From: Yu Kuai yukuai3@huawei.com
[ Upstream commit e879a0d9cb086c8e52ce6c04e5bfa63825a6213c ]
If blk-wbt is enabled by default, it's found that raid write performance is quite bad because all IO are throttled by wbt of underlying disks, due to flag REQ_IDLE is ignored. And turns out this behaviour exist since blk-wbt is introduced.
Other than REQ_IDLE, other flags should not be ignored as well, for example REQ_META can be set for filesystems, clearing it can cause priority reverse problems; And REQ_NOWAIT should not be cleared as well, because io will wait instead of failing directly in underlying disks.
Fix those problems by keep IO flags from master bio.
Fises: f51d46d0e7cb ("md: add support for REQ_NOWAIT") Fixes: e34cbd307477 ("blk-wbt: add general throttling mechanism") Fixes: 5404bc7a87b9 ("[PATCH] Allow file systems to differentiate between data and meta reads") Link: https://lore.kernel.org/linux-raid/20250227121657.832356-1-yukuai1@huaweiclo... Signed-off-by: Yu Kuai yukuai3@huawei.com (cherry picked from commit e879a0d9cb086c8e52ce6c04e5bfa63825a6213c) [Harshit: Resolve conflicts due to missing commit: f2a38abf5f1c ("md/raid1: Atomic write support") and commit: a1d9b4fd42d9 ("md/raid10: Atomic write support") in 6.12.y, we don't have Atomic writes feature in 6.12.y] Signed-off-by: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com --- drivers/md/raid1.c | 4 ---- drivers/md/raid10.c | 7 ------- 2 files changed, 11 deletions(-)
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index fe1599db69c8..6e93e3b6bd8c 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -1315,8 +1315,6 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, struct r1conf *conf = mddev->private; struct raid1_info *mirror; struct bio *read_bio; - const enum req_op op = bio_op(bio); - const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; int max_sectors; int rdisk; bool r1bio_existed = !!r1_bio; @@ -1399,7 +1397,6 @@ static void raid1_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_iter.bi_sector = r1_bio->sector + mirror->rdev->data_offset; read_bio->bi_end_io = raid1_end_read_request; - read_bio->bi_opf = op | do_sync; if (test_bit(FailFast, &mirror->rdev->flags) && test_bit(R1BIO_FailFast, &r1_bio->state)) read_bio->bi_opf |= MD_FAILFAST; @@ -1619,7 +1616,6 @@ static void raid1_write_request(struct mddev *mddev, struct bio *bio,
mbio->bi_iter.bi_sector = (r1_bio->sector + rdev->data_offset); mbio->bi_end_io = raid1_end_write_request; - mbio->bi_opf = bio_op(bio) | (bio->bi_opf & (REQ_SYNC | REQ_FUA)); if (test_bit(FailFast, &rdev->flags) && !test_bit(WriteMostly, &rdev->flags) && conf->raid_disks - mddev->degraded > 1) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7515a98001ca..8bb9ec39dc4f 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -1146,8 +1146,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, { struct r10conf *conf = mddev->private; struct bio *read_bio; - const enum req_op op = bio_op(bio); - const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; int max_sectors; struct md_rdev *rdev; char b[BDEVNAME_SIZE]; @@ -1226,7 +1224,6 @@ static void raid10_read_request(struct mddev *mddev, struct bio *bio, read_bio->bi_iter.bi_sector = r10_bio->devs[slot].addr + choose_data_offset(r10_bio, rdev); read_bio->bi_end_io = raid10_end_read_request; - read_bio->bi_opf = op | do_sync; if (test_bit(FailFast, &rdev->flags) && test_bit(R10BIO_FailFast, &r10_bio->state)) read_bio->bi_opf |= MD_FAILFAST; @@ -1240,9 +1237,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, struct bio *bio, bool replacement, int n_copy) { - const enum req_op op = bio_op(bio); - const blk_opf_t do_sync = bio->bi_opf & REQ_SYNC; - const blk_opf_t do_fua = bio->bi_opf & REQ_FUA; unsigned long flags; struct r10conf *conf = mddev->private; struct md_rdev *rdev; @@ -1261,7 +1255,6 @@ static void raid10_write_one_disk(struct mddev *mddev, struct r10bio *r10_bio, mbio->bi_iter.bi_sector = (r10_bio->devs[n_copy].addr + choose_data_offset(r10_bio, rdev)); mbio->bi_end_io = raid10_end_write_request; - mbio->bi_opf = op | do_sync | do_fua; if (!replacement && test_bit(FailFast, &conf->mirrors[devnum].rdev->flags) && enough(conf, devnum))