summaryrefslogtreecommitdiffstats
path: root/zfs/lib/libzpool/txg.c
blob: f810a0dc666f626522077967fe869a46d8a870e6 (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
/*
 * 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 2008 Sun Microsystems, Inc.  All rights reserved.
 * Use is subject to license terms.
 */

#pragma ident	"@(#)txg.c	1.4	08/03/20 SMI"

#include <sys/zfs_context.h>
#include <sys/txg_impl.h>
#include <sys/dmu_impl.h>
#include <sys/dsl_pool.h>
#include <sys/callb.h>

/*
 * Pool-wide transaction groups.
 */

static void txg_sync_thread(dsl_pool_t *dp);
static void txg_quiesce_thread(dsl_pool_t *dp);

int zfs_txg_timeout = 30;	/* max seconds worth of delta per txg */
int zfs_txg_synctime = 5;	/* target seconds to sync a txg */

int zfs_write_limit_shift = 3;	/* 1/8th of physical memory */

uint64_t zfs_write_limit_min = 32 << 20; /* min write limit is 32MB */
uint64_t zfs_write_limit_max = 0; /* max data payload per txg */
uint64_t zfs_write_limit_inflated = 0;

/*
 * Prepare the txg subsystem.
 */
void
txg_init(dsl_pool_t *dp, uint64_t txg)
{
	tx_state_t *tx = &dp->dp_tx;
	int c;
	bzero(tx, sizeof (tx_state_t));

	tx->tx_cpu = kmem_zalloc(max_ncpus * sizeof (tx_cpu_t), KM_SLEEP);

	for (c = 0; c < max_ncpus; c++) {
		int i;

		mutex_init(&tx->tx_cpu[c].tc_lock, NULL, MUTEX_DEFAULT, NULL);
		for (i = 0; i < TXG_SIZE; i++) {
			cv_init(&tx->tx_cpu[c].tc_cv[i], NULL, CV_DEFAULT,
			    NULL);
		}
	}

	rw_init(&tx->tx_suspend, NULL, RW_DEFAULT, NULL);
	mutex_init(&tx->tx_sync_lock, NULL, MUTEX_DEFAULT, NULL);

	tx->tx_open_txg = txg;
}

/*
 * Close down the txg subsystem.
 */
void
txg_fini(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	int c;

	ASSERT(tx->tx_threads == 0);

	rw_destroy(&tx->tx_suspend);
	mutex_destroy(&tx->tx_sync_lock);

	for (c = 0; c < max_ncpus; c++) {
		int i;

		mutex_destroy(&tx->tx_cpu[c].tc_lock);
		for (i = 0; i < TXG_SIZE; i++)
			cv_destroy(&tx->tx_cpu[c].tc_cv[i]);
	}

	kmem_free(tx->tx_cpu, max_ncpus * sizeof (tx_cpu_t));

	bzero(tx, sizeof (tx_state_t));
}

/*
 * Start syncing transaction groups.
 */
void
txg_sync_start(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;

	mutex_enter(&tx->tx_sync_lock);

	dprintf("pool %p\n", dp);

	ASSERT(tx->tx_threads == 0);

	tx->tx_threads = 2;

	tx->tx_quiesce_thread = thread_create(NULL, 0, txg_quiesce_thread,
	    dp, 0, &p0, TS_RUN, minclsyspri);

	tx->tx_sync_thread = thread_create(NULL, 0, txg_sync_thread,
	    dp, 0, &p0, TS_RUN, minclsyspri);

	mutex_exit(&tx->tx_sync_lock);
}

static void
txg_thread_enter(tx_state_t *tx, callb_cpr_t *cpr)
{
	CALLB_CPR_INIT(cpr, &tx->tx_sync_lock, callb_generic_cpr, FTAG);
	mutex_enter(&tx->tx_sync_lock);
}

static void
txg_thread_exit(tx_state_t *tx, callb_cpr_t *cpr, kthread_t **tpp)
{
	ASSERT(*tpp != NULL);
	*tpp = NULL;
	tx->tx_threads--;
	cv_broadcast(&tx->tx_exit_cv);
	CALLB_CPR_EXIT(cpr);		/* drops &tx->tx_sync_lock */
	thread_exit();
}

static void
txg_thread_wait(tx_state_t *tx, callb_cpr_t *cpr, kcondvar_t *cv, uint64_t time)
{
	CALLB_CPR_SAFE_BEGIN(cpr);

	if (time)
		(void) cv_timedwait(cv, &tx->tx_sync_lock, lbolt + time);
	else
		cv_wait(cv, &tx->tx_sync_lock);

	CALLB_CPR_SAFE_END(cpr, &tx->tx_sync_lock);
}

/*
 * Stop syncing transaction groups.
 */
void
txg_sync_stop(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;

	dprintf("pool %p\n", dp);
	/*
	 * Finish off any work in progress.
	 */
	ASSERT(tx->tx_threads == 2);
	txg_wait_synced(dp, 0);

	/*
	 * Wake all sync threads and wait for them to die.
	 */
	mutex_enter(&tx->tx_sync_lock);

	ASSERT(tx->tx_threads == 2);

	tx->tx_exiting = 1;

	cv_broadcast(&tx->tx_quiesce_more_cv);
	cv_broadcast(&tx->tx_quiesce_done_cv);
	cv_broadcast(&tx->tx_sync_more_cv);

	while (tx->tx_threads != 0)
		cv_wait(&tx->tx_exit_cv, &tx->tx_sync_lock);

	tx->tx_exiting = 0;

	mutex_exit(&tx->tx_sync_lock);
}

uint64_t
txg_hold_open(dsl_pool_t *dp, txg_handle_t *th)
{
	tx_state_t *tx = &dp->dp_tx;
	tx_cpu_t *tc = &tx->tx_cpu[CPU_SEQID];
	uint64_t txg;

	mutex_enter(&tc->tc_lock);

	txg = tx->tx_open_txg;
	tc->tc_count[txg & TXG_MASK]++;

	th->th_cpu = tc;
	th->th_txg = txg;

	return (txg);
}

void
txg_rele_to_quiesce(txg_handle_t *th)
{
	tx_cpu_t *tc = th->th_cpu;

	mutex_exit(&tc->tc_lock);
}

void
txg_rele_to_sync(txg_handle_t *th)
{
	tx_cpu_t *tc = th->th_cpu;
	int g = th->th_txg & TXG_MASK;

	mutex_enter(&tc->tc_lock);
	ASSERT(tc->tc_count[g] != 0);
	if (--tc->tc_count[g] == 0)
		cv_broadcast(&tc->tc_cv[g]);
	mutex_exit(&tc->tc_lock);

	th->th_cpu = NULL;	/* defensive */
}

static void
txg_quiesce(dsl_pool_t *dp, uint64_t txg)
{
	tx_state_t *tx = &dp->dp_tx;
	int g = txg & TXG_MASK;
	int c;

	/*
	 * Grab all tx_cpu locks so nobody else can get into this txg.
	 */
	for (c = 0; c < max_ncpus; c++)
		mutex_enter(&tx->tx_cpu[c].tc_lock);

	ASSERT(txg == tx->tx_open_txg);
	tx->tx_open_txg++;

	/*
	 * Now that we've incremented tx_open_txg, we can let threads
	 * enter the next transaction group.
	 */
	for (c = 0; c < max_ncpus; c++)
		mutex_exit(&tx->tx_cpu[c].tc_lock);

	/*
	 * Quiesce the transaction group by waiting for everyone to txg_exit().
	 */
	for (c = 0; c < max_ncpus; c++) {
		tx_cpu_t *tc = &tx->tx_cpu[c];
		mutex_enter(&tc->tc_lock);
		while (tc->tc_count[g] != 0)
			cv_wait(&tc->tc_cv[g], &tc->tc_lock);
		mutex_exit(&tc->tc_lock);
	}
}

static void
txg_sync_thread(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	callb_cpr_t cpr;
	uint64_t timeout, start, delta, timer;
	int target;

	txg_thread_enter(tx, &cpr);

	start = delta = 0;
	timeout = zfs_txg_timeout * hz;
	for (;;) {
		uint64_t txg, written;

		/*
		 * We sync when there's someone waiting on us, or the
		 * quiesce thread has handed off a txg to us, or we have
		 * reached our timeout.
		 */
		timer = (delta >= timeout ? 0 : timeout - delta);
		while (!tx->tx_exiting && timer > 0 &&
		    tx->tx_synced_txg >= tx->tx_sync_txg_waiting &&
		    tx->tx_quiesced_txg == 0) {
			dprintf("waiting; tx_synced=%llu waiting=%llu dp=%p\n",
			    tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
			txg_thread_wait(tx, &cpr, &tx->tx_sync_more_cv, timer);
			delta = lbolt - start;
			timer = (delta > timeout ? 0 : timeout - delta);
		}

		/*
		 * Wait until the quiesce thread hands off a txg to us,
		 * prompting it to do so if necessary.
		 */
		while (!tx->tx_exiting && tx->tx_quiesced_txg == 0) {
			if (tx->tx_quiesce_txg_waiting < tx->tx_open_txg+1)
				tx->tx_quiesce_txg_waiting = tx->tx_open_txg+1;
			cv_broadcast(&tx->tx_quiesce_more_cv);
			txg_thread_wait(tx, &cpr, &tx->tx_quiesce_done_cv, 0);
		}

		if (tx->tx_exiting)
			txg_thread_exit(tx, &cpr, &tx->tx_sync_thread);

		rw_enter(&tx->tx_suspend, RW_WRITER);

		/*
		 * Consume the quiesced txg which has been handed off to
		 * us.  This may cause the quiescing thread to now be
		 * able to quiesce another txg, so we must signal it.
		 */
		txg = tx->tx_quiesced_txg;
		tx->tx_quiesced_txg = 0;
		tx->tx_syncing_txg = txg;
		cv_broadcast(&tx->tx_quiesce_more_cv);
		rw_exit(&tx->tx_suspend);

		dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
		    txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
		mutex_exit(&tx->tx_sync_lock);
		start = lbolt;
		spa_sync(dp->dp_spa, txg);
		delta = lbolt - start;

		written = dp->dp_space_towrite[txg & TXG_MASK];
		dp->dp_space_towrite[txg & TXG_MASK] = 0;
		ASSERT(dp->dp_tempreserved[txg & TXG_MASK] == 0);

		/*
		 * If the write limit max has not been explicitly set, set it
		 * to a fraction of available phisical memory (default 1/8th).
		 * Note that we must inflate the limit because the spa
		 * inflates write sizes to account for data replication.
		 * Check this each sync phase to catch changing memory size.
		 */
		if (zfs_write_limit_inflated == 0 ||
		    (zfs_write_limit_shift && zfs_write_limit_max !=
		    physmem * PAGESIZE >> zfs_write_limit_shift)) {
			zfs_write_limit_max =
			    physmem * PAGESIZE >> zfs_write_limit_shift;
			zfs_write_limit_inflated =
			    spa_get_asize(dp->dp_spa, zfs_write_limit_max);
			if (zfs_write_limit_min > zfs_write_limit_inflated)
				zfs_write_limit_inflated = zfs_write_limit_min;
		}

		/*
		 * Attempt to keep the sync time consistant by adjusting the
		 * amount of write traffic allowed into each transaction group.
		 */
		target = zfs_txg_synctime * hz;
		if (delta > target) {
			uint64_t old = MIN(dp->dp_write_limit, written);

			dp->dp_write_limit = MAX(zfs_write_limit_min,
			    old * target / delta);
		} else if (written >= dp->dp_write_limit &&
		    delta >> 3 < target >> 3) {
			uint64_t rescale =
			    MIN((100 * target) / delta, 200);

			dp->dp_write_limit = MIN(zfs_write_limit_inflated,
			    written * rescale / 100);
		}

		mutex_enter(&tx->tx_sync_lock);
		rw_enter(&tx->tx_suspend, RW_WRITER);
		tx->tx_synced_txg = txg;
		tx->tx_syncing_txg = 0;
		rw_exit(&tx->tx_suspend);
		cv_broadcast(&tx->tx_sync_done_cv);
	}
}

static void
txg_quiesce_thread(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	callb_cpr_t cpr;

	txg_thread_enter(tx, &cpr);

	for (;;) {
		uint64_t txg;

		/*
		 * We quiesce when there's someone waiting on us.
		 * However, we can only have one txg in "quiescing" or
		 * "quiesced, waiting to sync" state.  So we wait until
		 * the "quiesced, waiting to sync" txg has been consumed
		 * by the sync thread.
		 */
		while (!tx->tx_exiting &&
		    (tx->tx_open_txg >= tx->tx_quiesce_txg_waiting ||
		    tx->tx_quiesced_txg != 0))
			txg_thread_wait(tx, &cpr, &tx->tx_quiesce_more_cv, 0);

		if (tx->tx_exiting)
			txg_thread_exit(tx, &cpr, &tx->tx_quiesce_thread);

		txg = tx->tx_open_txg;
		dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
		    txg, tx->tx_quiesce_txg_waiting,
		    tx->tx_sync_txg_waiting);
		mutex_exit(&tx->tx_sync_lock);
		txg_quiesce(dp, txg);
		mutex_enter(&tx->tx_sync_lock);

		/*
		 * Hand this txg off to the sync thread.
		 */
		dprintf("quiesce done, handing off txg %llu\n", txg);
		tx->tx_quiesced_txg = txg;
		cv_broadcast(&tx->tx_sync_more_cv);
		cv_broadcast(&tx->tx_quiesce_done_cv);
	}
}

/*
 * Delay this thread by 'ticks' if we are still in the open transaction
 * group and there is already a waiting txg quiesing or quiesced.  Abort
 * the delay if this txg stalls or enters the quiesing state.
 */
void
txg_delay(dsl_pool_t *dp, uint64_t txg, int ticks)
{
	tx_state_t *tx = &dp->dp_tx;
	int timeout = lbolt + ticks;

	/* don't delay if this txg could transition to quiesing immediately */
	if (tx->tx_open_txg > txg ||
	    tx->tx_syncing_txg == txg-1 || tx->tx_synced_txg == txg-1)
		return;

	mutex_enter(&tx->tx_sync_lock);
	if (tx->tx_open_txg > txg || tx->tx_synced_txg == txg-1) {
		mutex_exit(&tx->tx_sync_lock);
		return;
	}

	while (lbolt < timeout &&
	    tx->tx_syncing_txg < txg-1 && !txg_stalled(dp))
		(void) cv_timedwait(&tx->tx_quiesce_more_cv, &tx->tx_sync_lock,
		    timeout);

	mutex_exit(&tx->tx_sync_lock);
}

void
txg_wait_synced(dsl_pool_t *dp, uint64_t txg)
{
	tx_state_t *tx = &dp->dp_tx;

	mutex_enter(&tx->tx_sync_lock);
	ASSERT(tx->tx_threads == 2);
	if (txg == 0)
		txg = tx->tx_open_txg;
	if (tx->tx_sync_txg_waiting < txg)
		tx->tx_sync_txg_waiting = txg;
	dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
	    txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
	while (tx->tx_synced_txg < txg) {
		dprintf("broadcasting sync more "
		    "tx_synced=%llu waiting=%llu dp=%p\n",
		    tx->tx_synced_txg, tx->tx_sync_txg_waiting, dp);
		cv_broadcast(&tx->tx_sync_more_cv);
		cv_wait(&tx->tx_sync_done_cv, &tx->tx_sync_lock);
	}
	mutex_exit(&tx->tx_sync_lock);
}

void
txg_wait_open(dsl_pool_t *dp, uint64_t txg)
{
	tx_state_t *tx = &dp->dp_tx;

	mutex_enter(&tx->tx_sync_lock);
	ASSERT(tx->tx_threads == 2);
	if (txg == 0)
		txg = tx->tx_open_txg + 1;
	if (tx->tx_quiesce_txg_waiting < txg)
		tx->tx_quiesce_txg_waiting = txg;
	dprintf("txg=%llu quiesce_txg=%llu sync_txg=%llu\n",
	    txg, tx->tx_quiesce_txg_waiting, tx->tx_sync_txg_waiting);
	while (tx->tx_open_txg < txg) {
		cv_broadcast(&tx->tx_quiesce_more_cv);
		cv_wait(&tx->tx_quiesce_done_cv, &tx->tx_sync_lock);
	}
	mutex_exit(&tx->tx_sync_lock);
}

int
txg_stalled(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	return (tx->tx_quiesce_txg_waiting > tx->tx_open_txg);
}

void
txg_suspend(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	/* XXX some code paths suspend when they are already suspended! */
	rw_enter(&tx->tx_suspend, RW_READER);
}

void
txg_resume(dsl_pool_t *dp)
{
	tx_state_t *tx = &dp->dp_tx;
	rw_exit(&tx->tx_suspend);
}

/*
 * Per-txg object lists.
 */
void
txg_list_create(txg_list_t *tl, size_t offset)
{
	int t;

	mutex_init(&tl->tl_lock, NULL, MUTEX_DEFAULT, NULL);

	tl->tl_offset = offset;

	for (t = 0; t < TXG_SIZE; t++)
		tl->tl_head[t] = NULL;
}

void
txg_list_destroy(txg_list_t *tl)
{
	int t;

	for (t = 0; t < TXG_SIZE; t++)
		ASSERT(txg_list_empty(tl, t));

	mutex_destroy(&tl->tl_lock);
}

int
txg_list_empty(txg_list_t *tl, uint64_t txg)
{
	return (tl->tl_head[txg & TXG_MASK] == NULL);
}

/*
 * Add an entry to the list.
 * Returns 0 if it's a new entry, 1 if it's already there.
 */
int
txg_list_add(txg_list_t *tl, void *p, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);
	int already_on_list;

	mutex_enter(&tl->tl_lock);
	already_on_list = tn->tn_member[t];
	if (!already_on_list) {
		tn->tn_member[t] = 1;
		tn->tn_next[t] = tl->tl_head[t];
		tl->tl_head[t] = tn;
	}
	mutex_exit(&tl->tl_lock);

	return (already_on_list);
}

/*
 * Remove the head of the list and return it.
 */
void *
txg_list_remove(txg_list_t *tl, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn;
	void *p = NULL;

	mutex_enter(&tl->tl_lock);
	if ((tn = tl->tl_head[t]) != NULL) {
		p = (char *)tn - tl->tl_offset;
		tl->tl_head[t] = tn->tn_next[t];
		tn->tn_next[t] = NULL;
		tn->tn_member[t] = 0;
	}
	mutex_exit(&tl->tl_lock);

	return (p);
}

/*
 * Remove a specific item from the list and return it.
 */
void *
txg_list_remove_this(txg_list_t *tl, void *p, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn, **tp;

	mutex_enter(&tl->tl_lock);

	for (tp = &tl->tl_head[t]; (tn = *tp) != NULL; tp = &tn->tn_next[t]) {
		if ((char *)tn - tl->tl_offset == p) {
			*tp = tn->tn_next[t];
			tn->tn_next[t] = NULL;
			tn->tn_member[t] = 0;
			mutex_exit(&tl->tl_lock);
			return (p);
		}
	}

	mutex_exit(&tl->tl_lock);

	return (NULL);
}

int
txg_list_member(txg_list_t *tl, void *p, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);

	return (tn->tn_member[t]);
}

/*
 * Walk a txg list -- only safe if you know it's not changing.
 */
void *
txg_list_head(txg_list_t *tl, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn = tl->tl_head[t];

	return (tn == NULL ? NULL : (char *)tn - tl->tl_offset);
}

void *
txg_list_next(txg_list_t *tl, void *p, uint64_t txg)
{
	int t = txg & TXG_MASK;
	txg_node_t *tn = (txg_node_t *)((char *)p + tl->tl_offset);

	tn = tn->tn_next[t];

	return (tn == NULL ? NULL : (char *)tn - tl->tl_offset);
}