re-add a failed disk
PATCH 3/4 re-add a failed disk
This adds the capability of re-adding a failed disk by writing "re-add" to /sys/block/mdXX/md/dev-YYY/state.
This works for generic md, and is not (completely) related to clustering.
Signed-off-by Goldwyn Rodrigues <[email protected]>
--- drivers/md/md.c | 56 ++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 20 deletions(-)
drivers/md/md.c +36 -20
@@ -79,6 +79,7 @@ static struct workqueue_struct *md_misc_wq;static int remove_and_add_spares (struct mddev *mddev,struct md_rdev *this); +static int add_bound_rdev (struct md_rdev *); #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
@@ -2845,6 +2846,9 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)clear_bit (Replacement, &rdev->flags); err =0 ; } + }else if (cmd_match (buf,"re-add" )) { +clear_bit (Faulty, &rdev->flags); + err =add_bound_rdev (rdev); }if (!err)sysfs_notify_dirent_safe (rdev->sysfs_state);
@@ -5861,6 +5865,37 @@ static int get_disk_info(struct mddev * mddev, void __user * arg)return 0 ; } +static int add_bound_rdev (struct md_rdev *rdev) +{ +struct mddev *mddev = rdev->mddev; +int err =0 ; + +if (!mddev->pers->hot_remove_disk) { +/* If there is hot_add_disk but no hot_remove_disk +* then added disks for geometry changes, +* and should be added immediately. +*/ + super_types[mddev->major_version]. +validate_super (mddev, rdev); + err = mddev->pers->hot_add_disk (mddev, rdev); +if (err) +unbind_rdev_from_array (rdev); + } +if (err) +export_rdev (rdev); +else +sysfs_notify_dirent_safe (rdev->sysfs_state); + +set_bit (MD_CHANGE_DEVS , &mddev->flags); +if (mddev->degraded) +set_bit (MD_RECOVERY_RECOVER , &mddev->recovery); +set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); +if (!err) +md_new_event (mddev); +md_wakeup_thread (mddev->thread); +return err; +} +static int add_new_disk (struct mddev * mddev,mdu_disk_info_t *info) {char b[BDEVNAME_SIZE ], b2[BDEVNAME_SIZE ];
@@ -5989,29 +6024,10 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) rdev->raid_disk =-1 ; err =bind_rdev_to_array (rdev, mddev); -if (!err && !mddev->pers->hot_remove_disk) { -/* If there is hot_add_disk but no hot_remove_disk -* then added disks for geometry changes, -* and should be added immediately. -*/ - super_types[mddev->major_version]. -validate_super (mddev, rdev); - err = mddev->pers->hot_add_disk (mddev, rdev); -if (err) -unbind_rdev_from_array (rdev); - }if (err)export_rdev (rdev);else -sysfs_notify_dirent_safe (rdev->sysfs_state); - -set_bit (MD_CHANGE_DEVS , &mddev->flags); -if (mddev->degraded) -set_bit (MD_RECOVERY_RECOVER , &mddev->recovery); -set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); -if (!err) -md_new_event (mddev); -md_wakeup_thread (mddev->thread); + err =add_bound_rdev (rdev);if (mddev_is_clustered (mddev) && (info->state & (1 <<MD_DISK_CLUSTER_ADD ))) md_cluster_ops->add_new_disk_finish (mddev);
Signature · 1 line
2.1.4
Quoted 5 lines · On Wed, 8 Apr 2015 14:23:37 -0500 Goldwyn Rodrigues <[email protected]> wrote:
This adds the capability of re-adding a failed disk by writing "re-add" to
/sys/block/mdXX/md/dev-YYY/state.This works for generic md, and is not (completely) related to clustering.
Again, more words here would help.
Explain why "remove, then add" isn't sufficient.
Quoted 19 lines
Signed-off-by Goldwyn Rodrigues <[email protected]>--- drivers/md/md.c | 56 ++++++++++++++++++++++++++++++++++++-------------------- 1 file changed, 36 insertions(+), 20 deletions(-)drivers/md/md.c +1
-0@@ -79,6 +79,7 @@ static struct workqueue_struct *md_misc_wq;static int remove_and_add_spares (struct mddev *mddev,struct md_rdev *this); +static int add_bound_rdev (struct md_rdev *); #define MD_BUG(x...) { printk("md: bug in file %s, line %d\n", __FILE__, __LINE__); md_print_devices(); }
drivers/md/md.c state_store(struct md_rdev *rdev, const char *buf, size_t len) · line 2851
Quoted 6 lines
drivers/md/md.c +3
-0@@ -2845,6 +2846,9 @@ state_store(struct md_rdev *rdev, const char *buf, size_t len)clear_bit (Replacement, &rdev->flags); err =0 ; } + }else if (cmd_match (buf,"re-add" )) { +clear_bit (Faulty, &rdev->flags); + err =add_bound_rdev (rdev);
Shouldn't this fail if the device isn't Faulty, of if raid_disk isn't '-1' ??
Quoted 62 lines
drivers/md/md.c +31
-14}if (!err)sysfs_notify_dirent_safe (rdev->sysfs_state);@@ -5861,6 +5865,37 @@ static int get_disk_info(struct mddev * mddev, void __user * arg)return 0 ; } +static int add_bound_rdev (struct md_rdev *rdev) +{ +struct mddev *mddev = rdev->mddev; +int err =0 ; + +if (!mddev->pers->hot_remove_disk) { +/* If there is hot_add_disk but no hot_remove_disk +* then added disks for geometry changes, +* and should be added immediately. +*/ + super_types[mddev->major_version]. +validate_super (mddev, rdev); + err = mddev->pers->hot_add_disk (mddev, rdev); +if (err) +unbind_rdev_from_array (rdev); + } +if (err) +export_rdev (rdev); +else +sysfs_notify_dirent_safe (rdev->sysfs_state); + +set_bit (MD_CHANGE_DEVS , &mddev->flags); +if (mddev->degraded) +set_bit (MD_RECOVERY_RECOVER , &mddev->recovery); +set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); +if (!err) +md_new_event (mddev); +md_wakeup_thread (mddev->thread); +return err; +} +static int add_new_disk (struct mddev * mddev,mdu_disk_info_t *info) {char b[BDEVNAME_SIZE ], b2[BDEVNAME_SIZE ];@@ -5989,29 +6024,10 @@ static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) rdev->raid_disk =-1 ; err =bind_rdev_to_array (rdev, mddev); -if (!err && !mddev->pers->hot_remove_disk) { -/* If there is hot_add_disk but no hot_remove_disk -* then added disks for geometry changes, -* and should be added immediately. -*/ - super_types[mddev->major_version]. -validate_super (mddev, rdev); - err = mddev->pers->hot_add_disk (mddev, rdev); -if (err) -unbind_rdev_from_array (rdev); - }if (err)export_rdev (rdev);else -sysfs_notify_dirent_safe (rdev->sysfs_state); - -set_bit (MD_CHANGE_DEVS , &mddev->flags);
drivers/md/md.c static int add_new_disk(struct mddev * mddev, mdu_disk_info_t *info) · line 6033
Quoted 10 lines
drivers/md/md.c +1
-6-if (mddev->degraded) -set_bit (MD_RECOVERY_RECOVER , &mddev->recovery); -set_bit (MD_RECOVERY_NEEDED , &mddev->recovery); -if (!err) -md_new_event (mddev); -md_wakeup_thread (mddev->thread); + err =add_bound_rdev (rdev);if (mddev_is_clustered (mddev) && (info->state & (1 <<MD_DISK_CLUSTER_ADD ))) md_cluster_ops->add_new_disk_finish (mddev);
This is a rather nice clean-up. Possibly it could go in a separate patch - or maybe not.
Also I think there is more room for improvement.
There is only one place in add_bound_rdev() that can set 'err', and I think that when that happens we can just clean up and return. There is no real need for the 'set_bit's or the wakeup.
Would you mind cleaning up a bit more?
Thanks,
NeilBrown