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 at 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>
---
fs/btrfs/send.c | 11 +++++++++++
1 file changed, 11 insertions(+)
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 4f00446..6d198ef 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -3966,6 +3966,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64
offset, u32 len)
pgoff_t last_index;
unsigned pg_offset = offset & ~PAGE_CACHE_MASK;
ssize_t ret = 0;
+ struct file_ra_state *ra = NULL;
key.objectid = sctx->cur_ino;
key.type = BTRFS_INODE_ITEM_KEY;
@@ -3985,6 +3986,15 @@ 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 */
+ ra = kzalloc(sizeof(*ra), GFP_NOFS);
+ if (!ra)
+ goto out;
+
+ file_ra_state_init(ra, inode->i_mapping);
+ btrfs_force_ra(inode->i_mapping, ra, NULL, index, last_index-index + 1);
+
while (index <= last_index) {
unsigned cur_len = min_t(unsigned, len,
PAGE_CACHE_SIZE - pg_offset);
@@ -4016,6 +4026,7 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64
offset, u32 len)
ret += cur_len;
}
out:
+ kfree(ra);
iput(inode);
return ret;
}
--
1.8.2.1
--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs"
in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html