| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <4FFEE402.7090601@redhat.com>
Date: Thu, 12 Jul 2012 09:49:38 -0500
From: Eric Sandeen <sandeen@...hat.com>
To: Zheng Liu <gnehzuil.liu@...il.com>
CC: linux-ext4@...r.kernel.org, Zach Brown <zab@...bo.net>,
Andreas Dilger <adilger@...ger.ca>,
Zheng Liu <wenqing.lz@...bao.com>
Subject: Re: [PATCH v2] ext4: dynamical adjust the length of zero-out chunk
On 7/12/12 1:48 AM, Zheng Liu wrote:
> From: Zheng Liu <wenqing.lz@...bao.com>
>
> Currently in ext4 the length of zero-out chunk is set to 7. But it is
> too short so that it will cause a lot of fragmentation of extent when
> we use fallocate to preallocate some uninitialized extents and the
> workload frequently does some uninitialized extent conversions. Thus,
> now we set it to 256 (1MB chunk), and put it into super block in order
> to adjust it dynamically in sysfs.
Does this in fact help the workload for which you wanted the non-flagged
fallocate interface?
I'm a little wary of adding another user tunable; how will the user have
any idea what value to use here?
At any rate, something should also go into Documentation/filesystems/ext4.txt
to explain the new tunable.
Thanks,
-Eric
> CC: Zach Brown <zab@...bo.net>
> CC: Andreas Dilger <adilger@...ger.ca>
> Signed-off-by: Zheng Liu <wenqing.lz@...bao.com>
> ---
> v2 <- v1:
> * use a on-stack copy to avoid seeing differenet values
> * add missing spaces around '*'
>
> fs/ext4/ext4.h | 3 +++
> fs/ext4/extents.c | 13 ++++++++-----
> fs/ext4/super.c | 3 +++
> 3 files changed, 14 insertions(+), 5 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index cfc4e01..0f44577 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -1265,6 +1265,9 @@ struct ext4_sb_info {
> /* locality groups */
> struct ext4_locality_group __percpu *s_locality_groups;
>
> + /* the size of zero-out chunk */
> + unsigned int s_extent_zeroout_len;
> +
> /* for write statistics */
> unsigned long s_sectors_written_start;
> u64 s_kbytes_written;
> diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
> index 91341ec..a114d65 100644
> --- a/fs/ext4/extents.c
> +++ b/fs/ext4/extents.c
> @@ -3029,7 +3029,6 @@ 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
> @@ -3055,12 +3054,14 @@ 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;
> + unsigned int zeroout_len;
> int allocated;
> int err = 0;
> int split_flag = 0;
> @@ -3069,6 +3070,8 @@ 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);
> + zeroout_len = sbi->s_extent_zeroout_len;
> 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)
> @@ -3168,8 +3171,8 @@ 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 &&
> + /* If extent has less than 2*s_extent_zeroout_len zerout directly */
> + if (ee_len <= (2 * zeroout_len) &&
> (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
> err = ext4_ext_zeroout(inode, ex);
> if (err)
> @@ -3195,7 +3198,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
> split_map.m_len = map->m_len;
>
> if (allocated > map->m_len) {
> - if (allocated <= EXT4_EXT_ZERO_LEN &&
> + if (allocated <= zeroout_len &&
> (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
> /* case 3 */
> zero_ex.ee_block =
> @@ -3209,7 +3212,7 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
> 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) &&
> + zeroout_len) &&
> (EXT4_EXT_MAY_ZEROOUT & split_flag)) {
> /* case 2 */
> if (map->m_lblk != ee_block) {
> diff --git a/fs/ext4/super.c b/fs/ext4/super.c
> index eb7aa3e..ea7cb6b 100644
> --- a/fs/ext4/super.c
> +++ b/fs/ext4/super.c
> @@ -2535,6 +2535,7 @@ 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_zeroout_len, s_extent_zeroout_len);
> EXT4_ATTR(trigger_fs_error, 0200, NULL, trigger_test_error);
>
> static struct attribute *ext4_attrs[] = {
> @@ -2550,6 +2551,7 @@ static struct attribute *ext4_attrs[] = {
> ATTR_LIST(mb_stream_req),
> ATTR_LIST(mb_group_prealloc),
> ATTR_LIST(max_writeback_mb_bump),
> + ATTR_LIST(extent_zeroout_len),
> ATTR_LIST(trigger_fs_error),
> NULL,
> };
> @@ -3626,6 +3628,7 @@ 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_zeroout_len = 256;
>
> /*
> * set up enough so that it can read an inode
>
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists