btrfs: reorder extent buffer members for better packing

After the rwsem replaced the tree lock implementation, the extent buffer
got smaller but leaving some holes behind. By changing log_index type
and reordering, we can squeeze the size further to 240 bytes, measured on
release config on x86_64. Log_index spans only 3 values and needs to be
signed.

Before:

struct extent_buffer {
        u64                        start;                /*     0     8 */
        long unsigned int          len;                  /*     8     8 */
        long unsigned int          bflags;               /*    16     8 */
        struct btrfs_fs_info *     fs_info;              /*    24     8 */
        spinlock_t                 refs_lock;            /*    32     4 */
        atomic_t                   refs;                 /*    36     4 */
        atomic_t                   io_pages;             /*    40     4 */
        int                        read_mirror;          /*    44     4 */
        struct callback_head       callback_head __attribute__((__aligned__(8))); /*    48    16 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        pid_t                      lock_owner;           /*    64     4 */
        bool                       lock_recursed;        /*    68     1 */

        /* XXX 3 bytes hole, try to pack */

        struct rw_semaphore        lock;                 /*    72    40 */
        short int                  log_index;            /*   112     2 */

        /* XXX 6 bytes hole, try to pack */

        struct page *              pages[16];            /*   120   128 */

        /* size: 248, cachelines: 4, members: 14 */
        /* sum members: 239, holes: 2, sum holes: 9 */
        /* forced alignments: 1 */
        /* last cacheline: 56 bytes */
} __attribute__((__aligned__(8)));

After:

struct extent_buffer {
        u64                        start;                /*     0     8 */
        long unsigned int          len;                  /*     8     8 */
        long unsigned int          bflags;               /*    16     8 */
        struct btrfs_fs_info *     fs_info;              /*    24     8 */
        spinlock_t                 refs_lock;            /*    32     4 */
        atomic_t                   refs;                 /*    36     4 */
        atomic_t                   io_pages;             /*    40     4 */
        int                        read_mirror;          /*    44     4 */
        struct callback_head       callback_head __attribute__((__aligned__(8))); /*    48    16 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        pid_t                      lock_owner;           /*    64     4 */
        bool                       lock_recursed;        /*    68     1 */
        s8                         log_index;            /*    69     1 */

        /* XXX 2 bytes hole, try to pack */

        struct rw_semaphore        lock;                 /*    72    40 */
        struct page *              pages[16];            /*   112   128 */

        /* size: 240, cachelines: 4, members: 14 */
        /* sum members: 238, holes: 1, sum holes: 2 */
        /* forced alignments: 1 */
        /* last cacheline: 48 bytes */
} __attribute__((__aligned__(8)));

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: David Sterba <dsterba@suse.com>

diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5403354de0e11ff96e48c0e5abccc0110f327225..3c2bf21c54ebe61f75d061fea297d8f56d139aae 100644 (file)
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -88,10 +88,10 @@ struct extent_buffer {
        struct rcu_head rcu_head;
        pid_t lock_owner;
        bool lock_recursed;
-       struct rw_semaphore lock;
-
        /* >= 0 if eb belongs to a log tree, -1 otherwise */
-       short log_index;
+       s8 log_index;
+
+       struct rw_semaphore lock;
 
        struct page *pages[INLINE_EXTENT_BUFFER_PAGES];
 #ifdef CONFIG_BTRFS_DEBUG