ext4: use buckets for cr 1 block scan instead of rbtree

Using rbtree for sorting groups by average fragment size is relatively
expensive (needs rbtree update on every block freeing or allocation) and
leads to wide spreading of allocations because selection of block group
is very sentitive both to changes in free space and amount of blocks
allocated. Furthermore selecting group with the best matching average
fragment size is not necessary anyway, even more so because the
variability of fragment sizes within a group is likely large so average
is not telling much. We just need a group with large enough average
fragment size so that we have high probability of finding large enough
free extent and we don't want average fragment size to be too big so
that we are likely to find free extent only somewhat larger than what we
need.

So instead of maintaing rbtree of groups sorted by fragment size keep
bins (lists) or groups where average fragment size is in the interval
[2^i, 2^(i+1)). This structure requires less updates on block allocation
/ freeing, generally avoids chaotic spreading of allocations into block
groups, and still is able to quickly (even faster that the rbtree)
provide a block group which is likely to have a suitably sized free
space extent.

This patch reduces number of block groups used when untarring archive
with medium sized files (size somewhat above 64k which is default
mballoc limit for avoiding locality group preallocation) to about half
and thus improves write speeds for eMMC flash significantly.

Fixes: 196e402adf2e ("ext4: improve cr 0 / cr 1 group scanning")
CC: stable@kernel.org
Reported-and-tested-by: Stefan Wahren <stefan.wahren@i2se.com>
Tested-by: Ojaswin Mujoo <ojaswin@linux.ibm.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@gmail.com>
Link: https://lore.kernel.org/all/0d81a7c2-46b7-6010-62a4-3e6cfc1628d6@i2se.com/
Link: https://lore.kernel.org/r/20220908092136.11770-5-jack@suse.cz
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 5 insertions, 5 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9bca5565547b..3bf9a6926798 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -167,8 +167,6 @@ enum SHIFT_DIRECTION {
 #define EXT4_MB_CR0_OPTIMIZED		0x8000
 /* Avg fragment size rb tree lookup succeeded at least once for cr = 1 */
 #define EXT4_MB_CR1_OPTIMIZED		0x00010000
-/* Perform linear traversal for one group */
-#define EXT4_MB_SEARCH_NEXT_LINEAR	0x00020000
 struct ext4_allocation_request {
 	/* target inode for block we're allocating */
 	struct inode *inode;
@@ -1600,8 +1598,8 @@ struct ext4_sb_info {
 	struct list_head s_discard_list;
 	struct work_struct s_discard_work;
 	atomic_t s_retry_alloc_pending;
-	struct rb_root s_mb_avg_fragment_size_root;
-	rwlock_t s_mb_rb_lock;
+	struct list_head *s_mb_avg_fragment_size;
+	rwlock_t *s_mb_avg_fragment_size_locks;
 	struct list_head *s_mb_largest_free_orders;
 	rwlock_t *s_mb_largest_free_orders_locks;
 
@@ -3413,6 +3411,8 @@ struct ext4_group_info {
 	ext4_grpblk_t	bb_first_free;	/* first free block */
 	ext4_grpblk_t	bb_free;	/* total free blocks */
 	ext4_grpblk_t	bb_fragments;	/* nr of freespace fragments */
+	int		bb_avg_fragment_size_order;	/* order of average
+							   fragment in BG */
 	ext4_grpblk_t	bb_largest_free_order;/* order of largest frag in BG */
 	ext4_group_t	bb_group;	/* Group number */
 	struct          list_head bb_prealloc_list;
@@ -3420,7 +3420,7 @@ struct ext4_group_info {
 	void            *bb_bitmap;
 #endif
 	struct rw_semaphore alloc_sem;
-	struct rb_node	bb_avg_fragment_size_rb;
+	struct list_head bb_avg_fragment_size_node;
 	struct list_head bb_largest_free_order_node;
 	ext4_grpblk_t	bb_counters[];	/* Nr of free power-of-two-block
 					 * regions, index is order.