Skip to content

md/raid1,raid10: don't broken array on failfast metadata write fails #226

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
kpd-daemon wants to merge 3 commits into
base: md-6.16_base
Choose a base branch
from
Open

md/raid1,raid10: don't broken array on failfast metadata write fails #226

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f848e03
md/raid1,raid10: don't broken array on failfast metadata write fails
mgmlme Aug 17, 2025
2240d1e
md/raid1,raid10: Add error message when setting MD_BROKEN
mgmlme Aug 17, 2025
7b74857
md/raid1,raid10: Fix: Operation continuing on 0 devices.
mgmlme Aug 17, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 6 additions & 3 deletions drivers/md/md.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -986,14 +986,17 @@ static void super_written(struct bio *bio)
if (bio->bi_status) {
pr_err("md: %s gets error=%d\n", __func__,
blk_status_to_errno(bio->bi_status));
if (bio->bi_opf & MD_FAILFAST)
set_bit(FailfastIOFailure, &rdev->flags);
md_error(mddev, rdev);
if (!test_bit(Faulty, &rdev->flags)
&& (bio->bi_opf & MD_FAILFAST)) {
pr_warn("md: %s: Metadata write will be repeated to %pg\n",
mdname(mddev), rdev->bdev);
set_bit(MD_SB_NEED_REWRITE, &mddev->sb_flags);
set_bit(LastDev, &rdev->flags);
}
} else
clear_bit(LastDev, &rdev->flags);
clear_bit(FailfastIOFailure, &rdev->flags);

bio_put(bio);

Expand Down Expand Up @@ -1035,7 +1038,7 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,

if (test_bit(MD_FAILFAST_SUPPORTED, &mddev->flags) &&
test_bit(FailFast, &rdev->flags) &&
!test_bit(LastDev, &rdev->flags))
!test_bit(FailfastIOFailure, &rdev->flags))
bio->bi_opf |= MD_FAILFAST;

atomic_inc(&mddev->pending_writes);
Expand Down
7 changes: 4 additions & 3 deletions drivers/md/md.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -281,9 +281,10 @@ enum flag_bits {
* It is expects that no bad block log
* is present.
*/
LastDev, /* Seems to be the last working dev as
* it didn't fail, so don't use FailFast
* any more for metadata
FailfastIOFailure, /* A device that failled a metadata write
* with failfast.
* error_handler must not fail the array
* if last device has this flag.
*/
CollisionCheck, /*
* check if there is collision between raid1
Expand Down
26 changes: 20 additions & 6 deletions drivers/md/raid1.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1748,8 +1748,12 @@ static void raid1_status(struct seq_file *seq, struct mddev *mddev)
* - recovery is interrupted.
* - &mddev->degraded is bumped.
*
* @rdev is marked as &Faulty excluding case when array is failed and
* &mddev->fail_last_dev is off.
* If @rdev is marked with &FailfastIOFailure, it means that super_write
* failed in failfast and will be retried, so the @mddev did not fail.
*
* @rdev is marked as &Faulty excluding any cases:
* - when @mddev is failed and &mddev->fail_last_dev is off
* - when @rdev is last device and &FailfastIOFailure flag is set
*/
static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
{
Expand All @@ -1760,7 +1764,16 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)

if (test_bit(In_sync, &rdev->flags) &&
(conf->raid_disks - mddev->degraded) == 1) {
if (test_bit(FailfastIOFailure, &rdev->flags)) {
spin_unlock_irqrestore(&conf->device_lock, flags);
return;
}

set_bit(MD_BROKEN, &mddev->flags);
pr_crit("md/raid1:%s: Disk failure on %pg, this is the last device.\n"
"md/raid1:%s: Cannot continue operation (%d/%d failed).\n",
mdname(mddev), rdev->bdev,
mdname(mddev), mddev->degraded + 1, conf->raid_disks);

if (!mddev->fail_last_dev) {
conf->recovery_disabled = mddev->recovery_disabled;
Expand All @@ -1772,17 +1785,18 @@ static void raid1_error(struct mddev *mddev, struct md_rdev *rdev)
if (test_and_clear_bit(In_sync, &rdev->flags))
mddev->degraded++;
set_bit(Faulty, &rdev->flags);
if ((conf->raid_disks - mddev->degraded) > 0)
pr_crit("md/raid1:%s: Disk failure on %pg, disabling device.\n"
"md/raid1:%s: Operation continuing on %d devices.\n",
mdname(mddev), rdev->bdev,
mdname(mddev), conf->raid_disks - mddev->degraded);
spin_unlock_irqrestore(&conf->device_lock, flags);
/*
* if recovery is running, make sure it aborts.
*/
set_bit(MD_RECOVERY_INTR, &mddev->recovery);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
pr_crit("md/raid1:%s: Disk failure on %pg, disabling device.\n"
"md/raid1:%s: Operation continuing on %d devices.\n",
mdname(mddev), rdev->bdev,
mdname(mddev), conf->raid_disks - mddev->degraded);
}

static void print_conf(struct r1conf *conf)
Expand Down
26 changes: 20 additions & 6 deletions drivers/md/raid10.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1995,8 +1995,12 @@ static int enough(struct r10conf *conf, int ignore)
* - recovery is interrupted.
* - &mddev->degraded is bumped.
*
* @rdev is marked as &Faulty excluding case when array is failed and
* &mddev->fail_last_dev is off.
* If @rdev is marked with &FailfastIOFailure, it means that super_write
* failed in failfast, so the @mddev did not fail.
*
* @rdev is marked as &Faulty excluding any cases:
* - when @mddev is failed and &mddev->fail_last_dev is off
* - when @rdev is last device and &FailfastIOFailure flag is set
*/
static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
{
Expand All @@ -2006,7 +2010,16 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
spin_lock_irqsave(&conf->device_lock, flags);

if (test_bit(In_sync, &rdev->flags) && !enough(conf, rdev->raid_disk)) {
if (test_bit(FailfastIOFailure, &rdev->flags)) {
spin_unlock_irqrestore(&conf->device_lock, flags);
return;
}

set_bit(MD_BROKEN, &mddev->flags);
pr_crit("md/raid10:%s: Disk failure on %pg, this is the last device.\n"
"md/raid10:%s: Cannot continue operation (%d/%d failed).\n",
mdname(mddev), rdev->bdev,
mdname(mddev), mddev->degraded + 1, conf->geo.raid_disks);

if (!mddev->fail_last_dev) {
spin_unlock_irqrestore(&conf->device_lock, flags);
Expand All @@ -2021,11 +2034,12 @@ static void raid10_error(struct mddev *mddev, struct md_rdev *rdev)
set_bit(Faulty, &rdev->flags);
set_mask_bits(&mddev->sb_flags, 0,
BIT(MD_SB_CHANGE_DEVS) | BIT(MD_SB_CHANGE_PENDING));
if (enough(conf, -1))
pr_crit("md/raid10:%s: Disk failure on %pg, disabling device.\n"
"md/raid10:%s: Operation continuing on %d devices.\n",
mdname(mddev), rdev->bdev,
mdname(mddev), conf->geo.raid_disks - mddev->degraded);
spin_unlock_irqrestore(&conf->device_lock, flags);
pr_crit("md/raid10:%s: Disk failure on %pg, disabling device.\n"
"md/raid10:%s: Operation continuing on %d devices.\n",
mdname(mddev), rdev->bdev,
mdname(mddev), conf->geo.raid_disks - mddev->degraded);
}

static void print_conf(struct r10conf *conf)
Expand Down