On 2016/8/18 17:05, Chao Yu wrote: > 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)
Sorry, I miss one condition here, please ignore this patch. Thanks, > + set_sbi_flag(sbi, SBI_IS_DIRTY); > } > > static inline void inode_inc_dirty_pages(struct inode *inode) >
