md/raid1,raid10: don’t ignore IO flags
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@huaweicloud.com
Signed-off-by: Yu Kuai yukuai3@huawei.com
Diffstat
-rw-r–r-- drivers/md/raid1.c 5
-rw-r–r-- drivers/md/raid10.c 8
2 files changed, 0 insertions, 13 deletions
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 8ecbb0beb10039..e366d0bba79242 100644
— a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1317,8 +1317,6 @@ 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, error;
bool r1bio_existed = !!r1_bio;
@@ -1406,7 +1404,6 @@ 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;
@@ -1655,8 +1652,6 @@ 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 | REQ_ATOMIC)); 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 e68aa4b134eeab..1c2026682f86b6 100644
— a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -1147,8 +1147,6 @@ 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];
@@ -1229,7 +1227,6 @@ 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;
@@ -1248,10 +1245,6 @@ 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;
-
const blk_opf_t do_atomic = bio->bi_opf & REQ_ATOMIC;
unsigned long flags;
struct r10conf *conf = mddev->private;
struct md_rdev *rdev;
@@ -1270,7 +1263,6 @@ 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 | do_atomic;
if (!replacement && test_bit(FailFast,
&conf->mirrors[devnum].rdev->flags)
&& enough(conf, devnum))
二、缺陷分析结构反馈
影响性分析说明：
缺陷严重等级:(Critical/High/Moderate/Low)
缺陷根因说明:
受影响版本排查(受影响/不受影响):
openEuler-20.03-LTS-SP4
openEuler-22.03-LTS-SP3
openEuler-22.03-LTS-SP4
openEuler-24.03-LTS
openEuler-24.03-LTS-SP1
修复是否涉及abi变化(是/否):
openEuler-20.03-LTS-SP4
openEuler-22.03-LTS-SP3
openEuler-22.03-LTS-SP4
openEuler-24.03-LTS
openEuler-24.03-LTS-SP1