We don't guarantee integrity of user data after checkpoint, since we only guarantee meta data integrity for data consistency of filesystem.
Due to above reason, we only need to set fs as dirty when meta data is updated, so that we can skip writing checkpoint in some case of non-meta data is updated. Signed-off-by: Chao Yu <[email protected]> --- fs/f2fs/f2fs.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h index 5a10bce..1659d10 100644 --- a/fs/f2fs/f2fs.h +++ b/fs/f2fs/f2fs.h @@ -1220,7 +1220,9 @@ static inline void dec_valid_block_count(struct f2fs_sb_info *sbi, static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type) { percpu_counter_inc(&sbi->nr_pages[count_type]); - set_sbi_flag(sbi, SBI_IS_DIRTY); + if (count_type == F2FS_DIRTY_DENTS || count_type == F2FS_DIRTY_NODES || + count_type == F2FS_DIRTY_META) + set_sbi_flag(sbi, SBI_IS_DIRTY); } static inline void inode_inc_dirty_pages(struct inode *inode) -- 2.8.2.311.gee88674
