forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
raid10.c
4604 lines (4157 loc) · 126 KB
/
raid10.c
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
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* raid10.c : Multiple Devices driver for Linux
*
* Copyright (C) 2000-2004 Neil Brown
*
* RAID-10 support for md.
*
* Base on code in raid1.c. See raid1.c for further copyright information.
*
*
* 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; either version 2, or (at your option)
* any later version.
*
* You should have received a copy of the GNU General Public License
* (for example /usr/src/linux/COPYING); if not, write to the Free
* Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#include <linux/slab.h>
#include <linux/delay.h>
#include <linux/blkdev.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include "md.h"
#include "raid10.h"
#include "raid0.h"
#include "bitmap.h"
/*
* RAID10 provides a combination of RAID0 and RAID1 functionality.
* The layout of data is defined by
* chunk_size
* raid_disks
* near_copies (stored in low byte of layout)
* far_copies (stored in second byte of layout)
* far_offset (stored in bit 16 of layout )
* use_far_sets (stored in bit 17 of layout )
*
* The data to be stored is divided into chunks using chunksize. Each device
* is divided into far_copies sections. In each section, chunks are laid out
* in a style similar to raid0, but near_copies copies of each chunk is stored
* (each on a different drive). The starting device for each section is offset
* near_copies from the starting device of the previous section. Thus there
* are (near_copies * far_copies) of each chunk, and each is on a different
* drive. near_copies and far_copies must be at least one, and their product
* is at most raid_disks.
*
* If far_offset is true, then the far_copies are handled a bit differently.
* The copies are still in different stripes, but instead of being very far
* apart on disk, there are adjacent stripes.
*
* The far and offset algorithms are handled slightly differently if
* 'use_far_sets' is true. In this case, the array's devices are grouped into
* sets that are (near_copies * far_copies) in size. The far copied stripes
* are still shifted by 'near_copies' devices, but this shifting stays confined
* to the set rather than the entire array. This is done to improve the number
* of device combinations that can fail without causing the array to fail.
* Example 'far' algorithm w/o 'use_far_sets' (each letter represents a chunk
* on a device):
* A B C D A B C D E
* ... ...
* D A B C E A B C D
* Example 'far' algorithm w/ 'use_far_sets' enabled (sets illustrated w/ []'s):
* [A B] [C D] [A B] [C D E]
* |...| |...| |...| | ... |
* [B A] [D C] [B A] [E C D]
*/
/*
* Number of guaranteed r10bios in case of extreme VM load:
*/
#define NR_RAID10_BIOS 256
/* when we get a read error on a read-only array, we redirect to another
* device without failing the first device, or trying to over-write to
* correct the read error. To keep track of bad blocks on a per-bio
* level, we store IO_BLOCKED in the appropriate 'bios' pointer
*/
#define IO_BLOCKED ((struct bio *)1)
/* When we successfully write to a known bad-block, we need to remove the
* bad-block marking which must be done from process context. So we record
* the success by setting devs[n].bio to IO_MADE_GOOD
*/
#define IO_MADE_GOOD ((struct bio *)2)
#define BIO_SPECIAL(bio) ((unsigned long)bio <= 2)
/* When there are this many requests queued to be written by
* the raid10 thread, we become 'congested' to provide back-pressure
* for writeback.
*/
static int max_queued_requests = 1024;
static void allow_barrier(struct r10conf *conf);
static void lower_barrier(struct r10conf *conf);
static int _enough(struct r10conf *conf, int previous, int ignore);
static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr,
int *skipped);
static void reshape_request_write(struct mddev *mddev, struct r10bio *r10_bio);
static void end_reshape_write(struct bio *bio);
static void end_reshape(struct r10conf *conf);
static void * r10bio_pool_alloc(gfp_t gfp_flags, void *data)
{
struct r10conf *conf = data;
int size = offsetof(struct r10bio, devs[conf->copies]);
/* allocate a r10bio with room for raid_disks entries in the
* bios array */
return kzalloc(size, gfp_flags);
}
static void r10bio_pool_free(void *r10_bio, void *data)
{
kfree(r10_bio);
}
/* Maximum size of each resync request */
#define RESYNC_BLOCK_SIZE (64*1024)
#define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
/* amount of memory to reserve for resync requests */
#define RESYNC_WINDOW (1024*1024)
/* maximum number of concurrent requests, memory permitting */
#define RESYNC_DEPTH (32*1024*1024/RESYNC_BLOCK_SIZE)
/*
* When performing a resync, we need to read and compare, so
* we need as many pages are there are copies.
* When performing a recovery, we need 2 bios, one for read,
* one for write (we recover only one drive per r10buf)
*
*/
static void * r10buf_pool_alloc(gfp_t gfp_flags, void *data)
{
struct r10conf *conf = data;
struct page *page;
struct r10bio *r10_bio;
struct bio *bio;
int i, j;
int nalloc;
r10_bio = r10bio_pool_alloc(gfp_flags, conf);
if (!r10_bio)
return NULL;
if (test_bit(MD_RECOVERY_SYNC, &conf->mddev->recovery) ||
test_bit(MD_RECOVERY_RESHAPE, &conf->mddev->recovery))
nalloc = conf->copies; /* resync */
else
nalloc = 2; /* recovery */
/*
* Allocate bios.
*/
for (j = nalloc ; j-- ; ) {
bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r10_bio->devs[j].bio = bio;
if (!conf->have_replacement)
continue;
bio = bio_kmalloc(gfp_flags, RESYNC_PAGES);
if (!bio)
goto out_free_bio;
r10_bio->devs[j].repl_bio = bio;
}
/*
* Allocate RESYNC_PAGES data pages and attach them
* where needed.
*/
for (j = 0 ; j < nalloc; j++) {
struct bio *rbio = r10_bio->devs[j].repl_bio;
bio = r10_bio->devs[j].bio;
for (i = 0; i < RESYNC_PAGES; i++) {
if (j > 0 && !test_bit(MD_RECOVERY_SYNC,
&conf->mddev->recovery)) {
/* we can share bv_page's during recovery
* and reshape */
struct bio *rbio = r10_bio->devs[0].bio;
page = rbio->bi_io_vec[i].bv_page;
get_page(page);
} else
page = alloc_page(gfp_flags);
if (unlikely(!page))
goto out_free_pages;
bio->bi_io_vec[i].bv_page = page;
if (rbio)
rbio->bi_io_vec[i].bv_page = page;
}
}
return r10_bio;
out_free_pages:
for ( ; i > 0 ; i--)
safe_put_page(bio->bi_io_vec[i-1].bv_page);
while (j--)
for (i = 0; i < RESYNC_PAGES ; i++)
safe_put_page(r10_bio->devs[j].bio->bi_io_vec[i].bv_page);
j = 0;
out_free_bio:
for ( ; j < nalloc; j++) {
if (r10_bio->devs[j].bio)
bio_put(r10_bio->devs[j].bio);
if (r10_bio->devs[j].repl_bio)
bio_put(r10_bio->devs[j].repl_bio);
}
r10bio_pool_free(r10_bio, conf);
return NULL;
}
static void r10buf_pool_free(void *__r10_bio, void *data)
{
int i;
struct r10conf *conf = data;
struct r10bio *r10bio = __r10_bio;
int j;
for (j=0; j < conf->copies; j++) {
struct bio *bio = r10bio->devs[j].bio;
if (bio) {
for (i = 0; i < RESYNC_PAGES; i++) {
safe_put_page(bio->bi_io_vec[i].bv_page);
bio->bi_io_vec[i].bv_page = NULL;
}
bio_put(bio);
}
bio = r10bio->devs[j].repl_bio;
if (bio)
bio_put(bio);
}
r10bio_pool_free(r10bio, conf);
}
static void put_all_bios(struct r10conf *conf, struct r10bio *r10_bio)
{
int i;
for (i = 0; i < conf->copies; i++) {
struct bio **bio = & r10_bio->devs[i].bio;
if (!BIO_SPECIAL(*bio))
bio_put(*bio);
*bio = NULL;
bio = &r10_bio->devs[i].repl_bio;
if (r10_bio->read_slot < 0 && !BIO_SPECIAL(*bio))
bio_put(*bio);
*bio = NULL;
}
}
static void free_r10bio(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
put_all_bios(conf, r10_bio);
mempool_free(r10_bio, conf->r10bio_pool);
}
static void put_buf(struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
mempool_free(r10_bio, conf->r10buf_pool);
lower_barrier(conf);
}
static void reschedule_retry(struct r10bio *r10_bio)
{
unsigned long flags;
struct mddev *mddev = r10_bio->mddev;
struct r10conf *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r10_bio->retry_list, &conf->retry_list);
conf->nr_queued ++;
spin_unlock_irqrestore(&conf->device_lock, flags);
/* wake up frozen array... */
wake_up(&conf->wait_barrier);
md_wakeup_thread(mddev->thread);
}
/*
* raid_end_bio_io() is called when we have finished servicing a mirrored
* operation and are ready to return a success/failure code to the buffer
* cache layer.
*/
static void raid_end_bio_io(struct r10bio *r10_bio)
{
struct bio *bio = r10_bio->master_bio;
int done;
struct r10conf *conf = r10_bio->mddev->private;
if (bio->bi_phys_segments) {
unsigned long flags;
spin_lock_irqsave(&conf->device_lock, flags);
bio->bi_phys_segments--;
done = (bio->bi_phys_segments == 0);
spin_unlock_irqrestore(&conf->device_lock, flags);
} else
done = 1;
if (!test_bit(R10BIO_Uptodate, &r10_bio->state))
bio->bi_error = -EIO;
if (done) {
bio_endio(bio);
/*
* Wake up any possible resync thread that waits for the device
* to go idle.
*/
allow_barrier(conf);
}
free_r10bio(r10_bio);
}
/*
* Update disk head position estimator based on IRQ completion info.
*/
static inline void update_head_pos(int slot, struct r10bio *r10_bio)
{
struct r10conf *conf = r10_bio->mddev->private;
conf->mirrors[r10_bio->devs[slot].devnum].head_position =
r10_bio->devs[slot].addr + (r10_bio->sectors);
}
/*
* Find the disk number which triggered given bio
*/
static int find_bio_disk(struct r10conf *conf, struct r10bio *r10_bio,
struct bio *bio, int *slotp, int *replp)
{
int slot;
int repl = 0;
for (slot = 0; slot < conf->copies; slot++) {
if (r10_bio->devs[slot].bio == bio)
break;
if (r10_bio->devs[slot].repl_bio == bio) {
repl = 1;
break;
}
}
BUG_ON(slot == conf->copies);
update_head_pos(slot, r10_bio);
if (slotp)
*slotp = slot;
if (replp)
*replp = repl;
return r10_bio->devs[slot].devnum;
}
static void raid10_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_error;
struct r10bio *r10_bio = bio->bi_private;
int slot, dev;
struct md_rdev *rdev;
struct r10conf *conf = r10_bio->mddev->private;
slot = r10_bio->read_slot;
dev = r10_bio->devs[slot].devnum;
rdev = r10_bio->devs[slot].rdev;
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
update_head_pos(slot, r10_bio);
if (uptodate) {
/*
* Set R10BIO_Uptodate in our master bio, so that
* we will return a good error code to the higher
* levels even if IO on some other mirrored buffer fails.
*
* The 'master' represents the composite IO operation to
* user-side. So if something waits for IO, then it will
* wait for the 'master' bio.
*/
set_bit(R10BIO_Uptodate, &r10_bio->state);
} else {
/* If all other devices that store this block have
* failed, we want to return the error upwards rather
* than fail the last device. Here we redefine
* "uptodate" to mean "Don't want to retry"
*/
if (!_enough(conf, test_bit(R10BIO_Previous, &r10_bio->state),
rdev->raid_disk))
uptodate = 1;
}
if (uptodate) {
raid_end_bio_io(r10_bio);
rdev_dec_pending(rdev, conf->mddev);
} else {
/*
* oops, read error - keep the refcount on the rdev
*/
char b[BDEVNAME_SIZE];
printk_ratelimited(KERN_ERR
"md/raid10:%s: %s: rescheduling sector %llu\n",
mdname(conf->mddev),
bdevname(rdev->bdev, b),
(unsigned long long)r10_bio->sector);
set_bit(R10BIO_ReadError, &r10_bio->state);
reschedule_retry(r10_bio);
}
}
static void close_write(struct r10bio *r10_bio)
{
/* clear the bitmap if all writes complete successfully */
bitmap_endwrite(r10_bio->mddev->bitmap, r10_bio->sector,
r10_bio->sectors,
!test_bit(R10BIO_Degraded, &r10_bio->state),
0);
md_write_end(r10_bio->mddev);
}
static void one_write_done(struct r10bio *r10_bio)
{
if (atomic_dec_and_test(&r10_bio->remaining)) {
if (test_bit(R10BIO_WriteError, &r10_bio->state))
reschedule_retry(r10_bio);
else {
close_write(r10_bio);
if (test_bit(R10BIO_MadeGood, &r10_bio->state))
reschedule_retry(r10_bio);
else
raid_end_bio_io(r10_bio);
}
}
}
static void raid10_end_write_request(struct bio *bio)
{
struct r10bio *r10_bio = bio->bi_private;
int dev;
int dec_rdev = 1;
struct r10conf *conf = r10_bio->mddev->private;
int slot, repl;
struct md_rdev *rdev = NULL;
dev = find_bio_disk(conf, r10_bio, bio, &slot, &repl);
if (repl)
rdev = conf->mirrors[dev].replacement;
if (!rdev) {
smp_rmb();
repl = 0;
rdev = conf->mirrors[dev].rdev;
}
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
if (bio->bi_error) {
if (repl)
/* Never record new bad blocks to replacement,
* just fail it.
*/
md_error(rdev->mddev, rdev);
else {
set_bit(WriteErrorSeen, &rdev->flags);
if (!test_and_set_bit(WantReplacement, &rdev->flags))
set_bit(MD_RECOVERY_NEEDED,
&rdev->mddev->recovery);
set_bit(R10BIO_WriteError, &r10_bio->state);
dec_rdev = 0;
}
} else {
/*
* Set R10BIO_Uptodate in our master bio, so that
* we will return a good error code for to the higher
* levels even if IO on some other mirrored buffer fails.
*
* The 'master' represents the composite IO operation to
* user-side. So if something waits for IO, then it will
* wait for the 'master' bio.
*/
sector_t first_bad;
int bad_sectors;
/*
* Do not set R10BIO_Uptodate if the current device is
* rebuilding or Faulty. This is because we cannot use
* such device for properly reading the data back (we could
* potentially use it, if the current write would have felt
* before rdev->recovery_offset, but for simplicity we don't
* check this here.
*/
if (test_bit(In_sync, &rdev->flags) &&
!test_bit(Faulty, &rdev->flags))
set_bit(R10BIO_Uptodate, &r10_bio->state);
/* Maybe we can clear some bad blocks. */
if (is_badblock(rdev,
r10_bio->devs[slot].addr,
r10_bio->sectors,
&first_bad, &bad_sectors)) {
bio_put(bio);
if (repl)
r10_bio->devs[slot].repl_bio = IO_MADE_GOOD;
else
r10_bio->devs[slot].bio = IO_MADE_GOOD;
dec_rdev = 0;
set_bit(R10BIO_MadeGood, &r10_bio->state);
}
}
/*
*
* Let's see if all mirrored write operations have finished
* already.
*/
one_write_done(r10_bio);
if (dec_rdev)
rdev_dec_pending(rdev, conf->mddev);
}
/*
* RAID10 layout manager
* As well as the chunksize and raid_disks count, there are two
* parameters: near_copies and far_copies.
* near_copies * far_copies must be <= raid_disks.
* Normally one of these will be 1.
* If both are 1, we get raid0.
* If near_copies == raid_disks, we get raid1.
*
* Chunks are laid out in raid0 style with near_copies copies of the
* first chunk, followed by near_copies copies of the next chunk and
* so on.
* If far_copies > 1, then after 1/far_copies of the array has been assigned
* as described above, we start again with a device offset of near_copies.
* So we effectively have another copy of the whole array further down all
* the drives, but with blocks on different drives.
* With this layout, and block is never stored twice on the one device.
*
* raid10_find_phys finds the sector offset of a given virtual sector
* on each device that it is on.
*
* raid10_find_virt does the reverse mapping, from a device and a
* sector offset to a virtual address
*/
static void __raid10_find_phys(struct geom *geo, struct r10bio *r10bio)
{
int n,f;
sector_t sector;
sector_t chunk;
sector_t stripe;
int dev;
int slot = 0;
int last_far_set_start, last_far_set_size;
last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
last_far_set_start *= geo->far_set_size;
last_far_set_size = geo->far_set_size;
last_far_set_size += (geo->raid_disks % geo->far_set_size);
/* now calculate first sector/dev */
chunk = r10bio->sector >> geo->chunk_shift;
sector = r10bio->sector & geo->chunk_mask;
chunk *= geo->near_copies;
stripe = chunk;
dev = sector_div(stripe, geo->raid_disks);
if (geo->far_offset)
stripe *= geo->far_copies;
sector += stripe << geo->chunk_shift;
/* and calculate all the others */
for (n = 0; n < geo->near_copies; n++) {
int d = dev;
int set;
sector_t s = sector;
r10bio->devs[slot].devnum = d;
r10bio->devs[slot].addr = s;
slot++;
for (f = 1; f < geo->far_copies; f++) {
set = d / geo->far_set_size;
d += geo->near_copies;
if ((geo->raid_disks % geo->far_set_size) &&
(d > last_far_set_start)) {
d -= last_far_set_start;
d %= last_far_set_size;
d += last_far_set_start;
} else {
d %= geo->far_set_size;
d += geo->far_set_size * set;
}
s += geo->stride;
r10bio->devs[slot].devnum = d;
r10bio->devs[slot].addr = s;
slot++;
}
dev++;
if (dev >= geo->raid_disks) {
dev = 0;
sector += (geo->chunk_mask + 1);
}
}
}
static void raid10_find_phys(struct r10conf *conf, struct r10bio *r10bio)
{
struct geom *geo = &conf->geo;
if (conf->reshape_progress != MaxSector &&
((r10bio->sector >= conf->reshape_progress) !=
conf->mddev->reshape_backwards)) {
set_bit(R10BIO_Previous, &r10bio->state);
geo = &conf->prev;
} else
clear_bit(R10BIO_Previous, &r10bio->state);
__raid10_find_phys(geo, r10bio);
}
static sector_t raid10_find_virt(struct r10conf *conf, sector_t sector, int dev)
{
sector_t offset, chunk, vchunk;
/* Never use conf->prev as this is only called during resync
* or recovery, so reshape isn't happening
*/
struct geom *geo = &conf->geo;
int far_set_start = (dev / geo->far_set_size) * geo->far_set_size;
int far_set_size = geo->far_set_size;
int last_far_set_start;
if (geo->raid_disks % geo->far_set_size) {
last_far_set_start = (geo->raid_disks / geo->far_set_size) - 1;
last_far_set_start *= geo->far_set_size;
if (dev >= last_far_set_start) {
far_set_size = geo->far_set_size;
far_set_size += (geo->raid_disks % geo->far_set_size);
far_set_start = last_far_set_start;
}
}
offset = sector & geo->chunk_mask;
if (geo->far_offset) {
int fc;
chunk = sector >> geo->chunk_shift;
fc = sector_div(chunk, geo->far_copies);
dev -= fc * geo->near_copies;
if (dev < far_set_start)
dev += far_set_size;
} else {
while (sector >= geo->stride) {
sector -= geo->stride;
if (dev < (geo->near_copies + far_set_start))
dev += far_set_size - geo->near_copies;
else
dev -= geo->near_copies;
}
chunk = sector >> geo->chunk_shift;
}
vchunk = chunk * geo->raid_disks + dev;
sector_div(vchunk, geo->near_copies);
return (vchunk << geo->chunk_shift) + offset;
}
/*
* This routine returns the disk from which the requested read should
* be done. There is a per-array 'next expected sequential IO' sector
* number - if this matches on the next IO then we use the last disk.
* There is also a per-disk 'last know head position' sector that is
* maintained from IRQ contexts, both the normal and the resync IO
* completion handlers update this position correctly. If there is no
* perfect sequential match then we pick the disk whose head is closest.
*
* If there are 2 mirrors in the same 2 devices, performance degrades
* because position is mirror, not device based.
*
* The rdev for the device selected will have nr_pending incremented.
*/
/*
* FIXME: possibly should rethink readbalancing and do it differently
* depending on near_copies / far_copies geometry.
*/
static struct md_rdev *read_balance(struct r10conf *conf,
struct r10bio *r10_bio,
int *max_sectors)
{
const sector_t this_sector = r10_bio->sector;
int disk, slot;
int sectors = r10_bio->sectors;
int best_good_sectors;
sector_t new_distance, best_dist;
struct md_rdev *best_rdev, *rdev = NULL;
int do_balance;
int best_slot;
struct geom *geo = &conf->geo;
raid10_find_phys(conf, r10_bio);
rcu_read_lock();
retry:
sectors = r10_bio->sectors;
best_slot = -1;
best_rdev = NULL;
best_dist = MaxSector;
best_good_sectors = 0;
do_balance = 1;
/*
* Check if we can balance. We can balance on the whole
* device if no resync is going on (recovery is ok), or below
* the resync window. We take the first readable disk when
* above the resync window.
*/
if (conf->mddev->recovery_cp < MaxSector
&& (this_sector + sectors >= conf->next_resync))
do_balance = 0;
for (slot = 0; slot < conf->copies ; slot++) {
sector_t first_bad;
int bad_sectors;
sector_t dev_sector;
if (r10_bio->devs[slot].bio == IO_BLOCKED)
continue;
disk = r10_bio->devs[slot].devnum;
rdev = rcu_dereference(conf->mirrors[disk].replacement);
if (rdev == NULL || test_bit(Faulty, &rdev->flags) ||
r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
rdev = rcu_dereference(conf->mirrors[disk].rdev);
if (rdev == NULL ||
test_bit(Faulty, &rdev->flags))
continue;
if (!test_bit(In_sync, &rdev->flags) &&
r10_bio->devs[slot].addr + sectors > rdev->recovery_offset)
continue;
dev_sector = r10_bio->devs[slot].addr;
if (is_badblock(rdev, dev_sector, sectors,
&first_bad, &bad_sectors)) {
if (best_dist < MaxSector)
/* Already have a better slot */
continue;
if (first_bad <= dev_sector) {
/* Cannot read here. If this is the
* 'primary' device, then we must not read
* beyond 'bad_sectors' from another device.
*/
bad_sectors -= (dev_sector - first_bad);
if (!do_balance && sectors > bad_sectors)
sectors = bad_sectors;
if (best_good_sectors > sectors)
best_good_sectors = sectors;
} else {
sector_t good_sectors =
first_bad - dev_sector;
if (good_sectors > best_good_sectors) {
best_good_sectors = good_sectors;
best_slot = slot;
best_rdev = rdev;
}
if (!do_balance)
/* Must read from here */
break;
}
continue;
} else
best_good_sectors = sectors;
if (!do_balance)
break;
/* This optimisation is debatable, and completely destroys
* sequential read speed for 'far copies' arrays. So only
* keep it for 'near' arrays, and review those later.
*/
if (geo->near_copies > 1 && !atomic_read(&rdev->nr_pending))
break;
/* for far > 1 always use the lowest address */
if (geo->far_copies > 1)
new_distance = r10_bio->devs[slot].addr;
else
new_distance = abs(r10_bio->devs[slot].addr -
conf->mirrors[disk].head_position);
if (new_distance < best_dist) {
best_dist = new_distance;
best_slot = slot;
best_rdev = rdev;
}
}
if (slot >= conf->copies) {
slot = best_slot;
rdev = best_rdev;
}
if (slot >= 0) {
atomic_inc(&rdev->nr_pending);
if (test_bit(Faulty, &rdev->flags)) {
/* Cannot risk returning a device that failed
* before we inc'ed nr_pending
*/
rdev_dec_pending(rdev, conf->mddev);
goto retry;
}
r10_bio->read_slot = slot;
} else
rdev = NULL;
rcu_read_unlock();
*max_sectors = best_good_sectors;
return rdev;
}
static int raid10_congested(struct mddev *mddev, int bits)
{
struct r10conf *conf = mddev->private;
int i, ret = 0;
if ((bits & (1 << WB_async_congested)) &&
conf->pending_count >= max_queued_requests)
return 1;
rcu_read_lock();
for (i = 0;
(i < conf->geo.raid_disks || i < conf->prev.raid_disks)
&& ret == 0;
i++) {
struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev);
if (rdev && !test_bit(Faulty, &rdev->flags)) {
struct request_queue *q = bdev_get_queue(rdev->bdev);
ret |= bdi_congested(&q->backing_dev_info, bits);
}
}
rcu_read_unlock();
return ret;
}
static void flush_pending_writes(struct r10conf *conf)
{
/* Any writes that have been queued but are awaiting
* bitmap updates get flushed here.
*/
spin_lock_irq(&conf->device_lock);
if (conf->pending_bio_list.head) {
struct bio *bio;
bio = bio_list_get(&conf->pending_bio_list);
conf->pending_count = 0;
spin_unlock_irq(&conf->device_lock);
/* flush any pending bitmap writes to disk
* before proceeding w/ I/O */
bitmap_unplug(conf->mddev->bitmap);
wake_up(&conf->wait_barrier);
while (bio) { /* submit pending writes */
struct bio *next = bio->bi_next;
bio->bi_next = NULL;
if (unlikely((bio->bi_rw & REQ_DISCARD) &&
!blk_queue_discard(bdev_get_queue(bio->bi_bdev))))
/* Just ignore it */
bio_endio(bio);
else
generic_make_request(bio);
bio = next;
}
} else
spin_unlock_irq(&conf->device_lock);
}
/* Barriers....
* Sometimes we need to suspend IO while we do something else,
* either some resync/recovery, or reconfigure the array.
* To do this we raise a 'barrier'.
* The 'barrier' is a counter that can be raised multiple times
* to count how many activities are happening which preclude
* normal IO.
* We can only raise the barrier if there is no pending IO.
* i.e. if nr_pending == 0.
* We choose only to raise the barrier if no-one is waiting for the
* barrier to go down. This means that as soon as an IO request
* is ready, no other operations which require a barrier will start
* until the IO request has had a chance.
*
* So: regular IO calls 'wait_barrier'. When that returns there
* is no backgroup IO happening, It must arrange to call
* allow_barrier when it has finished its IO.
* backgroup IO calls must call raise_barrier. Once that returns
* there is no normal IO happeing. It must arrange to call
* lower_barrier when the particular background IO completes.
*/
static void raise_barrier(struct r10conf *conf, int force)
{
BUG_ON(force && !conf->barrier);
spin_lock_irq(&conf->resync_lock);
/* Wait until no block IO is waiting (unless 'force') */
wait_event_lock_irq(conf->wait_barrier, force || !conf->nr_waiting,
conf->resync_lock);
/* block any new IO from starting */
conf->barrier++;
/* Now wait for all pending IO to complete */
wait_event_lock_irq(conf->wait_barrier,
!conf->nr_pending && conf->barrier < RESYNC_DEPTH,
conf->resync_lock);
spin_unlock_irq(&conf->resync_lock);
}
static void lower_barrier(struct r10conf *conf)
{
unsigned long flags;
spin_lock_irqsave(&conf->resync_lock, flags);
conf->barrier--;
spin_unlock_irqrestore(&conf->resync_lock, flags);
wake_up(&conf->wait_barrier);
}
static void wait_barrier(struct r10conf *conf)
{
spin_lock_irq(&conf->resync_lock);
if (conf->barrier) {
conf->nr_waiting++;
/* Wait for the barrier to drop.
* However if there are already pending
* requests (preventing the barrier from
* rising completely), and the
* pre-process bio queue isn't empty,
* then don't wait, as we need to empty
* that queue to get the nr_pending
* count down.
*/
wait_event_lock_irq(conf->wait_barrier,
!conf->barrier ||
(conf->nr_pending &&
current->bio_list &&
!bio_list_empty(current->bio_list)),
conf->resync_lock);
conf->nr_waiting--;
}
conf->nr_pending++;
spin_unlock_irq(&conf->resync_lock);
}
static void allow_barrier(struct r10conf *conf)
{
unsigned long flags;
spin_lock_irqsave(&conf->resync_lock, flags);
conf->nr_pending--;
spin_unlock_irqrestore(&conf->resync_lock, flags);
wake_up(&conf->wait_barrier);
}
static void freeze_array(struct r10conf *conf, int extra)
{
/* stop syncio and normal IO and wait for everything to
* go quiet.
* We increment barrier and nr_waiting, and then
* wait until nr_pending match nr_queued+extra
* This is called in the context of one normal IO request
* that has failed. Thus any sync request that might be pending
* will be blocked by nr_pending, and we need to wait for
* pending IO requests to complete or be queued for re-try.
* Thus the number queued (nr_queued) plus this request (extra)
* must match the number of pending IOs (nr_pending) before
* we continue.
*/
spin_lock_irq(&conf->resync_lock);
conf->barrier++;
conf->nr_waiting++;
wait_event_lock_irq_cmd(conf->wait_barrier,
conf->nr_pending == conf->nr_queued+extra,
conf->resync_lock,
flush_pending_writes(conf));
spin_unlock_irq(&conf->resync_lock);
}
static void unfreeze_array(struct r10conf *conf)
{
/* reverse the effect of the freeze */
spin_lock_irq(&conf->resync_lock);
conf->barrier--;
conf->nr_waiting--;
wake_up(&conf->wait_barrier);
spin_unlock_irq(&conf->resync_lock);
}
static sector_t choose_data_offset(struct r10bio *r10_bio,