summaryrefslogtreecommitdiff
path: root/fs/bcachefs/movinggc.c
blob: 256431a6dc0caf502b11808877b625848048ad75 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Moving/copying garbage collector
 *
 * Copyright 2012 Google, Inc.
 */

#include "bcachefs.h"
#include "alloc_background.h"
#include "alloc_foreground.h"
#include "btree_iter.h"
#include "btree_update.h"
#include "btree_write_buffer.h"
#include "buckets.h"
#include "clock.h"
#include "disk_groups.h"
#include "errcode.h"
#include "error.h"
#include "extents.h"
#include "eytzinger.h"
#include "io.h"
#include "keylist.h"
#include "lru.h"
#include "move.h"
#include "movinggc.h"
#include "super-io.h"
#include "trace.h"

#include <linux/bsearch.h>
#include <linux/freezer.h>
#include <linux/kthread.h>
#include <linux/math64.h>
#include <linux/sched/task.h>
#include <linux/sort.h>
#include <linux/wait.h>

struct buckets_in_flight {
	struct rhashtable		table;
	struct move_bucket_in_flight	*first;
	struct move_bucket_in_flight	*last;
	size_t				nr;
	size_t				sectors;
};

static const struct rhashtable_params bch_move_bucket_params = {
	.head_offset	= offsetof(struct move_bucket_in_flight, hash),
	.key_offset	= offsetof(struct move_bucket_in_flight, bucket.k),
	.key_len	= sizeof(struct move_bucket_key),
};

static struct move_bucket_in_flight *
move_bucket_in_flight_add(struct buckets_in_flight *list, struct move_bucket b)
{
	struct move_bucket_in_flight *new = kzalloc(sizeof(*new), GFP_KERNEL);
	int ret;

	if (!new)
		return ERR_PTR(-ENOMEM);

	new->bucket = b;

	ret = rhashtable_lookup_insert_fast(&list->table, &new->hash,
					    bch_move_bucket_params);
	if (ret) {
		kfree(new);
		return ERR_PTR(ret);
	}

	if (!list->first)
		list->first = new;
	else
		list->last->next = new;

	list->last = new;
	list->nr++;
	list->sectors += b.sectors;
	return new;
}

static int bch2_bucket_is_movable(struct btree_trans *trans,
				  struct move_bucket *b, u64 time)
{
	struct btree_iter iter;
	struct bkey_s_c k;
	struct bch_alloc_v4 _a;
	const struct bch_alloc_v4 *a;
	int ret;

	if (bch2_bucket_is_open(trans->c,
				b->k.bucket.inode,
				b->k.bucket.offset))
		return 0;

	k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc,
			       b->k.bucket, BTREE_ITER_CACHED);
	ret = bkey_err(k);
	if (ret)
		return ret;

	a = bch2_alloc_to_v4(k, &_a);
	b->k.gen	= a->gen;
	b->sectors	= a->dirty_sectors;

	ret = data_type_movable(a->data_type) &&
		a->fragmentation_lru &&
		a->fragmentation_lru <= time;

	bch2_trans_iter_exit(trans, &iter);
	return ret;
}

static void move_buckets_wait(struct btree_trans *trans,
			      struct moving_context *ctxt,
			      struct buckets_in_flight *list,
			      bool flush)
{
	struct move_bucket_in_flight *i;
	int ret;

	while ((i = list->first)) {
		if (flush)
			move_ctxt_wait_event(ctxt, trans, !atomic_read(&i->count));

		if (atomic_read(&i->count))
			break;

		list->first = i->next;
		if (!list->first)
			list->last = NULL;

		list->nr--;
		list->sectors -= i->bucket.sectors;

		ret = rhashtable_remove_fast(&list->table, &i->hash,
					     bch_move_bucket_params);
		BUG_ON(ret);
		kfree(i);
	}

	bch2_trans_unlock(trans);
}

static bool bucket_in_flight(struct buckets_in_flight *list,
			     struct move_bucket_key k)
{
	return rhashtable_lookup_fast(&list->table, &k, bch_move_bucket_params);
}

typedef DARRAY(struct move_bucket) move_buckets;

static int bch2_copygc_get_buckets(struct btree_trans *trans,
			struct moving_context *ctxt,
			struct buckets_in_flight *buckets_in_flight,
			move_buckets *buckets)
{
	struct bch_fs *c = trans->c;
	struct btree_iter iter;
	struct bkey_s_c k;
	size_t nr_to_get = max(16UL, buckets_in_flight->nr / 4);
	size_t saw = 0, in_flight = 0, not_movable = 0, sectors = 0;
	int ret;

	move_buckets_wait(trans, ctxt, buckets_in_flight, false);

	ret = bch2_btree_write_buffer_flush(trans);
	if (bch2_fs_fatal_err_on(ret, c, "%s: error %s from bch2_btree_write_buffer_flush()",
				 __func__, bch2_err_str(ret)))
		return ret;

	ret = for_each_btree_key2_upto(trans, iter, BTREE_ID_lru,
				  lru_pos(BCH_LRU_FRAGMENTATION_START, 0, 0),
				  lru_pos(BCH_LRU_FRAGMENTATION_START, U64_MAX, LRU_TIME_MAX),
				  0, k, ({
		struct move_bucket b = { .k.bucket = u64_to_bucket(k.k->p.offset) };
		int ret = 0;

		saw++;

		if (!bch2_bucket_is_movable(trans, &b, lru_pos_time(k.k->p)))
			not_movable++;
		else if (bucket_in_flight(buckets_in_flight, b.k))
			in_flight++;
		else {
			ret = darray_push(buckets, b) ?: buckets->nr >= nr_to_get;
			if (ret >= 0)
				sectors += b.sectors;
		}
		ret;
	}));

	pr_debug("have: %zu (%zu) saw %zu in flight %zu not movable %zu got %zu (%zu)/%zu buckets ret %i",
		 buckets_in_flight->nr, buckets_in_flight->sectors,
		 saw, in_flight, not_movable, buckets->nr, sectors, nr_to_get, ret);

	return ret < 0 ? ret : 0;
}

noinline
static int bch2_copygc(struct btree_trans *trans,
		       struct moving_context *ctxt,
		       struct buckets_in_flight *buckets_in_flight)
{
	struct bch_fs *c = trans->c;
	struct data_update_opts data_opts = {
		.btree_insert_flags = BCH_WATERMARK_copygc,
	};
	move_buckets buckets = { 0 };
	struct move_bucket_in_flight *f;
	struct move_bucket *i;
	u64 moved = atomic64_read(&ctxt->stats->sectors_moved);
	int ret = 0;

	ret = bch2_copygc_get_buckets(trans, ctxt, buckets_in_flight, &buckets);
	if (ret)
		goto err;

	darray_for_each(buckets, i) {
		if (unlikely(freezing(current)))
			break;

		f = move_bucket_in_flight_add(buckets_in_flight, *i);
		ret = PTR_ERR_OR_ZERO(f);
		if (ret == -EEXIST) { /* rare race: copygc_get_buckets returned same bucket more than once */
			ret = 0;
			continue;
		}
		if (ret == -ENOMEM) { /* flush IO, continue later */
			ret = 0;
			break;
		}

		ret = __bch2_evacuate_bucket(trans, ctxt, f, f->bucket.k.bucket,
					     f->bucket.k.gen, data_opts);
		if (ret)
			goto err;
	}
err:
	darray_exit(&buckets);

	/* no entries in LRU btree found, or got to end: */
	if (bch2_err_matches(ret, ENOENT))
		ret = 0;

	if (ret < 0 && !bch2_err_matches(ret, EROFS))
		bch_err(c, "error from bch2_move_data() in copygc: %s", bch2_err_str(ret));

	moved = atomic64_read(&ctxt->stats->sectors_moved) - moved;
	trace_and_count(c, copygc, c, moved, 0, 0, 0);
	return ret;
}

/*
 * Copygc runs when the amount of fragmented data is above some arbitrary
 * threshold:
 *
 * The threshold at the limit - when the device is full - is the amount of space
 * we reserved in bch2_recalc_capacity; we can't have more than that amount of
 * disk space stranded due to fragmentation and store everything we have
 * promised to store.
 *
 * But we don't want to be running copygc unnecessarily when the device still
 * has plenty of free space - rather, we want copygc to smoothly run every so
 * often and continually reduce the amount of fragmented space as the device
 * fills up. So, we increase the threshold by half the current free space.
 */
unsigned long bch2_copygc_wait_amount(struct bch_fs *c)
{
	struct bch_dev *ca;
	unsigned dev_idx;
	s64 wait = S64_MAX, fragmented_allowed, fragmented;
	unsigned i;

	for_each_rw_member(ca, c, dev_idx) {
		struct bch_dev_usage usage = bch2_dev_usage_read(ca);

		fragmented_allowed = ((__dev_buckets_available(ca, usage, BCH_WATERMARK_stripe) *
				       ca->mi.bucket_size) >> 1);
		fragmented = 0;

		for (i = 0; i < BCH_DATA_NR; i++)
			if (data_type_movable(i))
				fragmented += usage.d[i].fragmented;

		wait = min(wait, max(0LL, fragmented_allowed - fragmented));
	}

	return wait;
}

void bch2_copygc_wait_to_text(struct printbuf *out, struct bch_fs *c)
{
	prt_printf(out, "Currently waiting for:     ");
	prt_human_readable_u64(out, max(0LL, c->copygc_wait -
					atomic64_read(&c->io_clock[WRITE].now)) << 9);
	prt_newline(out);

	prt_printf(out, "Currently waiting since:   ");
	prt_human_readable_u64(out, max(0LL,
					atomic64_read(&c->io_clock[WRITE].now) -
					c->copygc_wait_at) << 9);
	prt_newline(out);

	prt_printf(out, "Currently calculated wait: ");
	prt_human_readable_u64(out, bch2_copygc_wait_amount(c));
	prt_newline(out);
}

static int bch2_copygc_thread(void *arg)
{
	struct bch_fs *c = arg;
	struct btree_trans trans;
	struct moving_context ctxt;
	struct bch_move_stats move_stats;
	struct io_clock *clock = &c->io_clock[WRITE];
	struct buckets_in_flight move_buckets;
	u64 last, wait;
	int ret = 0;

	memset(&move_buckets, 0, sizeof(move_buckets));

	ret = rhashtable_init(&move_buckets.table, &bch_move_bucket_params);
	if (ret) {
		bch_err(c, "error allocating copygc buckets in flight: %s",
			bch2_err_str(ret));
		return ret;
	}

	set_freezable();
	bch2_trans_init(&trans, c, 0, 0);

	bch2_move_stats_init(&move_stats, "copygc");
	bch2_moving_ctxt_init(&ctxt, c, NULL, &move_stats,
			      writepoint_ptr(&c->copygc_write_point),
			      false);

	while (!ret && !kthread_should_stop()) {
		bch2_trans_unlock(&trans);
		cond_resched();

		if (!c->copy_gc_enabled) {
			move_buckets_wait(&trans, &ctxt, &move_buckets, true);
			kthread_wait_freezable(c->copy_gc_enabled);
		}

		if (unlikely(freezing(current))) {
			move_buckets_wait(&trans, &ctxt, &move_buckets, true);
			__refrigerator(false);
			continue;
		}

		last = atomic64_read(&clock->now);
		wait = bch2_copygc_wait_amount(c);

		if (wait > clock->max_slop) {
			c->copygc_wait_at = last;
			c->copygc_wait = last + wait;
			move_buckets_wait(&trans, &ctxt, &move_buckets, true);
			trace_and_count(c, copygc_wait, c, wait, last + wait);
			bch2_kthread_io_clock_wait(clock, last + wait,
					MAX_SCHEDULE_TIMEOUT);
			continue;
		}

		c->copygc_wait = 0;

		c->copygc_running = true;
		ret = bch2_copygc(&trans, &ctxt, &move_buckets);
		c->copygc_running = false;

		wake_up(&c->copygc_running_wq);
	}

	move_buckets_wait(&trans, &ctxt, &move_buckets, true);
	rhashtable_destroy(&move_buckets.table);
	bch2_trans_exit(&trans);
	bch2_moving_ctxt_exit(&ctxt);

	return 0;
}

void bch2_copygc_stop(struct bch_fs *c)
{
	if (c->copygc_thread) {
		kthread_stop(c->copygc_thread);
		put_task_struct(c->copygc_thread);
	}
	c->copygc_thread = NULL;
}

int bch2_copygc_start(struct bch_fs *c)
{
	struct task_struct *t;
	int ret;

	if (c->copygc_thread)
		return 0;

	if (c->opts.nochanges)
		return 0;

	if (bch2_fs_init_fault("copygc_start"))
		return -ENOMEM;

	t = kthread_create(bch2_copygc_thread, c, "bch-copygc/%s", c->name);
	ret = PTR_ERR_OR_ZERO(t);
	if (ret) {
		bch_err(c, "error creating copygc thread: %s", bch2_err_str(ret));
		return ret;
	}

	get_task_struct(t);

	c->copygc_thread = t;
	wake_up_process(c->copygc_thread);

	return 0;
}

void bch2_fs_copygc_init(struct bch_fs *c)
{
	init_waitqueue_head(&c->copygc_running_wq);
	c->copygc_running = false;
}