summaryrefslogtreecommitdiff
path: root/drivers/md/bcache/alloc.c
blob: 4c9852d92b0a909d5b103510ae77d55f4bb05ad0 (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
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
/*
 * Primary bucket allocation code
 *
 * Copyright 2012 Google, Inc.
 *
 * Allocation in bcache is done in terms of buckets:
 *
 * Each bucket has associated an 8 bit gen; this gen corresponds to the gen in
 * btree pointers - they must match for the pointer to be considered valid.
 *
 * Thus (assuming a bucket has no dirty data or metadata in it) we can reuse a
 * bucket simply by incrementing its gen.
 *
 * The gens (along with the priorities; it's really the gens are important but
 * the code is named as if it's the priorities) are written in an arbitrary list
 * of buckets on disk, with a pointer to them in the journal header.
 *
 * When we invalidate a bucket, we have to write its new gen to disk and wait
 * for that write to complete before we use it - otherwise after a crash we
 * could have pointers that appeared to be good but pointed to data that had
 * been overwritten.
 *
 * Since the gens and priorities are all stored contiguously on disk, we can
 * batch this up: We fill up the free_inc list with freshly invalidated buckets,
 * call prio_write(), and when prio_write() finishes we pull buckets off the
 * free_inc list and optionally discard them.
 *
 * free_inc isn't the only freelist - if it was, we'd often to sleep while
 * priorities and gens were being written before we could allocate. c->free is a
 * smaller freelist, and buckets on that list are always ready to be used.
 *
 * If we've got discards enabled, that happens when a bucket moves from the
 * free_inc list to the free list.
 *
 * There is another freelist, because sometimes we have buckets that we know
 * have nothing pointing into them - these we can reuse without waiting for
 * priorities to be rewritten. These come from freed btree nodes and buckets
 * that garbage collection discovered no longer had valid keys pointing into
 * them (because they were overwritten). That's the unused list - buckets on the
 * unused list move to the free list, optionally being discarded in the process.
 *
 * It's also important to ensure that gens don't wrap around - with respect to
 * either the oldest gen in the btree or the gen on disk. This is quite
 * difficult to do in practice, but we explicitly guard against it anyways - if
 * a bucket is in danger of wrapping around we simply skip invalidating it that
 * time around, and we garbage collect or rewrite the priorities sooner than we
 * would have otherwise.
 *
 * bch_bucket_alloc() allocates a single bucket from a specific cache.
 *
 * bch_bucket_alloc_set() allocates one or more buckets from different caches
 * out of a cache set.
 *
 * free_some_buckets() drives all the processes described above. It's called
 * from bch_bucket_alloc() and a few other places that need to make sure free
 * buckets are ready.
 *
 * invalidate_buckets_(lru|fifo)() find buckets that are available to be
 * invalidated, and then invalidate them and stick them on the free_inc list -
 * in either lru or fifo order.
 */

#include "bcache.h"
#include "btree.h"

#include <linux/blkdev.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/random.h>
#include <trace/events/bcache.h>

/* Bucket heap / gen */

uint8_t bch_inc_gen(struct cache *ca, struct bucket *b)
{
	uint8_t ret = ++b->gen;

	ca->set->need_gc = max(ca->set->need_gc, bucket_gc_gen(b));
	WARN_ON_ONCE(ca->set->need_gc > BUCKET_GC_GEN_MAX);

	if (CACHE_SYNC(&ca->set->sb)) {
		ca->need_save_prio = max(ca->need_save_prio,
					 bucket_disk_gen(b));
		WARN_ON_ONCE(ca->need_save_prio > BUCKET_DISK_GEN_MAX);
	}

	return ret;
}

void bch_rescale_priorities(struct cache_set *c, int sectors)
{
	struct cache *ca;
	struct bucket *b;
	unsigned next = c->nbuckets * c->sb.bucket_size / 1024;
	unsigned i;
	int r;

	atomic_sub(sectors, &c->rescale);

	do {
		r = atomic_read(&c->rescale);

		if (r >= 0)
			return;
	} while (atomic_cmpxchg(&c->rescale, r, r + next) != r);

	mutex_lock(&c->bucket_lock);

	c->min_prio = USHRT_MAX;

	for_each_cache(ca, c, i)
		for_each_bucket(b, ca)
			if (b->prio &&
			    b->prio != BTREE_PRIO &&
			    !atomic_read(&b->pin)) {
				b->prio--;
				c->min_prio = min(c->min_prio, b->prio);
			}

	mutex_unlock(&c->bucket_lock);
}

/* Allocation */

static inline bool can_inc_bucket_gen(struct bucket *b)
{
	return bucket_gc_gen(b) < BUCKET_GC_GEN_MAX &&
		bucket_disk_gen(b) < BUCKET_DISK_GEN_MAX;
}

bool bch_bucket_add_unused(struct cache *ca, struct bucket *b)
{
	BUG_ON(GC_MARK(b) || GC_SECTORS_USED(b));

	if (fifo_used(&ca->free) > ca->watermark[WATERMARK_MOVINGGC] &&
	    CACHE_REPLACEMENT(&ca->sb) == CACHE_REPLACEMENT_FIFO)
		return false;

	b->prio = 0;

	if (can_inc_bucket_gen(b) &&
	    fifo_push(&ca->unused, b - ca->buckets)) {
		atomic_inc(&b->pin);
		return true;
	}

	return false;
}

static bool can_invalidate_bucket(struct cache *ca, struct bucket *b)
{
	return GC_MARK(b) == GC_MARK_RECLAIMABLE &&
		!atomic_read(&b->pin) &&
		can_inc_bucket_gen(b);
}

static void invalidate_one_bucket(struct cache *ca, struct bucket *b)
{
	bch_inc_gen(ca, b);
	b->prio = INITIAL_PRIO;
	atomic_inc(&b->pin);
	fifo_push(&ca->free_inc, b - ca->buckets);
}

#define bucket_prio(b)				\
	(((unsigned) (b->prio - ca->set->min_prio)) * GC_SECTORS_USED(b))

#define bucket_max_cmp(l, r)	(bucket_prio(l) < bucket_prio(r))
#define bucket_min_cmp(l, r)	(bucket_prio(l) > bucket_prio(r))

static void invalidate_buckets_lru(struct cache *ca)
{
	struct bucket *b;
	ssize_t i;

	ca->heap.used = 0;

	for_each_bucket(b, ca) {
		/*
		 * If we fill up the unused list, if we then return before
		 * adding anything to the free_inc list we'll skip writing
		 * prios/gens and just go back to allocating from the unused
		 * list:
		 */
		if (fifo_full(&ca->unused))
			return;

		if (!can_invalidate_bucket(ca, b))
			continue;

		if (!GC_SECTORS_USED(b) &&
		    bch_bucket_add_unused(ca, b))
			continue;

		if (!heap_full(&ca->heap))
			heap_add(&ca->heap, b, bucket_max_cmp);
		else if (bucket_max_cmp(b, heap_peek(&ca->heap))) {
			ca->heap.data[0] = b;
			heap_sift(&ca->heap, 0, bucket_max_cmp);
		}
	}

	for (i = ca->heap.used / 2 - 1; i >= 0; --i)
		heap_sift(&ca->heap, i, bucket_min_cmp);

	while (!fifo_full(&ca->free_inc)) {
		if (!heap_pop(&ca->heap, b, bucket_min_cmp)) {
			/*
			 * We don't want to be calling invalidate_buckets()
			 * multiple times when it can't do anything
			 */
			ca->invalidate_needs_gc = 1;
			wake_up_gc(ca->set);
			return;
		}

		invalidate_one_bucket(ca, b);
	}
}

static void invalidate_buckets_fifo(struct cache *ca)
{
	struct bucket *b;
	size_t checked = 0;

	while (!fifo_full(&ca->free_inc)) {
		if (ca->fifo_last_bucket <  ca->sb.first_bucket ||
		    ca->fifo_last_bucket >= ca->sb.nbuckets)
			ca->fifo_last_bucket = ca->sb.first_bucket;

		b = ca->buckets + ca->fifo_last_bucket++;

		if (can_invalidate_bucket(ca, b))
			invalidate_one_bucket(ca, b);

		if (++checked >= ca->sb.nbuckets) {
			ca->invalidate_needs_gc = 1;
			wake_up_gc(ca->set);
			return;
		}
	}
}

static void invalidate_buckets_random(struct cache *ca)
{
	struct bucket *b;
	size_t checked = 0;

	while (!fifo_full(&ca->free_inc)) {
		size_t n;
		get_random_bytes(&n, sizeof(n));

		n %= (size_t) (ca->sb.nbuckets - ca->sb.first_bucket);
		n += ca->sb.first_bucket;

		b = ca->buckets + n;

		if (can_invalidate_bucket(ca, b))
			invalidate_one_bucket(ca, b);

		if (++checked >= ca->sb.nbuckets / 2) {
			ca->invalidate_needs_gc = 1;
			wake_up_gc(ca->set);
			return;
		}
	}
}

static void invalidate_buckets(struct cache *ca)
{
	if (ca->invalidate_needs_gc)
		return;

	switch (CACHE_REPLACEMENT(&ca->sb)) {
	case CACHE_REPLACEMENT_LRU:
		invalidate_buckets_lru(ca);
		break;
	case CACHE_REPLACEMENT_FIFO:
		invalidate_buckets_fifo(ca);
		break;
	case CACHE_REPLACEMENT_RANDOM:
		invalidate_buckets_random(ca);
		break;
	}

	trace_bcache_alloc_invalidate(ca);
}

#define allocator_wait(ca, cond)					\
do {									\
	while (1) {							\
		set_current_state(TASK_INTERRUPTIBLE);			\
		if (cond)						\
			break;						\
									\
		mutex_unlock(&(ca)->set->bucket_lock);			\
		if (kthread_should_stop())				\
			return 0;					\
									\
		try_to_freeze();					\
		schedule();						\
		mutex_lock(&(ca)->set->bucket_lock);			\
	}								\
	__set_current_state(TASK_RUNNING);				\
} while (0)

static int bch_allocator_thread(void *arg)
{
	struct cache *ca = arg;

	mutex_lock(&ca->set->bucket_lock);

	while (1) {
		/*
		 * First, we pull buckets off of the unused and free_inc lists,
		 * possibly issue discards to them, then we add the bucket to
		 * the free list:
		 */
		while (1) {
			long bucket;

			if ((!atomic_read(&ca->set->prio_blocked) ||
			     !CACHE_SYNC(&ca->set->sb)) &&
			    !fifo_empty(&ca->unused))
				fifo_pop(&ca->unused, bucket);
			else if (!fifo_empty(&ca->free_inc))
				fifo_pop(&ca->free_inc, bucket);
			else
				break;

			if (ca->discard) {
				mutex_unlock(&ca->set->bucket_lock);
				blkdev_issue_discard(ca->bdev,
					bucket_to_sector(ca->set, bucket),
					ca->sb.block_size, GFP_KERNEL, 0);
				mutex_lock(&ca->set->bucket_lock);
			}

			allocator_wait(ca, !fifo_full(&ca->free));

			fifo_push(&ca->free, bucket);
			wake_up(&ca->set->bucket_wait);
		}

		/*
		 * We've run out of free buckets, we need to find some buckets
		 * we can invalidate. First, invalidate them in memory and add
		 * them to the free_inc list:
		 */

		allocator_wait(ca, ca->set->gc_mark_valid &&
			       (ca->need_save_prio > 64 ||
				!ca->invalidate_needs_gc));
		invalidate_buckets(ca);

		/*
		 * Now, we write their new gens to disk so we can start writing
		 * new stuff to them:
		 */
		allocator_wait(ca, !atomic_read(&ca->set->prio_blocked));
		if (CACHE_SYNC(&ca->set->sb) &&
		    (!fifo_empty(&ca->free_inc) ||
		     ca->need_save_prio > 64))
			bch_prio_write(ca);
	}
}

long bch_bucket_alloc(struct cache *ca, unsigned watermark, bool wait)
{
	DEFINE_WAIT(w);
	struct bucket *b;
	long r;

	/* fastpath */
	if (fifo_used(&ca->free) > ca->watermark[watermark]) {
		fifo_pop(&ca->free, r);
		goto out;
	}

	if (!wait)
		return -1;

	while (1) {
		if (fifo_used(&ca->free) > ca->watermark[watermark]) {
			fifo_pop(&ca->free, r);
			break;
		}

		prepare_to_wait(&ca->set->bucket_wait, &w,
				TASK_UNINTERRUPTIBLE);

		mutex_unlock(&ca->set->bucket_lock);
		schedule();
		mutex_lock(&ca->set->bucket_lock);
	}

	finish_wait(&ca->set->bucket_wait, &w);
out:
	wake_up_process(ca->alloc_thread);

	if (expensive_debug_checks(ca->set)) {
		size_t iter;
		long i;

		for (iter = 0; iter < prio_buckets(ca) * 2; iter++)
			BUG_ON(ca->prio_buckets[iter] == (uint64_t) r);

		fifo_for_each(i, &ca->free, iter)
			BUG_ON(i == r);
		fifo_for_each(i, &ca->free_inc, iter)
			BUG_ON(i == r);
		fifo_for_each(i, &ca->unused, iter)
			BUG_ON(i == r);
	}

	b = ca->buckets + r;

	BUG_ON(atomic_read(&b->pin) != 1);

	SET_GC_SECTORS_USED(b, ca->sb.bucket_size);

	if (watermark <= WATERMARK_METADATA) {
		SET_GC_MARK(b, GC_MARK_METADATA);
		SET_GC_MOVE(b, 0);
		b->prio = BTREE_PRIO;
	} else {
		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
		SET_GC_MOVE(b, 0);
		b->prio = INITIAL_PRIO;
	}

	return r;
}

void bch_bucket_free(struct cache_set *c, struct bkey *k)
{
	unsigned i;

	for (i = 0; i < KEY_PTRS(k); i++) {
		struct bucket *b = PTR_BUCKET(c, k, i);

		SET_GC_MARK(b, GC_MARK_RECLAIMABLE);
		SET_GC_SECTORS_USED(b, 0);
		bch_bucket_add_unused(PTR_CACHE(c, k, i), b);
	}
}

int __bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
			   struct bkey *k, int n, bool wait)
{
	int i;

	lockdep_assert_held(&c->bucket_lock);
	BUG_ON(!n || n > c->caches_loaded || n > 8);

	bkey_init(k);

	/* sort by free space/prio of oldest data in caches */

	for (i = 0; i < n; i++) {
		struct cache *ca = c->cache_by_alloc[i];
		long b = bch_bucket_alloc(ca, watermark, wait);

		if (b == -1)
			goto err;

		k->ptr[i] = PTR(ca->buckets[b].gen,
				bucket_to_sector(c, b),
				ca->sb.nr_this_dev);

		SET_KEY_PTRS(k, i + 1);
	}

	return 0;
err:
	bch_bucket_free(c, k);
	bkey_put(c, k);
	return -1;
}

int bch_bucket_alloc_set(struct cache_set *c, unsigned watermark,
			 struct bkey *k, int n, bool wait)
{
	int ret;
	mutex_lock(&c->bucket_lock);
	ret = __bch_bucket_alloc_set(c, watermark, k, n, wait);
	mutex_unlock(&c->bucket_lock);
	return ret;
}

/* Sector allocator */

struct open_bucket {
	struct list_head	list;
	unsigned		last_write_point;
	unsigned		sectors_free;
	BKEY_PADDED(key);
};

/*
 * We keep multiple buckets open for writes, and try to segregate different
 * write streams for better cache utilization: first we look for a bucket where
 * the last write to it was sequential with the current write, and failing that
 * we look for a bucket that was last used by the same task.
 *
 * The ideas is if you've got multiple tasks pulling data into the cache at the
 * same time, you'll get better cache utilization if you try to segregate their
 * data and preserve locality.
 *
 * For example, say you've starting Firefox at the same time you're copying a
 * bunch of files. Firefox will likely end up being fairly hot and stay in the
 * cache awhile, but the data you copied might not be; if you wrote all that
 * data to the same buckets it'd get invalidated at the same time.
 *
 * Both of those tasks will be doing fairly random IO so we can't rely on
 * detecting sequential IO to segregate their data, but going off of the task
 * should be a sane heuristic.
 */
static struct open_bucket *pick_data_bucket(struct cache_set *c,
					    const struct bkey *search,
					    unsigned write_point,
					    struct bkey *alloc)
{
	struct open_bucket *ret, *ret_task = NULL;

	list_for_each_entry_reverse(ret, &c->data_buckets, list)
		if (!bkey_cmp(&ret->key, search))
			goto found;
		else if (ret->last_write_point == write_point)
			ret_task = ret;

	ret = ret_task ?: list_first_entry(&c->data_buckets,
					   struct open_bucket, list);
found:
	if (!ret->sectors_free && KEY_PTRS(alloc)) {
		ret->sectors_free = c->sb.bucket_size;
		bkey_copy(&ret->key, alloc);
		bkey_init(alloc);
	}

	if (!ret->sectors_free)
		ret = NULL;

	return ret;
}

/*
 * Allocates some space in the cache to write to, and k to point to the newly
 * allocated space, and updates KEY_SIZE(k) and KEY_OFFSET(k) (to point to the
 * end of the newly allocated space).
 *
 * May allocate fewer sectors than @sectors, KEY_SIZE(k) indicates how many
 * sectors were actually allocated.
 *
 * If s->writeback is true, will not fail.
 */
bool bch_alloc_sectors(struct cache_set *c, struct bkey *k, unsigned sectors,
		       unsigned write_point, unsigned write_prio, bool wait)
{
	struct open_bucket *b;
	BKEY_PADDED(key) alloc;
	unsigned i;

	/*
	 * We might have to allocate a new bucket, which we can't do with a
	 * spinlock held. So if we have to allocate, we drop the lock, allocate
	 * and then retry. KEY_PTRS() indicates whether alloc points to
	 * allocated bucket(s).
	 */

	bkey_init(&alloc.key);
	spin_lock(&c->data_bucket_lock);

	while (!(b = pick_data_bucket(c, k, write_point, &alloc.key))) {
		unsigned watermark = write_prio
			? WATERMARK_MOVINGGC
			: WATERMARK_NONE;

		spin_unlock(&c->data_bucket_lock);

		if (bch_bucket_alloc_set(c, watermark, &alloc.key, 1, wait))
			return false;

		spin_lock(&c->data_bucket_lock);
	}

	/*
	 * If we had to allocate, we might race and not need to allocate the
	 * second time we call find_data_bucket(). If we allocated a bucket but
	 * didn't use it, drop the refcount bch_bucket_alloc_set() took:
	 */
	if (KEY_PTRS(&alloc.key))
		bkey_put(c, &alloc.key);

	for (i = 0; i < KEY_PTRS(&b->key); i++)
		EBUG_ON(ptr_stale(c, &b->key, i));

	/* Set up the pointer to the space we're allocating: */

	for (i = 0; i < KEY_PTRS(&b->key); i++)
		k->ptr[i] = b->key.ptr[i];

	sectors = min(sectors, b->sectors_free);

	SET_KEY_OFFSET(k, KEY_OFFSET(k) + sectors);
	SET_KEY_SIZE(k, sectors);
	SET_KEY_PTRS(k, KEY_PTRS(&b->key));

	/*
	 * Move b to the end of the lru, and keep track of what this bucket was
	 * last used for:
	 */
	list_move_tail(&b->list, &c->data_buckets);
	bkey_copy_key(&b->key, k);
	b->last_write_point = write_point;

	b->sectors_free	-= sectors;

	for (i = 0; i < KEY_PTRS(&b->key); i++) {
		SET_PTR_OFFSET(&b->key, i, PTR_OFFSET(&b->key, i) + sectors);

		atomic_long_add(sectors,
				&PTR_CACHE(c, &b->key, i)->sectors_written);
	}

	if (b->sectors_free < c->sb.block_size)
		b->sectors_free = 0;

	/*
	 * k takes refcounts on the buckets it points to until it's inserted
	 * into the btree, but if we're done with this bucket we just transfer
	 * get_data_bucket()'s refcount.
	 */
	if (b->sectors_free)
		for (i = 0; i < KEY_PTRS(&b->key); i++)
			atomic_inc(&PTR_BUCKET(c, &b->key, i)->pin);

	spin_unlock(&c->data_bucket_lock);
	return true;
}

/* Init */

void bch_open_buckets_free(struct cache_set *c)
{
	struct open_bucket *b;

	while (!list_empty(&c->data_buckets)) {
		b = list_first_entry(&c->data_buckets,
				     struct open_bucket, list);
		list_del(&b->list);
		kfree(b);
	}
}

int bch_open_buckets_alloc(struct cache_set *c)
{
	int i;

	spin_lock_init(&c->data_bucket_lock);

	for (i = 0; i < 6; i++) {
		struct open_bucket *b = kzalloc(sizeof(*b), GFP_KERNEL);
		if (!b)
			return -ENOMEM;

		list_add(&b->list, &c->data_buckets);
	}

	return 0;
}

int bch_cache_allocator_start(struct cache *ca)
{
	struct task_struct *k = kthread_run(bch_allocator_thread,
					    ca, "bcache_allocator");
	if (IS_ERR(k))
		return PTR_ERR(k);

	ca->alloc_thread = k;
	return 0;
}

int bch_cache_allocator_init(struct cache *ca)
{
	/*
	 * Reserve:
	 * Prio/gen writes first
	 * Then 8 for btree allocations
	 * Then half for the moving garbage collector
	 */

	ca->watermark[WATERMARK_PRIO] = 0;

	ca->watermark[WATERMARK_METADATA] = prio_buckets(ca);

	ca->watermark[WATERMARK_MOVINGGC] = 8 +
		ca->watermark[WATERMARK_METADATA];

	ca->watermark[WATERMARK_NONE] = ca->free.size / 2 +
		ca->watermark[WATERMARK_MOVINGGC];

	return 0;
}