btrfs: zoned: automatically reclaim zones

When a file gets deleted on a zoned file system, the space freed is not
returned back into the block group's free space, but is migrated to
zone_unusable.

As this zone_unusable space is behind the current write pointer it is not
possible to use it for new allocations. In the current implementation a
zone is reset once all of the block group's space is accounted as zone
unusable.

This behaviour can lead to premature ENOSPC errors on a busy file system.

Instead of only reclaiming the zone once it is completely unusable,
kick off a reclaim job once the amount of unusable bytes exceeds a user
configurable threshold between 51% and 100%. It can be set per mounted
filesystem via the sysfs tunable bg_reclaim_threshold which is set to 75%
by default.

Similar to reclaiming unused block groups, these dirty block groups are
added to a to_reclaim list and then on a transaction commit, the reclaim
process is triggered but after we deleted unused block groups, which will
free space for the relocation process.

Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

1 files changed, 101 insertions, 0 deletions

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index bbb5a6e170c7..aa57bdc8fc89 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1485,6 +1485,97 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg)
 	spin_unlock(&fs_info->unused_bgs_lock);
 }
 
+void btrfs_reclaim_bgs_work(struct work_struct *work)
+{
+	struct btrfs_fs_info *fs_info =
+		container_of(work, struct btrfs_fs_info, reclaim_bgs_work);
+	struct btrfs_block_group *bg;
+	struct btrfs_space_info *space_info;
+	int ret;
+
+	if (!test_bit(BTRFS_FS_OPEN, &fs_info->flags))
+		return;
+
+	if (!btrfs_exclop_start(fs_info, BTRFS_EXCLOP_BALANCE))
+		return;
+
+	mutex_lock(&fs_info->reclaim_bgs_lock);
+	spin_lock(&fs_info->unused_bgs_lock);
+	while (!list_empty(&fs_info->reclaim_bgs)) {
+		bg = list_first_entry(&fs_info->reclaim_bgs,
+				      struct btrfs_block_group,
+				      bg_list);
+		list_del_init(&bg->bg_list);
+
+		space_info = bg->space_info;
+		spin_unlock(&fs_info->unused_bgs_lock);
+
+		/* Don't race with allocators so take the groups_sem */
+		down_write(&space_info->groups_sem);
+
+		spin_lock(&bg->lock);
+		if (bg->reserved || bg->pinned || bg->ro) {
+			/*
+			 * We want to bail if we made new allocations or have
+			 * outstanding allocations in this block group.  We do
+			 * the ro check in case balance is currently acting on
+			 * this block group.
+			 */
+			spin_unlock(&bg->lock);
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+		spin_unlock(&bg->lock);
+
+		/* Get out fast, in case we're unmounting the filesystem */
+		if (btrfs_fs_closing(fs_info)) {
+			up_write(&space_info->groups_sem);
+			goto next;
+		}
+
+		ret = inc_block_group_ro(bg, 0);
+		up_write(&space_info->groups_sem);
+		if (ret < 0)
+			goto next;
+
+		btrfs_info(fs_info, "reclaiming chunk %llu with %llu%% used",
+				bg->start, div_u64(bg->used * 100, bg->length));
+		trace_btrfs_reclaim_block_group(bg);
+		ret = btrfs_relocate_chunk(fs_info, bg->start);
+		if (ret)
+			btrfs_err(fs_info, "error relocating chunk %llu",
+				  bg->start);
+
+next:
+		btrfs_put_block_group(bg);
+		spin_lock(&fs_info->unused_bgs_lock);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+	mutex_unlock(&fs_info->reclaim_bgs_lock);
+	btrfs_exclop_finish(fs_info);
+}
+
+void btrfs_reclaim_bgs(struct btrfs_fs_info *fs_info)
+{
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (!list_empty(&fs_info->reclaim_bgs))
+		queue_work(system_unbound_wq, &fs_info->reclaim_bgs_work);
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
+
+void btrfs_mark_bg_to_reclaim(struct btrfs_block_group *bg)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		trace_btrfs_add_reclaim_block_group(bg);
+		list_add_tail(&bg->bg_list, &fs_info->reclaim_bgs);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
+
 static int read_bg_from_eb(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 			   struct btrfs_path *path)
 {
@@ -3446,6 +3537,16 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 	}
 	spin_unlock(&info->unused_bgs_lock);
 
+	spin_lock(&info->unused_bgs_lock);
+	while (!list_empty(&info->reclaim_bgs)) {
+		block_group = list_first_entry(&info->reclaim_bgs,
+					       struct btrfs_block_group,
+					       bg_list);
+		list_del_init(&block_group->bg_list);
+		btrfs_put_block_group(block_group);
+	}
+	spin_unlock(&info->unused_bgs_lock);
+
 	spin_lock(&info->block_group_cache_lock);
 	while ((n = rb_last(&info->block_group_cache_tree)) != NULL) {
 		block_group = rb_entry(n, struct btrfs_block_group,