For a bigalloc filesystem, converting the block bitmap from blocks
to chunks in ext2fs_convert_subcluster_bitmap() can take a long time
when the device is huge, because we test the bitmap
bit-by-bit using ext2fs_test_block_bitmap2().
Use ext2fs_find_first_set_block_bitmap2() which is more efficient
for mke2fs when the fs is mostly empty.
e2fsck can also benefit from this during pass1 block scanning.
Time taken for "mke2fs -O bigalloc,extent -C 131072 -b 4096" on a 1PB
device:
without patch:
real 27m49.457s
user 21m36.474s
sys 6m9.514s
with patch:
real 6m31.908s
user 0m1.806s
sys 6m29.697s
Signed-off-by: Li Dongyang <[email protected]>
Reviewed-by: Andreas Dilger <[email protected]>
---
lib/ext2fs/gen_bitmap64.c | 20 +++++++-------------
1 file changed, 7 insertions(+), 13 deletions(-)
diff --git a/lib/ext2fs/gen_bitmap64.c b/lib/ext2fs/gen_bitmap64.c
index 6e4d8b71..f1dd1891 100644
--- a/lib/ext2fs/gen_bitmap64.c
+++ b/lib/ext2fs/gen_bitmap64.c
@@ -799,8 +799,7 @@ errcode_t ext2fs_convert_subcluster_bitmap(ext2_filsys fs,
ext2fs_generic_bitmap_64 bmap, cmap;
ext2fs_block_bitmap gen_bmap = *bitmap, gen_cmap;
errcode_t retval;
- blk64_t i, b_end, c_end;
- int n, ratio;
+ blk64_t i, next, b_end, c_end;
bmap = (ext2fs_generic_bitmap_64) gen_bmap;
if (fs->cluster_ratio_bits == ext2fs_get_bitmap_granularity(gen_bmap))
@@ -817,18 +816,13 @@ errcode_t ext2fs_convert_subcluster_bitmap(ext2_filsys fs,
bmap->end = bmap->real_end;
c_end = cmap->end;
cmap->end = cmap->real_end;
- n = 0;
- ratio = 1 << fs->cluster_ratio_bits;
while (i < bmap->real_end) {
- if (ext2fs_test_block_bitmap2(gen_bmap, i)) {
- ext2fs_mark_block_bitmap2(gen_cmap, i);
- i += ratio - n;
- n = 0;
- continue;
- }
- i++; n++;
- if (n >= ratio)
- n = 0;
+ retval = ext2fs_find_first_set_block_bitmap2(gen_bmap,
+ i, bmap->real_end, &next);
+ if (retval)
+ break;
+ ext2fs_mark_block_bitmap2(gen_cmap, next);
+ i = EXT2FS_C2B(fs, EXT2FS_B2C(fs, next) + 1);
}
bmap->end = b_end;
cmap->end = c_end;
--
2.24.0
Rename s_overhead_blocks field from struct ext2_super_block to
make it consistent with the kernel counterpart.
Signed-off-by: Li Dongyang <[email protected]>
Reviewed-by: Andreas Dilger <[email protected]>
---
debugfs/set_fields.c | 2 +-
lib/e2p/ls.c | 6 +++---
lib/ext2fs/ext2_fs.h | 2 +-
lib/ext2fs/swapfs.c | 2 +-
lib/ext2fs/tst_super_size.c | 2 +-
5 files changed, 7 insertions(+), 7 deletions(-)
diff --git a/debugfs/set_fields.c b/debugfs/set_fields.c
index 5142554d..f497bd92 100644
--- a/debugfs/set_fields.c
+++ b/debugfs/set_fields.c
@@ -160,7 +160,7 @@ static struct field_set_info super_fields[] = {
{ "usr_quota_inum", &set_sb.s_usr_quota_inum, NULL, 4, parse_uint },
{ "grp_quota_inum", &set_sb.s_grp_quota_inum, NULL, 4, parse_uint },
{ "prj_quota_inum", &set_sb.s_prj_quota_inum, NULL, 4, parse_uint },
- { "overhead_blocks", &set_sb.s_overhead_blocks, NULL, 4, parse_uint },
+ { "overhead_clusters", &set_sb.s_overhead_clusters, NULL, 4, parse_uint },
{ "backup_bgs", &set_sb.s_backup_bgs[0], NULL, 4, parse_uint,
FLAG_ARRAY, 2 },
{ "checksum", &set_sb.s_checksum, NULL, 4, parse_uint },
diff --git a/lib/e2p/ls.c b/lib/e2p/ls.c
index 5a446178..5ca750f6 100644
--- a/lib/e2p/ls.c
+++ b/lib/e2p/ls.c
@@ -272,9 +272,9 @@ void list_super2(struct ext2_super_block * sb, FILE *f)
fprintf(f, "Inode count: %u\n", sb->s_inodes_count);
fprintf(f, "Block count: %llu\n", e2p_blocks_count(sb));
fprintf(f, "Reserved block count: %llu\n", e2p_r_blocks_count(sb));
- if (sb->s_overhead_blocks)
- fprintf(f, "Overhead blocks: %u\n",
- sb->s_overhead_blocks);
+ if (sb->s_overhead_clusters)
+ fprintf(f, "Overhead clusters: %u\n",
+ sb->s_overhead_clusters);
fprintf(f, "Free blocks: %llu\n", e2p_free_blocks_count(sb));
fprintf(f, "Free inodes: %u\n", sb->s_free_inodes_count);
fprintf(f, "First block: %u\n", sb->s_first_data_block);
diff --git a/lib/ext2fs/ext2_fs.h b/lib/ext2fs/ext2_fs.h
index 3165b389..7fa8406f 100644
--- a/lib/ext2fs/ext2_fs.h
+++ b/lib/ext2fs/ext2_fs.h
@@ -742,7 +742,7 @@ struct ext2_super_block {
/*200*/ __u8 s_mount_opts[64];
/*240*/ __u32 s_usr_quota_inum; /* inode number of user quota file */
__u32 s_grp_quota_inum; /* inode number of group quota file */
- __u32 s_overhead_blocks; /* overhead blocks/clusters in fs */
+ __u32 s_overhead_clusters; /* overhead blocks/clusters in fs */
/*24c*/ __u32 s_backup_bgs[2]; /* If sparse_super2 enabled */
/*254*/ __u8 s_encrypt_algos[4]; /* Encryption algorithms in use */
/*258*/ __u8 s_encrypt_pw_salt[16]; /* Salt used for string2key algorithm */
diff --git a/lib/ext2fs/swapfs.c b/lib/ext2fs/swapfs.c
index a1560045..63b24330 100644
--- a/lib/ext2fs/swapfs.c
+++ b/lib/ext2fs/swapfs.c
@@ -121,7 +121,7 @@ void ext2fs_swap_super(struct ext2_super_block * sb)
/* sb->s_mount_opts is __u8 and does not need swabbing */
sb->s_usr_quota_inum = ext2fs_swab32(sb->s_usr_quota_inum);
sb->s_grp_quota_inum = ext2fs_swab32(sb->s_grp_quota_inum);
- sb->s_overhead_blocks = ext2fs_swab32(sb->s_overhead_blocks);
+ sb->s_overhead_clusters = ext2fs_swab32(sb->s_overhead_clusters);
sb->s_backup_bgs[0] = ext2fs_swab32(sb->s_backup_bgs[0]);
sb->s_backup_bgs[1] = ext2fs_swab32(sb->s_backup_bgs[1]);
/* sb->s_encrypt_algos is __u8 and does not need swabbing */
diff --git a/lib/ext2fs/tst_super_size.c b/lib/ext2fs/tst_super_size.c
index a932685d..ab38dd59 100644
--- a/lib/ext2fs/tst_super_size.c
+++ b/lib/ext2fs/tst_super_size.c
@@ -135,7 +135,7 @@ int main(int argc, char **argv)
check_field(s_mount_opts, 64);
check_field(s_usr_quota_inum, 4);
check_field(s_grp_quota_inum, 4);
- check_field(s_overhead_blocks, 4);
+ check_field(s_overhead_clusters, 4);
check_field(s_backup_bgs, 8);
check_field(s_encrypt_algos, 4);
check_field(s_encrypt_pw_salt, 16);
--
2.24.0
Store the overhead in super block so we don't have
to calculate again during next mount.
It also gets updated after online resizing.
Signed-off-by: Li Dongyang <[email protected]>
---
fs/ext4/resize.c | 1 +
fs/ext4/super.c | 4 ++++
2 files changed, 5 insertions(+)
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index c0e9aef376a7..edab58c8ff20 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -1431,6 +1431,7 @@ static void ext4_update_super(struct super_block *sb,
* Update the fs overhead information
*/
ext4_calculate_overhead(sb);
+ es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead);
if (test_opt(sb, DEBUG))
printk(KERN_DEBUG "EXT4-fs: added group %u:"
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index dd654e53ba3d..c859c67cd5db 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4467,6 +4467,10 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
err = ext4_calculate_overhead(sb);
if (err)
goto failed_mount_wq;
+ if (!sb_rdonly(sb)) {
+ es->s_overhead_clusters = cpu_to_le32(sbi->s_overhead);
+ ext4_commit_super(sb, 1);
+ }
}
/*
--
2.24.0
If overhead is not recorded in the super block, it is caculated
during mount in kernel, for bigalloc file systems the it takes
O(groups**2) in time.
For a 1PB deivce with 32K cluste size it takes ~12 mins to
mount, with most of the time spent on figuring out overhead.
While we can not improve the overhead algorithm in kernel
due to the nature of bigalloc, we can work out the overhead
during mke2fs and set it in the super block, avoiding calculating
it every time when it mounts.
Overhead is s_first_data_block plus internal journal blocks plus
the block and inode bitmaps, inode table, super block backups and
group descriptor blocks for every group. This patch introduces
ext2fs_count_used_clusters(), which calculates the clusters used
in the block bitmap for the given range.
When bad blocks are involved, it gets tricky because the blocks
counted as overhead and the bad blocks can end up in the same
allocation cluster. In this case we will unmark the bad blocks from
the block bitmap, convert to cluster bitmap and get the overhead,
then mark the bad blocks back in the cluster bitmap.
Reset the overhead to zero when resizing, we can not simplly count
the used blocks as overhead like we do when mke2fs. The overhead
can be calculated by kernel side during mount.
Signed-off-by: Li Dongyang <[email protected]>
---
lib/ext2fs/ext2fs.h | 2 ++
lib/ext2fs/gen_bitmap64.c | 35 +++++++++++++++++++++++++++++
misc/mke2fs.c | 47 +++++++++++++++++++++++++++++++++++++++
resize/resize2fs.c | 1 +
4 files changed, 85 insertions(+)
diff --git a/lib/ext2fs/ext2fs.h b/lib/ext2fs/ext2fs.h
index da309947..78f84632 100644
--- a/lib/ext2fs/ext2fs.h
+++ b/lib/ext2fs/ext2fs.h
@@ -1442,6 +1442,8 @@ errcode_t ext2fs_set_generic_bmap_range(ext2fs_generic_bitmap bmap,
void *in);
errcode_t ext2fs_convert_subcluster_bitmap(ext2_filsys fs,
ext2fs_block_bitmap *bitmap);
+errcode_t ext2fs_count_used_clusters(ext2_filsys fs, blk64_t start,
+ blk64_t end, blk64_t *out);
/* get_num_dirs.c */
extern errcode_t ext2fs_get_num_dirs(ext2_filsys fs, ext2_ino_t *ret_num_dirs);
diff --git a/lib/ext2fs/gen_bitmap64.c b/lib/ext2fs/gen_bitmap64.c
index f1dd1891..b2370667 100644
--- a/lib/ext2fs/gen_bitmap64.c
+++ b/lib/ext2fs/gen_bitmap64.c
@@ -940,3 +940,38 @@ errcode_t ext2fs_find_first_set_generic_bmap(ext2fs_generic_bitmap bitmap,
return ENOENT;
}
+
+errcode_t ext2fs_count_used_clusters(ext2_filsys fs, blk64_t start,
+ blk64_t end, blk64_t *out)
+{
+ blk64_t next;
+ blk64_t tot_set = 0;
+ errcode_t retval;
+
+ while (start < end) {
+ retval = ext2fs_find_first_set_block_bitmap2(fs->block_map,
+ start, end, &next);
+ if (retval) {
+ if (retval == ENOENT)
+ retval = 0;
+ break;
+ }
+ start = next;
+
+ retval = ext2fs_find_first_zero_block_bitmap2(fs->block_map,
+ start, end, &next);
+ if (retval == 0) {
+ tot_set += next - start;
+ start = next + 1;
+ } else if (retval == ENOENT) {
+ retval = 0;
+ tot_set += end - start + 1;
+ break;
+ } else
+ break;
+ }
+
+ if (!retval)
+ *out = EXT2FS_NUM_B2C(fs, tot_set);
+ return retval;
+}
diff --git a/misc/mke2fs.c b/misc/mke2fs.c
index be38d2c4..542a3030 100644
--- a/misc/mke2fs.c
+++ b/misc/mke2fs.c
@@ -2914,6 +2914,8 @@ int main (int argc, char *argv[])
errcode_t retval = 0;
ext2_filsys fs;
badblocks_list bb_list = 0;
+ badblocks_iterate bb_iter;
+ blk_t blk;
unsigned int journal_blocks = 0;
unsigned int i, checkinterval;
int max_mnt_count;
@@ -2924,6 +2926,7 @@ int main (int argc, char *argv[])
char opt_string[40];
char *hash_alg_str;
int itable_zeroed = 0;
+ blk64_t overhead;
#ifdef ENABLE_NLS
setlocale(LC_MESSAGES, "");
@@ -3215,6 +3218,23 @@ int main (int argc, char *argv[])
if (!quiet)
printf("%s", _("done \n"));
+ /*
+ * Unmark bad blocks to calculate overhead, because metadata
+ * blocks and bad blocks can land on the same allocation cluster.
+ */
+ if (bb_list) {
+ retval = ext2fs_badblocks_list_iterate_begin(bb_list,
+ &bb_iter);
+ if (retval) {
+ com_err("ext2fs_badblocks_list_iterate_begin", retval,
+ "%s", _("while unmarking bad blocks"));
+ exit(1);
+ }
+ while (ext2fs_badblocks_list_iterate(bb_iter, &blk))
+ ext2fs_unmark_block_bitmap2(fs->block_map, blk);
+ ext2fs_badblocks_list_iterate_end(bb_iter);
+ }
+
retval = ext2fs_convert_subcluster_bitmap(fs, &fs->block_map);
if (retval) {
com_err(program_name, retval, "%s",
@@ -3222,6 +3242,28 @@ int main (int argc, char *argv[])
exit(1);
}
+ retval = ext2fs_count_used_clusters(fs, fs->super->s_first_data_block,
+ ext2fs_blocks_count(fs->super) - 1,
+ &overhead);
+ if (retval) {
+ com_err(program_name, retval, "%s",
+ _("while calculating overhead"));
+ exit(1);
+ }
+
+ if (bb_list) {
+ retval = ext2fs_badblocks_list_iterate_begin(bb_list,
+ &bb_iter);
+ if (retval) {
+ com_err("ext2fs_badblocks_list_iterate_begin", retval,
+ "%s", _("while marking bad blocks as used"));
+ exit(1);
+ }
+ while (ext2fs_badblocks_list_iterate(bb_iter, &blk))
+ ext2fs_mark_block_bitmap2(fs->block_map, blk);
+ ext2fs_badblocks_list_iterate_end(bb_iter);
+ }
+
if (super_only) {
check_plausibility(device_name, CHECK_FS_EXIST, NULL);
printf(_("%s may be further corrupted by superblock rewrite\n"),
@@ -3319,6 +3361,7 @@ int main (int argc, char *argv[])
free(journal_device);
} else if ((journal_size) ||
ext2fs_has_feature_journal(&fs_param)) {
+ overhead += EXT2FS_NUM_B2C(fs, journal_blocks);
if (super_only) {
printf("%s", _("Skipping journal creation in super-only mode\n"));
fs->super->s_journal_inum = EXT2_JOURNAL_INO;
@@ -3361,6 +3404,10 @@ no_journal:
fs->super->s_mmp_update_interval);
}
+ overhead += fs->super->s_first_data_block;
+ if (!super_only)
+ fs->super->s_overhead_clusters = overhead;
+
if (ext2fs_has_feature_bigalloc(&fs_param))
fix_cluster_bg_counts(fs);
if (ext2fs_has_feature_quota(&fs_param))
diff --git a/resize/resize2fs.c b/resize/resize2fs.c
index 8a3d08db..2443ff67 100644
--- a/resize/resize2fs.c
+++ b/resize/resize2fs.c
@@ -703,6 +703,7 @@ errcode_t adjust_fs_info(ext2_filsys fs, ext2_filsys old_fs,
double percent;
ext2fs_blocks_count_set(fs->super, new_size);
+ fs->super->s_overhead_clusters = 0;
retry:
fs->group_desc_count = ext2fs_div64_ceil(ext2fs_blocks_count(fs->super) -
--
2.24.0
On Wed, Nov 20, 2019 at 04:35:25AM +0000, Li Dongyang wrote:
> Rename s_overhead_blocks field from struct ext2_super_block to
> make it consistent with the kernel counterpart.
>
> Signed-off-by: Li Dongyang <[email protected]>
> Reviewed-by: Andreas Dilger <[email protected]>
Applied, thanks.
- Ted
On Wed, Nov 20, 2019 at 04:35:21AM +0000, Li Dongyang wrote:
> For a bigalloc filesystem, converting the block bitmap from blocks
> to chunks in ext2fs_convert_subcluster_bitmap() can take a long time
> when the device is huge, because we test the bitmap
> bit-by-bit using ext2fs_test_block_bitmap2().
> Use ext2fs_find_first_set_block_bitmap2() which is more efficient
> for mke2fs when the fs is mostly empty.
>
> e2fsck can also benefit from this during pass1 block scanning.
>
> Time taken for "mke2fs -O bigalloc,extent -C 131072 -b 4096" on a 1PB
> device:
>
> without patch:
> real 27m49.457s
> user 21m36.474s
> sys 6m9.514s
>
> with patch:
> real 6m31.908s
> user 0m1.806s
> sys 6m29.697s
>
> Signed-off-by: Li Dongyang <[email protected]>
> Reviewed-by: Andreas Dilger <[email protected]>
Applied, thanks.
- Ted
On Wed, Nov 20, 2019 at 04:35:27AM +0000, Li Dongyang wrote:
> If overhead is not recorded in the super block, it is caculated
> during mount in kernel, for bigalloc file systems the it takes
> O(groups**2) in time.
> For a 1PB deivce with 32K cluste size it takes ~12 mins to
> mount, with most of the time spent on figuring out overhead.
>
> While we can not improve the overhead algorithm in kernel
> due to the nature of bigalloc, we can work out the overhead
> during mke2fs and set it in the super block, avoiding calculating
> it every time when it mounts.
>
> Overhead is s_first_data_block plus internal journal blocks plus
> the block and inode bitmaps, inode table, super block backups and
> group descriptor blocks for every group. This patch introduces
> ext2fs_count_used_clusters(), which calculates the clusters used
> in the block bitmap for the given range.
>
> When bad blocks are involved, it gets tricky because the blocks
> counted as overhead and the bad blocks can end up in the same
> allocation cluster. In this case we will unmark the bad blocks from
> the block bitmap, convert to cluster bitmap and get the overhead,
> then mark the bad blocks back in the cluster bitmap.
>
> Reset the overhead to zero when resizing, we can not simplly count
> the used blocks as overhead like we do when mke2fs. The overhead
> can be calculated by kernel side during mount.
>
> Signed-off-by: Li Dongyang <[email protected]>
Applied, but I had to fix up a number of spelling errors in the commit
description, and fix up a large number of test failures caused by this
change.
- Ted