Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit d5f66990 authored by Jaegeuk Kim's avatar Jaegeuk Kim
Browse files

f2fs: decrease the lock granularity during write_begin 



This patch reduces the lock granularity during write_begin.
When the system is under memory pressure, it would be better to reduce
the locking time for the data pages.

Signed-off-by: default avatarJaegeuk Kim <jaegeuk.kim@samsung.com>
parent bde44686

fs/f2fs/data.c

+13 −1
Original line number Diff line number Diff line
@@ -909,6 +909,10 @@ repeat: 
	page = grab_cache_page_write_begin(mapping, index, flags);

	if (!page)

		return -ENOMEM;



	/* to avoid latency during memory pressure */

	unlock_page(page);



	*pagep = page;



	if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
@@ -920,10 +924,18 @@ repeat: 
	f2fs_unlock_op(sbi);



	if (err) {

		f2fs_put_page(page, 1);

		f2fs_put_page(page, 0);

		return err;

	}

inline_data:

	lock_page(page);

	if (unlikely(page->mapping != mapping)) {

		f2fs_put_page(page, 1);

		goto repeat;

	}



	f2fs_wait_on_page_writeback(page, DATA);



	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))

		return 0;