summaryrefslogtreecommitdiffstats
path: root/module/zfs/dmu_zfetch.c
blob: 9d41bdc0f1320acc91df7077db5870b3fa75df7b (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
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
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */
/*
 * Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */

/*
 * Copyright (c) 2013 by Delphix. All rights reserved.
 */

#include <sys/zfs_context.h>
#include <sys/dnode.h>
#include <sys/dmu_objset.h>
#include <sys/dmu_zfetch.h>
#include <sys/dmu.h>
#include <sys/dbuf.h>
#include <sys/kstat.h>

/*
 * I'm against tune-ables, but these should probably exist as tweakable globals
 * until we can get this working the way we want it to.
 */

int zfs_prefetch_disable = 0;

/* max # of streams per zfetch */
unsigned int	zfetch_max_streams = 8;
/* min time before stream reclaim */
unsigned int	zfetch_min_sec_reap = 2;
/* max number of blocks to fetch at a time */
unsigned int	zfetch_block_cap = 256;
/* number of bytes in a array_read at which we stop prefetching (1Mb) */
unsigned long	zfetch_array_rd_sz = 1024 * 1024;

/* forward decls for static routines */
static boolean_t	dmu_zfetch_colinear(zfetch_t *, zstream_t *);
static void		dmu_zfetch_dofetch(zfetch_t *, zstream_t *);
static uint64_t		dmu_zfetch_fetch(dnode_t *, uint64_t, uint64_t);
static uint64_t		dmu_zfetch_fetchsz(dnode_t *, uint64_t, uint64_t);
static boolean_t	dmu_zfetch_find(zfetch_t *, zstream_t *, int);
static int		dmu_zfetch_stream_insert(zfetch_t *, zstream_t *);
static zstream_t	*dmu_zfetch_stream_reclaim(zfetch_t *);
static void		dmu_zfetch_stream_remove(zfetch_t *, zstream_t *);
static int		dmu_zfetch_streams_equal(zstream_t *, zstream_t *);

typedef struct zfetch_stats {
	kstat_named_t zfetchstat_hits;
	kstat_named_t zfetchstat_misses;
	kstat_named_t zfetchstat_colinear_hits;
	kstat_named_t zfetchstat_colinear_misses;
	kstat_named_t zfetchstat_stride_hits;
	kstat_named_t zfetchstat_stride_misses;
	kstat_named_t zfetchstat_reclaim_successes;
	kstat_named_t zfetchstat_reclaim_failures;
	kstat_named_t zfetchstat_stream_resets;
	kstat_named_t zfetchstat_stream_noresets;
	kstat_named_t zfetchstat_bogus_streams;
} zfetch_stats_t;

static zfetch_stats_t zfetch_stats = {
	{ "hits",			KSTAT_DATA_UINT64 },
	{ "misses",			KSTAT_DATA_UINT64 },
	{ "colinear_hits",		KSTAT_DATA_UINT64 },
	{ "colinear_misses",		KSTAT_DATA_UINT64 },
	{ "stride_hits",		KSTAT_DATA_UINT64 },
	{ "stride_misses",		KSTAT_DATA_UINT64 },
	{ "reclaim_successes",		KSTAT_DATA_UINT64 },
	{ "reclaim_failures",		KSTAT_DATA_UINT64 },
	{ "streams_resets",		KSTAT_DATA_UINT64 },
	{ "streams_noresets",		KSTAT_DATA_UINT64 },
	{ "bogus_streams",		KSTAT_DATA_UINT64 },
};

#define	ZFETCHSTAT_INCR(stat, val) \
	atomic_add_64(&zfetch_stats.stat.value.ui64, (val));

#define	ZFETCHSTAT_BUMP(stat)		ZFETCHSTAT_INCR(stat, 1);

kstat_t		*zfetch_ksp;

/*
 * Given a zfetch structure and a zstream structure, determine whether the
 * blocks to be read are part of a co-linear pair of existing prefetch
 * streams.  If a set is found, coalesce the streams, removing one, and
 * configure the prefetch so it looks for a strided access pattern.
 *
 * In other words: if we find two sequential access streams that are
 * the same length and distance N appart, and this read is N from the
 * last stream, then we are probably in a strided access pattern.  So
 * combine the two sequential streams into a single strided stream.
 *
 * Returns whether co-linear streams were found.
 */
static boolean_t
dmu_zfetch_colinear(zfetch_t *zf, zstream_t *zh)
{
	zstream_t	*z_walk;
	zstream_t	*z_comp;

	if (! rw_tryenter(&zf->zf_rwlock, RW_WRITER))
		return (0);

	if (zh == NULL) {
		rw_exit(&zf->zf_rwlock);
		return (0);
	}

	for (z_walk = list_head(&zf->zf_stream); z_walk;
	    z_walk = list_next(&zf->zf_stream, z_walk)) {
		for (z_comp = list_next(&zf->zf_stream, z_walk); z_comp;
		    z_comp = list_next(&zf->zf_stream, z_comp)) {
			int64_t		diff;

			if (z_walk->zst_len != z_walk->zst_stride ||
			    z_comp->zst_len != z_comp->zst_stride) {
				continue;
			}

			diff = z_comp->zst_offset - z_walk->zst_offset;
			if (z_comp->zst_offset + diff == zh->zst_offset) {
				z_walk->zst_offset = zh->zst_offset;
				z_walk->zst_direction = diff < 0 ?
				    ZFETCH_BACKWARD : ZFETCH_FORWARD;
				z_walk->zst_stride =
				    diff * z_walk->zst_direction;
				z_walk->zst_ph_offset =
				    zh->zst_offset + z_walk->zst_stride;
				dmu_zfetch_stream_remove(zf, z_comp);
				mutex_destroy(&z_comp->zst_lock);
				kmem_free(z_comp, sizeof (zstream_t));

				dmu_zfetch_dofetch(zf, z_walk);

				rw_exit(&zf->zf_rwlock);
				return (1);
			}

			diff = z_walk->zst_offset - z_comp->zst_offset;
			if (z_walk->zst_offset + diff == zh->zst_offset) {
				z_walk->zst_offset = zh->zst_offset;
				z_walk->zst_direction = diff < 0 ?
				    ZFETCH_BACKWARD : ZFETCH_FORWARD;
				z_walk->zst_stride =
				    diff * z_walk->zst_direction;
				z_walk->zst_ph_offset =
				    zh->zst_offset + z_walk->zst_stride;
				dmu_zfetch_stream_remove(zf, z_comp);
				mutex_destroy(&z_comp->zst_lock);
				kmem_free(z_comp, sizeof (zstream_t));

				dmu_zfetch_dofetch(zf, z_walk);

				rw_exit(&zf->zf_rwlock);
				return (1);
			}
		}
	}

	rw_exit(&zf->zf_rwlock);
	return (0);
}

/*
 * Given a zstream_t, determine the bounds of the prefetch.  Then call the
 * routine that actually prefetches the individual blocks.
 */
static void
dmu_zfetch_dofetch(zfetch_t *zf, zstream_t *zs)
{
	uint64_t	prefetch_tail;
	uint64_t	prefetch_limit;
	uint64_t	prefetch_ofst;
	uint64_t	prefetch_len;
	uint64_t	blocks_fetched;

	zs->zst_stride = MAX((int64_t)zs->zst_stride, zs->zst_len);
	zs->zst_cap = MIN(zfetch_block_cap, 2 * zs->zst_cap);

	prefetch_tail = MAX((int64_t)zs->zst_ph_offset,
	    (int64_t)(zs->zst_offset + zs->zst_stride));
	/*
	 * XXX: use a faster division method?
	 */
	prefetch_limit = zs->zst_offset + zs->zst_len +
	    (zs->zst_cap * zs->zst_stride) / zs->zst_len;

	while (prefetch_tail < prefetch_limit) {
		prefetch_ofst = zs->zst_offset + zs->zst_direction *
		    (prefetch_tail - zs->zst_offset);

		prefetch_len = zs->zst_len;

		/*
		 * Don't prefetch beyond the end of the file, if working
		 * backwards.
		 */
		if ((zs->zst_direction == ZFETCH_BACKWARD) &&
		    (prefetch_ofst > prefetch_tail)) {
			prefetch_len += prefetch_ofst;
			prefetch_ofst = 0;
		}

		/* don't prefetch more than we're supposed to */
		if (prefetch_len > zs->zst_len)
			break;

		blocks_fetched = dmu_zfetch_fetch(zf->zf_dnode,
		    prefetch_ofst, zs->zst_len);

		prefetch_tail += zs->zst_stride;
		/* stop if we've run out of stuff to prefetch */
		if (blocks_fetched < zs->zst_len)
			break;
	}
	zs->zst_ph_offset = prefetch_tail;
	zs->zst_last = ddi_get_lbolt();
}

void
zfetch_init(void)
{

	zfetch_ksp = kstat_create("zfs", 0, "zfetchstats", "misc",
	    KSTAT_TYPE_NAMED, sizeof (zfetch_stats) / sizeof (kstat_named_t),
	    KSTAT_FLAG_VIRTUAL);

	if (zfetch_ksp != NULL) {
		zfetch_ksp->ks_data = &zfetch_stats;
		kstat_install(zfetch_ksp);
	}
}

void
zfetch_fini(void)
{
	if (zfetch_ksp != NULL) {
		kstat_delete(zfetch_ksp);
		zfetch_ksp = NULL;
	}
}

/*
 * This takes a pointer to a zfetch structure and a dnode.  It performs the
 * necessary setup for the zfetch structure, grokking data from the
 * associated dnode.
 */
void
dmu_zfetch_init(zfetch_t *zf, dnode_t *dno)
{
	if (zf == NULL) {
		return;
	}

	zf->zf_dnode = dno;
	zf->zf_stream_cnt = 0;
	zf->zf_alloc_fail = 0;

	list_create(&zf->zf_stream, sizeof (zstream_t),
	    offsetof(zstream_t, zst_node));

	rw_init(&zf->zf_rwlock, NULL, RW_DEFAULT, NULL);
}

/*
 * This function computes the actual size, in blocks, that can be prefetched,
 * and fetches it.
 */
static uint64_t
dmu_zfetch_fetch(dnode_t *dn, uint64_t blkid, uint64_t nblks)
{
	uint64_t	fetchsz;
	uint64_t	i;

	fetchsz = dmu_zfetch_fetchsz(dn, blkid, nblks);

	for (i = 0; i < fetchsz; i++) {
		dbuf_prefetch(dn, 0, blkid + i, ZIO_PRIORITY_ASYNC_READ,
		    ARC_FLAG_PREFETCH);
	}

	return (fetchsz);
}

/*
 * this function returns the number of blocks that would be prefetched, based
 * upon the supplied dnode, blockid, and nblks.  This is used so that we can
 * update streams in place, and then prefetch with their old value after the
 * fact.  This way, we can delay the prefetch, but subsequent accesses to the
 * stream won't result in the same data being prefetched multiple times.
 */
static uint64_t
dmu_zfetch_fetchsz(dnode_t *dn, uint64_t blkid, uint64_t nblks)
{
	uint64_t	fetchsz;

	if (blkid > dn->dn_maxblkid) {
		return (0);
	}

	/* compute fetch size */
	if (blkid + nblks + 1 > dn->dn_maxblkid) {
		fetchsz = (dn->dn_maxblkid - blkid) + 1;
		ASSERT(blkid + fetchsz - 1 <= dn->dn_maxblkid);
	} else {
		fetchsz = nblks;
	}


	return (fetchsz);
}

/*
 * given a zfetch and a zstream structure, see if there is an associated zstream
 * for this block read.  If so, it starts a prefetch for the stream it
 * located and returns true, otherwise it returns false
 */
static boolean_t
dmu_zfetch_find(zfetch_t *zf, zstream_t *zh, int prefetched)
{
	zstream_t	*zs;
	int64_t		diff;
	int		reset = !prefetched;
	int		rc = 0;

	if (zh == NULL)
		return (0);

	/*
	 * XXX: This locking strategy is a bit coarse; however, it's impact has
	 * yet to be tested.  If this turns out to be an issue, it can be
	 * modified in a number of different ways.
	 */

	rw_enter(&zf->zf_rwlock, RW_READER);
top:

	for (zs = list_head(&zf->zf_stream); zs;
	    zs = list_next(&zf->zf_stream, zs)) {

		/*
		 * XXX - should this be an assert?
		 */
		if (zs->zst_len == 0) {
			/* bogus stream */
			ZFETCHSTAT_BUMP(zfetchstat_bogus_streams);
			continue;
		}

		/*
		 * We hit this case when we are in a strided prefetch stream:
		 * we will read "len" blocks before "striding".
		 */
		if (zh->zst_offset >= zs->zst_offset &&
		    zh->zst_offset < zs->zst_offset + zs->zst_len) {
			if (prefetched) {
				/* already fetched */
				ZFETCHSTAT_BUMP(zfetchstat_stride_hits);
				rc = 1;
				goto out;
			} else {
				ZFETCHSTAT_BUMP(zfetchstat_stride_misses);
			}
		}

		/*
		 * This is the forward sequential read case: we increment
		 * len by one each time we hit here, so we will enter this
		 * case on every read.
		 */
		if (zh->zst_offset == zs->zst_offset + zs->zst_len) {

			reset = !prefetched && zs->zst_len > 1;

			mutex_enter(&zs->zst_lock);

			if (zh->zst_offset != zs->zst_offset + zs->zst_len) {
				mutex_exit(&zs->zst_lock);
				goto top;
			}
			zs->zst_len += zh->zst_len;
			diff = zs->zst_len - zfetch_block_cap;
			if (diff > 0) {
				zs->zst_offset += diff;
				zs->zst_len = zs->zst_len > diff ?
				    zs->zst_len - diff : 0;
			}
			zs->zst_direction = ZFETCH_FORWARD;

			break;

		/*
		 * Same as above, but reading backwards through the file.
		 */
		} else if (zh->zst_offset == zs->zst_offset - zh->zst_len) {
			/* backwards sequential access */

			reset = !prefetched && zs->zst_len > 1;

			mutex_enter(&zs->zst_lock);

			if (zh->zst_offset != zs->zst_offset - zh->zst_len) {
				mutex_exit(&zs->zst_lock);
				goto top;
			}

			zs->zst_offset = zs->zst_offset > zh->zst_len ?
			    zs->zst_offset - zh->zst_len : 0;
			zs->zst_ph_offset = zs->zst_ph_offset > zh->zst_len ?
			    zs->zst_ph_offset - zh->zst_len : 0;
			zs->zst_len += zh->zst_len;

			diff = zs->zst_len - zfetch_block_cap;
			if (diff > 0) {
				zs->zst_ph_offset = zs->zst_ph_offset > diff ?
				    zs->zst_ph_offset - diff : 0;
				zs->zst_len = zs->zst_len > diff ?
				    zs->zst_len - diff : zs->zst_len;
			}
			zs->zst_direction = ZFETCH_BACKWARD;

			break;

		} else if ((zh->zst_offset - zs->zst_offset - zs->zst_stride <
		    zs->zst_len) && (zs->zst_len != zs->zst_stride)) {
			/* strided forward access */

			mutex_enter(&zs->zst_lock);

			if ((zh->zst_offset - zs->zst_offset - zs->zst_stride >=
			    zs->zst_len) || (zs->zst_len == zs->zst_stride)) {
				mutex_exit(&zs->zst_lock);
				goto top;
			}

			zs->zst_offset += zs->zst_stride;
			zs->zst_direction = ZFETCH_FORWARD;

			break;

		} else if ((zh->zst_offset - zs->zst_offset + zs->zst_stride <
		    zs->zst_len) && (zs->zst_len != zs->zst_stride)) {
			/* strided reverse access */

			mutex_enter(&zs->zst_lock);

			if ((zh->zst_offset - zs->zst_offset + zs->zst_stride >=
			    zs->zst_len) || (zs->zst_len == zs->zst_stride)) {
				mutex_exit(&zs->zst_lock);
				goto top;
			}

			zs->zst_offset = zs->zst_offset > zs->zst_stride ?
			    zs->zst_offset - zs->zst_stride : 0;
			zs->zst_ph_offset = (zs->zst_ph_offset >
			    (2 * zs->zst_stride)) ?
			    (zs->zst_ph_offset - (2 * zs->zst_stride)) : 0;
			zs->zst_direction = ZFETCH_BACKWARD;

			break;
		}
	}

	if (zs) {
		if (reset) {
			zstream_t *remove = zs;

			ZFETCHSTAT_BUMP(zfetchstat_stream_resets);
			rc = 0;
			mutex_exit(&zs->zst_lock);
			rw_exit(&zf->zf_rwlock);
			rw_enter(&zf->zf_rwlock, RW_WRITER);
			/*
			 * Relocate the stream, in case someone removes
			 * it while we were acquiring the WRITER lock.
			 */
			for (zs = list_head(&zf->zf_stream); zs;
			    zs = list_next(&zf->zf_stream, zs)) {
				if (zs == remove) {
					dmu_zfetch_stream_remove(zf, zs);
					mutex_destroy(&zs->zst_lock);
					kmem_free(zs, sizeof (zstream_t));
					break;
				}
			}
		} else {
			ZFETCHSTAT_BUMP(zfetchstat_stream_noresets);
			rc = 1;
			dmu_zfetch_dofetch(zf, zs);
			mutex_exit(&zs->zst_lock);
		}
	}
out:
	rw_exit(&zf->zf_rwlock);
	return (rc);
}

/*
 * Clean-up state associated with a zfetch structure.  This frees allocated
 * structure members, empties the zf_stream tree, and generally makes things
 * nice.  This doesn't free the zfetch_t itself, that's left to the caller.
 */
void
dmu_zfetch_rele(zfetch_t *zf)
{
	zstream_t	*zs;
	zstream_t	*zs_next;

	ASSERT(!RW_LOCK_HELD(&zf->zf_rwlock));

	for (zs = list_head(&zf->zf_stream); zs; zs = zs_next) {
		zs_next = list_next(&zf->zf_stream, zs);

		list_remove(&zf->zf_stream, zs);
		mutex_destroy(&zs->zst_lock);
		kmem_free(zs, sizeof (zstream_t));
	}
	list_destroy(&zf->zf_stream);
	rw_destroy(&zf->zf_rwlock);

	zf->zf_dnode = NULL;
}

/*
 * Given a zfetch and zstream structure, insert the zstream structure into the
 * AVL tree contained within the zfetch structure.  Peform the appropriate
 * book-keeping.  It is possible that another thread has inserted a stream which
 * matches one that we are about to insert, so we must be sure to check for this
 * case.  If one is found, return failure, and let the caller cleanup the
 * duplicates.
 */
static int
dmu_zfetch_stream_insert(zfetch_t *zf, zstream_t *zs)
{
	zstream_t	*zs_walk;
	zstream_t	*zs_next;

	ASSERT(RW_WRITE_HELD(&zf->zf_rwlock));

	for (zs_walk = list_head(&zf->zf_stream); zs_walk; zs_walk = zs_next) {
		zs_next = list_next(&zf->zf_stream, zs_walk);

		if (dmu_zfetch_streams_equal(zs_walk, zs)) {
			return (0);
		}
	}

	list_insert_head(&zf->zf_stream, zs);
	zf->zf_stream_cnt++;
	return (1);
}


/*
 * Walk the list of zstreams in the given zfetch, find an old one (by time), and
 * reclaim it for use by the caller.
 */
static zstream_t *
dmu_zfetch_stream_reclaim(zfetch_t *zf)
{
	zstream_t	*zs;

	if (! rw_tryenter(&zf->zf_rwlock, RW_WRITER))
		return (0);

	for (zs = list_head(&zf->zf_stream); zs;
	    zs = list_next(&zf->zf_stream, zs)) {

		if (((ddi_get_lbolt() - zs->zst_last)/hz) > zfetch_min_sec_reap)
			break;
	}

	if (zs) {
		dmu_zfetch_stream_remove(zf, zs);
		mutex_destroy(&zs->zst_lock);
		bzero(zs, sizeof (zstream_t));
	} else {
		zf->zf_alloc_fail++;
	}
	rw_exit(&zf->zf_rwlock);

	return (zs);
}

/*
 * Given a zfetch and zstream structure, remove the zstream structure from its
 * container in the zfetch structure.  Perform the appropriate book-keeping.
 */
static void
dmu_zfetch_stream_remove(zfetch_t *zf, zstream_t *zs)
{
	ASSERT(RW_WRITE_HELD(&zf->zf_rwlock));

	list_remove(&zf->zf_stream, zs);
	zf->zf_stream_cnt--;
}

static int
dmu_zfetch_streams_equal(zstream_t *zs1, zstream_t *zs2)
{
	if (zs1->zst_offset != zs2->zst_offset)
		return (0);

	if (zs1->zst_len != zs2->zst_len)
		return (0);

	if (zs1->zst_stride != zs2->zst_stride)
		return (0);

	if (zs1->zst_ph_offset != zs2->zst_ph_offset)
		return (0);

	if (zs1->zst_cap != zs2->zst_cap)
		return (0);

	if (zs1->zst_direction != zs2->zst_direction)
		return (0);

	return (1);
}

/*
 * This is the prefetch entry point.  It calls all of the other dmu_zfetch
 * routines to create, delete, find, or operate upon prefetch streams.
 */
void
dmu_zfetch(zfetch_t *zf, uint64_t offset, uint64_t size, int prefetched)
{
	zstream_t	zst;
	zstream_t	*newstream;
	boolean_t	fetched;
	int		inserted;
	unsigned int	blkshft;
	uint64_t	blksz;

	if (zfs_prefetch_disable)
		return;

	/* files that aren't ln2 blocksz are only one block -- nothing to do */
	if (!zf->zf_dnode->dn_datablkshift)
		return;

	/* convert offset and size, into blockid and nblocks */
	blkshft = zf->zf_dnode->dn_datablkshift;
	blksz = (1 << blkshft);

	bzero(&zst, sizeof (zstream_t));
	zst.zst_offset = offset >> blkshft;
	zst.zst_len = (P2ROUNDUP(offset + size, blksz) -
	    P2ALIGN(offset, blksz)) >> blkshft;

	fetched = dmu_zfetch_find(zf, &zst, prefetched);
	if (fetched) {
		ZFETCHSTAT_BUMP(zfetchstat_hits);
	} else {
		ZFETCHSTAT_BUMP(zfetchstat_misses);
		if ((fetched = dmu_zfetch_colinear(zf, &zst))) {
			ZFETCHSTAT_BUMP(zfetchstat_colinear_hits);
		} else {
			ZFETCHSTAT_BUMP(zfetchstat_colinear_misses);
		}
	}

	if (!fetched) {
		newstream = dmu_zfetch_stream_reclaim(zf);

		/*
		 * we still couldn't find a stream, drop the lock, and allocate
		 * one if possible.  Otherwise, give up and go home.
		 */
		if (newstream) {
			ZFETCHSTAT_BUMP(zfetchstat_reclaim_successes);
		} else {
			uint64_t	maxblocks;
			uint32_t	max_streams;
			uint32_t	cur_streams;

			ZFETCHSTAT_BUMP(zfetchstat_reclaim_failures);
			cur_streams = zf->zf_stream_cnt;
			maxblocks = zf->zf_dnode->dn_maxblkid;

			max_streams = MIN(zfetch_max_streams,
			    (maxblocks / zfetch_block_cap));
			if (max_streams == 0) {
				max_streams++;
			}

			if (cur_streams >= max_streams) {
				return;
			}
			newstream =
			    kmem_zalloc(sizeof (zstream_t), KM_SLEEP);
		}

		newstream->zst_offset = zst.zst_offset;
		newstream->zst_len = zst.zst_len;
		newstream->zst_stride = zst.zst_len;
		newstream->zst_ph_offset = zst.zst_len + zst.zst_offset;
		newstream->zst_cap = zst.zst_len;
		newstream->zst_direction = ZFETCH_FORWARD;
		newstream->zst_last = ddi_get_lbolt();

		mutex_init(&newstream->zst_lock, NULL, MUTEX_DEFAULT, NULL);

		rw_enter(&zf->zf_rwlock, RW_WRITER);
		inserted = dmu_zfetch_stream_insert(zf, newstream);
		rw_exit(&zf->zf_rwlock);

		if (!inserted) {
			mutex_destroy(&newstream->zst_lock);
			kmem_free(newstream, sizeof (zstream_t));
		}
	}
}

#if defined(_KERNEL) && defined(HAVE_SPL)
module_param(zfs_prefetch_disable, int, 0644);
MODULE_PARM_DESC(zfs_prefetch_disable, "Disable all ZFS prefetching");

module_param(zfetch_max_streams, uint, 0644);
MODULE_PARM_DESC(zfetch_max_streams, "Max number of streams per zfetch");

module_param(zfetch_min_sec_reap, uint, 0644);
MODULE_PARM_DESC(zfetch_min_sec_reap, "Min time before stream reclaim");

module_param(zfetch_block_cap, uint, 0644);
MODULE_PARM_DESC(zfetch_block_cap, "Max number of blocks to fetch at a time");

module_param(zfetch_array_rd_sz, ulong, 0644);
MODULE_PARM_DESC(zfetch_array_rd_sz, "Number of bytes in a array_read");
#endif