ext4: New inode allocation for FLEX_BG meta-data groups.

This patch mostly controls the way inode are allocated in order to
make ialloc aware of flex_bg block group grouping.  It achieves this
by bypassing the Orlov allocator when block group meta-data are packed
toghether through mke2fs.  Since the impact on the block allocator is
minimal, this patch should have little or no effect on other block
allocation algorithms. By controlling the inode allocation, it can
basically control where the initial search for new block begins and
thus indirectly manipulate the block allocator.

This allocator favors data and meta-data locality so the disk will
gradually be filled from block group zero upward.  This helps improve
performance by reducing seek time.  Since the group of inode tables
within one flex_bg are treated as one giant inode table, uninitialized
block groups would not need to partially initialize as many inode
table as with Orlov which would help fsck time as the filesystem usage
goes up.

Signed-off-by: Jose R. Santos <jrs@us.ibm.com>
Signed-off-by: Valerie Clement <valerie.clement@bull.net>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

1 files changed, 24 insertions, 1 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 109c7d4c19ad..0bfeae18f1a2 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -170,6 +170,15 @@ struct ext4_group_desc
         __u32   bg_reserved2[3];
 };
 
+/*
+ * Structure of a flex block group info
+ */
+
+struct flex_groups {
+        __u32 free_inodes;
+        __u32 free_blocks;
+};
+
 #define EXT4_BG_INODE_UNINIT    0x0001 /* Inode table/bitmap not in use */
 #define EXT4_BG_BLOCK_UNINIT    0x0002 /* Block bitmap not in use */
 #define EXT4_BG_INODE_ZEROED    0x0004 /* On-disk itable initialized to zero */
@@ -647,7 +656,10 @@ struct ext4_super_block {
         __le16  s_mmp_interval;         /* # seconds to wait in MMP checking */
         __le64  s_mmp_block;            /* Block for multi-mount protection */
         __le32  s_raid_stripe_width;    /* blocks on all data disks (N*stride)*/
-        __u32   s_reserved[163];        /* Padding to the end of the block */
+        __u8    s_log_groups_per_flex;  /* FLEX_BG group size */
+        __u8    s_reserved_char_pad2;
+        __le16  s_reserved_pad;
+        __u32   s_reserved[162];        /* Padding to the end of the block */
 };
 
 #ifdef __KERNEL__
@@ -1160,6 +1172,17 @@ struct ext4_group_info *ext4_get_group_info(struct super_block *sb,
 }
 
 
+static inline ext4_group_t ext4_flex_group(struct ext4_sb_info *sbi,
+                                             ext4_group_t block_group)
+{
+        return block_group >> sbi->s_log_groups_per_flex;
+}
+
+static inline unsigned int ext4_flex_bg_size(struct ext4_sb_info *sbi)
+{
+        return 1 << sbi->s_log_groups_per_flex;
+}
+
 #define ext4_std_error(sb, errno)                               \
 do {                                                            \
         if ((errno))                                            \