From: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
Reloading of superblock must be performed under reconfig_mutex. However,
this cannot be done with md_reload_sb because it would deadlock with
the message DLM lock. So, we defer it in md_check_recovery() which is
executed by mddev->thread.
This introduces a new flag, MD_RELOAD_SB, which if set, will reload the
superblock.
Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
---
drivers/md/md-cluster.c | 12 +++++++++++-
drivers/md/md-cluster.h | 1 +
drivers/md/md.c | 3 +++
drivers/md/md.h | 3 +++
4 files changed, 18 insertions(+), 1 deletion(-)
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index a681706..9a36ad6 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -71,6 +71,7 @@ struct md_cluster_info {
struct md_thread *recv_thread;
struct completion newdisk_completion;
unsigned long state;
+ atomic_t good_device_nr;
};
enum msg_type {
@@ -434,8 +435,10 @@ static void process_add_new_disk(struct mddev *mddev, struct cluster_msg *cmsg)
static void process_metadata_update(struct mddev *mddev, struct cluster_msg *msg)
{
struct md_cluster_info *cinfo = mddev->cluster_info;
- md_reload_sb(mddev, le32_to_cpu(msg->raid_slot));
+ atomic_set(&cinfo->good_device_nr, le32_to_cpu(msg->raid_slot));
+ set_bit(MD_RELOAD_SB, &mddev->flags);
dlm_lock_sync(cinfo->no_new_dev_lockres, DLM_LOCK_CR);
+ md_wakeup_thread(mddev->thread);
}
static void process_remove_disk(struct mddev *mddev, struct cluster_msg *msg)
@@ -1047,6 +1050,12 @@ out:
return err;
}
+static int good_device_nr(struct mddev *mddev)
+{
+ struct md_cluster_info *cinfo = mddev->cluster_info;
+ return atomic_read(&cinfo->good_device_nr);
+}
+
static struct md_cluster_operations cluster_ops = {
.join = join,
.leave = leave,
@@ -1063,6 +1072,7 @@ static struct md_cluster_operations cluster_ops = {
.new_disk_ack = new_disk_ack,
.remove_disk = remove_disk,
.gather_bitmaps = gather_bitmaps,
+ .good_device_nr = good_device_nr,
};
static int __init cluster_init(void)
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index e75ea26..c699c6c 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -24,6 +24,7 @@ struct md_cluster_operations {
int (*new_disk_ack)(struct mddev *mddev, bool ack);
int (*remove_disk)(struct mddev *mddev, struct md_rdev *rdev);
int (*gather_bitmaps)(struct md_rdev *rdev);
+ int (*good_device_nr)(struct mddev *mddev);
};
#endif /* _MD_CLUSTER_H */
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 32ca592..65b6326 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8184,6 +8184,7 @@ void md_check_recovery(struct mddev *mddev)
(mddev->flags & MD_UPDATE_SB_FLAGS & ~ (1<<MD_CHANGE_PENDING)) ||
test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) ||
test_bit(MD_RECOVERY_DONE, &mddev->recovery) ||
+ test_bit(MD_RELOAD_SB, &mddev->flags) ||
(mddev->external == 0 && mddev->safemode == 1) ||
(mddev->safemode == 2 && ! atomic_read(&mddev->writes_pending)
&& !mddev->in_sync && mddev->recovery_cp == MaxSector)
@@ -8232,6 +8233,8 @@ void md_check_recovery(struct mddev *mddev)
rdev->raid_disk < 0)
md_kick_rdev_from_array(rdev);
}
+ if (test_and_clear_bit(MD_RELOAD_SB, &mddev->flags))
+ md_reload_sb(mddev, md_cluster_ops->good_device_nr(mddev));
}
if (!mddev->external) {
diff --git a/drivers/md/md.h b/drivers/md/md.h
index db54341..f89866d 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -222,6 +222,9 @@ struct mddev {
#define MD_STILL_CLOSED 4 /* If set, then array has not been opened since
* md_ioctl checked on it.
*/
+#define MD_RELOAD_SB 5 /* Reload the superblock because another node
+ * updated it.
+ */
int suspended;
atomic_t active_io;
--
1.8.5.6
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
