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
|
// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (C) 2017 Western Digital Corporation or its affiliates.
*
* This file is released under the GPL.
*/
#include "dm-zoned.h"
#include <linux/module.h>
#define DM_MSG_PREFIX "zoned reclaim"
struct dmz_reclaim {
struct dmz_metadata *metadata;
struct delayed_work work;
struct workqueue_struct *wq;
struct dm_kcopyd_client *kc;
struct dm_kcopyd_throttle kc_throttle;
int kc_err;
unsigned long flags;
/* Last target access time */
unsigned long atime;
};
/*
* Reclaim state flags.
*/
enum {
DMZ_RECLAIM_KCOPY,
};
/*
* Number of seconds of target BIO inactivity to consider the target idle.
*/
#define DMZ_IDLE_PERIOD (10UL * HZ)
/*
* Percentage of unmapped (free) random zones below which reclaim starts
* even if the target is busy.
*/
#define DMZ_RECLAIM_LOW_UNMAP_RND 30
/*
* Percentage of unmapped (free) random zones above which reclaim will
* stop if the target is busy.
*/
#define DMZ_RECLAIM_HIGH_UNMAP_RND 50
/*
* Align a sequential zone write pointer to chunk_block.
*/
static int dmz_reclaim_align_wp(struct dmz_reclaim *zrc, struct dm_zone *zone,
sector_t block)
{
struct dmz_metadata *zmd = zrc->metadata;
struct dmz_dev *dev = dmz_zone_to_dev(zmd, zone);
sector_t wp_block = zone->wp_block;
unsigned int nr_blocks;
int ret;
if (wp_block == block)
return 0;
if (wp_block > block)
return -EIO;
/*
* Zeroout the space between the write
* pointer and the requested position.
*/
nr_blocks = block - wp_block;
ret = blkdev_issue_zeroout(dev->bdev,
dmz_start_sect(zmd, zone) + dmz_blk2sect(wp_block),
dmz_blk2sect(nr_blocks), GFP_NOIO, 0);
if (ret) {
dmz_dev_err(dev,
"Align zone %u wp %llu to %llu (wp+%u) blocks failed %d",
zone->id, (unsigned long long)wp_block,
(unsigned long long)block, nr_blocks, ret);
dmz_check_bdev(dev);
return ret;
}
zone->wp_block = block;
return 0;
}
/*
* dm_kcopyd_copy end notification.
*/
static void dmz_reclaim_kcopy_end(int read_err, unsigned long write_err,
void *context)
{
struct dmz_reclaim *zrc = context;
if (read_err || write_err)
zrc->kc_err = -EIO;
else
zrc->kc_err = 0;
clear_bit_unlock(DMZ_RECLAIM_KCOPY, &zrc->flags);
smp_mb__after_atomic();
wake_up_bit(&zrc->flags, DMZ_RECLAIM_KCOPY);
}
/*
* Copy valid blocks of src_zone into dst_zone.
*/
static int dmz_reclaim_copy(struct dmz_reclaim *zrc,
struct dm_zone *src_zone, struct dm_zone *dst_zone)
{
struct dmz_metadata *zmd = zrc->metadata;
struct dmz_dev *src_dev, *dst_dev;
struct dm_io_region src, dst;
sector_t block = 0, end_block;
sector_t nr_blocks;
sector_t src_zone_block;
sector_t dst_zone_block;
unsigned long flags = 0;
int ret;
if (dmz_is_seq(src_zone))
end_block = src_zone->wp_block;
else
end_block = dmz_zone_nr_blocks(zmd);
src_zone_block = dmz_start_block(zmd, src_zone);
src_dev = dmz_zone_to_dev(zmd, src_zone);
dst_zone_block = dmz_start_block(zmd, dst_zone);
dst_dev = dmz_zone_to_dev(zmd, dst_zone);
if (dmz_is_seq(dst_zone))
set_bit(DM_KCOPYD_WRITE_SEQ, &flags);
while (block < end_block) {
if (src_dev->flags & DMZ_BDEV_DYING)
return -EIO;
if (dst_dev->flags & DMZ_BDEV_DYING)
return -EIO;
/* Get a valid region from the source zone */
ret = dmz_first_valid_block(zmd, src_zone, &block);
if (ret <= 0)
return ret;
nr_blocks = ret;
/*
* If we are writing in a sequential zone, we must make sure
* that writes are sequential. So Zeroout any eventual hole
* between writes.
*/
if (dmz_is_seq(dst_zone)) {
ret = dmz_reclaim_align_wp(zrc, dst_zone, block);
if (ret)
return ret;
}
src.bdev = src_dev->bdev;
src.sector = dmz_blk2sect(src_zone_block + block);
src.count = dmz_blk2sect(nr_blocks);
dst.bdev = dst_dev->bdev;
dst.sector = dmz_blk2sect(dst_zone_block + block);
dst.count = src.count;
/* Copy the valid region */
set_bit(DMZ_RECLAIM_KCOPY, &zrc->flags);
dm_kcopyd_copy(zrc->kc, &src, 1, &dst, flags,
dmz_reclaim_kcopy_end, zrc);
/* Wait for copy to complete */
wait_on_bit_io(&zrc->flags, DMZ_RECLAIM_KCOPY,
TASK_UNINTERRUPTIBLE);
if (zrc->kc_err)
return zrc->kc_err;
block += nr_blocks;
if (dmz_is_seq(dst_zone))
dst_zone->wp_block = block;
}
return 0;
}
/*
* Move valid blocks of dzone buffer zone into dzone (after its write pointer)
* and free the buffer zone.
*/
static int dmz_reclaim_buf(struct dmz_reclaim *zrc, struct dm_zone *dzone)
{
struct dm_zone *bzone = dzone->bzone;
sector_t chunk_block = dzone->wp_block;
struct dmz_metadata *zmd = zrc->metadata;
int ret;
DMDEBUG("(%s): Chunk %u, move buf zone %u (weight %u) to data zone %u (weight %u)",
dmz_metadata_label(zmd),
dzone->chunk, bzone->id, dmz_weight(bzone),
dzone->id, dmz_weight(dzone));
/* Flush data zone into the buffer zone */
ret = dmz_reclaim_copy(zrc, bzone, dzone);
if (ret < 0)
return ret;
dmz_lock_flush(zmd);
/* Validate copied blocks */
ret = dmz_merge_valid_blocks(zmd, bzone, dzone, chunk_block);
if (ret == 0) {
/* Free the buffer zone */
dmz_invalidate_blocks(zmd, bzone, 0, dmz_zone_nr_blocks(zmd));
dmz_lock_map(zmd);
dmz_unmap_zone(zmd, bzone);
dmz_unlock_zone_reclaim(dzone);
dmz_free_zone(zmd, bzone);
dmz_unlock_map(zmd);
}
dmz_unlock_flush(zmd);
return ret;
}
/*
* Merge valid blocks of dzone into its buffer zone and free dzone.
*/
static int dmz_reclaim_seq_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
{
unsigned int chunk = dzone->chunk;
struct dm_zone *bzone = dzone->bzone;
struct dmz_metadata *zmd = zrc->metadata;
int ret = 0;
DMDEBUG("(%s): Chunk %u, move data zone %u (weight %u) to buf zone %u (weight %u)",
dmz_metadata_label(zmd),
chunk, dzone->id, dmz_weight(dzone),
bzone->id, dmz_weight(bzone));
/* Flush data zone into the buffer zone */
ret = dmz_reclaim_copy(zrc, dzone, bzone);
if (ret < 0)
return ret;
dmz_lock_flush(zmd);
/* Validate copied blocks */
ret = dmz_merge_valid_blocks(zmd, dzone, bzone, 0);
if (ret == 0) {
/*
* Free the data zone and remap the chunk to
* the buffer zone.
*/
dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd));
dmz_lock_map(zmd);
dmz_unmap_zone(zmd, bzone);
dmz_unmap_zone(zmd, dzone);
dmz_unlock_zone_reclaim(dzone);
dmz_free_zone(zmd, dzone);
dmz_map_zone(zmd, bzone, chunk);
dmz_unlock_map(zmd);
}
dmz_unlock_flush(zmd);
return ret;
}
/*
* Move valid blocks of the random data zone dzone into a free sequential zone.
* Once blocks are moved, remap the zone chunk to the sequential zone.
*/
static int dmz_reclaim_rnd_data(struct dmz_reclaim *zrc, struct dm_zone *dzone)
{
unsigned int chunk = dzone->chunk;
struct dm_zone *szone = NULL;
struct dmz_metadata *zmd = zrc->metadata;
int ret;
/* Get a free sequential zone */
dmz_lock_map(zmd);
szone = dmz_alloc_zone(zmd, DMZ_ALLOC_RECLAIM);
dmz_unlock_map(zmd);
if (!szone)
return -ENOSPC;
DMDEBUG("(%s): Chunk %u, move rnd zone %u (weight %u) to seq zone %u",
dmz_metadata_label(zmd),
chunk, dzone->id, dmz_weight(dzone), szone->id);
/* Flush the random data zone into the sequential zone */
ret = dmz_reclaim_copy(zrc, dzone, szone);
dmz_lock_flush(zmd);
if (ret == 0) {
/* Validate copied blocks */
ret = dmz_copy_valid_blocks(zmd, dzone, szone);
}
if (ret) {
/* Free the sequential zone */
dmz_lock_map(zmd);
dmz_free_zone(zmd, szone);
dmz_unlock_map(zmd);
} else {
/* Free the data zone and remap the chunk */
dmz_invalidate_blocks(zmd, dzone, 0, dmz_zone_nr_blocks(zmd));
dmz_lock_map(zmd);
dmz_unmap_zone(zmd, dzone);
dmz_unlock_zone_reclaim(dzone);
dmz_free_zone(zmd, dzone);
dmz_map_zone(zmd, szone, chunk);
dmz_unlock_map(zmd);
}
dmz_unlock_flush(zmd);
return ret;
}
/*
* Reclaim an empty zone.
*/
static void dmz_reclaim_empty(struct dmz_reclaim *zrc, struct dm_zone *dzone)
{
struct dmz_metadata *zmd = zrc->metadata;
dmz_lock_flush(zmd);
dmz_lock_map(zmd);
dmz_unmap_zone(zmd, dzone);
dmz_unlock_zone_reclaim(dzone);
dmz_free_zone(zmd, dzone);
dmz_unlock_map(zmd);
dmz_unlock_flush(zmd);
}
/*
* Find a candidate zone for reclaim and process it.
*/
static int dmz_do_reclaim(struct dmz_reclaim *zrc)
{
struct dmz_metadata *zmd = zrc->metadata;
struct dm_zone *dzone;
struct dm_zone *rzone;
unsigned long start;
int ret;
/* Get a data zone */
dzone = dmz_get_zone_for_reclaim(zmd);
if (IS_ERR(dzone))
return PTR_ERR(dzone);
start = jiffies;
if (dmz_is_rnd(dzone)) {
if (!dmz_weight(dzone)) {
/* Empty zone */
dmz_reclaim_empty(zrc, dzone);
ret = 0;
} else {
/*
* Reclaim the random data zone by moving its
* valid data blocks to a free sequential zone.
*/
ret = dmz_reclaim_rnd_data(zrc, dzone);
}
rzone = dzone;
} else {
struct dm_zone *bzone = dzone->bzone;
sector_t chunk_block = 0;
ret = dmz_first_valid_block(zmd, bzone, &chunk_block);
if (ret < 0)
goto out;
if (ret == 0 || chunk_block >= dzone->wp_block) {
/*
* The buffer zone is empty or its valid blocks are
* after the data zone write pointer.
*/
ret = dmz_reclaim_buf(zrc, dzone);
rzone = bzone;
} else {
/*
* Reclaim the data zone by merging it into the
* buffer zone so that the buffer zone itself can
* be later reclaimed.
*/
ret = dmz_reclaim_seq_data(zrc, dzone);
rzone = dzone;
}
}
out:
if (ret) {
dmz_unlock_zone_reclaim(dzone);
return ret;
}
ret = dmz_flush_metadata(zrc->metadata);
if (ret) {
DMDEBUG("(%s): Metadata flush for zone %u failed, err %d\n",
dmz_metadata_label(zmd), rzone->id, ret);
return ret;
}
DMDEBUG("(%s): Reclaimed zone %u in %u ms",
dmz_metadata_label(zmd),
rzone->id, jiffies_to_msecs(jiffies - start));
return 0;
}
/*
* Test if the target device is idle.
*/
static inline int dmz_target_idle(struct dmz_reclaim *zrc)
{
return time_is_before_jiffies(zrc->atime + DMZ_IDLE_PERIOD);
}
/*
* Test if reclaim is necessary.
*/
static bool dmz_should_reclaim(struct dmz_reclaim *zrc)
{
struct dmz_metadata *zmd = zrc->metadata;
unsigned int nr_rnd = dmz_nr_rnd_zones(zmd);
unsigned int nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
unsigned int p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
/* Reclaim when idle */
if (dmz_target_idle(zrc) && nr_unmap_rnd < nr_rnd)
return true;
/* If there are still plenty of random zones, do not reclaim */
if (p_unmap_rnd >= DMZ_RECLAIM_HIGH_UNMAP_RND)
return false;
/*
* If the percentage of unmapped random zones is low,
* reclaim even if the target is busy.
*/
return p_unmap_rnd <= DMZ_RECLAIM_LOW_UNMAP_RND;
}
/*
* Reclaim work function.
*/
static void dmz_reclaim_work(struct work_struct *work)
{
struct dmz_reclaim *zrc = container_of(work, struct dmz_reclaim, work.work);
struct dmz_metadata *zmd = zrc->metadata;
unsigned int nr_rnd, nr_unmap_rnd;
unsigned int p_unmap_rnd;
int ret;
if (dmz_dev_is_dying(zmd))
return;
if (!dmz_should_reclaim(zrc)) {
mod_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
return;
}
/*
* We need to start reclaiming random zones: set up zone copy
* throttling to either go fast if we are very low on random zones
* and slower if there are still some free random zones to avoid
* as much as possible to negatively impact the user workload.
*/
nr_rnd = dmz_nr_rnd_zones(zmd);
nr_unmap_rnd = dmz_nr_unmap_rnd_zones(zmd);
p_unmap_rnd = nr_unmap_rnd * 100 / nr_rnd;
if (dmz_target_idle(zrc) || p_unmap_rnd < DMZ_RECLAIM_LOW_UNMAP_RND / 2) {
/* Idle or very low percentage: go fast */
zrc->kc_throttle.throttle = 100;
} else {
/* Busy but we still have some random zone: throttle */
zrc->kc_throttle.throttle = min(75U, 100U - p_unmap_rnd / 2);
}
DMDEBUG("(%s): Reclaim (%u): %s, %u%% free rnd zones (%u/%u)",
dmz_metadata_label(zmd),
zrc->kc_throttle.throttle,
(dmz_target_idle(zrc) ? "Idle" : "Busy"),
p_unmap_rnd, nr_unmap_rnd, nr_rnd);
ret = dmz_do_reclaim(zrc);
if (ret) {
DMDEBUG("(%s): Reclaim error %d\n",
dmz_metadata_label(zmd), ret);
if (!dmz_check_dev(zmd))
return;
}
dmz_schedule_reclaim(zrc);
}
/*
* Initialize reclaim.
*/
int dmz_ctr_reclaim(struct dmz_metadata *zmd,
struct dmz_reclaim **reclaim)
{
struct dmz_reclaim *zrc;
int ret;
zrc = kzalloc(sizeof(struct dmz_reclaim), GFP_KERNEL);
if (!zrc)
return -ENOMEM;
zrc->metadata = zmd;
zrc->atime = jiffies;
/* Reclaim kcopyd client */
zrc->kc = dm_kcopyd_client_create(&zrc->kc_throttle);
if (IS_ERR(zrc->kc)) {
ret = PTR_ERR(zrc->kc);
zrc->kc = NULL;
goto err;
}
/* Reclaim work */
INIT_DELAYED_WORK(&zrc->work, dmz_reclaim_work);
zrc->wq = alloc_ordered_workqueue("dmz_rwq_%s", WQ_MEM_RECLAIM,
dmz_metadata_label(zmd));
if (!zrc->wq) {
ret = -ENOMEM;
goto err;
}
*reclaim = zrc;
queue_delayed_work(zrc->wq, &zrc->work, 0);
return 0;
err:
if (zrc->kc)
dm_kcopyd_client_destroy(zrc->kc);
kfree(zrc);
return ret;
}
/*
* Terminate reclaim.
*/
void dmz_dtr_reclaim(struct dmz_reclaim *zrc)
{
cancel_delayed_work_sync(&zrc->work);
destroy_workqueue(zrc->wq);
dm_kcopyd_client_destroy(zrc->kc);
kfree(zrc);
}
/*
* Suspend reclaim.
*/
void dmz_suspend_reclaim(struct dmz_reclaim *zrc)
{
cancel_delayed_work_sync(&zrc->work);
}
/*
* Resume reclaim.
*/
void dmz_resume_reclaim(struct dmz_reclaim *zrc)
{
queue_delayed_work(zrc->wq, &zrc->work, DMZ_IDLE_PERIOD);
}
/*
* BIO accounting.
*/
void dmz_reclaim_bio_acc(struct dmz_reclaim *zrc)
{
zrc->atime = jiffies;
}
/*
* Start reclaim if necessary.
*/
void dmz_schedule_reclaim(struct dmz_reclaim *zrc)
{
if (dmz_should_reclaim(zrc))
mod_delayed_work(zrc->wq, &zrc->work, 0);
}
|