diff options
author | Goldwyn Rodrigues <rgoldwyn@suse.com> | 2014-10-29 18:51:31 -0500 |
---|---|---|
committer | Goldwyn Rodrigues <rgoldwyn@suse.com> | 2015-02-23 09:59:07 -0600 |
commit | 1aee41f637694d4bbf91c24195f2b63e3f6badd2 (patch) | |
tree | b6f532e5a4265193dd5ebc547a0ab9f772143762 /drivers/md/md.c | |
parent | 7d49ffcfa3cc08aa2301bf3fdb1e423a3fd33ee7 (diff) |
Add new disk to clustered array
Algorithm:
1. Node 1 issues mdadm --manage /dev/mdX --add /dev/sdYY which issues
ioctl(ADD_NEW_DISC with disc.state set to MD_DISK_CLUSTER_ADD)
2. Node 1 sends NEWDISK with uuid and slot number
3. Other nodes issue kobject_uevent_env with uuid and slot number
(Steps 4,5 could be a udev rule)
4. In userspace, the node searches for the disk, perhaps
using blkid -t SUB_UUID=""
5. Other nodes issue either of the following depending on whether the disk
was found:
ioctl(ADD_NEW_DISK with disc.state set to MD_DISK_CANDIDATE and
disc.number set to slot number)
ioctl(CLUSTERED_DISK_NACK)
6. Other nodes drop lock on no-new-devs (CR) if device is found
7. Node 1 attempts EX lock on no-new-devs
8. If node 1 gets the lock, it sends METADATA_UPDATED after unmarking the disk
as SpareLocal
9. If not (get no-new-dev lock), it fails the operation and sends METADATA_UPDATED
10. Other nodes understand if the device is added or not by reading the superblock again after receiving the METADATA_UPDATED message.
Signed-off-by: Lidong Zhong <lzhong@suse.com>
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r-- | drivers/md/md.c | 52 |
1 files changed, 49 insertions, 3 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c index fe0484648de4..5703c2e89f3a 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -2210,7 +2210,7 @@ static void sync_sbs(struct mddev *mddev, int nospares) } } -static void md_update_sb(struct mddev *mddev, int force_change) +void md_update_sb(struct mddev *mddev, int force_change) { struct md_rdev *rdev; int sync_req; @@ -2371,6 +2371,7 @@ repeat: wake_up(&rdev->blocked_wait); } } +EXPORT_SYMBOL(md_update_sb); /* words written to sysfs files may, or may not, be \n terminated. * We want to accept with case. For this we use cmd_match. @@ -3151,7 +3152,7 @@ static void analyze_sbs(struct mddev *mddev) kick_rdev_from_array(rdev); continue; } - if (rdev != freshest) + if (rdev != freshest) { if (super_types[mddev->major_version]. validate_super(mddev, rdev)) { printk(KERN_WARNING "md: kicking non-fresh %s" @@ -3160,6 +3161,15 @@ static void analyze_sbs(struct mddev *mddev) kick_rdev_from_array(rdev); continue; } + /* No device should have a Candidate flag + * when reading devices + */ + if (test_bit(Candidate, &rdev->flags)) { + pr_info("md: kicking Cluster Candidate %s from array!\n", + bdevname(rdev->bdev, b)); + kick_rdev_from_array(rdev); + } + } if (mddev->level == LEVEL_MULTIPATH) { rdev->desc_nr = i++; rdev->raid_disk = rdev->desc_nr; @@ -5655,7 +5665,6 @@ static int get_array_info(struct mddev *mddev, void __user *arg) info.state |= (1<<MD_SB_BITMAP_PRESENT); if (mddev_is_clustered(mddev)) info.state |= (1<<MD_SB_CLUSTERED); - info.active_disks = insync; info.working_disks = working; info.failed_disks = failed; @@ -5744,6 +5753,13 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) struct md_rdev *rdev; dev_t dev = MKDEV(info->major,info->minor); + if (mddev_is_clustered(mddev) && + !(info->state & ((1 << MD_DISK_CLUSTER_ADD) | (1 << MD_DISK_CANDIDATE)))) { + pr_err("%s: Cannot add to clustered mddev. Try --cluster-add\n", + mdname(mddev)); + return -EINVAL; + } + if (info->major != MAJOR(dev) || info->minor != MINOR(dev)) return -EOVERFLOW; @@ -5830,6 +5846,25 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) else clear_bit(WriteMostly, &rdev->flags); + /* + * check whether the device shows up in other nodes + */ + if (mddev_is_clustered(mddev)) { + if (info->state & (1 << MD_DISK_CANDIDATE)) { + /* Through --cluster-confirm */ + set_bit(Candidate, &rdev->flags); + md_cluster_ops->new_disk_ack(mddev, true); + } else if (info->state & (1 << MD_DISK_CLUSTER_ADD)) { + /* --add initiated by this node */ + err = md_cluster_ops->add_new_disk_start(mddev, rdev); + if (err) { + md_cluster_ops->add_new_disk_finish(mddev); + export_rdev(rdev); + return err; + } + } + } + rdev->raid_disk = -1; err = bind_rdev_to_array(rdev, mddev); if (!err && !mddev->pers->hot_remove_disk) { @@ -5855,6 +5890,9 @@ static int add_new_disk(struct mddev *mddev, mdu_disk_info_t *info) if (!err) md_new_event(mddev); md_wakeup_thread(mddev->thread); + if (mddev_is_clustered(mddev) && + (info->state & (1 << MD_DISK_CLUSTER_ADD))) + md_cluster_ops->add_new_disk_finish(mddev); return err; } @@ -6456,6 +6494,7 @@ static inline bool md_ioctl_valid(unsigned int cmd) case SET_DISK_FAULTY: case STOP_ARRAY: case STOP_ARRAY_RO: + case CLUSTERED_DISK_NACK: return true; default: return false; @@ -6728,6 +6767,13 @@ static int md_ioctl(struct block_device *bdev, fmode_t mode, goto unlock; } + case CLUSTERED_DISK_NACK: + if (mddev_is_clustered(mddev)) + md_cluster_ops->new_disk_ack(mddev, false); + else + err = -EINVAL; + goto unlock; + case HOT_ADD_DISK: err = hot_add_disk(mddev, new_decode_dev(arg)); goto unlock; |