提交 5459aa97 编写于 作者: J Jaegeuk Kim

f2fs: write dirty meta pages collectively

This patch enhances writing dirty meta pages collectively in background.
During the file data writes, it'd better avoid to write small dirty meta pages
frequently.
So let's give a chance to collect a number of dirty meta pages for a while.
Signed-off-by: NJaegeuk Kim <jaegeuk.kim@samsung.com>
上级 bfad7c2d
...@@ -107,18 +107,19 @@ static int f2fs_write_meta_pages(struct address_space *mapping, ...@@ -107,18 +107,19 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
struct writeback_control *wbc) struct writeback_control *wbc)
{ {
struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb); struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
struct block_device *bdev = sbi->sb->s_bdev; int nrpages = MAX_BIO_BLOCKS(max_hw_blocks(sbi));
long written; long written;
if (wbc->for_kupdate) if (wbc->for_kupdate)
return 0; return 0;
if (get_pages(sbi, F2FS_DIRTY_META) == 0) /* collect a number of dirty meta pages and write together */
if (get_pages(sbi, F2FS_DIRTY_META) < nrpages)
return 0; return 0;
/* if mounting is failed, skip writing node pages */ /* if mounting is failed, skip writing node pages */
mutex_lock(&sbi->cp_mutex); mutex_lock(&sbi->cp_mutex);
written = sync_meta_pages(sbi, META, bio_get_nr_vecs(bdev)); written = sync_meta_pages(sbi, META, nrpages);
mutex_unlock(&sbi->cp_mutex); mutex_unlock(&sbi->cp_mutex);
wbc->nr_to_write -= written; wbc->nr_to_write -= written;
return 0; return 0;
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册