summaryrefslogtreecommitdiff
path: root/drivers/md/md-cluster.c
diff options
context:
space:
mode:
authorGoldwyn Rodrigues <rgoldwyn@suse.de>2015-04-14 18:45:42 +0300
committerNeilBrown <neilb@suse.de>2015-04-22 00:59:39 +0300
commit97f6cd39da227459cb46ed4088d37d5d8db51c50 (patch)
tree129f07ab60f7f7fd4b6ac792bb29d40bcf938aa1 /drivers/md/md-cluster.c
parenta6da4ef85cef0382244fc588c901e133a2ec5109 (diff)
downloadlinux-97f6cd39da227459cb46ed4088d37d5d8db51c50.tar.xz
md-cluster: re-add capabilities
When "re-add" is writted to /sys/block/mdXX/md/dev-YYY/state, the clustered md: 1. Sends RE_ADD message with the desc_nr. Nodes receiving the message clear the Faulty bit in their respective rdev->flags. 2. The node initiating re-add, gathers the bitmaps of all nodes and copies them into the local bitmap. It does not clear the bitmap from which it is copying. 3. Initiating node schedules a md recovery to sync the devices. Signed-off-by: Guoqing Jiang <gqjiang@suse.com> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com> Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'drivers/md/md-cluster.c')
-rw-r--r--drivers/md/md-cluster.c48
1 files changed, 47 insertions, 1 deletions
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 30b41b70db17..fcfc4b9b2672 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -73,6 +73,7 @@ enum msg_type {
RESYNCING,
NEWDISK,
REMOVE,
+ RE_ADD,
};
struct cluster_msg {
@@ -253,7 +254,7 @@ static void recover_bitmaps(struct md_thread *thread)
str, ret);
goto clear_bit;
}
- ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi);
+ ret = bitmap_copy_from_slot(mddev, slot, &lo, &hi, true);
if (ret) {
pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
goto dlm_unlock;
@@ -412,6 +413,16 @@ static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
pr_warn("%s: %d Could not find disk(%d) to REMOVE\n", __func__, __LINE__, msg->raid_slot);
}
+static void process_readd_disk(struct mddev *mddev, struct cluster_msg *msg)
+{
+ struct md_rdev *rdev = md_find_rdev_nr_rcu(mddev, msg->raid_slot);
+
+ if (rdev && test_bit(Faulty, &rdev->flags))
+ clear_bit(Faulty, &rdev->flags);
+ else
+ pr_warn("%s: %d Could not find disk(%d) which is faulty", __func__, __LINE__, msg->raid_slot);
+}
+
static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
{
switch (msg->type) {
@@ -436,6 +447,11 @@ static void process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
__func__, __LINE__, msg->slot);
process_remove_disk(mddev, msg);
break;
+ case RE_ADD:
+ pr_info("%s: %d Received RE_ADD from %d\n",
+ __func__, __LINE__, msg->slot);
+ process_readd_disk(mddev, msg);
+ break;
default:
pr_warn("%s:%d Received unknown message from %d\n",
__func__, __LINE__, msg->slot);
@@ -883,6 +899,35 @@ static int remove_disk(struct mddev *mddev, struct md_rdev *rdev)
return __sendmsg(cinfo, &cmsg);
}
+static int gather_bitmaps(struct md_rdev *rdev)
+{
+ int sn, err;
+ sector_t lo, hi;
+ struct cluster_msg cmsg;
+ struct mddev *mddev = rdev->mddev;
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+
+ cmsg.type = RE_ADD;
+ cmsg.raid_slot = rdev->desc_nr;
+ err = sendmsg(cinfo, &cmsg);
+ if (err)
+ goto out;
+
+ for (sn = 0; sn < mddev->bitmap_info.nodes; sn++) {
+ if (sn == (cinfo->slot_number - 1))
+ continue;
+ err = bitmap_copy_from_slot(mddev, sn, &lo, &hi, false);
+ if (err) {
+ pr_warn("md-cluster: Could not gather bitmaps from slot %d", sn);
+ goto out;
+ }
+ if ((hi > 0) && (lo < mddev->recovery_cp))
+ mddev->recovery_cp = lo;
+ }
+out:
+ return err;
+}
+
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
@@ -898,6 +943,7 @@ static struct md_cluster_operations cluster_ops = {
.add_new_disk_finish = add_new_disk_finish,
.new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
+ .gather_bitmaps = gather_bitmaps,
};
static int __init cluster_init(void)