summaryrefslogtreecommitdiff
path: root/fs/xfs/xfs_extent_busy.c
blob: 13e3d1a69e761ed3f19f0258201d677f888d9bb9 (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
/*
 * Copyright (c) 2000-2002,2005 Silicon Graphics, Inc.
 * Copyright (c) 2010 David Chinner.
 * Copyright (c) 2011 Christoph Hellwig.
 * All Rights Reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it would be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write the Free Software Foundation,
 * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 */
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_shared.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_alloc.h"
#include "xfs_extent_busy.h"
#include "xfs_trace.h"
#include "xfs_trans.h"
#include "xfs_log.h"

void
xfs_extent_busy_insert(
	struct xfs_trans	*tp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len,
	unsigned int		flags)
{
	struct xfs_extent_busy	*new;
	struct xfs_extent_busy	*busyp;
	struct xfs_perag	*pag;
	struct rb_node		**rbp;
	struct rb_node		*parent = NULL;

	new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_SLEEP);
	new->agno = agno;
	new->bno = bno;
	new->length = len;
	INIT_LIST_HEAD(&new->list);
	new->flags = flags;

	/* trace before insert to be able to see failed inserts */
	trace_xfs_extent_busy(tp->t_mountp, agno, bno, len);

	pag = xfs_perag_get(tp->t_mountp, new->agno);
	spin_lock(&pag->pagb_lock);
	rbp = &pag->pagb_tree.rb_node;
	while (*rbp) {
		parent = *rbp;
		busyp = rb_entry(parent, struct xfs_extent_busy, rb_node);

		if (new->bno < busyp->bno) {
			rbp = &(*rbp)->rb_left;
			ASSERT(new->bno + new->length <= busyp->bno);
		} else if (new->bno > busyp->bno) {
			rbp = &(*rbp)->rb_right;
			ASSERT(bno >= busyp->bno + busyp->length);
		} else {
			ASSERT(0);
		}
	}

	rb_link_node(&new->rb_node, parent, rbp);
	rb_insert_color(&new->rb_node, &pag->pagb_tree);

	list_add(&new->list, &tp->t_busy);
	spin_unlock(&pag->pagb_lock);
	xfs_perag_put(pag);
}

/*
 * Search for a busy extent within the range of the extent we are about to
 * allocate.  You need to be holding the busy extent tree lock when calling
 * xfs_extent_busy_search(). This function returns 0 for no overlapping busy
 * extent, -1 for an overlapping but not exact busy extent, and 1 for an exact
 * match. This is done so that a non-zero return indicates an overlap that
 * will require a synchronous transaction, but it can still be
 * used to distinguish between a partial or exact match.
 */
int
xfs_extent_busy_search(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		bno,
	xfs_extlen_t		len)
{
	struct xfs_perag	*pag;
	struct rb_node		*rbp;
	struct xfs_extent_busy	*busyp;
	int			match = 0;

	pag = xfs_perag_get(mp, agno);
	spin_lock(&pag->pagb_lock);

	rbp = pag->pagb_tree.rb_node;

	/* find closest start bno overlap */
	while (rbp) {
		busyp = rb_entry(rbp, struct xfs_extent_busy, rb_node);
		if (bno < busyp->bno) {
			/* may overlap, but exact start block is lower */
			if (bno + len > busyp->bno)
				match = -1;
			rbp = rbp->rb_left;
		} else if (bno > busyp->bno) {
			/* may overlap, but exact start block is higher */
			if (bno < busyp->bno + busyp->length)
				match = -1;
			rbp = rbp->rb_right;
		} else {
			/* bno matches busyp, length determines exact match */
			match = (busyp->length == len) ? 1 : -1;
			break;
		}
	}
	spin_unlock(&pag->pagb_lock);
	xfs_perag_put(pag);
	return match;
}

/*
 * The found free extent [fbno, fend] overlaps part or all of the given busy
 * extent.  If the overlap covers the beginning, the end, or all of the busy
 * extent, the overlapping portion can be made unbusy and used for the
 * allocation.  We can't split a busy extent because we can't modify a
 * transaction/CIL context busy list, but we can update an entry's block
 * number or length.
 *
 * Returns true if the extent can safely be reused, or false if the search
 * needs to be restarted.
 */
STATIC bool
xfs_extent_busy_update_extent(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	struct xfs_extent_busy	*busyp,
	xfs_agblock_t		fbno,
	xfs_extlen_t		flen,
	bool			userdata) __releases(&pag->pagb_lock)
					  __acquires(&pag->pagb_lock)
{
	xfs_agblock_t		fend = fbno + flen;
	xfs_agblock_t		bbno = busyp->bno;
	xfs_agblock_t		bend = bbno + busyp->length;

	/*
	 * This extent is currently being discarded.  Give the thread
	 * performing the discard a chance to mark the extent unbusy
	 * and retry.
	 */
	if (busyp->flags & XFS_EXTENT_BUSY_DISCARDED) {
		spin_unlock(&pag->pagb_lock);
		delay(1);
		spin_lock(&pag->pagb_lock);
		return false;
	}

	/*
	 * If there is a busy extent overlapping a user allocation, we have
	 * no choice but to force the log and retry the search.
	 *
	 * Fortunately this does not happen during normal operation, but
	 * only if the filesystem is very low on space and has to dip into
	 * the AGFL for normal allocations.
	 */
	if (userdata)
		goto out_force_log;

	if (bbno < fbno && bend > fend) {
		/*
		 * Case 1:
		 *    bbno           bend
		 *    +BBBBBBBBBBBBBBBBB+
		 *        +---------+
		 *        fbno   fend
		 */

		/*
		 * We would have to split the busy extent to be able to track
		 * it correct, which we cannot do because we would have to
		 * modify the list of busy extents attached to the transaction
		 * or CIL context, which is immutable.
		 *
		 * Force out the log to clear the busy extent and retry the
		 * search.
		 */
		goto out_force_log;
	} else if (bbno >= fbno && bend <= fend) {
		/*
		 * Case 2:
		 *    bbno           bend
		 *    +BBBBBBBBBBBBBBBBB+
		 *    +-----------------+
		 *    fbno           fend
		 *
		 * Case 3:
		 *    bbno           bend
		 *    +BBBBBBBBBBBBBBBBB+
		 *    +--------------------------+
		 *    fbno                    fend
		 *
		 * Case 4:
		 *             bbno           bend
		 *             +BBBBBBBBBBBBBBBBB+
		 *    +--------------------------+
		 *    fbno                    fend
		 *
		 * Case 5:
		 *             bbno           bend
		 *             +BBBBBBBBBBBBBBBBB+
		 *    +-----------------------------------+
		 *    fbno                             fend
		 *
		 */

		/*
		 * The busy extent is fully covered by the extent we are
		 * allocating, and can simply be removed from the rbtree.
		 * However we cannot remove it from the immutable list
		 * tracking busy extents in the transaction or CIL context,
		 * so set the length to zero to mark it invalid.
		 *
		 * We also need to restart the busy extent search from the
		 * tree root, because erasing the node can rearrange the
		 * tree topology.
		 */
		rb_erase(&busyp->rb_node, &pag->pagb_tree);
		busyp->length = 0;
		return false;
	} else if (fend < bend) {
		/*
		 * Case 6:
		 *              bbno           bend
		 *             +BBBBBBBBBBBBBBBBB+
		 *             +---------+
		 *             fbno   fend
		 *
		 * Case 7:
		 *             bbno           bend
		 *             +BBBBBBBBBBBBBBBBB+
		 *    +------------------+
		 *    fbno            fend
		 *
		 */
		busyp->bno = fend;
	} else if (bbno < fbno) {
		/*
		 * Case 8:
		 *    bbno           bend
		 *    +BBBBBBBBBBBBBBBBB+
		 *        +-------------+
		 *        fbno       fend
		 *
		 * Case 9:
		 *    bbno           bend
		 *    +BBBBBBBBBBBBBBBBB+
		 *        +----------------------+
		 *        fbno                fend
		 */
		busyp->length = fbno - busyp->bno;
	} else {
		ASSERT(0);
	}

	trace_xfs_extent_busy_reuse(mp, pag->pag_agno, fbno, flen);
	return true;

out_force_log:
	spin_unlock(&pag->pagb_lock);
	xfs_log_force(mp, XFS_LOG_SYNC);
	trace_xfs_extent_busy_force(mp, pag->pag_agno, fbno, flen);
	spin_lock(&pag->pagb_lock);
	return false;
}


/*
 * For a given extent [fbno, flen], make sure we can reuse it safely.
 */
void
xfs_extent_busy_reuse(
	struct xfs_mount	*mp,
	xfs_agnumber_t		agno,
	xfs_agblock_t		fbno,
	xfs_extlen_t		flen,
	bool			userdata)
{
	struct xfs_perag	*pag;
	struct rb_node		*rbp;

	ASSERT(flen > 0);

	pag = xfs_perag_get(mp, agno);
	spin_lock(&pag->pagb_lock);
restart:
	rbp = pag->pagb_tree.rb_node;
	while (rbp) {
		struct xfs_extent_busy *busyp =
			rb_entry(rbp, struct xfs_extent_busy, rb_node);
		xfs_agblock_t	bbno = busyp->bno;
		xfs_agblock_t	bend = bbno + busyp->length;

		if (fbno + flen <= bbno) {
			rbp = rbp->rb_left;
			continue;
		} else if (fbno >= bend) {
			rbp = rbp->rb_right;
			continue;
		}

		if (!xfs_extent_busy_update_extent(mp, pag, busyp, fbno, flen,
						  userdata))
			goto restart;
	}
	spin_unlock(&pag->pagb_lock);
	xfs_perag_put(pag);
}

/*
 * For a given extent [fbno, flen], search the busy extent list to find a
 * subset of the extent that is not busy.  If *rlen is smaller than
 * args->minlen no suitable extent could be found, and the higher level
 * code needs to force out the log and retry the allocation.
 *
 * Return the current busy generation for the AG if the extent is busy. This
 * value can be used to wait for at least one of the currently busy extents
 * to be cleared. Note that the busy list is not guaranteed to be empty after
 * the gen is woken. The state of a specific extent must always be confirmed
 * with another call to xfs_extent_busy_trim() before it can be used.
 */
bool
xfs_extent_busy_trim(
	struct xfs_alloc_arg	*args,
	xfs_agblock_t		*bno,
	xfs_extlen_t		*len,
	unsigned		*busy_gen)
{
	xfs_agblock_t		fbno;
	xfs_extlen_t		flen;
	struct rb_node		*rbp;
	bool			ret = false;

	ASSERT(*len > 0);

	spin_lock(&args->pag->pagb_lock);
restart:
	fbno = *bno;
	flen = *len;
	rbp = args->pag->pagb_tree.rb_node;
	while (rbp && flen >= args->minlen) {
		struct xfs_extent_busy *busyp =
			rb_entry(rbp, struct xfs_extent_busy, rb_node);
		xfs_agblock_t	fend = fbno + flen;
		xfs_agblock_t	bbno = busyp->bno;
		xfs_agblock_t	bend = bbno + busyp->length;

		if (fend <= bbno) {
			rbp = rbp->rb_left;
			continue;
		} else if (fbno >= bend) {
			rbp = rbp->rb_right;
			continue;
		}

		/*
		 * If this is a metadata allocation, try to reuse the busy
		 * extent instead of trimming the allocation.
		 */
		if (!xfs_alloc_is_userdata(args->datatype) &&
		    !(busyp->flags & XFS_EXTENT_BUSY_DISCARDED)) {
			if (!xfs_extent_busy_update_extent(args->mp, args->pag,
							  busyp, fbno, flen,
							  false))
				goto restart;
			continue;
		}

		if (bbno <= fbno) {
			/* start overlap */

			/*
			 * Case 1:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *        +---------+
			 *        fbno   fend
			 *
			 * Case 2:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *    +-------------+
			 *    fbno       fend
			 *
			 * Case 3:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *        +-------------+
			 *        fbno       fend
			 *
			 * Case 4:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *    +-----------------+
			 *    fbno           fend
			 *
			 * No unbusy region in extent, return failure.
			 */
			if (fend <= bend)
				goto fail;

			/*
			 * Case 5:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *        +----------------------+
			 *        fbno                fend
			 *
			 * Case 6:
			 *    bbno           bend
			 *    +BBBBBBBBBBBBBBBBB+
			 *    +--------------------------+
			 *    fbno                    fend
			 *
			 * Needs to be trimmed to:
			 *                       +-------+
			 *                       fbno fend
			 */
			fbno = bend;
		} else if (bend >= fend) {
			/* end overlap */

			/*
			 * Case 7:
			 *             bbno           bend
			 *             +BBBBBBBBBBBBBBBBB+
			 *    +------------------+
			 *    fbno            fend
			 *
			 * Case 8:
			 *             bbno           bend
			 *             +BBBBBBBBBBBBBBBBB+
			 *    +--------------------------+
			 *    fbno                    fend
			 *
			 * Needs to be trimmed to:
			 *    +-------+
			 *    fbno fend
			 */
			fend = bbno;
		} else {
			/* middle overlap */

			/*
			 * Case 9:
			 *             bbno           bend
			 *             +BBBBBBBBBBBBBBBBB+
			 *    +-----------------------------------+
			 *    fbno                             fend
			 *
			 * Can be trimmed to:
			 *    +-------+        OR         +-------+
			 *    fbno fend                   fbno fend
			 *
			 * Backward allocation leads to significant
			 * fragmentation of directories, which degrades
			 * directory performance, therefore we always want to
			 * choose the option that produces forward allocation
			 * patterns.
			 * Preferring the lower bno extent will make the next
			 * request use "fend" as the start of the next
			 * allocation;  if the segment is no longer busy at
			 * that point, we'll get a contiguous allocation, but
			 * even if it is still busy, we will get a forward
			 * allocation.
			 * We try to avoid choosing the segment at "bend",
			 * because that can lead to the next allocation
			 * taking the segment at "fbno", which would be a
			 * backward allocation.  We only use the segment at
			 * "fbno" if it is much larger than the current
			 * requested size, because in that case there's a
			 * good chance subsequent allocations will be
			 * contiguous.
			 */
			if (bbno - fbno >= args->maxlen) {
				/* left candidate fits perfect */
				fend = bbno;
			} else if (fend - bend >= args->maxlen * 4) {
				/* right candidate has enough free space */
				fbno = bend;
			} else if (bbno - fbno >= args->minlen) {
				/* left candidate fits minimum requirement */
				fend = bbno;
			} else {
				goto fail;
			}
		}

		flen = fend - fbno;
	}
out:

	if (fbno != *bno || flen != *len) {
		trace_xfs_extent_busy_trim(args->mp, args->agno, *bno, *len,
					  fbno, flen);
		*bno = fbno;
		*len = flen;
		*busy_gen = args->pag->pagb_gen;
		ret = true;
	}
	spin_unlock(&args->pag->pagb_lock);
	return ret;
fail:
	/*
	 * Return a zero extent length as failure indications.  All callers
	 * re-check if the trimmed extent satisfies the minlen requirement.
	 */
	flen = 0;
	goto out;
}

STATIC void
xfs_extent_busy_clear_one(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	struct xfs_extent_busy	*busyp)
{
	if (busyp->length) {
		trace_xfs_extent_busy_clear(mp, busyp->agno, busyp->bno,
						busyp->length);
		rb_erase(&busyp->rb_node, &pag->pagb_tree);
	}

	list_del_init(&busyp->list);
	kmem_free(busyp);
}

static void
xfs_extent_busy_put_pag(
	struct xfs_perag	*pag,
	bool			wakeup)
		__releases(pag->pagb_lock)
{
	if (wakeup) {
		pag->pagb_gen++;
		wake_up_all(&pag->pagb_wait);
	}

	spin_unlock(&pag->pagb_lock);
	xfs_perag_put(pag);
}

/*
 * Remove all extents on the passed in list from the busy extents tree.
 * If do_discard is set skip extents that need to be discarded, and mark
 * these as undergoing a discard operation instead.
 */
void
xfs_extent_busy_clear(
	struct xfs_mount	*mp,
	struct list_head	*list,
	bool			do_discard)
{
	struct xfs_extent_busy	*busyp, *n;
	struct xfs_perag	*pag = NULL;
	xfs_agnumber_t		agno = NULLAGNUMBER;
	bool			wakeup = false;

	list_for_each_entry_safe(busyp, n, list, list) {
		if (busyp->agno != agno) {
			if (pag)
				xfs_extent_busy_put_pag(pag, wakeup);
			agno = busyp->agno;
			pag = xfs_perag_get(mp, agno);
			spin_lock(&pag->pagb_lock);
			wakeup = false;
		}

		if (do_discard && busyp->length &&
		    !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) {
			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
		} else {
			xfs_extent_busy_clear_one(mp, pag, busyp);
			wakeup = true;
		}
	}

	if (pag)
		xfs_extent_busy_put_pag(pag, wakeup);
}

/*
 * Flush out all busy extents for this AG.
 */
void
xfs_extent_busy_flush(
	struct xfs_mount	*mp,
	struct xfs_perag	*pag,
	unsigned		busy_gen)
{
	DEFINE_WAIT		(wait);
	int			error;

	error = xfs_log_force(mp, XFS_LOG_SYNC);
	if (error)
		return;

	do {
		prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
		if  (busy_gen != READ_ONCE(pag->pagb_gen))
			break;
		schedule();
	} while (1);

	finish_wait(&pag->pagb_wait, &wait);
}

void
xfs_extent_busy_wait_all(
	struct xfs_mount	*mp)
{
	DEFINE_WAIT		(wait);
	xfs_agnumber_t		agno;

	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
		struct xfs_perag *pag = xfs_perag_get(mp, agno);

		do {
			prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
			if  (RB_EMPTY_ROOT(&pag->pagb_tree))
				break;
			schedule();
		} while (1);
		finish_wait(&pag->pagb_wait, &wait);

		xfs_perag_put(pag);
	}
}

/*
 * Callback for list_sort to sort busy extents by the AG they reside in.
 */
int
xfs_extent_busy_ag_cmp(
	void			*priv,
	struct list_head	*l1,
	struct list_head	*l2)
{
	struct xfs_extent_busy	*b1 =
		container_of(l1, struct xfs_extent_busy, list);
	struct xfs_extent_busy	*b2 =
		container_of(l2, struct xfs_extent_busy, list);
	s32 diff;

	diff = b1->agno - b2->agno;
	if (!diff)
		diff = b1->bno - b2->bno;
	return diff;
}