f2fs: give an option to enable in-place-updates during fsync to users

If user wrote F2FS_IPU_FSYNC:4 in /sys/fs/f2fs/ipu_policy, f2fs_sync_file
only starts to try in-place-updates.
And, if the number of dirty pages is over /sys/fs/f2fs/min_fsync_blocks, it
keeps out-of-order manner. Otherwise, it triggers in-place-updates.

This may be used by storage showing very high random write performance.

For example, it can be used when,

Seq. writes (Data) + wait + Seq. writes (Node)

is pretty much slower than,

Rand. writes (Data)

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

5 files changed, 18 insertions, 9 deletions

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index ad7e9b369319..8efa170352ff 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -386,6 +386,7 @@ struct f2fs_sm_info {
 
 	unsigned int ipu_policy;	/* in-place-update policy */
 	unsigned int min_ipu_util;	/* in-place-update threshold */
+	unsigned int min_fsync_blocks;	/* threshold for fsync */
 
 	/* for flush command control */
 	struct flush_cmd_control *cmd_control_info;
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 77426c7eb0f1..af06e22a0dbd 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -154,12 +154,11 @@ int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	trace_f2fs_sync_file_enter(inode);
 
 	/* if fdatasync is triggered, let's do in-place-update */
-	if (datasync)
+	if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
 		set_inode_flag(fi, FI_NEED_IPU);
-
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
-	if (datasync)
-		clear_inode_flag(fi, FI_NEED_IPU);
+	clear_inode_flag(fi, FI_NEED_IPU);
+
 	if (ret) {
 		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
 		return ret;
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index e158d6358474..c6f627b492cd 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -1928,8 +1928,9 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 	sm_info->ssa_blkaddr = le32_to_cpu(raw_super->ssa_blkaddr);
 	sm_info->rec_prefree_segments = sm_info->main_segments *
 					DEF_RECLAIM_PREFREE_SEGMENTS / 100;
-	sm_info->ipu_policy = F2FS_IPU_DISABLE;
+	sm_info->ipu_policy = F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
+	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
 
 	INIT_LIST_HEAD(&sm_info->discard_list);
 	sm_info->nr_discards = 0;
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index bed0dc967f29..013aed2f3539 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -472,15 +472,20 @@ static inline int utilization(struct f2fs_sb_info *sbi)
  * F2FS_IPU_UTIL - if FS utilization is over threashold,
  * F2FS_IPU_SSR_UTIL - if SSR mode is activated and FS utilization is over
  *                     threashold,
+ * F2FS_IPU_FSYNC - activated in fsync path only for high performance flash
+ *                     storages. IPU will be triggered only if the # of dirty
+ *                     pages over min_fsync_blocks.
  * F2FS_IPUT_DISABLE - disable IPU. (=default option)
  */
 #define DEF_MIN_IPU_UTIL	70
+#define DEF_MIN_FSYNC_BLOCKS	8
 
 enum {
 	F2FS_IPU_FORCE,
 	F2FS_IPU_SSR,
 	F2FS_IPU_UTIL,
 	F2FS_IPU_SSR_UTIL,
+	F2FS_IPU_FSYNC,
 	F2FS_IPU_DISABLE,
 };
 
@@ -492,10 +497,6 @@ static inline bool need_inplace_update(struct inode *inode)
 	if (S_ISDIR(inode->i_mode))
 		return false;
 
-	/* this is only set during fdatasync */
-	if (is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
-		return true;
-
 	switch (SM_I(sbi)->ipu_policy) {
 	case F2FS_IPU_FORCE:
 		return true;
@@ -511,6 +512,11 @@ static inline bool need_inplace_update(struct inode *inode)
 		if (need_SSR(sbi) && utilization(sbi) > SM_I(sbi)->min_ipu_util)
 			return true;
 		break;
+	case F2FS_IPU_FSYNC:
+		/* this is only set during fdatasync */
+		if (is_inode_flag_set(F2FS_I(inode), FI_NEED_IPU))
+			return true;
+		break;
 	case F2FS_IPU_DISABLE:
 		break;
 	}
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index b5af9be94a4d..ed4095e5e8a7 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -190,6 +190,7 @@ F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
 F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
 F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
 F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
@@ -204,6 +205,7 @@ static struct attribute *f2fs_attrs[] = {
 	ATTR_LIST(max_small_discards),
 	ATTR_LIST(ipu_policy),
 	ATTR_LIST(min_ipu_util),
+	ATTR_LIST(min_fsync_blocks),
 	ATTR_LIST(max_victim_search),
 	ATTR_LIST(dir_level),
 	ATTR_LIST(ram_thresh),