From 9631abdbf406c764f2a5d8305eac063bc3396a0a Mon Sep 17 00:00:00 2001 From: Mariusz Tkaczyk Date: Tue, 22 Mar 2022 16:23:38 +0100 Subject: md: Set MD_BROKEN for RAID1 and RAID10 There is no direct mechanism to determine raid failure outside personality. It is done by checking rdev->flags after executing md_error(). If "faulty" flag is not set then -EBUSY is returned to userspace. -EBUSY means that array will be failed after drive removal. Mdadm has special routine to handle the array failure and it is executed if -EBUSY is returned by md. There are at least two known reasons to not consider this mechanism as correct: 1. drive can be removed even if array will be failed[1]. 2. -EBUSY seems to be wrong status. Array is not busy, but removal process cannot proceed safe. -EBUSY expectation cannot be removed without breaking compatibility with userspace. In this patch first issue is resolved by adding support for MD_BROKEN flag for RAID1 and RAID10. Support for RAID456 is added in next commit. The idea is to set the MD_BROKEN if we are sure that raid is in failed state now. This is done in each error_handler(). In md_error() MD_BROKEN flag is checked. If is set, then -EBUSY is returned to userspace. As in previous commit, it causes that #mdadm --set-faulty is able to fail array. Previously proposed workaround is valid if optional functionality[1] is disabled. [1] commit 9a567843f7ce("md: allow last device to be forcibly removed from RAID1/RAID10.") Reviewd-by: Xiao Ni Signed-off-by: Mariusz Tkaczyk Signed-off-by: Song Liu --- drivers/md/md.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'drivers/md/md.c') diff --git a/drivers/md/md.c b/drivers/md/md.c index 2587f872c088..9294f13e0c9d 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2984,10 +2984,11 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len) if (cmd_match(buf, "faulty") && rdev->mddev->pers) { md_error(rdev->mddev, rdev); - if (test_bit(Faulty, &rdev->flags)) - err = 0; - else + + if (test_bit(MD_BROKEN, &rdev->mddev->flags)) err = -EBUSY; + else + err = 0; } else if (cmd_match(buf, "remove")) { if (rdev->mddev->pers) { clear_bit(Blocked, &rdev->flags); @@ -4353,10 +4354,9 @@ __ATTR_PREALLOC(resync_start, S_IRUGO|S_IWUSR, * like active, but no writes have been seen for a while (100msec). * * broken - * RAID0/LINEAR-only: same as clean, but array is missing a member. - * It's useful because RAID0/LINEAR mounted-arrays aren't stopped - * when a member is gone, so this state will at least alert the - * user that something is wrong. +* Array is failed. It's useful because mounted-arrays aren't stopped +* when array is failed, so this state will at least alert the user that +* something is wrong. */ enum array_state { clear, inactive, suspended, readonly, read_auto, clean, active, write_pending, active_idle, broken, bad_word}; @@ -7443,7 +7443,7 @@ static int set_disk_faulty(struct mddev *mddev, dev_t dev) err = -ENODEV; else { md_error(mddev, rdev); - if (!test_bit(Faulty, &rdev->flags)) + if (test_bit(MD_BROKEN, &mddev->flags)) err = -EBUSY; } rcu_read_unlock(); @@ -7984,13 +7984,16 @@ void md_error(struct mddev *mddev, struct md_rdev *rdev) if (!mddev->pers || !mddev->pers->error_handler) return; - mddev->pers->error_handler(mddev,rdev); - if (mddev->degraded) + mddev->pers->error_handler(mddev, rdev); + + if (mddev->degraded && !test_bit(MD_BROKEN, &mddev->flags)) set_bit(MD_RECOVERY_RECOVER, &mddev->recovery); sysfs_notify_dirent_safe(rdev->sysfs_state); set_bit(MD_RECOVERY_INTR, &mddev->recovery); - set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - md_wakeup_thread(mddev->thread); + if (!test_bit(MD_BROKEN, &mddev->flags)) { + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + md_wakeup_thread(mddev->thread); + } if (mddev->event_work.func) queue_work(md_misc_wq, &mddev->event_work); md_new_event(); -- cgit v1.2.1