@@ -325,6 +325,41 @@ static int find_bio_disk(struct r1bio *r1_bio, struct bio *bio)
return mirror;
}
+/* merge children's rd hint to master bio */
+static void raid1_merge_rd_hint(struct bio *bio)
+{
+ struct r1bio *r1_bio = bio->bi_private;
+ struct r1conf *conf = r1_bio->mddev->private;
+ struct md_rdev *tmp_rdev = NULL;
+ int i = conf->raid_disks - 1;
+ int cnt = 0;
+ int read_disk = r1_bio->read_disk;
+ DECLARE_BITMAP(tmp_bitmap, BLKDEV_MAX_MIRRORS);
+
+ if (!r1_bio->master_bio)
+ return;
+
+ /* ignore replace case now */
+ if (read_disk > conf->raid_disks - 1)
+ read_disk = r1_bio->read_disk - conf->raid_disks;
+
+ for (; i >= 0; i--) {
+ tmp_rdev = conf->mirrors[i].rdev;
+ if (i == read_disk)
+ break;
+ cnt += blk_queue_get_mirrors(bdev_get_queue(tmp_rdev->bdev));
+ }
+
+ /* init map properly from most lower layer */
+ if (blk_queue_get_mirrors(bdev_get_queue(tmp_rdev->bdev)) == 1)
+ bitmap_set(bio->bi_rd_hint, 0, 1);
+
+ bitmap_shift_left(tmp_bitmap, bio->bi_rd_hint, cnt, BLKDEV_MAX_MIRRORS);
+ bitmap_or(r1_bio->master_bio->bi_rd_hint,
+ r1_bio->master_bio->bi_rd_hint, tmp_bitmap,
+ BLKDEV_MAX_MIRRORS);
+}
+
static void raid1_end_read_request(struct bio *bio)
{
int uptodate = !bio->bi_status;
@@ -332,6 +367,7 @@ static void raid1_end_read_request(struct bio *bio)
struct r1conf *conf = r1_bio->mddev->private;
struct md_rdev *rdev = conf->mirrors[r1_bio->read_disk].rdev;
+ raid1_merge_rd_hint(bio);
/*
* this branch is our 'one mirror IO has finished' event handler:
*/
@@ -539,6 +575,37 @@ static sector_t align_to_barrier_unit_end(sector_t start_sector,
return len;
}
+static long choose_disk_from_rd_hint(struct r1conf *conf, struct r1bio *r1_bio)
+{
+ struct md_rdev *tmp_rdev;
+ unsigned long bit, cnt;
+ struct bio *bio = r1_bio->master_bio;
+ int mirror = conf->raid_disks - 1;
+
+ cnt = blk_queue_get_mirrors(r1_bio->mddev->queue);
+ /* Find a never-readed device */
+ bit = bitmap_find_next_zero_area(bio->bi_rd_hint, cnt, 0, 1, 0);
+ if (bit >= cnt)
+ /* Already tried all mirrors */
+ return -1;
+
+ /* Decide this device belongs to which mirror for stacked-layer raid
+ * devices. */
+ cnt = 0;
+ for ( ; mirror >= 0; mirror--) {
+ tmp_rdev = conf->mirrors[mirror].rdev;
+ cnt += blk_queue_get_mirrors(bdev_get_queue(tmp_rdev->bdev));
+ /* bit start from 0, while mirrors start from 1. So should compare
+ * with (bit + 1) */
+ if (cnt >= (bit + 1)) {
+ return mirror;
+ }
+ }
+
+ /* Should not arrive here. */
+ return -1;
+}
+
/*
* This routine returns the disk from which the requested read should
* be done. There is a per-array 'next expected sequential IO' sector
@@ -566,6 +633,7 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
struct md_rdev *rdev;
int choose_first;
int choose_next_idle;
+ int max_disks;
rcu_read_lock();
/*
@@ -593,7 +661,18 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect
else
choose_first = 0;
- for (disk = 0 ; disk < conf->raid_disks * 2 ; disk++) {
+ if (!bitmap_empty(r1_bio->master_bio->bi_rd_hint, BLKDEV_MAX_MIRRORS)) {
+ disk = choose_disk_from_rd_hint(conf, r1_bio);
+ if (disk < 0)
+ return -1;
+
+ /* Use the specific disk */
+ max_disks = disk + 1;
+ } else {
+ disk = 0;
+ max_disks = conf->raid_disks * 2;
+ }
+ for (; disk < max_disks; disk++) {
sector_t dist;
sector_t first_bad;
int bad_sectors;
@@ -1186,6 +1265,34 @@ alloc_r1bio(struct mddev *mddev, struct bio *bio)
return r1_bio;
}
+static void raid1_split_rd_hint(struct bio *bio)
+{
+ struct r1bio *r1_bio = bio->bi_private;
+ struct r1conf *conf = r1_bio->mddev->private;
+ unsigned int cnt = 0;
+ DECLARE_BITMAP(tmp_bitmap, BLKDEV_MAX_MIRRORS);
+
+ int i = conf->raid_disks - 1;
+ struct md_rdev *tmp_rdev = NULL;
+
+ for (; i >= 0; i--) {
+ tmp_rdev = conf->mirrors[i].rdev;
+ if (i == r1_bio->read_disk)
+ break;
+ cnt += blk_queue_get_mirrors(bdev_get_queue(tmp_rdev->bdev));
+ }
+
+ bitmap_zero(tmp_bitmap, BLKDEV_MAX_MIRRORS);
+ bitmap_shift_right(bio->bi_rd_hint, r1_bio->master_bio->bi_rd_hint, cnt,
+ BLKDEV_MAX_MIRRORS);
+
+ cnt = blk_queue_get_mirrors(bdev_get_queue(tmp_rdev->bdev));
+ bitmap_set(tmp_bitmap, 0, cnt);
+
+ bitmap_and(bio->bi_rd_hint, bio->bi_rd_hint, tmp_bitmap,
+ BLKDEV_MAX_MIRRORS);
+}
+
static void raid1_read_request(struct mddev *mddev, struct bio *bio,
int max_read_sectors, struct r1bio *r1_bio)
{
@@ -1199,6 +1306,7 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
int rdisk;
bool print_msg = !!r1_bio;
char b[BDEVNAME_SIZE];
+ bool auto_select_mirror;
/*
* If r1_bio is set, we are blocking the raid1d thread
@@ -1230,6 +1338,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
else
init_r1bio(r1_bio, mddev, bio);
r1_bio->sectors = max_read_sectors;
+ auto_select_mirror = bitmap_empty(r1_bio->master_bio->bi_rd_hint, BLKDEV_MAX_MIRRORS);
+
/*
* make_request() can abort the operation when read-ahead is being
@@ -1238,6 +1348,9 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
rdisk = read_balance(conf, r1_bio, &max_sectors);
if (rdisk < 0) {
+ if (auto_select_mirror)
+ bitmap_set(r1_bio->master_bio->bi_rd_hint, 0, BLKDEV_MAX_MIRRORS);
+
/* couldn't find anywhere to read from */
if (print_msg) {
pr_crit_ratelimited("md/raid1:%s: %s: unrecoverable I/O read error for block %llu\n",
@@ -1292,6 +1405,8 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio,
test_bit(R1BIO_FailFast, &r1_bio->state))
read_bio->bi_opf |= MD_FAILFAST;
read_bio->bi_private = r1_bio;
+ /* rd_hint of read_bio is a subset of master_bio. */
+ raid1_split_rd_hint(read_bio);
if (mddev->gendisk)
trace_block_bio_remap(read_bio->bi_disk->queue, read_bio,
rd_hint is a bit map for stacked md layer supporting. When submit bio to a lower md layer, the bio->bi_rd_hint should be split according mirror number of each device of lower layer. And merge bio->bi_rd_hint in the end path vise versa. For a two layer stacked md case like: /dev/md0 / | \ /dev/md1-a /dev/md1-b /dev/md1-c / \ / | \ / | \ /dev/sda /dev/sdb /dev/sdc /dev/sdd /dev/sde /dev/sdf /dev/sdg /dev/sdh - 1) First the top layer sumbit bio with bi_rd_hint = [00 000 000], then the value of bi_rd_hint changed as below when bio goes to lower layer. [00 000 000] / | \ [00] [000] [000] / \ / | \ / | \ [0] [0] [0] [0] [0] [0] [0] [0] - 2) i/o may goes to /dev/sda at first: [1] [0] [0] [0] [0] [0] [0] [0] \ / \ | / \ | / [10] [000] [000] \ | / [10 000 000] The top layer will get bio->bi_rd_hint = [10 000 000] - 3) Fs check the data is corrupt, resumbit bio with bi_rd_hint = [10 000 000] [10 000 000] / | \ [10] [000] [000] / \ / | \ / | \ [1] [0] [0] [0] [0] [0] [0] [0] - 4) i/o can go to any dev except /dev/sda(already tried), assum goes to /dev/sdg this time. [1] [0] [0] [0] [0] [0] [1] [0] \ / \ | / \ | / [10] [000] [010] \ | / [10 000 010] The top layer will get bio->bi_rd_hint = [10 000 010], which means we already tried /dev/sda and /dev/sdg. - 5) If the data is corrupt again, resumbit bio with bi_rd_hint = [10 000 010]. Loop until all mirrors are tried.. Signed-off-by: Bob Liu <bob.liu@oracle.com> --- drivers/md/raid1.c | 117 ++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 116 insertions(+), 1 deletion(-)