Commit c40f341f authored by Goldwyn Rodrigues's avatar Goldwyn Rodrigues
Browse files

md-cluster: Use a small window for resync 



Suspending the entire device for resync could take too long. Resync
in small chunks.

cluster's resync window (32M) is maintained in r1conf as
cluster_sync_low and cluster_sync_high and processed in
raid1's sync_request(). If the current resync is outside the cluster
resync window:

1. Set the cluster_sync_low to curr_resync_completed.
2. Check if the sync will fit in the new window, if not issue a
   wait_barrier() and set cluster_sync_low to sector_nr.
3. Set cluster_sync_high to cluster_sync_low + resync_window.
4. Send a message to all nodes so they may add it in their suspension
   list.

bitmap_cond_end_sync is modified to allow to force a sync inorder
to get the curr_resync_completed uptodate with the sector passed.

Signed-off-by: default avatarGoldwyn Rodrigues <rgoldwyn@suse.com>
Signed-off-by: default avatarNeilBrown <neilb@suse.de>
parent 3c462c88

drivers/md/bitmap.c

+2 −2
Original line number Diff line number Diff line
@@ -1570,7 +1570,7 @@ void bitmap_close_sync(struct bitmap *bitmap) 
}

EXPORT_SYMBOL(bitmap_close_sync);



void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)

void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force)

{

	sector_t s = 0;

	sector_t blocks;
@@ -1581,7 +1581,7 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector) 
		bitmap->last_end_sync = jiffies;

		return;

	}

	if (time_before(jiffies, (bitmap->last_end_sync

	if (!force && time_before(jiffies, (bitmap->last_end_sync

				  + bitmap->mddev->bitmap_info.daemon_sleep)))

		return;

	wait_event(bitmap->mddev->recovery_wait,

drivers/md/bitmap.h

+1 −1
Original line number Diff line number Diff line
@@ -257,7 +257,7 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, 
int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int degraded);

void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, sector_t *blocks, int aborted);

void bitmap_close_sync(struct bitmap *bitmap);

void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector);

void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector, bool force);



void bitmap_unplug(struct bitmap *bitmap);

void bitmap_daemon_work(struct mddev *mddev);

drivers/md/md-cluster.c

+5 −36
Original line number Diff line number Diff line
@@ -802,15 +802,6 @@ static int slot_number(struct mddev *mddev) 
	return cinfo->slot_number - 1;

}



static void resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)

{

	struct md_cluster_info *cinfo = mddev->cluster_info;



	add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);

	/* Re-acquire the lock to refresh LVB */

	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);

}



static int metadata_update_start(struct mddev *mddev)

{

	return lock_comm(mddev->cluster_info);
@@ -836,45 +827,25 @@ static int metadata_update_cancel(struct mddev *mddev) 
	return dlm_unlock_sync(cinfo->token_lockres);

}



static int resync_send(struct mddev *mddev, enum msg_type type,

		sector_t lo, sector_t hi)

static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)

{

	struct md_cluster_info *cinfo = mddev->cluster_info;

	struct cluster_msg cmsg;

	int slot = cinfo->slot_number - 1;



	add_resync_info(mddev, cinfo->bitmap_lockres, lo, hi);

	/* Re-acquire the lock to refresh LVB */

	dlm_lock_sync(cinfo->bitmap_lockres, DLM_LOCK_PW);

	pr_info("%s:%d lo: %llu hi: %llu\n", __func__, __LINE__,

			(unsigned long long)lo,

			(unsigned long long)hi);

	resync_info_update(mddev, lo, hi);

	cmsg.type = cpu_to_le32(type);

	cmsg.type = cpu_to_le32(RESYNCING);

	cmsg.slot = cpu_to_le32(slot);

	cmsg.low = cpu_to_le64(lo);

	cmsg.high = cpu_to_le64(hi);

	return sendmsg(cinfo, &cmsg);

}



static int resync_start(struct mddev *mddev, sector_t lo, sector_t hi)

{

	pr_info("%s:%d\n", __func__, __LINE__);

	return resync_send(mddev, RESYNCING, lo, hi);

}



static void resync_finish(struct mddev *mddev)

{

	struct md_cluster_info *cinfo = mddev->cluster_info;

	struct cluster_msg cmsg;

	int slot = cinfo->slot_number - 1;



	pr_info("%s:%d\n", __func__, __LINE__);

	resync_send(mddev, RESYNCING, 0, 0);

	if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {

		cmsg.type = cpu_to_le32(BITMAP_NEEDS_SYNC);

		cmsg.slot = cpu_to_le32(slot);

		sendmsg(cinfo, &cmsg);

	}

}



static int area_resyncing(struct mddev *mddev, int direction,

		sector_t lo, sector_t hi)

{
@@ -997,8 +968,6 @@ static struct md_cluster_operations cluster_ops = { 
	.leave  = leave,

	.slot_number = slot_number,

	.resync_info_update = resync_info_update,

	.resync_start = resync_start,

	.resync_finish = resync_finish,

	.metadata_update_start = metadata_update_start,

	.metadata_update_finish = metadata_update_finish,

	.metadata_update_cancel = metadata_update_cancel,

drivers/md/md-cluster.h

+1 −3
Original line number Diff line number Diff line
@@ -12,9 +12,7 @@ struct md_cluster_operations { 
	int (*join)(struct mddev *mddev, int nodes);

	int (*leave)(struct mddev *mddev);

	int (*slot_number)(struct mddev *mddev);

	void (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);

	int (*resync_start)(struct mddev *mddev, sector_t lo, sector_t hi);

	void (*resync_finish)(struct mddev *mddev);

	int (*resync_info_update)(struct mddev *mddev, sector_t lo, sector_t hi);

	int (*metadata_update_start)(struct mddev *mddev);

	int (*metadata_update_finish)(struct mddev *mddev);

	int (*metadata_update_cancel)(struct mddev *mddev);

drivers/md/md.c

+0 −8
Original line number Diff line number Diff line
@@ -7805,9 +7805,6 @@ void md_do_sync(struct md_thread *thread) 
	md_new_event(mddev);

	update_time = jiffies;



	if (mddev_is_clustered(mddev))

		md_cluster_ops->resync_start(mddev, j, max_sectors);



	blk_start_plug(&plug);

	while (j < max_sectors) {

		sector_t sectors;
@@ -7871,8 +7868,6 @@ void md_do_sync(struct md_thread *thread) 
			j = max_sectors;

		if (j > 2)

			mddev->curr_resync = j;

		if (mddev_is_clustered(mddev))

			md_cluster_ops->resync_info_update(mddev, j, max_sectors);

		mddev->curr_mark_cnt = io_sectors;

		if (last_check == 0)

			/* this is the earliest that rebuild will be
@@ -7979,9 +7974,6 @@ void md_do_sync(struct md_thread *thread) 
		}

	}

 skip:

	if (mddev_is_clustered(mddev))

		md_cluster_ops->resync_finish(mddev);



	set_bit(MD_CHANGE_DEVS, &mddev->flags);



	spin_lock(&mddev->lock);

CRA Git | Maintained and supported by SUSTech CRA and CCSE