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, 13 insertions, 0 deletions

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e52b89ad0a61..c9a3036c23bf 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1898,6 +1898,13 @@ static int cleaner_kthread(void *arg)
 		 * unused block groups.
 		 */
 		btrfs_delete_unused_bgs(fs_info);
+
+		/*
+		 * Reclaim block groups in the reclaim_bgs list after we deleted
+		 * all unused block_groups. This possibly gives us some more free
+		 * space.
+		 */
+		btrfs_reclaim_bgs(fs_info);
 sleep:
 		clear_and_wake_up_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags);
 		if (kthread_should_park())
@@ -2886,6 +2893,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&fs_info->space_info);
 	INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
 	INIT_LIST_HEAD(&fs_info->unused_bgs);
+	INIT_LIST_HEAD(&fs_info->reclaim_bgs);
 #ifdef CONFIG_BTRFS_DEBUG
 	INIT_LIST_HEAD(&fs_info->allocated_roots);
 	INIT_LIST_HEAD(&fs_info->allocated_ebs);
@@ -2974,6 +2982,9 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
 	fs_info->swapfile_pins = RB_ROOT;
 
 	fs_info->send_in_progress = 0;
+
+	fs_info->bg_reclaim_threshold = BTRFS_DEFAULT_RECLAIM_THRESH;
+	INIT_WORK(&fs_info->reclaim_bgs_work, btrfs_reclaim_bgs_work);
 }
 
 static int init_mount_fs_info(struct btrfs_fs_info *fs_info, struct super_block *sb)
@@ -4332,6 +4343,8 @@ void __cold close_ctree(struct btrfs_fs_info *fs_info)
 	cancel_work_sync(&fs_info->async_data_reclaim_work);
 	cancel_work_sync(&fs_info->preempt_reclaim_work);
 
+	cancel_work_sync(&fs_info->reclaim_bgs_work);
+
 	/* Cancel or finish ongoing discard work */
 	btrfs_discard_cleanup(fs_info);