Suspend writes in RAID1 if within range

If there is a resync going on, all nodes must suspend writes to the
range. This is recorded in the suspend_info/suspend_list.

If there is an I/O within the ranges of any of the suspend_info,
should_suspend will return 1.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 6b0dffebc90f13c060933a6cd43a7734c980c8aa..d85a6ca4443ee58ce70d54d78cabb27eb1053e78 100644 (file)
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -723,6 +723,25 @@ static void resync_finish(struct mddev *mddev)
        resync_send(mddev, RESYNCING, 0, 0);
 }
 
+static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi)
+{
+       struct md_cluster_info *cinfo = mddev->cluster_info;
+       int ret = 0;
+       struct suspend_info *s;
+
+       spin_lock_irq(&cinfo->suspend_lock);
+       if (list_empty(&cinfo->suspend_list))
+               goto out;
+       list_for_each_entry(s, &cinfo->suspend_list, list)
+               if (hi > s->lo && lo < s->hi) {
+                       ret = 1;
+                       break;
+               }
+out:
+       spin_unlock_irq(&cinfo->suspend_lock);
+       return ret;
+}
+
 static struct md_cluster_operations cluster_ops = {
        .join   = join,
        .leave  = leave,
@@ -733,6 +752,7 @@ static struct md_cluster_operations cluster_ops = {
        .metadata_update_start = metadata_update_start,
        .metadata_update_finish = metadata_update_finish,
        .metadata_update_cancel = metadata_update_cancel,
+       .area_resyncing = area_resyncing,
 };
 
 static int __init cluster_init(void)

diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index 054f9eafa065769582e312f538370bf9bb9dcc5a..03785402afaaa85f7d488107e65eef018fb07e2c 100644 (file)
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -17,6 +17,7 @@ struct md_cluster_operations {
        int (*metadata_update_start)(struct mddev *mddev);
        int (*metadata_update_finish)(struct mddev *mddev);
        int (*metadata_update_cancel)(struct mddev *mddev);
+       int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi);
 };
 
 #endif /* _MD_CLUSTER_H */

diff --git a/drivers/md/md.c b/drivers/md/md.c
index a1af24d369fc8f87069e67942f3d2dcbf81e173d..fe0484648de4c0df62b1ede2f409871bbe0fce6c 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -68,6 +68,7 @@ static LIST_HEAD(pers_list);
 static DEFINE_SPINLOCK(pers_lock);
 
 struct md_cluster_operations *md_cluster_ops;
+EXPORT_SYMBOL(md_cluster_ops);
 struct module *md_cluster_mod;
 EXPORT_SYMBOL(md_cluster_mod);
 

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4153da5d40111844616e8247a78e16c561602395..3aa58ab5b1fdbb5dbfc0f9cb8124b1f83d4c34f3 100644 (file)
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1101,8 +1101,10 @@ static void make_request(struct mddev *mddev, struct bio * bio)
        md_write_start(mddev, bio); /* wait on superblock update early */
 
        if (bio_data_dir(bio) == WRITE &&
-           bio_end_sector(bio) > mddev->suspend_lo &&
-           bio->bi_iter.bi_sector < mddev->suspend_hi) {
+           ((bio_end_sector(bio) > mddev->suspend_lo &&
+           bio->bi_iter.bi_sector < mddev->suspend_hi) ||
+           (mddev_is_clustered(mddev) &&
+            md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
                /* As the suspend_* range is controlled by
                 * userspace, we want an interruptible
                 * wait.
@@ -1113,7 +1115,10 @@ static void make_request(struct mddev *mddev, struct bio * bio)
                        prepare_to_wait(&conf->wait_barrier,
                                        &w, TASK_INTERRUPTIBLE);
                        if (bio_end_sector(bio) <= mddev->suspend_lo ||
-                           bio->bi_iter.bi_sector >= mddev->suspend_hi)
+                           bio->bi_iter.bi_sector >= mddev->suspend_hi ||
+                           (mddev_is_clustered(mddev) &&
+                            !md_cluster_ops->area_resyncing(mddev,
+                                    bio->bi_iter.bi_sector, bio_end_sector(bio))))
                                break;
                        schedule();
                }