Merge branch 'md-next' of git://github.com/goldwynr/linux into for-next

md-cluster: A better way for METADATA_UPDATED processing

The processing of METADATA_UPDATED message is too simple and prone to
errors. Besides, it would not update the internal data structures as
required.

This set of patches reads the superblock from one of the device of the MD
and checks for changes in the in-memory data structures. If there is a change,
it performs the necessary actions to keep the internal data structures
as it would be in the primary node.

An example is if a devices turns faulty. The algorithm is:

1. The initiator node marks the device as faulty and updates the superblock
2. The initiator node sends METADATA_UPDATED with an advisory  device number to the rest of the nodes.
3. The receiving node on receiving the METADATA_UPDATED message
  3.1 Reads the superblock
  3.2 Detects a device has failed by comparing with memory structure
  3.3 Calls the necessary functions to record the failure and get the device out of the active array.
  3.4 Acknowledges the message.

The patch series also fixes adding the disk which was impacted because of
the changes.

Patches can also be found at
https://github.com/goldwynr/linux branch md-next

Changes since V2:
 - Fix status synchrnoization after --add and --re-add operations
 - Included Guoqing's patches on endian correctness, zeroing cmsg etc
 - Restructure add_new_disk() and cancel()

1 files changed, 32 insertions, 1 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index ddd8a5f..ce2d797 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -90,6 +90,8 @@ static void r1bio_pool_free(void *r1_bio, void *data)
 #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
 #define RESYNC_WINDOW (RESYNC_BLOCK_SIZE * RESYNC_DEPTH)
 #define RESYNC_WINDOW_SECTORS (RESYNC_WINDOW >> 9)
+#define CLUSTER_RESYNC_WINDOW (16 * RESYNC_WINDOW)
+#define CLUSTER_RESYNC_WINDOW_SECTORS (CLUSTER_RESYNC_WINDOW >> 9)
 #define NEXT_NORMALIO_DISTANCE (3 * RESYNC_WINDOW_SECTORS)
 
 static void * r1buf_pool_alloc(gfp_t gfp_flags, void *data)
@@ -1590,6 +1592,15 @@ static int raid1_add_disk(struct mddev *mddev, struct md_rdev *rdev)
 	if (rdev->raid_disk >= 0)
 		first = last = rdev->raid_disk;
 
+	/*
+	 * find the disk ... but prefer rdev->saved_raid_disk
+	 * if possible.
+	 */
+	if (rdev->saved_raid_disk >= 0 &&
+	    rdev->saved_raid_disk >= first &&
+	    conf->mirrors[rdev->saved_raid_disk].rdev == NULL)
+		first = last = rdev->saved_raid_disk;
+
 	for (mirror = first; mirror <= last; mirror++) {
 		p = conf->mirrors+mirror;
 		if (!p->rdev) {
@@ -2488,6 +2499,11 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 
 		bitmap_close_sync(mddev->bitmap);
 		close_sync(conf);
+
+		if (mddev_is_clustered(mddev)) {
+			conf->cluster_sync_low = 0;
+			conf->cluster_sync_high = 0;
+		}
 		return 0;
 	}
 
@@ -2508,7 +2524,12 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
 		return sync_blocks;
 	}
 
-	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
+	/* we are incrementing sector_nr below. To be safe, we check against
+	 * sector_nr + two times RESYNC_SECTORS
+	 */
+
+	bitmap_cond_end_sync(mddev->bitmap, sector_nr,
+		mddev_is_clustered(mddev) && (sector_nr + 2 * RESYNC_SECTORS > conf->cluster_sync_high));
 	r1_bio = mempool_alloc(conf->r1buf_pool, GFP_NOIO);
 
 	raise_barrier(conf, sector_nr);
@@ -2699,6 +2720,16 @@ static sector_t sync_request(struct mddev *mddev, sector_t sector_nr, int *skipp
  bio_full:
 	r1_bio->sectors = nr_sectors;
 
+	if (mddev_is_clustered(mddev) &&
+			conf->cluster_sync_high < sector_nr + nr_sectors) {
+		conf->cluster_sync_low = mddev->curr_resync_completed;
+		conf->cluster_sync_high = conf->cluster_sync_low + CLUSTER_RESYNC_WINDOW_SECTORS;
+		/* Send resync message */
+		md_cluster_ops->resync_info_update(mddev,
+				conf->cluster_sync_low,
+				conf->cluster_sync_high);
+	}
+
 	/* For a user-requested sync, we read all readable devices and do a
 	 * compare
 	 */