[PATCH] f2fs: keep dirty inodes selectively for checkpoint

From: Jaegeuk Kim
Date: Fri Oct 14 2016 - 14:51:23 EST


This is to avoid no free segment bug during checkpoint caused by a number of
dirty inodes.

The case was reported by Chao like this.

1. mount with lazytime option
2. fragment space
3. touch all files in the image
4. umount

In this case, we actually don't need to flush dirty inode to inode page during
checkpoint.

Reported-by: Chao Yu <chao@xxxxxxxxxx>
Signed-off-by: Jaegeuk Kim <jaegeuk@xxxxxxxxxx>
---
fs/f2fs/acl.c | 2 +-
fs/f2fs/dir.c | 6 +++---
fs/f2fs/extent_cache.c | 2 +-
fs/f2fs/f2fs.h | 25 +++++++++++++------------
fs/f2fs/file.c | 8 ++++----
fs/f2fs/inline.c | 2 +-
fs/f2fs/inode.c | 10 +++++-----
fs/f2fs/namei.c | 6 +++---
fs/f2fs/super.c | 3 +++
fs/f2fs/xattr.c | 4 ++--
10 files changed, 36 insertions(+), 32 deletions(-)

diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 1e29630..6266fba 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -386,7 +386,7 @@ int f2fs_init_acl(struct inode *inode, struct inode *dir, struct page *ipage,
if (error)
return error;

- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);

if (default_acl) {
error = __f2fs_set_acl(inode, ACL_TYPE_DEFAULT, default_acl,
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index a46079a..e71793c 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -313,7 +313,7 @@ void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
set_page_dirty(page);

dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);
f2fs_put_page(page, 1);
}

@@ -466,7 +466,7 @@ void update_parent_metadata(struct inode *dir, struct inode *inode,
clear_inode_flag(inode, FI_NEW_INODE);
}
dir->i_mtime = dir->i_ctime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);

if (F2FS_I(dir)->i_current_depth != current_depth)
f2fs_i_depth_write(dir, current_depth);
@@ -731,7 +731,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
set_page_dirty(page);

dir->i_ctime = dir->i_mtime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);

if (inode)
f2fs_drop_nlink(dir, inode);
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 2b06d4f..4db44da 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -172,7 +172,7 @@ static void __drop_largest_extent(struct inode *inode,

if (fofs < largest->fofs + largest->len && fofs + len > largest->fofs) {
largest->len = 0;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 6dc004e..921f44d 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -513,13 +513,13 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
return __is_extent_mergeable(cur, front);
}

-extern void f2fs_mark_inode_dirty_sync(struct inode *);
+extern void f2fs_mark_inode_dirty_sync(struct inode *, bool);
static inline void __try_update_largest_extent(struct inode *inode,
struct extent_tree *et, struct extent_node *en)
{
if (en->ei.len > et->largest.len) {
et->largest = en->ei;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}

@@ -1625,6 +1625,7 @@ static inline void f2fs_change_bit(unsigned int nr, char *addr)
enum {
FI_NEW_INODE, /* indicate newly allocated inode */
FI_DIRTY_INODE, /* indicate inode is dirty or not */
+ FI_DIRTY_INODE_SYNC, /* indicate inode needs to be synced or not */
FI_AUTO_RECOVER, /* indicate inode is recoverable */
FI_DIRTY_DIR, /* indicate directory has dirty pages */
FI_INC_LINK, /* need to increment i_nlink */
@@ -1659,7 +1660,7 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
return;
case FI_DATA_EXIST:
case FI_INLINE_DOTS:
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}
}

@@ -1686,7 +1687,7 @@ static inline void set_acl_inode(struct inode *inode, umode_t mode)
{
F2FS_I(inode)->i_acl_mode = mode;
set_inode_flag(inode, FI_ACL_MODE);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
}

static inline void f2fs_i_links_write(struct inode *inode, bool inc)
@@ -1695,7 +1696,7 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
inc_nlink(inode);
else
drop_nlink(inode);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_blocks_write(struct inode *inode,
@@ -1706,7 +1707,7 @@ static inline void f2fs_i_blocks_write(struct inode *inode,

inode->i_blocks = add ? inode->i_blocks + diff :
inode->i_blocks - diff;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
@@ -1720,7 +1721,7 @@ static inline void f2fs_i_size_write(struct inode *inode, loff_t i_size)
return;

i_size_write(inode, i_size);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (clean || recover)
set_inode_flag(inode, FI_AUTO_RECOVER);
}
@@ -1735,19 +1736,19 @@ static inline bool f2fs_skip_inode_update(struct inode *inode)
static inline void f2fs_i_depth_write(struct inode *inode, unsigned int depth)
{
F2FS_I(inode)->i_current_depth = depth;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_xnid_write(struct inode *inode, nid_t xnid)
{
F2FS_I(inode)->i_xattr_nid = xnid;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void f2fs_i_pino_write(struct inode *inode, nid_t pino)
{
F2FS_I(inode)->i_pino = pino;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
@@ -1875,13 +1876,13 @@ static inline int is_file(struct inode *inode, int type)
static inline void set_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise |= type;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline void clear_file(struct inode *inode, int type)
{
F2FS_I(inode)->i_advise &= ~type;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
}

static inline int f2fs_readonly(struct super_block *sb)
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index bfce575..aa778c6 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -266,7 +266,6 @@ sync_nodes:
}

if (need_inode_block_update(sbi, ino)) {
- f2fs_mark_inode_dirty_sync(inode);
f2fs_write_inode(inode, NULL);
goto sync_nodes;
}
@@ -671,7 +670,7 @@ int f2fs_truncate(struct inode *inode)
return err;

inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
return 0;
}

@@ -760,7 +759,8 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
}
}

- f2fs_mark_inode_dirty_sync(inode);
+ /* update attributes only */
+ f2fs_mark_inode_dirty_sync(inode, false);

/* inode change will produce dirty node pages flushed by checkpoint */
f2fs_balance_fs(F2FS_I_SB(inode), true);
@@ -1441,7 +1441,7 @@ static long f2fs_fallocate(struct file *file, int mode,

if (!ret) {
inode->i_mtime = inode->i_ctime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
}

diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 8d71d64..a05be5d 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -575,7 +575,7 @@ void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
f2fs_put_page(page, 1);

dir->i_ctime = dir->i_mtime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(dir);
+ f2fs_mark_inode_dirty_sync(dir, false);

if (inode)
f2fs_drop_nlink(dir, inode);
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index d32fd03..4368ee7 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -19,10 +19,13 @@

#include <trace/events/f2fs.h>

-void f2fs_mark_inode_dirty_sync(struct inode *inode)
+void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
{
+ if (sync)
+ set_inode_flag(inode, FI_DIRTY_INODE_SYNC);
if (f2fs_inode_dirtied(inode))
return;
+
mark_inode_dirty_sync(inode);
}

@@ -43,7 +46,7 @@ void f2fs_set_inode_flags(struct inode *inode)
new_fl |= S_DIRSYNC;
inode_set_flags(inode, new_fl,
S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, false);
}

static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -331,9 +334,6 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
inode->i_ino == F2FS_META_INO(sbi))
return 0;

- if (!is_inode_flag_set(inode, FI_DIRTY_INODE))
- return 0;
-
/*
* We need to balance fs here to prevent from producing dirty node pages
* during the urgent cleaning time when runing out of free sections.
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 300aef8..21b336a 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -778,7 +778,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
up_write(&F2FS_I(old_inode)->i_sem);

old_inode->i_ctime = CURRENT_TIME;
- f2fs_mark_inode_dirty_sync(old_inode);
+ f2fs_mark_inode_dirty_sync(old_inode, false);

f2fs_delete_entry(old_entry, old_page, old_dir, NULL);

@@ -938,7 +938,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_i_links_write(old_dir, old_nlink > 0);
up_write(&F2FS_I(old_dir)->i_sem);
}
- f2fs_mark_inode_dirty_sync(old_dir);
+ f2fs_mark_inode_dirty_sync(old_dir, false);

/* update directory entry info of new dir inode */
f2fs_set_link(new_dir, new_entry, new_page, old_inode);
@@ -953,7 +953,7 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
f2fs_i_links_write(new_dir, new_nlink > 0);
up_write(&F2FS_I(new_dir)->i_sem);
}
- f2fs_mark_inode_dirty_sync(new_dir);
+ f2fs_mark_inode_dirty_sync(new_dir, false);

f2fs_unlock_op(sbi);

diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 0559cd6..d22a4d2 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -651,6 +651,7 @@ void f2fs_inode_synced(struct inode *inode)
}
list_del_init(&F2FS_I(inode)->gdirty_list);
clear_inode_flag(inode, FI_DIRTY_INODE);
+ clear_inode_flag(inode, FI_DIRTY_INODE_SYNC);
clear_inode_flag(inode, FI_AUTO_RECOVER);
dec_page_count(sbi, F2FS_DIRTY_IMETA);
stat_dec_dirty_inode(F2FS_I_SB(inode), DIRTY_META);
@@ -672,6 +673,8 @@ static void f2fs_dirty_inode(struct inode *inode, int flags)

if (flags == I_DIRTY_TIME)
return;
+ if (!is_inode_flag_set(inode, FI_DIRTY_INODE_SYNC))
+ return;

if (is_inode_flag_set(inode, FI_AUTO_RECOVER))
clear_inode_flag(inode, FI_AUTO_RECOVER);
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index 83234dd..4effb96 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -106,7 +106,7 @@ static int f2fs_xattr_advise_set(const struct xattr_handler *handler,
return -EINVAL;

F2FS_I(inode)->i_advise |= *(char *)value;
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
return 0;
}

@@ -561,7 +561,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
else
file_clear_key(inode);
}
- f2fs_mark_inode_dirty_sync(inode);
+ f2fs_mark_inode_dirty_sync(inode, true);
if (!error && S_ISDIR(inode->i_mode))
set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
exit:
--
2.8.3