[RFC PATHC 2/2] f2fs: apply write hints to select the type of segment for direct write

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 



From: Hyunchul Lee <cheol.lee@xxxxxxx>

Select the type of the segment using write hints, when blocks are
allocated for direct write.

There are unhandled corner cases. Hints are not applied in
in-place update.  And if the blocks of a file is not pre-allocated
because of the invalid user buffer, CURSEG_WARM_DATA segment will
be selected.

Signed-off-by: Hyunchul Lee <cheol.lee@xxxxxxx>
---
 fs/f2fs/data.c | 101 ++++++++++++++++++++++++++++++++++-----------------------
 fs/f2fs/f2fs.h |   1 +
 2 files changed, 61 insertions(+), 41 deletions(-)

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 36b5352..d06048a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -783,7 +783,7 @@ struct page *get_new_data_page(struct inode *inode,
 	return page;
 }
 
-static int __allocate_data_block(struct dnode_of_data *dn)
+static int __allocate_data_block(struct dnode_of_data *dn, int seg_type)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
 	struct f2fs_summary sum;
@@ -808,7 +808,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-					&sum, CURSEG_WARM_DATA, NULL, false);
+					&sum, seg_type, NULL, false);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -827,42 +827,6 @@ static inline bool __force_buffered_io(struct inode *inode, int rw)
 			F2FS_I_SB(inode)->s_ndevs);
 }
 
-int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
-{
-	struct inode *inode = file_inode(iocb->ki_filp);
-	struct f2fs_map_blocks map;
-	int err = 0;
-
-	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
-		return 0;
-
-	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
-	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
-	if (map.m_len > map.m_lblk)
-		map.m_len -= map.m_lblk;
-	else
-		map.m_len = 0;
-
-	map.m_next_pgofs = NULL;
-
-	if (iocb->ki_flags & IOCB_DIRECT) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-		return f2fs_map_blocks(inode, &map, 1,
-			__force_buffered_io(inode, WRITE) ?
-				F2FS_GET_BLOCK_PRE_AIO :
-				F2FS_GET_BLOCK_PRE_DIO);
-	}
-	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
-		err = f2fs_convert_inline_inode(inode);
-		if (err)
-			return err;
-	}
-	if (!f2fs_has_inline_data(inode))
-		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
-	return err;
-}
 
 static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
 {
@@ -888,8 +852,8 @@ static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
  *     b. do not use extent cache for better performance
  *     c. give the block addresses to blockdev
  */
-int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
-						int create, int flag)
+static int __f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+				int create, int flag, int seg_type)
 {
 	unsigned int maxblocks = map->m_len;
 	struct dnode_of_data dn;
@@ -957,7 +921,12 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 					last_ofs_in_node = dn.ofs_in_node;
 				}
 			} else {
-				err = __allocate_data_block(&dn);
+				/* if this inode is marked with FI_NO_PREALLOC,
+				 * @seg_type is NO_CHECK_TYPE
+				 */
+				if (seg_type == NO_CHECK_TYPE)
+					seg_type = CURSEG_WARM_DATA;
+				err = __allocate_data_block(&dn, seg_type);
 				if (!err)
 					set_inode_flag(inode, FI_APPEND_WRITE);
 			}
@@ -1048,6 +1017,51 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	return err;
 }
 
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+						int create, int flag)
+{
+	return __f2fs_map_blocks(inode, map, create, flag, NO_CHECK_TYPE);
+}
+
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+	struct f2fs_map_blocks map;
+	int err = 0;
+
+	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+		return 0;
+
+	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
+	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
+	if (map.m_len > map.m_lblk)
+		map.m_len -= map.m_lblk;
+	else
+		map.m_len = 0;
+
+	map.m_next_pgofs = NULL;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+		return __f2fs_map_blocks(inode, &map, 1,
+			__force_buffered_io(inode, WRITE) ?
+				F2FS_GET_BLOCK_PRE_AIO :
+				F2FS_GET_BLOCK_PRE_DIO,
+				rw_hint_to_seg_type(iocb->ki_hint));
+	}
+	if (iocb->ki_pos + iov_iter_count(from) > MAX_INLINE_DATA(inode)) {
+		err = f2fs_convert_inline_inode(inode);
+		if (err)
+			return err;
+	}
+	if (!f2fs_has_inline_data(inode))
+		return f2fs_map_blocks(inode, &map, 1, F2FS_GET_BLOCK_PRE_AIO);
+
+	return err;
+}
+
 static int __get_data_block(struct inode *inode, sector_t iblock,
 			struct buffer_head *bh, int create, int flag,
 			pgoff_t *next_pgofs)
@@ -2082,6 +2096,11 @@ static ssize_t f2fs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 	trace_f2fs_direct_IO_enter(inode, offset, count, rw);
 
+	/* This is for avoiding the situation that the data of a segment is
+	 * passed down to devices with different hints
+	 */
+	iocb->ki_hint = WRITE_LIFE_NOT_SET;
+
 	down_read(&F2FS_I(inode)->dio_rwsem[rw]);
 	err = blockdev_direct_IO(iocb, inode, iter, get_data_block_dio);
 	up_read(&F2FS_I(inode)->dio_rwsem[rw]);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4b4a72f..9be5658 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -2562,6 +2562,7 @@ int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
 void destroy_segment_manager(struct f2fs_sb_info *sbi);
 int __init create_segment_manager_caches(void);
 void destroy_segment_manager_caches(void);
+int rw_hint_to_seg_type(enum rw_hint hint);
 
 /*
  * checkpoint.c
-- 
1.9.1




[Index of Archives]     [Linux Ext4 Filesystem]     [Union Filesystem]     [Filesystem Testing]     [Ceph Users]     [Ecryptfs]     [AutoFS]     [Kernel Newbies]     [Share Photos]     [Security]     [Netfilter]     [Bugtraq]     [Yosemite News]     [MIPS Linux]     [ARM Linux]     [Linux Security]     [Linux Cachefs]     [Reiser Filesystem]     [Linux RAID]     [Samba]     [Device Mapper]     [CEPH Development]
  Powered by Linux