Btrfs: send, apply asynchronous page cache readahead to enhance page read

By analyzing the perf on btrfs send, we found it take large amount of
cpu time on page_cache_sync_readahead. This effort can be reduced after
switching to asynchronous one. Overall performance gain on HDD and SSD
were 9 and 15 percent if simply send a large file.

Signed-off-by: Kuanling Huang <peterh@synology.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

fs/btrfs/send.c

@@ -4720,17 +4720,28 @@ static ssize_t fill_read_buf(struct send_ctx *sctx, u64 offset, u32 len)
 	/* initial readahead */
 	memset(&sctx->ra, 0, sizeof(struct file_ra_state));
 	file_ra_state_init(&sctx->ra, inode->i_mapping);
-	page_cache_sync_readahead(inode->i_mapping, &sctx->ra, NULL, index,
-		       last_index - index + 1);
 
 	while (index <= last_index) {
 		unsigned cur_len = min_t(unsigned, len,
 					 PAGE_SIZE - pg_offset);
-		page = find_or_create_page(inode->i_mapping, index, GFP_KERNEL);
+
+		page = find_lock_page(inode->i_mapping, index);
+		if (!page) {
+			page_cache_sync_readahead(inode->i_mapping, &sctx->ra,
+				NULL, index, last_index + 1 - index);
+
+			page = find_or_create_page(inode->i_mapping, index,
+					GFP_KERNEL);
 			if (!page) {
 				ret = -ENOMEM;
 				break;
 			}
+		}
+
+		if (PageReadahead(page)) {
+			page_cache_async_readahead(inode->i_mapping, &sctx->ra,
+				NULL, page, index, last_index + 1 - index);
+		}
 
 		if (!PageUptodate(page)) {
 			btrfs_readpage(NULL, page);