diff options
author | Zheng Liu <wenqing.lz@taobao.com> | 2014-07-15 10:10:04 -0400 |
---|---|---|
committer | Theodore Ts'o <tytso@mit.edu> | 2014-07-15 10:10:04 -0400 |
commit | 83447ccb4df6e6051027bedff2a8cfc6a52ebcf8 (patch) | |
tree | 92302fbc7d77b82d58ac0f2acda54c4bf4096a65 /fs/ext4 | |
parent | 590a141863f726216d452f26bdcc59d648fd7cb0 (diff) | |
download | op-kernel-dev-83447ccb4df6e6051027bedff2a8cfc6a52ebcf8.zip op-kernel-dev-83447ccb4df6e6051027bedff2a8cfc6a52ebcf8.tar.gz |
ext4: make ext4_has_inline_data() as a inline function
Now ext4_has_inline_data() is used in wide spread codepaths. So we need
to make it as a inline function to avoid burning some CPU cycles.
Change in text size:
text data bss dec hex filename
before: 326110 19258 5528 350896 55ab0 fs/ext4/ext4.o
after: 326227 19258 5528 351013 55b25 fs/ext4/ext4.o
I use the following script to measure the CPU usage.
#!/bin/bash
shm_base='/dev/shm'
img=${shm_base}/ext4-img
mnt=/mnt/loop
e2fsprgs_base=$HOME/e2fsprogs
mkfs=${e2fsprgs_base}/misc/mke2fs
fsck=${e2fsprgs_base}/e2fsck/e2fsck
sudo umount $mnt
dd if=/dev/zero of=$img bs=4k count=3145728
${mkfs} -t ext4 -O inline_data -F $img
sudo mount -t ext4 -o loop $img $mnt
# start testing...
testdir="${mnt}/testdir"
mkdir $testdir
cd $testdir
echo "start testing..."
for ((cnt=0;cnt<100;cnt++)); do
for ((i=0;i<5;i++)); do
for ((j=0;j<5;j++)); do
for ((k=0;k<5;k++)); do
for ((l=0;l<5;l++)); do
mkdir -p $i/$j/$k/$l
echo "$i-$j-$k-$l" > $i/$j/$k/$l/testfile
done
done
done
done
ls -R $testdir > /dev/null
rm -rf $testdir/*
done
The result of `perf top -G -U` is as below.
vanilla:
13.92% [ext4] [k] ext4_do_update_inode
9.36% [ext4] [k] __ext4_get_inode_loc
4.07% [ext4] [k] ftrace_define_fields_ext4_writepages
3.83% [ext4] [k] __ext4_handle_dirty_metadata
3.42% [ext4] [k] ext4_get_inode_flags
2.71% [ext4] [k] ext4_mark_iloc_dirty
2.46% [ext4] [k] ftrace_define_fields_ext4_direct_IO_enter
2.26% [ext4] [k] ext4_get_inode_loc
2.22% [ext4] [k] ext4_has_inline_data
[...]
After applied the patch, we don't see ext4_has_inline_data() because it
has been inlined and perf couldn't sample it. Although it doesn't mean
that the CPU cycles can be saved but at least the overhead of function
calls can be eliminated. So IMHO we'd better inline this function.
Cc: Andreas Dilger <adilger.kernel@dilger.ca>
Signed-off-by: Zheng Liu <wenqing.lz@taobao.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Diffstat (limited to 'fs/ext4')
-rw-r--r-- | fs/ext4/ext4.h | 7 | ||||
-rw-r--r-- | fs/ext4/inline.c | 6 |
2 files changed, 6 insertions, 7 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 5535ed2..321760d 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -2559,7 +2559,6 @@ extern const struct file_operations ext4_file_operations; extern loff_t ext4_llseek(struct file *file, loff_t offset, int origin); /* inline.c */ -extern int ext4_has_inline_data(struct inode *inode); extern int ext4_get_max_inline_size(struct inode *inode); extern int ext4_find_inline_data_nolock(struct inode *inode); extern int ext4_init_inline_data(handle_t *handle, struct inode *inode, @@ -2625,6 +2624,12 @@ extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline); extern int ext4_convert_inline_data(struct inode *inode); +static inline int ext4_has_inline_data(struct inode *inode) +{ + return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && + EXT4_I(inode)->i_inline_off; +} + /* namei.c */ extern const struct inode_operations ext4_dir_inode_operations; extern const struct inode_operations ext4_special_inode_operations; diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c index 645205d..141b6ac 100644 --- a/fs/ext4/inline.c +++ b/fs/ext4/inline.c @@ -120,12 +120,6 @@ int ext4_get_max_inline_size(struct inode *inode) return max_inline_size + EXT4_MIN_INLINE_DATA_SIZE; } -int ext4_has_inline_data(struct inode *inode) -{ - return ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA) && - EXT4_I(inode)->i_inline_off; -} - /* * this function does not take xattr_sem, which is OK because it is * currently only used in a code path coming form ext4_iget, before |