higher than bit 50, we don't need to check anything higher than bit
 * 50.
 *
 * We don't usually need the rest of the bits, either; we only need enough bits
 * to partition the key range we're currently checking.  Consider key n - the
 * key our auxiliary search tree node corresponds to, and key p, the key
 * immediately preceding n.  The lowest bit we need to store in the auxiliary
 * search tree is the highest bit that differs between n and p.
 *
 * Note that this could be bit 0 - we might sometimes need all 80 bits to do the
 * comparison. But we'd really like our nodes in the auxiliary search tree to be
 * of fixed size.
 *
 * The solution is to make them fixed size, and when we're constructing a node
 * check if p and n differed in the bits we needed them to. If they don't we
 * flag that node, and when doing lookups we fallback to comparing against the
 * real key. As long as this doesn't happen to often (and it seems to reliably
 * happen a bit less than 1% of the time), we win - even on failures, that key
 * is then more likely to be in cache than if we were doing binary searches all
 * the way, since we're touching so much less memory.
 *
 * The keys in the auxiliary search tree are stored in (software) floating
 * point, with an exponent and a mantissa. The exponent needs to be big enough
 * to address all the bits in the original key, but the number of bits in the
 * mantissa is somewhat arbitrary; more bits just gets us fewer failures.
 *
 * We need 7 bits for the exponent and 3 bits for the key's offset (since keys
 * are 8 byte aligned); using 22 bits for the mantissa means a node is 4 bytes.
 * We need one node per 128 bytes in the btree node, which means the auxiliary
 * search trees take up 3% as much memory as the btree itself.
 *
 * Constructing these auxiliary search trees is moderately expensive, and we
 * don't want to be constantly rebuilding the search tree for the last set
 * whenever we insert another key into it. For the unwritten set, we use a much
 * simpler lookup table - it's just a flat array, so index i in the lookup table
 * corresponds to the i range of BSET_CACHELINE bytes in the set. Indexing
 * within each byte range works the same as with the auxiliary search trees.
 *
 * These are much easier to keep up to date when we insert a key - we do it
 * somewhat lazily; when we shift a key up we usually just increment the pointer
 * to it, only when it would overflow do we go to the trouble of finding the
 * first key in that range of bytes again.
 */

struct btree_keys;
struct btree_iter;
struct btree_iter_set;
struct bkey_float;

#define MAX_BSETS		4U

struct bset_tree {
	/*
	 * We construct a binary tree in an array as if the array
	 * started at 1, so that things line up on the same cachelines
	 * better: see comments in bset.c at cacheline_to_bkey() for
	 * details
	 */

	/* size of the binary tree and prev array */
	unsigned int		size;

	/* function of size - precalculated for to_inorder() */
	unsigned int		extra;

	/* copy of the last key in the set */
	struct bkey		end;
	struct bkey_float	*tree;

	/*
	 * The nodes in the bset tree point to specific keys - this
	 * array holds the sizes of the previous key.
	 *
	 * Conceptually it's a member of struct bkey_float, but we want
	 * to keep bkey_float to 4 bytes and prev isn't used in the fast
	 * path.
	 */
	uint8_t			*prev;

	/* The actual btree node, with pointers to each sorted set */
	struct bset		*data;
};

struct btree_keys_ops {
	bool		(*sort_cmp)(struct btree_iter_set l,
				    struct btree_iter_set r);
	struct bkey	*(*sort_fixup)(struct btree_iter *iter,
				       struct bkey *tmp);
	bool		(*insert_fixup)(struct btree_keys *b,
					struct bkey *insert,
					struct btree_iter *iter,
					struct bkey *replace_key);
	bool		(*key_invalid)(struct btree_keys *bk,
				       const struct bkey *k);
	bool		(*key_bad)(struct btree_keys *bk,
				   const struct bkey *k);
	bool		(*key_merge)(struct btree_keys *bk,
				     struct bkey *l, struct bkey *r);
	void		(*key_to_text)(char *buf,
				       size_t size,
				       const struct bkey *k);
	void		(*key_dump)(struct btree_keys *keys,
				    const struct bkey *k);

	/*
	 * Only used for deciding whether to use START_KEY(k) or just the key
	 * itself in a couple places
	 */
	bool		is_extents;
};

struct btree_keys {
	const struct btree_keys_ops	*ops;
	uint8_t			page_order;
	uint8_t			nsets;
	unsigned int		last_set_unwritten:1;
	bool			*expensive_debug_checks;

	/*
	 * Sets of sorted keys - the real btree node - plus a binary search tree
	 *
	 * set[0] is special; set[0]->tree, set[0]->prev and set[0]->data point
	 * to the memory we have allocated for this btree node. Additionally,
	 * set[0]->data points to the entire btree node as it exists on disk.
	 */
	struct bset_tree	set[MAX_BSETS];
};

static inline struct bset_tree *bset_tree_last(struct btree_keys *b)
{
	return b->set + b->nsets;
}

static inline bool bset_written(struct btree_keys *b, struct bset_tree *t)
{
	return t <= b->set + b->nsets - b->last_set_unwritten;
}

static inline bool bkey_written(struct btree_keys *b, struct bkey *k)
{
	return !b->last_set_unwritten || k < b->set[b->nsets].data->start;
}

static inline unsigned int bset_byte_offset(struct btree_keys *b,
					    struct bset *i)
{
	return ((size_t) i) - ((size_t) b->set->data);
}

static inline unsigned int bset_sector_offset(struct btree_keys *b,
					      struct bset *i)
{
	return bset_byte_offset(b, i) >> 9;
}

#define __set_bytes(i, k)	(sizeof(*(i)) + (k) * sizeof(uint64_t))
#define set_bytes(i)		__set_bytes(i, i->keys)

#define __set_blocks(i, k, block_bytes)				\
	DIV_ROUND_UP(__set_bytes(i, k), block_bytes)
#define set_blocks(i, block_bytes)				\
	__set_blocks(i, (i)->keys, block_bytes)

static inline size_t bch_btree_keys_u64s_remaining(struct btree_keys *b)
{
	struct bset_tree *t = bset_tree_last(b);

	BUG_ON((PAGE_SIZE << b->page_order) <
	       (bset_byte_offset(b, t->data) + set_bytes(t->data)));

	if (!b->last_set_unwritten)
		return 0;

	return ((PAGE_SIZE << b->page_order) -
		(bset_byte_offset(b, t->data) + set_bytes(t->data))) /
		sizeof(u64);
}

static inline struct bset *bset_next_set(struct btree_keys *b,
					 unsigned int block_bytes)
{
	struct bset *i = bset_tree_last(b)->data;

	return ((void *) i) + roundup(set_bytes(i), block_bytes);
}

void bch_btree_keys_free(struct btree_keys *b);
int bch_btree_keys_alloc(struct btree_keys *b, unsigned int page_order,
			 gfp_t gfp);
void bch_btree_keys_init(struct btree_keys *b, const struct btree_keys_ops *ops,
			 bool *expensive_debug_checks);

void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic);
void bch_bset_build_written_tree(struct btree_keys *b);
void bch_bset_fix_invalidated_key(struct btree_keys *b, struct bkey *k);
bool bch_bkey_try_merge(struct btree_keys *b, struct bkey *l, struct bkey *r);
void bch_bset_insert(struct btree_keys *b, struct bkey *where,
		     struct bkey *insert);
unsigned int bch_btree_insert_key(struct btree_keys *b, struct bkey *k,
			      struct bkey *replace_key);

enum {
	BTREE_INSERT_STATUS_NO_INSERT = 0,
	BTREE_INSERT_STATUS_INSERT,
	BTREE_INSERT_STATUS_BACK_MERGE,
	BTREE_INSERT_STATUS_OVERWROTE,
	BTREE_INSERT_STATUS_FRONT_MERGE,
};

/* Btree key iteration */

struct btree_iter {
	size_t size, used;
#ifdef CONFIG_BCACHE_DEBUG
	struct btree_keys *b;
#endif
	struct btree_iter_set {
		struct bkey *k, *end;
	} data[MAX_BSETS];
};

typedef bool (*ptr_filter_fn)(struct btree_keys *b, const struct bkey *k);

struct bkey *bch_btree_iter_next(struct btree_iter *iter);
struct bkey *bch_btree_iter_next_filter(struct btree_iter *iter,
					struct btree_keys *b,
					ptr_filter_fn fn);

void bch_btree_iter_push(struct btree_iter *iter, struct bkey *k,
			 struct bkey *end);
struct bkey *bch_btree_iter_init(struct btree_keys *b,
				 struct btree_iter *iter,
				 struct bkey *search);

struct bkey *__bch_bset_search(struct btree_keys *b, struct bset_tree *t,
			       const struct bkey *search);

/*
 * Returns the first key that is strictly greater than search
 */
static inline struct bkey *bch_bset_search(struct btree_keys *b,
					   struct bset_tree *t,
					   const struct bkey *search)
{
	return search ? __bch_bset_search(b, t, search) : t->data->start;
}

#define for_each_key_filter(b, k, iter, filter)				\
	for (bch_btree_iter_init((b), (iter), NULL);			\
	     ((k) = bch_btree_iter_next_filter((iter), (b), filter));)

#define for_each_key(b, k, iter)					\
	for (bch_btree_iter_init((b), (iter), NULL);			\
	     ((k) = bch_btree_iter_next(iter));)

/* Sorting */

struct bset_sort_state {
	mempool_t		pool;

	unsigned int		page_order;
	unsigned int		crit_factor;

	struct time_stats	time;
};

void bch_bset_sort_state_free(struct bset_sort_state *state);
int bch_bset_sort_state_init(struct bset_sort_state *state,
			     unsigned int page_order);
void bch_btree_sort_lazy(struct btree_keys *b, struct bset_sort_state *state);
void bch_btree_sort_into(struct btree_keys *b, struct btree_keys *new,
			 struct bset_sort_state *state);
void bch_btree_sort_and_fix_extents(struct btree_keys *b,
				    struct btree_iter *iter,
				    struct bset_sort_state *state);
void bch_btree_sort_partial(struct btree_keys *b, unsigned int start,
			    struct bset_sort_state *state);

static inline void bch_btree_sort(struct btree_keys *b,
				  struct bset_sort_state *state)
{
	bch_btree_sort_partial(b, 0, state);
}

struct bset_stats {
	size_t sets_written, sets_unwritten;
	size_t bytes_written, bytes_unwritten;
	size_t floats, failed;
};

void bch_btree_keys_stats(struct btree_keys *b, struct bset_stats *state);

/* Bkey utility code */

#define bset_bkey_last(i)	bkey_idx((struct bkey *) (i)->d, \
					 (unsigned int)(i)->keys)

static inline struct bkey *bset_bkey_idx(struct bset *i, unsigned int idx)
{
	return bkey_idx(i->start, idx);
}

static inline void bkey_init(struct bkey *k)
{
	*k = ZERO_KEY;
}

static __always_inline int64_t bkey_cmp(const struct bkey *l,
					const struct bkey *r)
{
	return unlikely(KEY_INODE(l) != KEY_INODE(r))
		? (int64_t) KEY_INODE(l) - (int64_t) KEY_INODE(r)
		: (int64_t) KEY_OFFSET(l) - (int64_t) KEY_OFFSET(r);
}

void bch_bkey_copy_single_ptr(struct bkey *dest, const struct bkey *src,
			      unsigned int i);
bool __bch_cut_front(const struct bkey *where, struct bkey *k);
bool __bch_cut_back(const struct bkey *where, struct bkey *k);

static inline bool bch_cut_front(const struct bkey *where, struct bkey *k)
{
	BUG_ON(bkey_cmp(where, k) > 0);
	return __bch_cut_front(where, k);
}

static inline bool bch_cut_back(const struct bkey *where, struct bkey *k)
{
	BUG_ON(bkey_cmp(where, &START_KEY(k)) < 0);
	return __bch_cut_back(where, k);
}

/*
 * Pointer '*preceding_key_p' points to a memory object to store preceding
 * key of k. If the preceding key does not exist, set '*preceding_key_p' to
 * NULL. So the caller of preceding_key() needs to take care of memory
 * which '*preceding_key_p' pointed to before calling preceding_key().
 * Currently the only caller of preceding_key() is bch_btree_insert_key(),
 * and it points to an on-stack variable, so the memory release is handled
 * by stackframe itself.
 */
static inline void preceding_key(struct bkey *k, struct bkey **preceding_key_p)
{
	if (KEY_INODE(k) || KEY_OFFSET(k)) {
		(**preceding_key_p) = KEY(KEY_INODE(k), KEY_OFFSET(k), 0);
		if (!(*preceding_key_p)->low)
			(*preceding_key_p)->high--;
		(*preceding_key_p)->low--;
	} else {
		(*preceding_key_p) = NULL;
	}
}

static inline bool bch_ptr_invalid(struct btree_keys *b, const struct bkey *k)
{
	return b->ops->key_invalid(b, k);
}

static inline bool bch_ptr_bad(struct btree_keys *b, const struct bkey *k)
{
	return b->ops->key_bad(b, k);
}

static inline void bch_bkey_to_text(struct btree_keys *b, char *buf,
				    size_t size, const struct bkey *k)
{
	return b->ops->key_to_text(buf, size, k);
}

static inline bool bch_bkey_equal_header(const struct bkey *l,
					 const struct bkey *r)
{
	return (KEY_DIRTY(l) == KEY_DIRTY(r) &&
		KEY_PTRS(l) == KEY_PTRS(r) &&
		KEY_CSUM(l) == KEY_CSUM(r));
}

/* Keylists */

struct keylist {
	union {
		struct bkey		*keys;
		uint64_t		*keys_p;
	};
	union {
		struct bkey		*top;
		uint64_t		*top_p;
	};

	/* Enough room for btree_split's keys without realloc */
#define KEYLIST_INLINE		16
	uint64_t		inline_keys[KEYLIST_INLINE];
};

static inline void bch_keylist_init(struct keylist *l)
{
	l->top_p = l->keys_p = l->inline_keys;
}

static inline void bch_keylist_init_single(struct keylist *l, struct bkey *k)
{
	l->keys = k;
	l->top = bkey_next(k);
}

static inline void bch_keylist_push(struct keylist *l)
{
	l->top = bkey_next(l->top);
}

static inline void bch_keylist_add(struct keylist *l, struct bkey *k)
{
	bkey_copy(l->top, k);
	bch_keylist_push(l);
}

static inline bool bch_keylist_empty(struct keylist *l)
{
	return l->top == l->keys;
}

static inline void bch_keylist_reset(struct keylist *l)
{
	l->top = l->keys;
}

static inline void bch_keylist_free(struct keylist *l)
{
	if (l->keys_p != l->inline_keys)
		kfree(l->keys_p);
}

static inline size_t bch_keylist_nkeys(struct keylist *l)
{
	return l->top_p - l->keys_p;
}

static inline size_t bch_keylist_bytes(struct keylist *l)
{
	return bch_keylist_nkeys(l) * sizeof(uint64_t);
}

struct bkey *bch_keylist_pop(struct keylist *l);
void bch_keylist_pop_front(struct keylist *l);
int __bch_keylist_realloc(struct keylist *l, unsigned int u64s);

/* Debug stuff */

#ifdef CONFIG_BCACHE_DEBUG

int __bch_count_data(struct btree_keys *b);
void __printf(2, 3) __bch_check_keys(struct btree_keys *b,
				     const char *fmt,
				     ...);
void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned int set);
void bch_dump_bucket(struct btree_keys *b);

#else

static inline int __bch_count_data(struct btree_keys *b) { return -1; }
static inline void __printf(2, 3)
	__bch_check_keys(struct btree_keys *b, const char *fmt, ...) {}
static inline void bch_dump_bucket(struct btree_keys *b) {}
void bch_dump_bset(struct btree_keys *b, struct bset *i, unsigned int set);

#endif

static inline bool btree_keys_expensive_checks(struct btree_keys *b)
{
#ifdef CONFIG_BCACHE_DEBUG
	return *b->expensive_debug_checks;
#else
	return false;
#endif
}

static inline int bch_count_data(struct btree_keys *b)
{
	return btree_keys_expensive_checks(b) ? __bch_count_data(b) : -1;
}

#define bch_check_keys(b, ...)						\
do {									\
	if (btree_keys_expensive_checks(b))				\
		__bch_check_keys(b, __VA_ARGS__);			\
} while (0)

#endif