* 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 they 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.
+ * 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 be very far apart
- * on disk, there are adjacent stripes.
+ * 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]
*/
/*
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;
/* 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].addr = 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 (d >= geo->raid_disks)
- d -= geo->raid_disks;
+
+ 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;
* 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) {
chunk = sector >> geo->chunk_shift;
fc = sector_div(chunk, geo->far_copies);
dev -= fc * geo->near_copies;
- if (dev < 0)
- dev += geo->raid_disks;
+ if (dev < far_set_start)
+ dev += far_set_size;
} else {
while (sector >= geo->stride) {
sector -= geo->stride;
- if (dev < geo->near_copies)
- dev += geo->raid_disks - geo->near_copies;
+ if (dev < (geo->near_copies + far_set_start))
+ dev += far_set_size - geo->near_copies;
else
dev -= geo->near_copies;
}
bio_list_merge(&conf->pending_bio_list, &plug->pending);
conf->pending_count += plug->pending_cnt;
spin_unlock_irq(&conf->device_lock);
+ wake_up(&conf->wait_barrier);
md_wakeup_thread(mddev->thread);
kfree(plug);
return;
const unsigned long do_fua = (bio->bi_rw & REQ_FUA);
const unsigned long do_discard = (bio->bi_rw
& (REQ_DISCARD | REQ_SECURE));
+ const unsigned long do_same = (bio->bi_rw & REQ_WRITE_SAME);
unsigned long flags;
struct md_rdev *blocked_rdev;
struct blk_plug_cb *cb;
/* If this request crosses a chunk boundary, we need to
* split it. This will only happen for 1 PAGE (or less) requests.
*/
- if (unlikely((bio->bi_sector & chunk_mask) + (bio->bi_size >> 9)
+ if (unlikely((bio->bi_sector & chunk_mask) + bio_sectors(bio)
> chunk_sects
&& (conf->geo.near_copies < conf->geo.raid_disks
|| conf->prev.near_copies < conf->prev.raid_disks))) {
struct bio_pair *bp;
/* Sanity check -- queue functions should prevent this happening */
- if ((bio->bi_vcnt != 1 && bio->bi_vcnt != 0) ||
- bio->bi_idx != 0)
+ if (bio_segments(bio) > 1)
goto bad_map;
/* This is a one page bio that upper layers
* refuse to split for us, so we need to split it.
bad_map:
printk("md/raid10:%s: make_request bug: can't convert block across chunks"
" or bigger than %dk %llu %d\n", mdname(mddev), chunk_sects/2,
- (unsigned long long)bio->bi_sector, bio->bi_size >> 10);
+ (unsigned long long)bio->bi_sector, bio_sectors(bio) / 2);
bio_io_error(bio);
return;
*/
wait_barrier(conf);
- sectors = bio->bi_size >> 9;
+ sectors = bio_sectors(bio);
while (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
bio->bi_sector < conf->reshape_progress &&
bio->bi_sector + sectors > conf->reshape_progress) {
r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
- r10_bio->sectors = ((bio->bi_size >> 9)
- - sectors_handled);
+ r10_bio->sectors = bio_sectors(bio) - sectors_handled;
r10_bio->state = 0;
r10_bio->mddev = mddev;
r10_bio->sector = bio->bi_sector + sectors_handled;
rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ mbio->bi_rw =
+ WRITE | do_sync | do_fua | do_discard | do_same;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
r10_bio, rdev));
mbio->bi_bdev = rdev->bdev;
mbio->bi_end_io = raid10_end_write_request;
- mbio->bi_rw = WRITE | do_sync | do_fua | do_discard;
+ mbio->bi_rw =
+ WRITE | do_sync | do_fua | do_discard | do_same;
mbio->bi_private = r10_bio;
atomic_inc(&r10_bio->remaining);
* after checking if we need to go around again.
*/
- if (sectors_handled < (bio->bi_size >> 9)) {
+ if (sectors_handled < bio_sectors(bio)) {
one_write_done(r10_bio);
/* We need another r10_bio. It has already been counted
* in bio->bi_phys_segments.
r10_bio = mempool_alloc(conf->r10bio_pool, GFP_NOIO);
r10_bio->master_bio = bio;
- r10_bio->sectors = (bio->bi_size >> 9) - sectors_handled;
+ r10_bio->sectors = bio_sectors(bio) - sectors_handled;
r10_bio->mddev = mddev;
r10_bio->sector = bio->bi_sector + sectors_handled;
d = r10_bio->devs[i].devnum;
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
atomic_inc(&r10_bio->remaining);
- md_sync_acct(conf->mirrors[d].rdev->bdev, tbio->bi_size >> 9);
+ md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(tbio));
tbio->bi_sector += conf->mirrors[d].rdev->data_offset;
tbio->bi_bdev = conf->mirrors[d].rdev->bdev;
d = r10_bio->devs[i].devnum;
atomic_inc(&r10_bio->remaining);
md_sync_acct(conf->mirrors[d].replacement->bdev,
- tbio->bi_size >> 9);
+ bio_sectors(tbio));
generic_make_request(tbio);
}
wbio2 = r10_bio->devs[1].repl_bio;
if (wbio->bi_end_io) {
atomic_inc(&conf->mirrors[d].rdev->nr_pending);
- md_sync_acct(conf->mirrors[d].rdev->bdev, wbio->bi_size >> 9);
+ md_sync_acct(conf->mirrors[d].rdev->bdev, bio_sectors(wbio));
generic_make_request(wbio);
}
if (wbio2 && wbio2->bi_end_io) {
atomic_inc(&conf->mirrors[d].replacement->nr_pending);
md_sync_acct(conf->mirrors[d].replacement->bdev,
- wbio2->bi_size >> 9);
+ bio_sectors(wbio2));
generic_make_request(wbio2);
}
}
}
}
-static void bi_complete(struct bio *bio, int error)
-{
- complete((struct completion *)bio->bi_private);
-}
-
-static int submit_bio_wait(int rw, struct bio *bio)
-{
- struct completion event;
- rw |= REQ_SYNC;
-
- init_completion(&event);
- bio->bi_private = &event;
- bio->bi_end_io = bi_complete;
- submit_bio(rw, bio);
- wait_for_completion(&event);
-
- return test_bit(BIO_UPTODATE, &bio->bi_flags);
-}
-
static int narrow_write_error(struct r10bio *r10_bio, int i)
{
struct bio *bio = r10_bio->master_bio;
r10_bio = mempool_alloc(conf->r10bio_pool,
GFP_NOIO);
r10_bio->master_bio = mbio;
- r10_bio->sectors = (mbio->bi_size >> 9)
- - sectors_handled;
+ r10_bio->sectors = bio_sectors(mbio) - sectors_handled;
r10_bio->state = 0;
set_bit(R10BIO_ReadError,
&r10_bio->state);
disks = mddev->raid_disks + mddev->delta_disks;
break;
}
- if (layout >> 17)
+ if (layout >> 18)
return -1;
if (chunk < (PAGE_SIZE >> 9) ||
!is_power_of_2(chunk))
geo->near_copies = nc;
geo->far_copies = fc;
geo->far_offset = fo;
+ geo->far_set_size = (layout & (1<<17)) ? disks / fc : disks;
geo->chunk_mask = chunk - 1;
geo->chunk_shift = ffz(~chunk);
return nc*fc;
if (mddev->queue) {
blk_queue_max_discard_sectors(mddev->queue,
mddev->chunk_sectors);
+ blk_queue_max_write_same_sectors(mddev->queue,
+ mddev->chunk_sectors);
blk_queue_io_min(mddev->queue, chunk_size);
if (conf->geo.raid_disks % conf->geo.near_copies)
blk_queue_io_opt(mddev->queue, chunk_size * conf->geo.raid_disks);
read_bio->bi_flags &= ~(BIO_POOL_MASK - 1);
read_bio->bi_flags |= 1 << BIO_UPTODATE;
read_bio->bi_vcnt = 0;
- read_bio->bi_idx = 0;
read_bio->bi_size = 0;
r10_bio->master_bio = read_bio;
r10_bio->read_slot = r10_bio->devs[r10_bio->read_slot].devnum;