From: Zheng Liu <wenqing.lz@xxxxxxxxxx>
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@xxxxxxxxx>
CC: Andreas Dilger <adilger@xxxxxxxxx>
Signed-off-by: Zheng Liu <wenqing.lz@xxxxxxxxxx>
Signed-off-by: "Theodore Ts'o" <tytso@xxxxxxx>
---
Documentation/ABI/testing/sysfs-fs-ext4 | 13 +++++++++++++
fs/ext4/ext4.h | 3 +++
fs/ext4/extents.c | 25 +++++++++++++------------
fs/ext4/super.c | 3 +++
4 files changed, 32 insertions(+), 12 deletions(-)
diff --git a/Documentation/ABI/testing/sysfs-fs-ext4 b/Documentation/ABI/testing/sysfs-fs-ext4
index f22ac08..c631253 100644
--- a/Documentation/ABI/testing/sysfs-fs-ext4
+++ b/Documentation/ABI/testing/sysfs-fs-ext4
@@ -96,3 +96,16 @@ Contact: "Theodore Ts'o" <tytso@xxxxxxx>
Description:
The maximum number of megabytes the writeback code will
try to write out before move on to another inode.
+
+What: /sys/fs/ext4/<disk>/extent_max_zeroout_kb
+Date: August 2012
+Contact: "Theodore Ts'o" <tytso@xxxxxxx>
+Description:
+ The maximum number of kilobytes which will be zeroed
+ out in preference to creating a new uninitialized
+ extent when manipulating an inode's extent tree. Note
+ that using a larger value will increase the
+ variability of time necessary to complete a random
+ write operation (since a 4k random write might turn
+ into a much larger write due to the zeroout
+ operation).
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7c0841e..0df5ee1 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1271,6 +1271,9 @@ struct ext4_sb_info {
unsigned long s_sectors_written_start;
u64 s_kbytes_written;
+ /* the size of zero-out chunk */
+ unsigned int s_extent_max_zeroout_kb;
+
unsigned int s_log_groups_per_flex;
struct flex_groups *s_flex_groups;
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 92fac2f..769151d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3084,7 +3084,6 @@ 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
@@ -3110,13 +3109,14 @@ 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;
@@ -3124,6 +3124,7 @@ 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)
@@ -3223,9 +3224,12 @@ 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;
@@ -3249,9 +3253,8 @@ 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);
@@ -3263,9 +3266,7 @@ 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;
@@ -3285,7 +3286,7 @@ 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;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 5896dcb..7dc4bd7 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -2541,6 +2541,7 @@ EXT4_RW_ATTR_SBI_UI(mb_order2_req, s_mb_order2_reqs);
EXT4_RW_ATTR_SBI_UI(mb_stream_req, s_mb_stream_request);
EXT4_RW_ATTR_SBI_UI(mb_group_prealloc, s_mb_group_prealloc);
EXT4_RW_ATTR_SBI_UI(max_writeback_mb_bump, s_max_writeback_mb_bump);
+EXT4_RW_ATTR_SBI_UI(extent_max_zeroout_kb, s_extent_max_zeroout_kb);
EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
static struct attribute *ext4_attrs[] = {
@@ -2556,6 +2557,7 @@ static struct attribute *ext4_attrs[] = {
ATTR_LIST(mb_stream_req),
ATTR_LIST(mb_group_prealloc),
ATTR_LIST(max_writeback_mb_bump),
+ ATTR_LIST(extent_max_zeroout_kb),
ATTR_LIST(trigger_fs_error),
NULL,
};
@@ -3752,6 +3754,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
sbi->s_stripe = ext4_get_stripe_size(sbi);
sbi->s_max_writeback_mb_bump = 128;
+ sbi->s_extent_max_zeroout_kb = 256;
/*
* set up enough so that it can read an inode
--
1.7.12.rc0.22.gcdd159b
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
