ext4: add prefetching for block allocation bitmaps

This should significantly improve bitmap loading, especially for flex
groups as it tries to load all bitmaps within a flex.group instead of
one by one synchronously.

Prefetching is done in 8 * flex_bg groups, so it should be 8
read-ahead reads for a single allocating thread. At the end of
allocation the thread waits for read-ahead completion and initializes
buddy information so that read-aheads are not lost in case of memory
pressure.

At cr=0 the number of prefetching IOs is limited per allocation
context to prevent a situation when mballoc loads thousands of bitmaps
looking for a perfect group and ignoring groups with good chunks.

Together with the patch "ext4: limit scanning of uninitialized groups"
the mount time (which includes few tiny allocations) of a 1PB
filesystem is reduced significantly:

               0% full    50%-full unpatched    patched
  mount time       33s                9279s       563s

[ Restructured by tytso; removed the state flags in the allocation
  context, so it can be used to lazily prefetch the allocation bitmaps
  immediately after the file system is mounted.  Skip prefetching
  block groups which are uninitialized.  Finally pass in the
  REQ_RAHEAD flag to the block layer while prefetching. ]

Signed-off-by: Alex Zhuravlev <bzzz@whamcloud.com>
Reviewed-by: Andreas Dilger <adilger@whamcloud.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

1 files changed, 7 insertions, 1 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index dd5e6c645442..4fba138b8722 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1521,6 +1521,8 @@ struct ext4_sb_info {
 	/* where last allocation was done - for stream allocation */
 	unsigned long s_mb_last_group;
 	unsigned long s_mb_last_start;
+	unsigned int s_mb_prefetch;
+	unsigned int s_mb_prefetch_limit;
 
 	/* stats for buddy allocator */
 	atomic_t s_bal_reqs;	/* number of reqs with len > 1 */
@@ -2462,7 +2464,8 @@ extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,
 extern int ext4_should_retry_alloc(struct super_block *sb, int *retries);
 
 extern struct buffer_head *ext4_read_block_bitmap_nowait(struct super_block *sb,
-						ext4_group_t block_group);
+						ext4_group_t block_group,
+						bool ignore_locked);
 extern int ext4_wait_block_bitmap(struct super_block *sb,
 				  ext4_group_t block_group,
 				  struct buffer_head *bh);
@@ -3161,6 +3164,7 @@ struct ext4_group_info {
 	(1 << EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT)
 #define EXT4_GROUP_INFO_IBITMAP_CORRUPT		\
 	(1 << EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT)
+#define EXT4_GROUP_INFO_BBITMAP_READ_BIT	4
 
 #define EXT4_MB_GRP_NEED_INIT(grp)	\
 	(test_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &((grp)->bb_state)))
@@ -3175,6 +3179,8 @@ struct ext4_group_info {
 	(set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
 #define EXT4_MB_GRP_CLEAR_TRIMMED(grp)	\
 	(clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
+#define EXT4_MB_GRP_TEST_AND_SET_READ(grp)	\
+	(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
 
 #define EXT4_MAX_CONTENTION		8
 #define EXT4_CONTENTION_THRESHOLD	2