Merge tag 'md/4.4' of git://neil.brown.name/md

Pull md updates from Neil Brown:
 "Two major components to this update.

   1) The clustered-raid1 support from SUSE is nearly complete.  There
      are a few outstanding issues being worked on.  Maybe half a dozen
      patches will bring this to a usable state.

   2) The first stage of journalled-raid5 support from Facebook makes an
      appearance.  With a journal device configured (typically NVRAM or
      SSD), the "RAID5 write hole" should be closed - a crash during
      degraded operations cannot result in data corruption.

      The next stage will be to use the journal as a write-behind cache
      so that latency can be reduced and in some cases throughput
      increased by performing more full-stripe writes.

* tag 'md/4.4' of git://neil.brown.name/md: (66 commits)
  MD: when RAID journal is missing/faulty, block RESTART_ARRAY_RW
  MD: set journal disk ->raid_disk
  MD: kick out journal disk if it's not fresh
  raid5-cache: start raid5 readonly if journal is missing
  MD: add new bit to indicate raid array with journal
  raid5-cache: IO error handling
  raid5: journal disk can't be removed
  raid5-cache: add trim support for log
  MD: fix info output for journal disk
  raid5-cache: use bio chaining
  raid5-cache: small log->seq cleanup
  raid5-cache: new helper: r5_reserve_log_entry
  raid5-cache: inline r5l_alloc_io_unit into r5l_new_meta
  raid5-cache: take rdev->data_offset into account early on
  raid5-cache: refactor bio allocation
  raid5-cache: clean up r5l_get_meta
  raid5-cache: simplify state machine when caches flushes are not needed
  raid5-cache: factor out a helper to run all stripes for an I/O unit
  raid5-cache: rename flushed_ios to finished_ios
  raid5-cache: free I/O units earlier
  ...

1 files changed, 37 insertions, 4 deletions

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 33e59876678b..e2169ff6e0f0 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) {
@@ -2495,6 +2506,11 @@ 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;
 	}
 
@@ -2515,7 +2531,12 @@ 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);
@@ -2706,6 +2727,16 @@ 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
 	 */
@@ -3020,9 +3051,11 @@ static int raid1_reshape(struct mddev *mddev)
 		return -EINVAL;
 	}
 
-	err = md_allow_write(mddev);
-	if (err)
-		return err;
+	if (!mddev_is_clustered(mddev)) {
+		err = md_allow_write(mddev);
+		if (err)
+			return err;
+	}
 
 	raid_disks = mddev->raid_disks + mddev->delta_disks;