This is a patch that speeds up statfs. It is very simple -
the "overhead" calculation, which takes a huge amount of time
for large filesystems, never changes unless the size of the
filesystem itself changes. That means we can store it in memory
and only recalculate if the filesystem has been resized (almost
never).
It also fixes a minor problem that we never update the on-disk
superblock free blocks/inodes counts until the filesystem is
unmounted. While not fatal, we may as well update that on disk
when we have the information, and it makes things like debugfs
and dumpe2fs report a bit more accurate info.
Signed-off-by: Badari Pulavarty <[email protected]>
Signed-off-by: Andreas Dilger <[email protected]>
fs/ext4/super.c | 25 +++++++++++++++----------
include/linux/ext4_fs_sb.h | 2 ++
2 files changed, 17 insertions(+), 10 deletions(-)
Index: linux-2.6.22-rc7/include/linux/ext4_fs_sb.h
===================================================================
--- linux-2.6.22-rc7.orig/include/linux/ext4_fs_sb.h 2007-07-01 12:54:24.000000000 -0700
+++ linux-2.6.22-rc7/include/linux/ext4_fs_sb.h 2007-07-04 22:09:59.000000000 -0700
@@ -39,6 +39,8 @@ struct ext4_sb_info {
unsigned long s_gdb_count; /* Number of group descriptor blocks */
unsigned long s_desc_per_block; /* Number of group descriptors per block */
unsigned long s_groups_count; /* Number of groups in the fs */
+ unsigned long s_overhead_last; /* Last calculated overhead */
+ unsigned long s_blocks_last; /* Last seen block count */
struct buffer_head * s_sbh; /* Buffer containing the super block */
struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
struct buffer_head ** s_group_desc;
Index: linux-2.6.22-rc7/fs/ext4/super.c
===================================================================
--- linux-2.6.22-rc7.orig/fs/ext4/super.c 2007-07-01 12:54:24.000000000 -0700
+++ linux-2.6.22-rc7/fs/ext4/super.c 2007-07-04 22:12:27.000000000 -0700
@@ -2481,19 +2481,19 @@ static int ext4_statfs (struct dentry *
struct super_block *sb = dentry->d_sb;
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
- ext4_fsblk_t overhead;
- int i;
u64 fsid;
- if (test_opt (sb, MINIX_DF))
- overhead = 0;
- else {
- unsigned long ngroups;
- ngroups = EXT4_SB(sb)->s_groups_count;
+ if (test_opt(sb, MINIX_DF)) {
+ sbi->s_overhead_last = 0;
+ } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
+ unsigned long ngroups = sbi->s_groups_count, i;
+ ext4_fsblk_t overhead = 0;
smp_rmb();
/*
- * Compute the overhead (FS structures)
+ * Compute the overhead (FS structures). This is constant
+ * for a given filesystem unless the number of block groups
+ * changes so we cache the previous value until it does.
*/
/*
@@ -2517,18 +2517,23 @@ static int ext4_statfs (struct dentry *
* Every block group has an inode bitmap, a block
* bitmap, and an inode table.
*/
- overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group));
+ overhead += ngroups * (2 + sbi->s_itb_per_group);
+ sbi->s_overhead_last = overhead;
+ smp_wmb();
+ sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
}
buf->f_type = EXT4_SUPER_MAGIC;
buf->f_bsize = sb->s_blocksize;
- buf->f_blocks = ext4_blocks_count(es) - overhead;
+ buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
+ es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
if (buf->f_bfree < ext4_r_blocks_count(es))
buf->f_bavail = 0;
buf->f_files = le32_to_cpu(es->s_inodes_count);
buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
+ es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
buf->f_namelen = EXT4_NAME_LEN;
fsid = le64_to_cpup((void *)es->s_uuid) ^
le64_to_cpup((void *)es->s_uuid + sizeof(u64));
Badari,
How about the performance improvement, is there any benchmark result ?
Coly
在 2007-07-05四的 11:11 -0700，Badari Pulavarty写道：
> This is a patch that speeds up statfs. It is very simple -
> the "overhead" calculation, which takes a huge amount of time
> for large filesystems, never changes unless the size of the
> filesystem itself changes. That means we can store it in memory
> and only recalculate if the filesystem has been resized (almost
> never).
>
> It also fixes a minor problem that we never update the on-disk
> superblock free blocks/inodes counts until the filesystem is
> unmounted. While not fatal, we may as well update that on disk
> when we have the information, and it makes things like debugfs
> and dumpe2fs report a bit more accurate info.
>
> Signed-off-by: Badari Pulavarty <[email protected]>
> Signed-off-by: Andreas Dilger <[email protected]>
>
> fs/ext4/super.c | 25 +++++++++++++++----------
> include/linux/ext4_fs_sb.h | 2 ++
> 2 files changed, 17 insertions(+), 10 deletions(-)
>
> Index: linux-2.6.22-rc7/include/linux/ext4_fs_sb.h
> ===================================================================
> --- linux-2.6.22-rc7.orig/include/linux/ext4_fs_sb.h 2007-07-01 12:54:24.000000000 -0700
> +++ linux-2.6.22-rc7/include/linux/ext4_fs_sb.h 2007-07-04 22:09:59.000000000 -0700
> @@ -39,6 +39,8 @@ struct ext4_sb_info {
> unsigned long s_gdb_count; /* Number of group descriptor blocks */
> unsigned long s_desc_per_block; /* Number of group descriptors per block */
> unsigned long s_groups_count; /* Number of groups in the fs */
> + unsigned long s_overhead_last; /* Last calculated overhead */
> + unsigned long s_blocks_last; /* Last seen block count */
> struct buffer_head * s_sbh; /* Buffer containing the super block */
> struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
> struct buffer_head ** s_group_desc;
> Index: linux-2.6.22-rc7/fs/ext4/super.c
> ===================================================================
> --- linux-2.6.22-rc7.orig/fs/ext4/super.c 2007-07-01 12:54:24.000000000 -0700
> +++ linux-2.6.22-rc7/fs/ext4/super.c 2007-07-04 22:12:27.000000000 -0700
> @@ -2481,19 +2481,19 @@ static int ext4_statfs (struct dentry *
> struct super_block *sb = dentry->d_sb;
> struct ext4_sb_info *sbi = EXT4_SB(sb);
> struct ext4_super_block *es = sbi->s_es;
> - ext4_fsblk_t overhead;
> - int i;
> u64 fsid;
>
> - if (test_opt (sb, MINIX_DF))
> - overhead = 0;
> - else {
> - unsigned long ngroups;
> - ngroups = EXT4_SB(sb)->s_groups_count;
> + if (test_opt(sb, MINIX_DF)) {
> + sbi->s_overhead_last = 0;
> + } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
> + unsigned long ngroups = sbi->s_groups_count, i;
> + ext4_fsblk_t overhead = 0;
> smp_rmb();
>
> /*
> - * Compute the overhead (FS structures)
> + * Compute the overhead (FS structures). This is constant
> + * for a given filesystem unless the number of block groups
> + * changes so we cache the previous value until it does.
> */
>
> /*
> @@ -2517,18 +2517,23 @@ static int ext4_statfs (struct dentry *
> * Every block group has an inode bitmap, a block
> * bitmap, and an inode table.
> */
> - overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group));
> + overhead += ngroups * (2 + sbi->s_itb_per_group);
> + sbi->s_overhead_last = overhead;
> + smp_wmb();
> + sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
> }
>
> buf->f_type = EXT4_SUPER_MAGIC;
> buf->f_bsize = sb->s_blocksize;
> - buf->f_blocks = ext4_blocks_count(es) - overhead;
> + buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
> buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
> + es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
> buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
> if (buf->f_bfree < ext4_r_blocks_count(es))
> buf->f_bavail = 0;
> buf->f_files = le32_to_cpu(es->s_inodes_count);
> buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
> + es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
> buf->f_namelen = EXT4_NAME_LEN;
> fsid = le64_to_cpup((void *)es->s_uuid) ^
> le64_to_cpup((void *)es->s_uuid + sizeof(u64));
>
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> the body of a message to [email protected]
> More majordomo info at http://vger.kernel.org/majordomo-info.html
On Fri, 2007-07-06 at 02:44 +0800, coly li wrote:
> Badari,
>
> How about the performance improvement, is there any benchmark result ?
>
> Coly
The original patch came from Andrea Dilger - where they use this patch
in their luster code. Andrea, do you have perf. numbers ?
BTW, I am doing perf. analysis too. I will share the results.
Thanks,
Badari
>
>
> 在 2007-07-05四的 11:11 -0700，Badari Pulavarty写道：
> > This is a patch that speeds up statfs. It is very simple -
> > the "overhead" calculation, which takes a huge amount of time
> > for large filesystems, never changes unless the size of the
> > filesystem itself changes. That means we can store it in memory
> > and only recalculate if the filesystem has been resized (almost
> > never).
> >
> > It also fixes a minor problem that we never update the on-disk
> > superblock free blocks/inodes counts until the filesystem is
> > unmounted. While not fatal, we may as well update that on disk
> > when we have the information, and it makes things like debugfs
> > and dumpe2fs report a bit more accurate info.
> >
> > Signed-off-by: Badari Pulavarty <[email protected]>
> > Signed-off-by: Andreas Dilger <[email protected]>
> >
> > fs/ext4/super.c | 25 +++++++++++++++----------
> > include/linux/ext4_fs_sb.h | 2 ++
> > 2 files changed, 17 insertions(+), 10 deletions(-)
> >
> > Index: linux-2.6.22-rc7/include/linux/ext4_fs_sb.h
> > ===================================================================
> > --- linux-2.6.22-rc7.orig/include/linux/ext4_fs_sb.h 2007-07-01 12:54:24.000000000 -0700
> > +++ linux-2.6.22-rc7/include/linux/ext4_fs_sb.h 2007-07-04 22:09:59.000000000 -0700
> > @@ -39,6 +39,8 @@ struct ext4_sb_info {
> > unsigned long s_gdb_count; /* Number of group descriptor blocks */
> > unsigned long s_desc_per_block; /* Number of group descriptors per block */
> > unsigned long s_groups_count; /* Number of groups in the fs */
> > + unsigned long s_overhead_last; /* Last calculated overhead */
> > + unsigned long s_blocks_last; /* Last seen block count */
> > struct buffer_head * s_sbh; /* Buffer containing the super block */
> > struct ext4_super_block * s_es; /* Pointer to the super block in the buffer */
> > struct buffer_head ** s_group_desc;
> > Index: linux-2.6.22-rc7/fs/ext4/super.c
> > ===================================================================
> > --- linux-2.6.22-rc7.orig/fs/ext4/super.c 2007-07-01 12:54:24.000000000 -0700
> > +++ linux-2.6.22-rc7/fs/ext4/super.c 2007-07-04 22:12:27.000000000 -0700
> > @@ -2481,19 +2481,19 @@ static int ext4_statfs (struct dentry *
> > struct super_block *sb = dentry->d_sb;
> > struct ext4_sb_info *sbi = EXT4_SB(sb);
> > struct ext4_super_block *es = sbi->s_es;
> > - ext4_fsblk_t overhead;
> > - int i;
> > u64 fsid;
> >
> > - if (test_opt (sb, MINIX_DF))
> > - overhead = 0;
> > - else {
> > - unsigned long ngroups;
> > - ngroups = EXT4_SB(sb)->s_groups_count;
> > + if (test_opt(sb, MINIX_DF)) {
> > + sbi->s_overhead_last = 0;
> > + } else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
> > + unsigned long ngroups = sbi->s_groups_count, i;
> > + ext4_fsblk_t overhead = 0;
> > smp_rmb();
> >
> > /*
> > - * Compute the overhead (FS structures)
> > + * Compute the overhead (FS structures). This is constant
> > + * for a given filesystem unless the number of block groups
> > + * changes so we cache the previous value until it does.
> > */
> >
> > /*
> > @@ -2517,18 +2517,23 @@ static int ext4_statfs (struct dentry *
> > * Every block group has an inode bitmap, a block
> > * bitmap, and an inode table.
> > */
> > - overhead += (ngroups * (2 + EXT4_SB(sb)->s_itb_per_group));
> > + overhead += ngroups * (2 + sbi->s_itb_per_group);
> > + sbi->s_overhead_last = overhead;
> > + smp_wmb();
> > + sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
> > }
> >
> > buf->f_type = EXT4_SUPER_MAGIC;
> > buf->f_bsize = sb->s_blocksize;
> > - buf->f_blocks = ext4_blocks_count(es) - overhead;
> > + buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
> > buf->f_bfree = percpu_counter_sum(&sbi->s_freeblocks_counter);
> > + es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
> > buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
> > if (buf->f_bfree < ext4_r_blocks_count(es))
> > buf->f_bavail = 0;
> > buf->f_files = le32_to_cpu(es->s_inodes_count);
> > buf->f_ffree = percpu_counter_sum(&sbi->s_freeinodes_counter);
> > + es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
> > buf->f_namelen = EXT4_NAME_LEN;
> > fsid = le64_to_cpup((void *)es->s_uuid) ^
> > le64_to_cpup((void *)es->s_uuid + sizeof(u64));
> >
> >
> > -
> > To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
> > the body of a message to [email protected]
> > More majordomo info at http://vger.kernel.org/majordomo-info.html
>