Btrfs: add readahead for send_write

Btrfs send reads data from disk and then writes to a stream via pipe or
a file via flush.

Currently we're going to read each page a time, so every page results
in a disk read, which is not friendly to disks, esp. HDD.  Given that,
the performance can be gained by adding readahead for those pages.

Here is a quick test:
$ btrfs subvolume create send
$ xfs_io -f -c "pwrite 0 1G" send/foobar
$ btrfs subvolume snap -r send ro
$ time "btrfs send ro -f /dev/null"

           w/o             w
real    1m37.527s       0m9.097s
user    0m0.122s        0m0.086s
sys     0m53.191s       0m12.857s

Signed-off-by: Liu Bo <bo.li.liu@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fb.com>

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 112eb647b5cd98391b66ab6207078463f773a8fa..6463691796974ad5f9951bbcfd722296a9014845 100644 (file)
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -124,6 +124,8 @@ struct send_ctx {
        struct list_head name_cache_list;
        int name_cache_size;
 
+       struct file_ra_state ra;
+
        char *read_buf;
 
        /*
@@ -4170,6 +4172,13 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
                goto out;
 
        last_index = (offset + len - 1) >> PAGE_CACHE_SHIFT;
+
+       /* initial readahead */
+       memset(&sctx->ra, 0, sizeof(struct file_ra_state));
+       file_ra_state_init(&sctx->ra, inode->i_mapping);
+       btrfs_force_ra(inode->i_mapping, &sctx->ra, NULL, index,
+                      last_index - index + 1);
+
        while (index <= last_index) {
                unsigned cur_len = min_t(unsigned, len,
                                         PAGE_CACHE_SIZE - pg_offset);