Commit 9ecb5ef5 authored by Qu Wenruo's avatar Qu Wenruo Committed by David Sterba

btrfs: scrub: introduce the main read repair worker for scrub_stripe

The new helper, scrub_stripe_read_repair_worker(), would handle the
read-repair part:

- Wait for the previous submitted read IO to finish

- Verify the contents of the stripe

- Go through the remaining mirrors, using as large blocksize as possible
  At this stage, we just read out all the failed sectors from each
  mirror and re-verify.
  If no more failed sector, we can exit.

- Go through all mirrors again, sector-by-sector
  This time, we read sector by sector, this is to address cases where
  one bad sector mismatches the drive's internal checksum, and cause the
  whole read range to fail.

  We put this recovery method as the last resort, as sector-by-sector
  reading is slow, and reading from other mirrors may have already fixed
  the errors.
Signed-off-by: default avatarQu Wenruo <wqu@suse.com>
Reviewed-by: default avatarDavid Sterba <dsterba@suse.com>
Signed-off-by: default avatarDavid Sterba <dsterba@suse.com>
parent 97cf8f37
...@@ -121,6 +121,7 @@ struct scrub_stripe { ...@@ -121,6 +121,7 @@ struct scrub_stripe {
atomic_t pending_io; atomic_t pending_io;
wait_queue_head_t io_wait; wait_queue_head_t io_wait;
wait_queue_head_t repair_wait;
/* /*
* Indicate the states of the stripe. Bits are defined in * Indicate the states of the stripe. Bits are defined in
...@@ -156,6 +157,8 @@ struct scrub_stripe { ...@@ -156,6 +157,8 @@ struct scrub_stripe {
* group. * group.
*/ */
u8 *csums; u8 *csums;
struct work_struct work;
}; };
struct scrub_recover { struct scrub_recover {
...@@ -381,6 +384,7 @@ int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe ...@@ -381,6 +384,7 @@ int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe
stripe->state = 0; stripe->state = 0;
init_waitqueue_head(&stripe->io_wait); init_waitqueue_head(&stripe->io_wait);
init_waitqueue_head(&stripe->repair_wait);
atomic_set(&stripe->pending_io, 0); atomic_set(&stripe->pending_io, 0);
ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages); ret = btrfs_alloc_page_array(SCRUB_STRIPE_PAGES, stripe->pages);
...@@ -403,7 +407,7 @@ int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe ...@@ -403,7 +407,7 @@ int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe
return -ENOMEM; return -ENOMEM;
} }
void wait_scrub_stripe_io(struct scrub_stripe *stripe) static void wait_scrub_stripe_io(struct scrub_stripe *stripe)
{ {
wait_event(stripe->io_wait, atomic_read(&stripe->pending_io) == 0); wait_event(stripe->io_wait, atomic_read(&stripe->pending_io) == 0);
} }
...@@ -2327,7 +2331,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr) ...@@ -2327,7 +2331,7 @@ static void scrub_verify_one_sector(struct scrub_stripe *stripe, int sector_nr)
} }
/* Verify specified sectors of a stripe. */ /* Verify specified sectors of a stripe. */
void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap) static void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap)
{ {
struct btrfs_fs_info *fs_info = stripe->bg->fs_info; struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits; const u32 sectors_per_tree = fs_info->nodesize >> fs_info->sectorsize_bits;
...@@ -2340,6 +2344,203 @@ void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap) ...@@ -2340,6 +2344,203 @@ void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap)
} }
} }
static int calc_sector_number(struct scrub_stripe *stripe, struct bio_vec *first_bvec)
{
int i;
for (i = 0; i < stripe->nr_sectors; i++) {
if (scrub_stripe_get_page(stripe, i) == first_bvec->bv_page &&
scrub_stripe_get_page_offset(stripe, i) == first_bvec->bv_offset)
break;
}
ASSERT(i < stripe->nr_sectors);
return i;
}
/*
* Repair read is different to the regular read:
*
* - Only reads the failed sectors
* - May have extra blocksize limits
*/
static void scrub_repair_read_endio(struct btrfs_bio *bbio)
{
struct scrub_stripe *stripe = bbio->private;
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
struct bio_vec *bvec;
int sector_nr = calc_sector_number(stripe, bio_first_bvec_all(&bbio->bio));
u32 bio_size = 0;
int i;
ASSERT(sector_nr < stripe->nr_sectors);
bio_for_each_bvec_all(bvec, &bbio->bio, i)
bio_size += bvec->bv_len;
if (bbio->bio.bi_status) {
bitmap_set(&stripe->io_error_bitmap, sector_nr,
bio_size >> fs_info->sectorsize_bits);
bitmap_set(&stripe->error_bitmap, sector_nr,
bio_size >> fs_info->sectorsize_bits);
} else {
bitmap_clear(&stripe->io_error_bitmap, sector_nr,
bio_size >> fs_info->sectorsize_bits);
}
bio_put(&bbio->bio);
if (atomic_dec_and_test(&stripe->pending_io))
wake_up(&stripe->io_wait);
}
static int calc_next_mirror(int mirror, int num_copies)
{
ASSERT(mirror <= num_copies);
return (mirror + 1 > num_copies) ? 1 : mirror + 1;
}
static void scrub_stripe_submit_repair_read(struct scrub_stripe *stripe,
int mirror, int blocksize, bool wait)
{
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
struct btrfs_bio *bbio = NULL;
const unsigned long old_error_bitmap = stripe->error_bitmap;
int i;
ASSERT(stripe->mirror_num >= 1);
ASSERT(atomic_read(&stripe->pending_io) == 0);
for_each_set_bit(i, &old_error_bitmap, stripe->nr_sectors) {
struct page *page;
int pgoff;
int ret;
page = scrub_stripe_get_page(stripe, i);
pgoff = scrub_stripe_get_page_offset(stripe, i);
/* The current sector cannot be merged, submit the bio. */
if (bbio && ((i > 0 && !test_bit(i - 1, &stripe->error_bitmap)) ||
bbio->bio.bi_iter.bi_size >= blocksize)) {
ASSERT(bbio->bio.bi_iter.bi_size);
atomic_inc(&stripe->pending_io);
btrfs_submit_bio(bbio, mirror);
if (wait)
wait_scrub_stripe_io(stripe);
bbio = NULL;
}
if (!bbio) {
bbio = btrfs_bio_alloc(stripe->nr_sectors, REQ_OP_READ,
fs_info, scrub_repair_read_endio, stripe);
bbio->bio.bi_iter.bi_sector = (stripe->logical +
(i << fs_info->sectorsize_bits)) >> SECTOR_SHIFT;
}
ret = bio_add_page(&bbio->bio, page, fs_info->sectorsize, pgoff);
ASSERT(ret == fs_info->sectorsize);
}
if (bbio) {
ASSERT(bbio->bio.bi_iter.bi_size);
atomic_inc(&stripe->pending_io);
btrfs_submit_bio(bbio, mirror);
if (wait)
wait_scrub_stripe_io(stripe);
}
}
/*
* The main entrance for all read related scrub work, including:
*
* - Wait for the initial read to finish
* - Verify and locate any bad sectors
* - Go through the remaining mirrors and try to read as large blocksize as
* possible
* - Go through all mirrors (including the failed mirror) sector-by-sector
*
* Writeback does not happen here, it needs extra synchronization.
*/
static void scrub_stripe_read_repair_worker(struct work_struct *work)
{
struct scrub_stripe *stripe = container_of(work, struct scrub_stripe, work);
struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
int num_copies = btrfs_num_copies(fs_info, stripe->bg->start,
stripe->bg->length);
int mirror;
int i;
ASSERT(stripe->mirror_num > 0);
wait_scrub_stripe_io(stripe);
scrub_verify_one_stripe(stripe, stripe->extent_sector_bitmap);
/* Save the initial failed bitmap for later repair and report usage. */
stripe->init_error_bitmap = stripe->error_bitmap;
if (bitmap_empty(&stripe->init_error_bitmap, stripe->nr_sectors))
goto out;
/*
* Try all remaining mirrors.
*
* Here we still try to read as large block as possible, as this is
* faster and we have extra safety nets to rely on.
*/
for (mirror = calc_next_mirror(stripe->mirror_num, num_copies);
mirror != stripe->mirror_num;
mirror = calc_next_mirror(mirror, num_copies)) {
const unsigned long old_error_bitmap = stripe->error_bitmap;
scrub_stripe_submit_repair_read(stripe, mirror,
BTRFS_STRIPE_LEN, false);
wait_scrub_stripe_io(stripe);
scrub_verify_one_stripe(stripe, old_error_bitmap);
if (bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors))
goto out;
}
/*
* Last safety net, try re-checking all mirrors, including the failed
* one, sector-by-sector.
*
* As if one sector failed the drive's internal csum, the whole read
* containing the offending sector would be marked as error.
* Thus here we do sector-by-sector read.
*
* This can be slow, thus we only try it as the last resort.
*/
for (i = 0, mirror = stripe->mirror_num;
i < num_copies;
i++, mirror = calc_next_mirror(mirror, num_copies)) {
const unsigned long old_error_bitmap = stripe->error_bitmap;
scrub_stripe_submit_repair_read(stripe, mirror,
fs_info->sectorsize, true);
wait_scrub_stripe_io(stripe);
scrub_verify_one_stripe(stripe, old_error_bitmap);
if (bitmap_empty(&stripe->error_bitmap, stripe->nr_sectors))
goto out;
}
out:
set_bit(SCRUB_STRIPE_FLAG_REPAIR_DONE, &stripe->state);
wake_up(&stripe->repair_wait);
}
void scrub_read_endio(struct btrfs_bio *bbio)
{
struct scrub_stripe *stripe = bbio->private;
if (bbio->bio.bi_status) {
bitmap_set(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
bitmap_set(&stripe->error_bitmap, 0, stripe->nr_sectors);
} else {
bitmap_clear(&stripe->io_error_bitmap, 0, stripe->nr_sectors);
}
bio_put(&bbio->bio);
if (atomic_dec_and_test(&stripe->pending_io)) {
wake_up(&stripe->io_wait);
INIT_WORK(&stripe->work, scrub_stripe_read_repair_worker);
queue_work(stripe->bg->fs_info->scrub_workers, &stripe->work);
}
}
static int scrub_checksum_tree_block(struct scrub_block *sblock) static int scrub_checksum_tree_block(struct scrub_block *sblock)
{ {
struct scrub_ctx *sctx = sblock->sctx; struct scrub_ctx *sctx = sblock->sctx;
......
...@@ -19,11 +19,10 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid, ...@@ -19,11 +19,10 @@ int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
*/ */
struct scrub_stripe; struct scrub_stripe;
int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe); int init_scrub_stripe(struct btrfs_fs_info *fs_info, struct scrub_stripe *stripe);
void wait_scrub_stripe_io(struct scrub_stripe *stripe);
int scrub_find_fill_first_stripe(struct btrfs_block_group *bg, int scrub_find_fill_first_stripe(struct btrfs_block_group *bg,
struct btrfs_device *dev, u64 physical, struct btrfs_device *dev, u64 physical,
int mirror_num, u64 logical_start, int mirror_num, u64 logical_start,
u32 logical_len, struct scrub_stripe *stripe); u32 logical_len, struct scrub_stripe *stripe);
void scrub_verify_one_stripe(struct scrub_stripe *stripe, unsigned long bitmap); void scrub_read_endio(struct btrfs_bio *bbio);
#endif #endif
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment