[PATCH 034 of 35] Simplify bio_add_page and raid1/raid10 resync which use it.
From: NeilBrown
Date: Mon Jul 30 2007 - 22:31:02 EST
__bio_add_page no longer needs 'max_sectors' and can now
only fail when the bio is full.
So raid1/raid10 do not need to cope with unpredictable failure of
bio_add_page, and can be simplified. Infact they get simplified so
much that they don't use bio_add_page at all (they we only using
before to check when the bio got too big).
Signed-off-by: Neil Brown <neilb@xxxxxxx>
### Diffstat output
./drivers/md/raid1.c | 41 +++++++++++++++--------------------------
./drivers/md/raid10.c | 42 +++++++++++++-----------------------------
./fs/bio.c | 33 +++++++++------------------------
3 files changed, 37 insertions(+), 79 deletions(-)
diff .prev/drivers/md/raid10.c ./drivers/md/raid10.c
--- .prev/drivers/md/raid10.c 2007-07-31 11:21:27.000000000 +1000
+++ ./drivers/md/raid10.c 2007-07-31 11:21:29.000000000 +1000
@@ -129,6 +129,8 @@ static void * r10buf_pool_alloc(gfp_t gf
if (unlikely(!page))
goto out_free_pages;
+ bio->bi_io_vec[i].bv_offset = 0;
+ bio->bi_io_vec[i].bv_len = PAGE_SIZE;
bio->bi_io_vec[i].bv_page = page;
}
}
@@ -1576,7 +1578,6 @@ static sector_t sync_request(mddev_t *md
r10bio_t *r10_bio;
struct bio *biolist = NULL, *bio;
sector_t max_sector, nr_sectors;
- int disk;
int i;
int max_sync;
int sync_blocks;
@@ -1828,51 +1829,34 @@ static sector_t sync_request(mddev_t *md
}
}
- for (bio = biolist; bio ; bio=bio->bi_next) {
-
- bio->bi_flags &= ~(BIO_POOL_MASK - 1);
- if (bio->bi_end_io)
- bio->bi_flags |= 1 << BIO_UPTODATE;
- bio->bi_vcnt = 0;
- bio->bi_size = 0;
- }
-
nr_sectors = 0;
if (sector_nr + max_sync < max_sector)
max_sector = sector_nr + max_sync;
do {
- struct page *page;
int len = PAGE_SIZE;
- disk = 0;
+
if (sector_nr + (len>>9) > max_sector)
len = (max_sector - sector_nr) << 9;
if (len == 0)
break;
- for (bio= biolist ; bio ; bio=bio->bi_next) {
- page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
- if (bio_add_page(bio, page, len, 0) == 0) {
- /* stop here */
- struct bio *bio2;
- bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
- for (bio2 = biolist; bio2 && bio2 != bio; bio2 = bio2->bi_next) {
- /* remove last page from this bio */
- bio2->bi_vcnt--;
- bio2->bi_size -= len;
- }
- goto bio_full;
- }
- disk = i;
- }
+
nr_sectors += len>>9;
sector_nr += len>>9;
- } while (biolist->bi_vcnt < RESYNC_PAGES);
- bio_full:
+ } while (nr_sectors < (RESYNC_PAGES << (PAGE_SHIFT-9)));
+
r10_bio->sectors = nr_sectors;
while (biolist) {
bio = biolist;
biolist = biolist->bi_next;
+ bio->bi_flags &= ~(BIO_POOL_MASK - 1);
+ if (bio->bi_end_io)
+ bio->bi_flags |= 1 << BIO_UPTODATE;
+ bio->bi_size = nr_sectors << 9;
+ bio->bi_offset = 0;
+ bio->bi_vcnt = DIV_ROUND_UP(bio->bi_size, PAGE_SIZE);
+
bio->bi_next = NULL;
r10_bio = bio->bi_private;
r10_bio->sectors = nr_sectors;
diff .prev/drivers/md/raid1.c ./drivers/md/raid1.c
--- .prev/drivers/md/raid1.c 2007-07-31 11:21:27.000000000 +1000
+++ ./drivers/md/raid1.c 2007-07-31 11:21:29.000000000 +1000
@@ -119,14 +119,19 @@ static void * r1buf_pool_alloc(gfp_t gfp
goto out_free_pages;
bio->bi_io_vec[i].bv_page = page;
+ bio->bi_io_vec[i].bv_offset = 0;
+ bio->bi_io_vec[i].bv_len = PAGE_SIZE;
}
}
/* If not user-requests, copy the page pointers to all bios */
if (!test_bit(MD_RECOVERY_REQUESTED, &pi->mddev->recovery)) {
for (i=0; i<RESYNC_PAGES ; i++)
- for (j=1; j<pi->raid_disks; j++)
+ for (j = 1; j < pi->raid_disks; j++) {
+ r1_bio->bios[j]->bi_io_vec[i].bv_offset = 0;
+ r1_bio->bios[j]->bi_io_vec[i].bv_len = PAGE_SIZE;
r1_bio->bios[j]->bi_io_vec[i].bv_page =
r1_bio->bios[0]->bi_io_vec[i].bv_page;
+ }
}
r1_bio->master_bio = NULL;
@@ -1780,7 +1785,6 @@ static sector_t sync_request(mddev_t *md
nr_sectors = 0;
sync_blocks = 0;
do {
- struct page *page;
int len = PAGE_SIZE;
if (sector_nr + (len>>9) > max_sector)
len = (max_sector - sector_nr) << 9;
@@ -1796,32 +1800,18 @@ static sector_t sync_request(mddev_t *md
if (len > (sync_blocks<<9))
len = sync_blocks<<9;
}
-
- for (i=0 ; i < conf->raid_disks; i++) {
- bio = r1_bio->bios[i];
- if (bio->bi_end_io) {
- page = bio->bi_io_vec[bio->bi_vcnt].bv_page;
- if (bio_add_page(bio, page, len, 0) == 0) {
- /* stop here */
- bio->bi_io_vec[bio->bi_vcnt].bv_page = page;
- while (i > 0) {
- i--;
- bio = r1_bio->bios[i];
- if (bio->bi_end_io==NULL)
- continue;
- /* remove last page from this bio */
- bio->bi_vcnt--;
- bio->bi_size -= len;
- }
- goto bio_full;
- }
- }
- }
nr_sectors += len>>9;
sector_nr += len>>9;
sync_blocks -= (len>>9);
- } while (r1_bio->bios[disk]->bi_vcnt < RESYNC_PAGES);
- bio_full:
+ } while (nr_sectors < (RESYNC_PAGES << (PAGE_SHIFT-9)));
+
+ for (i = 0; i < conf->raid_disks ; i++) {
+ bio = r1_bio->bios[i];
+ bio->bi_size = nr_sectors << 9;
+ bio->bi_offset = 0;
+ bio->bi_vcnt = DIV_ROUND_UP(bio->bi_size, PAGE_SIZE);
+ }
+
r1_bio->sectors = nr_sectors;
/* For a user-requested sync, we read all readable devices and do a
@@ -1841,7 +1831,6 @@ static sector_t sync_request(mddev_t *md
bio = r1_bio->bios[r1_bio->read_disk];
md_sync_acct(bio->bi_bdev, nr_sectors);
generic_make_request(bio);
-
}
return nr_sectors;
}
diff .prev/fs/bio.c ./fs/bio.c
--- .prev/fs/bio.c 2007-07-31 11:21:27.000000000 +1000
+++ ./fs/bio.c 2007-07-31 11:21:29.000000000 +1000
@@ -290,19 +290,14 @@ int bio_get_nr_vecs(struct block_device
}
static int __bio_add_page(struct request_queue *q, struct bio *bio, struct page
- *page, unsigned int len, unsigned int offset,
- unsigned short max_sectors)
+ *page, unsigned int len, unsigned int offset)
{
struct bio_vec *bvec;
/*
- * cloned bio must not modify vec list
+ * cloned bio must never try to modify vec list
*/
- if (unlikely(bio_flagged(bio, BIO_CLONED)))
- return 0;
-
- if (((bio->bi_size + len) >> 9) > max_sectors)
- return 0;
+ BUG_ON(bio_flagged(bio, BIO_CLONED));
/*
* For filesystems with a blocksize smaller than the pagesize
@@ -323,10 +318,6 @@ static int __bio_add_page(struct request
if (bio->bi_vcnt >= bio->bi_max_vecs)
return 0;
- /*
- * setup the new entry, we might clear it again later if we
- * cannot add the page
- */
bvec = &bio->bi_io_vec[bio->bi_vcnt];
bvec->bv_page = page;
bvec->bv_len = len;
@@ -346,16 +337,13 @@ static int __bio_add_page(struct request
* @len: vec entry length
* @offset: vec entry offset
*
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block
- * device limitations. The target block device must allow bio's
- * smaller than PAGE_SIZE, so it is always possible to add a single
- * page to an empty bio. This should only be used by REQ_PC bios.
+ * Attempt to add a page to the bio_vec maplist. This can fail only
+ * if the bio is full. This should only be used by REQ_PC bios.
*/
int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page *page,
unsigned int len, unsigned int offset)
{
- return __bio_add_page(q, bio, page, len, offset, q->max_hw_sectors);
+ return __bio_add_page(q, bio, page, len, offset);
}
/**
@@ -365,17 +353,14 @@ int bio_add_pc_page(struct request_queue
* @len: vec entry length
* @offset: vec entry offset
*
- * Attempt to add a page to the bio_vec maplist. This can fail for a
- * number of reasons, such as the bio being full or target block
- * device limitations. The target block device must allow bio's
- * smaller than PAGE_SIZE, so it is always possible to add a single
- * page to an empty bio.
+ * Attempt to add a page to the bio_vec maplist. This can fail only
+ * if the bio is full.
*/
int bio_add_page(struct bio *bio, struct page *page, unsigned int len,
unsigned int offset)
{
struct request_queue *q = bdev_get_queue(bio->bi_bdev);
- return __bio_add_page(q, bio, page, len, offset, q->max_sectors);
+ return __bio_add_page(q, bio, page, len, offset);
}
struct bio_map_data {
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/