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, 35 insertions, 0 deletions

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index a99d1f415a7f..436ac7b4b334 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -980,6 +980,40 @@ static ssize_t btrfs_read_policy_store(struct kobject *kobj,
 }
 BTRFS_ATTR_RW(, read_policy, btrfs_read_policy_show, btrfs_read_policy_store);
 
+static ssize_t btrfs_bg_reclaim_threshold_show(struct kobject *kobj,
+					       struct kobj_attribute *a,
+					       char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	ssize_t ret;
+
+	ret = scnprintf(buf, PAGE_SIZE, "%d\n", fs_info->bg_reclaim_threshold);
+
+	return ret;
+}
+
+static ssize_t btrfs_bg_reclaim_threshold_store(struct kobject *kobj,
+						struct kobj_attribute *a,
+						const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	int thresh;
+	int ret;
+
+	ret = kstrtoint(buf, 10, &thresh);
+	if (ret)
+		return ret;
+
+	if (thresh <= 50 || thresh > 100)
+		return -EINVAL;
+
+	fs_info->bg_reclaim_threshold = thresh;
+
+	return len;
+}
+BTRFS_ATTR_RW(, bg_reclaim_threshold, btrfs_bg_reclaim_threshold_show,
+	      btrfs_bg_reclaim_threshold_store);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, label),
 	BTRFS_ATTR_PTR(, nodesize),
@@ -991,6 +1025,7 @@ static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(, exclusive_operation),
 	BTRFS_ATTR_PTR(, generation),
 	BTRFS_ATTR_PTR(, read_policy),
+	BTRFS_ATTR_PTR(, bg_reclaim_threshold),
 	NULL,
 };