summaryrefslogtreecommitdiff
path: root/fs/ext4/extents.c
diff options
context:
space:
mode:
authorZheng Liu <wenqing.lz@taobao.com>2012-08-17 17:54:17 +0400
committerTheodore Ts'o <tytso@mit.edu>2012-08-17 17:54:17 +0400
commit67a5da564f97f31c4054d358e00b34d7ee570da5 (patch)
tree525f256d46cfac4be0b0acd90cc2bad5fcdb1b77 /fs/ext4/extents.c
parent81370291722ac1e0ec95234a0ea91a5bc76b6185 (diff)
downloadlinux-67a5da564f97f31c4054d358e00b34d7ee570da5.tar.xz
ext4: make the zero-out chunk size tunable
Currently in ext4 the length of zero-out chunk is set to 7 file system blocks. But if an inode has uninitailized extents from using fallocate to preallocate space, and the workload issues many random writes, this can cause a fragmented extent tree that will unnecessarily grow the extent tree. So create a new sysfs tunable, extent_max_zeroout_kb, which controls the maximum size where blocks will be zeroed out instead of creating a new uninitialized extent. The default of this has been sent to 32kb. CC: Zach Brown <zab@zabbo.net> CC: Andreas Dilger <adilger@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/extents.c')
-rw-r--r--fs/ext4/extents.c25
1 files changed, 13 insertions, 12 deletions
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index e8755c21f4b9..2f082abf4992 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3085,7 +3085,6 @@ out:
return err ? err : map->m_len;
}
-#define EXT4_EXT_ZERO_LEN 7
/*
* This function is called by ext4_ext_map_blocks() if someone tries to write
* to an uninitialized extent. It may result in splitting the uninitialized
@@ -3111,13 +3110,14 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
struct ext4_map_blocks *map,
struct ext4_ext_path *path)
{
+ struct ext4_sb_info *sbi;
struct ext4_extent_header *eh;
struct ext4_map_blocks split_map;
struct ext4_extent zero_ex;
struct ext4_extent *ex;
ext4_lblk_t ee_block, eof_block;
unsigned int ee_len, depth;
- int allocated;
+ int allocated, max_zeroout = 0;
int err = 0;
int split_flag = 0;
@@ -3125,6 +3125,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
"block %llu, max_blocks %u\n", inode->i_ino,
(unsigned long long)map->m_lblk, map->m_len);
+ sbi = EXT4_SB(inode->i_sb);
eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
inode->i_sb->s_blocksize_bits;
if (eof_block < map->m_lblk + map->m_len)
@@ -3224,9 +3225,12 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
*/
split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
- /* If extent has less than 2*EXT4_EXT_ZERO_LEN zerout directly */
- if (ee_len <= 2*EXT4_EXT_ZERO_LEN &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (EXT4_EXT_MAY_ZEROOUT & split_flag)
+ max_zeroout = sbi->s_extent_max_zeroout_kb >>
+ inode->i_sb->s_blocksize_bits;
+
+ /* If extent is less than s_max_zeroout_kb, zeroout directly */
+ if (max_zeroout && (ee_len <= max_zeroout)) {
err = ext4_ext_zeroout(inode, ex);
if (err)
goto out;
@@ -3250,9 +3254,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
split_map.m_lblk = map->m_lblk;
split_map.m_len = map->m_len;
- if (allocated > map->m_len) {
- if (allocated <= EXT4_EXT_ZERO_LEN &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ if (max_zeroout && (allocated > map->m_len)) {
+ if (allocated <= max_zeroout) {
/* case 3 */
zero_ex.ee_block =
cpu_to_le32(map->m_lblk);
@@ -3264,9 +3267,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
goto out;
split_map.m_lblk = map->m_lblk;
split_map.m_len = allocated;
- } else if ((map->m_lblk - ee_block + map->m_len <
- EXT4_EXT_ZERO_LEN) &&
- (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
+ } else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
/* case 2 */
if (map->m_lblk != ee_block) {
zero_ex.ee_block = ex->ee_block;
@@ -3286,7 +3287,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
}
allocated = ext4_split_extent(handle, inode, path,
- &split_map, split_flag, 0);
+ &split_map, split_flag, 0);
if (allocated < 0)
err = allocated;