[PATCH 1/3] btrfs: extend balance filter limit to take minimum and maximum

[David Sterba <dsterba@suse.com>]

The 'limit' filter is underdesigned, it should have been a range for
[min,max], with some relaxed semantics when one of the bounds is
missing. Besides that, using a full u64 for a single value is a waste of
bytes.

Let's fix both by extending the use of the u64 bytes for the [min,max]
range. This can be done in a backward compatible way, the range will be
interpreted only if the appropriate flag is set
(BTRFS_BALANCE_ARGS_LIMIT_RANGE).

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h           | 14 ++++++++++++--
 fs/btrfs/volumes.c         | 42 ++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.h         |  1 +
 include/uapi/linux/btrfs.h | 13 ++++++++++++-
 4 files changed, 67 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 938efe33be80..852c738d6954 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -846,8 +846,18 @@ struct btrfs_disk_balance_args {
 	/* BTRFS_BALANCE_ARGS_* */
 	__le64 flags;
 
-	/* BTRFS_BALANCE_ARGS_LIMIT value */
-	__le64 limit;
+	/*
+	 * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
+	 * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
+	 * and maximum
+	 */
+	union {
+		__le64 limit;
+		struct {
+			__le32 limit_min;
+			__le32 limit_max;
+		};
+	};
 
 	__le64 unused[7];
 } __attribute__ ((__packed__));
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6fc735869c18..b90a79c2bcf9 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3250,6 +3250,16 @@ static int should_balance_chunk(struct btrfs_root *root,
 			return 0;
 		else
 			bargs->limit--;
+	} else if ((bargs->flags & BTRFS_BALANCE_ARGS_LIMIT_RANGE)) {
+		/*
+		 * Same logic as the 'limit' filter; the minimum cannot be
+		 * determined here because we do not have the global informatoin
+		 * about the count of all chunks that satisfy the filters.
+		 */
+		if (bargs->limit_max == 0)
+			return 0;
+		else
+			bargs->limit_max--;
 	}
 
 	return 1;
@@ -3264,6 +3274,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	struct btrfs_device *device;
 	u64 old_size;
 	u64 size_to_free;
+	u64 chunk_type;
 	struct btrfs_chunk *chunk;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -3274,9 +3285,13 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	int ret;
 	int enospc_errors = 0;
 	bool counting = true;
+	/* The single value limit and min/max limits use the same bytes in the */
 	u64 limit_data = bctl->data.limit;
 	u64 limit_meta = bctl->meta.limit;
 	u64 limit_sys = bctl->sys.limit;
+	u32 count_data = 0;
+	u32 count_meta = 0;
+	u32 count_sys = 0;
 
 	/* step one make some room on all the devices */
 	devices = &fs_info->fs_devices->devices;
@@ -3317,6 +3332,10 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 	spin_unlock(&fs_info->balance_lock);
 again:
 	if (!counting) {
+		/*
+		 * The single value limit and min/max limits use the same bytes
+		 * in the
+		 */
 		bctl->data.limit = limit_data;
 		bctl->meta.limit = limit_meta;
 		bctl->sys.limit = limit_sys;
@@ -3364,6 +3383,7 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 		}
 
 		chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
+		chunk_type = btrfs_chunk_type(leaf, chunk);
 
 		if (!counting) {
 			spin_lock(&fs_info->balance_lock);
@@ -3384,6 +3404,28 @@ static int __btrfs_balance(struct btrfs_fs_info *fs_info)
 			spin_lock(&fs_info->balance_lock);
 			bctl->stat.expected++;
 			spin_unlock(&fs_info->balance_lock);
+
+			if (chunk_type & BTRFS_BLOCK_GROUP_DATA)
+				count_data++;
+			else if (chunk_type & BTRFS_BLOCK_GROUP_SYSTEM)
+				count_sys++;
+			else if (chunk_type & BTRFS_BLOCK_GROUP_METADATA)
+				count_meta++;
+
+			goto loop;
+		}
+
+		/*
+		 * Apply limit_min filter, no need to check if the LIMITS
+		 * filter is used, limit_min is 0 by default
+		 */
+		if (((chunk_type & BTRFS_BLOCK_GROUP_DATA) &&
+					count_data < bctl->data.limit_min)
+				|| ((chunk_type & BTRFS_BLOCK_GROUP_METADATA) &&
+					count_meta < bctl->meta.limit_min)
+				|| ((chunk_type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+					count_sys < bctl->sys.limit_min)) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			goto loop;
 		}
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 2ca784a14e84..c34578ee49f9 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -375,6 +375,7 @@ struct map_lookup {
 #define BTRFS_BALANCE_ARGS_DRANGE	(1ULL << 3)
 #define BTRFS_BALANCE_ARGS_VRANGE	(1ULL << 4)
 #define BTRFS_BALANCE_ARGS_LIMIT	(1ULL << 5)
+#define BTRFS_BALANCE_ARGS_LIMIT_RANGE	(1ULL << 6)
 
 /*
  * Profile changing flags.  When SOFT is set we won't relocate chunk if
diff --git a/include/uapi/linux/btrfs.h b/include/uapi/linux/btrfs.h
index b6dec05c7196..11f13108b78b 100644
--- a/include/uapi/linux/btrfs.h
+++ b/include/uapi/linux/btrfs.h
@@ -217,7 +217,18 @@ struct btrfs_balance_args {
 
 	__u64 flags;
 
-	__u64 limit;		/* limit number of processed chunks */
+	/*
+	 * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
+	 * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
+	 * and maximum
+	 */
+	union {
+		__u64 limit;		/* limit number of processed chunks */
+		struct {
+			__u32 limit_min;
+			__u32 limit_max;
+		};
+	};
 	__u64 unused[7];
 } __attribute__ ((__packed__));
 
-- 
2.6.2