Currently the flag indicating block group has done fstrim is not
persistent, and trim status will be lost after remount, as
a result fstrim can not skip the already trimmed groups, which
could be slow on very large devices.
This patch introduces a new block group flag EXT4_BG_TRIMMED,
we need 1 extra block group descriptor write after trimming each
block group.
When clearing the flag, the block group descriptor is journalled
already so no extra overhead.
Add a new super block flag EXT2_FLAGS_TRACK_TRIM, to indicate if
we should honour EXT4_BG_TRIMMED when doing fstrim.
The new super block flag can be turned on/off via tune2fs.
Cc: Shuichi Ihara <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Wang Shilong <[email protected]>
Signed-off-by: Wang Shilong <[email protected]>
Signed-off-by: Li Dongyang <[email protected]>
---
fs/ext4/ext4.h | 10 ++------
fs/ext4/ext4_jbd2.h | 3 ++-
fs/ext4/mballoc.c | 62 +++++++++++++++++++++++++++++++++++----------
3 files changed, 52 insertions(+), 23 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 0a2d55faa095..a990fb49b24f 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -437,6 +437,7 @@ struct flex_groups {
#define EXT4_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not in use */
#define EXT4_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not in use */
#define EXT4_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
+#define EXT4_BG_TRIMMED 0x0008 /* block group was trimmed */
/*
* Macro-instructions used to manage group descriptors
@@ -1166,6 +1167,7 @@ struct ext4_inode_info {
#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* to test development code */
+#define EXT2_FLAGS_TRACK_TRIM 0x0008 /* Track trim status in each bg */
/*
* Mount flags set via mount options or defaults
@@ -3412,7 +3414,6 @@ struct ext4_group_info {
};
#define EXT4_GROUP_INFO_NEED_INIT_BIT 0
-#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT 1
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT 2
#define EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT 3
#define EXT4_GROUP_INFO_BBITMAP_CORRUPT \
@@ -3427,13 +3428,6 @@ struct ext4_group_info {
(test_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_IBITMAP_CORRUPT(grp) \
(test_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT, &((grp)->bb_state)))
-
-#define EXT4_MB_GRP_WAS_TRIMMED(grp) \
- (test_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
-#define EXT4_MB_GRP_SET_TRIMMED(grp) \
- (set_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
-#define EXT4_MB_GRP_CLEAR_TRIMMED(grp) \
- (clear_bit(EXT4_GROUP_INFO_WAS_TRIMMED_BIT, &((grp)->bb_state)))
#define EXT4_MB_GRP_TEST_AND_SET_READ(grp) \
(test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_READ_BIT, &((grp)->bb_state)))
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 0c77697d5e90..ce529a454b2a 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -120,7 +120,8 @@
#define EXT4_HT_MOVE_EXTENTS 9
#define EXT4_HT_XATTR 10
#define EXT4_HT_EXT_CONVERT 11
-#define EXT4_HT_MAX 12
+#define EXT4_HT_FS_TRIM 12
+#define EXT4_HT_MAX 13
/**
* struct ext4_journal_cb_entry - Base structure for callback information.
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 21b903fe546e..80283be01363 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3849,15 +3849,6 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
rb_erase(&entry->efd_node, &(db->bb_free_root));
mb_free_blocks(NULL, &e4b, entry->efd_start_cluster, entry->efd_count);
- /*
- * Clear the trimmed flag for the group so that the next
- * ext4_trim_fs can trim it.
- * If the volume is mounted with -o discard, online discard
- * is supported and the free blocks will be trimmed online.
- */
- if (!test_opt(sb, DISCARD))
- EXT4_MB_GRP_CLEAR_TRIMMED(db);
-
if (!db->bb_free_root.rb_node) {
/* No more items in the per group rb tree
* balance refcounts from ext4_mb_free_metadata()
@@ -6587,8 +6578,7 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
" group:%u block:%d count:%lu failed"
" with %d", block_group, bit, count,
err);
- } else
- EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
+ }
ext4_lock_group(sb, block_group);
mb_clear_bits(bitmap_bh->b_data, bit, count_clusters);
@@ -6598,6 +6588,14 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
ret = ext4_free_group_clusters(sb, gdp) + count_clusters;
ext4_free_group_clusters_set(sb, gdp, ret);
ext4_block_bitmap_csum_set(sb, gdp, bitmap_bh);
+ /*
+ * Clear the trimmed flag for the group so that the next
+ * ext4_trim_fs can trim it.
+ * If the volume is mounted with -o discard, online discard
+ * is supported and the free blocks will be trimmed online.
+ */
+ if (!test_opt(sb, DISCARD))
+ gdp->bg_flags &= cpu_to_le16(~EXT4_BG_TRIMMED);
ext4_group_desc_csum_set(sb, block_group, gdp);
ext4_unlock_group(sb, block_group);
@@ -6995,10 +6993,19 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_grpblk_t minblocks, bool set_trimmed)
{
struct ext4_buddy e4b;
+ struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ struct ext4_group_desc *gdp;
+ struct buffer_head *gd_bh;
int ret;
trace_ext4_trim_all_free(sb, group, start, max);
+ gdp = ext4_get_group_desc(sb, group, &gd_bh);
+ if (!gdp) {
+ ret = -EIO;
+ return ret;
+ }
+
ret = ext4_mb_load_buddy(sb, group, &e4b);
if (ret) {
ext4_warning(sb, "Error %d loading buddy information for %u",
@@ -7008,11 +7015,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_lock_group(sb, group);
- if (!EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) ||
+ if (!(es->s_flags & cpu_to_le16(EXT2_FLAGS_TRACK_TRIM) &&
+ gdp->bg_flags & cpu_to_le16(EXT4_BG_TRIMMED)) ||
minblocks < EXT4_SB(sb)->s_last_trim_minblks) {
ret = ext4_try_to_trim_range(sb, &e4b, start, max, minblocks);
- if (ret >= 0 && set_trimmed)
- EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
} else {
ret = 0;
}
@@ -7020,6 +7026,34 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
ext4_unlock_group(sb, group);
ext4_mb_unload_buddy(&e4b);
+ if (ret > 0 && set_trimmed) {
+ int err;
+ handle_t *handle;
+
+ handle = ext4_journal_start_sb(sb, EXT4_HT_FS_TRIM, 1);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_return;
+ }
+ err = ext4_journal_get_write_access(handle, sb, gd_bh,
+ EXT4_JTR_NONE);
+ if (err) {
+ ret = err;
+ goto out_journal;
+ }
+ ext4_lock_group(sb, group);
+ gdp->bg_flags |= cpu_to_le16(EXT4_BG_TRIMMED);
+ ext4_group_desc_csum_set(sb, group, gdp);
+ ext4_unlock_group(sb, group);
+ err = ext4_handle_dirty_metadata(handle, NULL, gd_bh);
+ if (err)
+ ret = err;
+out_journal:
+ err = ext4_journal_stop(handle);
+ if (err)
+ ret = err;
+ }
+out_return:
ext4_debug("trimmed %d blocks in the group %d\n",
ret, group);
--
2.41.0
This adds EXT2_FLAG_BG_TRIMMED, which is used on block group
descriptors during mke2fs after discard is done.
The EXT2_FLAG_BG_TRIMMED flag is cleared on the block group when
we free blocks.
Introduce EXT2_FLAGS_TRACK_TRIM, which is a new super block flag,
to indicate whether we should honour the EXT2_FLAG_BG_TRIMMED
set on each block group.
EXT2_FLAGS_TRACK_TRIM itself can be turned on/off via tune2fs.
Make dumpe2fs aware of the new flags.
Cc: Shuichi Ihara <[email protected]>
Cc: Andreas Dilger <[email protected]>
Cc: Wang Shilong <[email protected]>
Signed-off-by: Wang Shilong <[email protected]>
Signed-off-by: Li Dongyang <[email protected]>
---
lib/e2p/ls.c | 4 ++++
lib/ext2fs/alloc_stats.c | 8 ++++++--
lib/ext2fs/ext2_fs.h | 2 ++
misc/dumpe2fs.c | 2 ++
misc/mke2fs.c | 9 +++++++++
misc/tune2fs.8.in | 8 ++++++++
misc/tune2fs.c | 10 ++++++++++
7 files changed, 41 insertions(+), 2 deletions(-)
diff --git a/lib/e2p/ls.c b/lib/e2p/ls.c
index 0b74aea2b..4b356eca6 100644
--- a/lib/e2p/ls.c
+++ b/lib/e2p/ls.c
@@ -162,6 +162,10 @@ static void print_super_flags(struct ext2_super_block * s, FILE *f)
fputs("test_filesystem ", f);
flags_found++;
}
+ if (s->s_flags & EXT2_FLAGS_TRACK_TRIM) {
+ fputs("track_trim ", f);
+ flags_found++;
+ }
if (flags_found)
fputs("\n", f);
else
diff --git a/lib/ext2fs/alloc_stats.c b/lib/ext2fs/alloc_stats.c
index 6f98bcc7c..4e03f92a4 100644
--- a/lib/ext2fs/alloc_stats.c
+++ b/lib/ext2fs/alloc_stats.c
@@ -70,10 +70,12 @@ void ext2fs_block_alloc_stats2(ext2_filsys fs, blk64_t blk, int inuse)
#endif
return;
}
- if (inuse > 0)
+ if (inuse > 0) {
ext2fs_mark_block_bitmap2(fs->block_map, blk);
- else
+ } else {
ext2fs_unmark_block_bitmap2(fs->block_map, blk);
+ ext2fs_bg_flags_clear(fs, group, EXT2_BG_TRIMMED);
+ }
ext2fs_bg_free_blocks_count_set(fs, group, ext2fs_bg_free_blocks_count(fs, group) - inuse);
ext2fs_bg_flags_clear(fs, group, EXT2_BG_BLOCK_UNINIT);
ext2fs_group_desc_csum_set(fs, group);
@@ -139,6 +141,8 @@ void ext2fs_block_alloc_stats_range(ext2_filsys fs, blk64_t blk,
ext2fs_bg_free_blocks_count(fs, group) -
inuse*n/EXT2FS_CLUSTER_RATIO(fs));
ext2fs_bg_flags_clear(fs, group, EXT2_BG_BLOCK_UNINIT);
+ if (inuse < 0)
+ ext2fs_bg_flags_clear(fs, group, EXT2_BG_TRIMMED);
ext2fs_group_desc_csum_set(fs, group);
ext2fs_free_blocks_count_add(fs->super, -inuse * (blk64_t) n);
blk += n;
diff --git a/lib/ext2fs/ext2_fs.h b/lib/ext2fs/ext2_fs.h
index 0fc9c09a5..88e1114c9 100644
--- a/lib/ext2fs/ext2_fs.h
+++ b/lib/ext2fs/ext2_fs.h
@@ -223,6 +223,7 @@ struct ext4_group_desc
#define EXT2_BG_INODE_UNINIT 0x0001 /* Inode table/bitmap not initialized */
#define EXT2_BG_BLOCK_UNINIT 0x0002 /* Block bitmap not initialized */
#define EXT2_BG_INODE_ZEROED 0x0004 /* On-disk itable initialized to zero */
+#define EXT2_BG_TRIMMED 0x0008 /* Block group was trimmed */
/*
* Data structures used by the directory indexing feature
@@ -563,6 +564,7 @@ struct ext2_inode *EXT2_INODE(struct ext2_inode_large *large_inode)
#define EXT2_FLAGS_SIGNED_HASH 0x0001 /* Signed dirhash in use */
#define EXT2_FLAGS_UNSIGNED_HASH 0x0002 /* Unsigned dirhash in use */
#define EXT2_FLAGS_TEST_FILESYS 0x0004 /* OK for use on development code */
+#define EXT2_FLAGS_TRACK_TRIM 0x0008 /* Track trim status in each bg */
#define EXT2_FLAGS_IS_SNAPSHOT 0x0010 /* This is a snapshot image */
#define EXT2_FLAGS_FIX_SNAPSHOT 0x0020 /* Snapshot inodes corrupted */
#define EXT2_FLAGS_FIX_EXCLUDE 0x0040 /* Exclude bitmaps corrupted */
diff --git a/misc/dumpe2fs.c b/misc/dumpe2fs.c
index 7c080ed9f..afe569dff 100644
--- a/misc/dumpe2fs.c
+++ b/misc/dumpe2fs.c
@@ -131,6 +131,8 @@ static void print_bg_opts(ext2_filsys fs, dgrp_t i)
&first);
print_bg_opt(bg_flags, EXT2_BG_INODE_ZEROED, "ITABLE_ZEROED",
&first);
+ print_bg_opt(bg_flags, EXT2_BG_TRIMMED, "TRIMMED",
+ &first);
if (!first)
fputc(']', stdout);
fputc('\n', stdout);
diff --git a/misc/mke2fs.c b/misc/mke2fs.c
index 4a9c1b092..bbfcde478 100644
--- a/misc/mke2fs.c
+++ b/misc/mke2fs.c
@@ -3154,6 +3154,15 @@ int main (int argc, char *argv[])
/* Can't undo discard ... */
if (!noaction && discard && dev_size && (io_ptr != undo_io_manager)) {
retval = mke2fs_discard_device(fs);
+ if (!retval) {
+ dgrp_t i;
+
+ fs->super->s_flags |= EXT2_FLAGS_TRACK_TRIM;
+ for (i = 0; i < fs->group_desc_count; i++) {
+ ext2fs_bg_flags_set(fs, i, EXT2_BG_TRIMMED);
+ ext2fs_group_desc_csum_set(fs, i);
+ }
+ }
if (!retval && io_channel_discard_zeroes_data(fs->io)) {
if (verbose)
printf("%s",
diff --git a/misc/tune2fs.8.in b/misc/tune2fs.8.in
index dcf108c1f..2eb7e88ed 100644
--- a/misc/tune2fs.8.in
+++ b/misc/tune2fs.8.in
@@ -273,6 +273,14 @@ mounted using experimental kernel code, such as the ext4dev file system.
.B ^test_fs
Clear the test_fs flag, indicating the file system should only be mounted
using production-level file system code.
+.TP
+.B track_trim
+Set a flag in the file system superblock to make fstrim save the trim status
+in each block group and skip the block groups already been trimmed.
+.TP
+.B ^track_trim
+Clear the track_trim flag to make fstrim ignore the trim status saved in
+each block group, and trim every block group.
.RE
.TP
.B \-f
diff --git a/misc/tune2fs.c b/misc/tune2fs.c
index 458f7cf6a..dd9e8eab0 100644
--- a/misc/tune2fs.c
+++ b/misc/tune2fs.c
@@ -2312,6 +2312,14 @@ static int parse_extended_opts(ext2_filsys fs, const char *opts)
sb->s_flags &= ~EXT2_FLAGS_TEST_FILESYS;
printf("Clearing test filesystem flag\n");
ext2fs_mark_super_dirty(fs);
+ } else if (!strcmp(token, "track_trim")) {
+ sb->s_flags |= EXT2_FLAGS_TRACK_TRIM;
+ printf("Setting track_trim flag\n");
+ ext2fs_mark_super_dirty(fs);
+ } else if (!strcmp(token, "^track_trim")) {
+ sb->s_flags &= ~EXT2_FLAGS_TRACK_TRIM;
+ printf("Clearing track_trim flag\n");
+ ext2fs_mark_super_dirty(fs);
} else if (strcmp(token, "stride") == 0) {
if (!arg) {
r_usage++;
@@ -2458,6 +2466,8 @@ static int parse_extended_opts(ext2_filsys fs, const char *opts)
"\tforce_fsck\n"
"\ttest_fs\n"
"\t^test_fs\n"
+ "\ttrack_trim\n"
+ "\t^track_trim\n"
"\tencoding=<encoding>\n"
"\tencoding_flags=<flags>\n"));
free(buf);
--
2.41.0
On Fri, Aug 11, 2023 at 04:19:04PM +1000, Li Dongyang wrote:
> Currently the flag indicating block group has done fstrim is not
> persistent, and trim status will be lost after remount, as
> a result fstrim can not skip the already trimmed groups, which
> could be slow on very large devices.
>
> This patch introduces a new block group flag EXT4_BG_TRIMMED,
> we need 1 extra block group descriptor write after trimming each
> block group.
> When clearing the flag, the block group descriptor is journalled
> already so no extra overhead.
If we journalling is enabled (and it normally is enabled) then there
is also writes to the journalling. Updating the block group
descriptor is also a random 4k write, which is not nothing. So if we
are going to do this, then we should not try to set the flag if the
block group is unitialized, and we should actually send the discard in
that case, since presumably the blocks in question were discard when
the file system was mkfs'ed.
> Add a new super block flag EXT2_FLAGS_TRACK_TRIM, to indicate if
> we should honour EXT4_BG_TRIMMED when doing fstrim.
> The new super block flag can be turned on/off via tune2fs.
I don't see the point of having the superblock flag. It seems to me
that either we should either do this via a proper feature flag, which
means that older kernels (and grub bootloaders that get release
updates at a super-lackadasical pace) won't touch file systems that
have the feature flag set --- or we don't have any kind of flag at
all, and kernels and userspace utilities which are EXT4_BG_TRIMMED
enlightened will honor and set/clear the flag.
This risk if we go down that path is that if we have a file system
which is normally used by a kernel that has support for this feature,
and that file system is mounted by an older kernel which doesn't have
this flag, there might be cases where the file system would be trimmed
without setting these flags, or blocks might get released on a block
group without clearing the flag. Fortunately, trim is advisory, so if
we trim a block group that doesn't need it, or we don't trim a block
group where discard might be useful, it's not the end of the world.
And we could always have "e2fsck -E discard" ignore the
EXT4_BG_TRIMMED flag, and just trim all the blocks[1].
[1] https://photos.app.goo.gl/eVL9yHpjdXhjAnq88
- Ted