diff options
| author | Jaegeuk Kim <jaegeuk@kernel.org> | 2016-12-14 10:12:56 -0800 |
|---|---|---|
| committer | Mister Oyster <oysterized@gmail.com> | 2017-04-13 12:34:41 +0200 |
| commit | 204f03d0539319cb64001288bf5308b60f0ec58a (patch) | |
| tree | a7781d72d2fb78ee32985235c3daf2cc0e14ba69 /fs/f2fs/segment.h | |
| parent | f1f67d336359290a86b2ed11ebbc35422fd8f8f4 (diff) | |
f2fs: support IO alignment for DATA and NODE writes
This patch implements IO alignment by filling dummy blocks in DATA and NODE
write bios. If we can guarantee, for example, 32KB or 64KB for such the IOs,
we can eliminate underlying dummy page problem which FTL conducts in order to
close MLC or TLC partial written pages.
Note that,
- it requires "-o mode=lfs".
- IO size should be power of 2, not exceed BIO_MAX_PAGES, 256.
- read IO is still 4KB.
- do checkpoint at fsync, if dummy NODE page was written.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
Diffstat (limited to 'fs/f2fs/segment.h')
| -rw-r--r-- | fs/f2fs/segment.h | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h index 4fe8d9ccc..502154022 100644 --- a/fs/f2fs/segment.h +++ b/fs/f2fs/segment.h @@ -185,9 +185,12 @@ struct segment_allocation { * the page is atomically written, and it is in inmem_pages list. */ #define ATOMIC_WRITTEN_PAGE ((unsigned long)-1) +#define DUMMY_WRITTEN_PAGE ((unsigned long)-2) #define IS_ATOMIC_WRITTEN_PAGE(page) \ (page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE) +#define IS_DUMMY_WRITTEN_PAGE(page) \ + (page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE) struct inmem_pages { struct list_head list; |