btrfs: make the chunk allocator utilize the devices better

With this patch, we change the handling method when we can not get enough free
extents with default size.

Implementation:
1. Look up the suitable free extent on each device and keep the search result.
   If not find a suitable free extent, keep the max free extent
2. If we get enough suitable free extents with default size, chunk allocation
   succeeds.
3. If we can not get enough free extents, but the number of the extent with
   default size is >= min_stripes, we just change the mapping information
   (reduce the number of stripes in the extent map), and chunk allocation
   succeeds.
4. If the number of the extent with default size is < min_stripes, sort the
   devices by its max free extent's size descending
5. Use the size of the max free extent on the (num_stripes - 1)th device as the
   stripe size to allocate the device space

By this way, the chunk allocator can allocate chunks as large as possible when
the devices' space is not enough and make full use of the devices.

Signed-off-by: Miao Xie <miaox@cn.fujitsu.com>
Signed-off-by: Chris Mason <chris.mason@oracle.com>

1 files changed, 24 insertions, 0 deletions

diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index a668c011698..a5cfedf393f 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -20,8 +20,11 @@
 #define __BTRFS_VOLUMES_
 
 #include <linux/bio.h>
+#include <linux/sort.h>
 #include "async-thread.h"
 
+#define BTRFS_STRIPE_LEN	(64 * 1024)
+
 struct buffer_head;
 struct btrfs_pending_bios {
 	struct bio *head;
@@ -137,6 +140,27 @@ struct btrfs_multi_bio {
 	struct btrfs_bio_stripe stripes[];
 };
 
+struct btrfs_device_info {
+	struct btrfs_device *dev;
+	u64 dev_offset;
+	u64 max_avail;
+};
+
+/* Used to sort the devices by max_avail(descending sort) */
+int btrfs_cmp_device_free_bytes(const void *dev_info1, const void *dev_info2);
+
+/*
+ * sort the devices by max_avail, in which max free extent size of each device
+ * is stored.(Descending Sort)
+ */
+static inline void btrfs_descending_sort_devices(
+					struct btrfs_device_info *devices,
+					size_t nr_devices)
+{
+	sort(devices, nr_devices, sizeof(struct btrfs_device_info),
+	     btrfs_cmp_device_free_bytes, NULL);
+}
+
 #define btrfs_multi_bio_size(n) (sizeof(struct btrfs_multi_bio) + \
 			    (sizeof(struct btrfs_bio_stripe) * (n)))