ext4: Speed up FITRIM by recording flags in ext4_group_info

In ext4, when FITRIM is called every time, we iterate all the
groups and do trim one by one. It is a bit time wasting if the
group has been trimmed and there is no change since the last
trim.

So this patch adds a new flag in ext4_group_info->bb_state to
indicate that the group has been trimmed, and it will be cleared
if some blocks is freed(in release_blocks_on_commit). Another
trim_minlen is added in ext4_sb_info to record the last minlen
we use to trim the volume, so that if the caller provide a small
one, we will go on the trim regardless of the bb_state.

A simple test with my intel x25m ssd:
df -h shows:
/dev/sdb1              40G   21G   17G  56% /mnt/ext4
Block size:               4096

run the FITRIM with the following parameter:
range.start = 0;
range.len = UINT64_MAX;
range.minlen = 1048576;

without the patch:
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m5.505s
user	0m0.000s
sys	0m1.224s
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m5.359s
user	0m0.000s
sys	0m1.178s
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m5.228s
user	0m0.000s
sys	0m1.151s

with the patch:
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m5.625s
user	0m0.000s
sys	0m1.269s
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m0.002s
user	0m0.000s
sys	0m0.001s
[root@boyu-tm linux-2.6]# time ./ftrim /mnt/ext4/a
real	0m0.002s
user	0m0.000s
sys	0m0.001s

A big improvement for the 2nd and 3rd run.

Even after I delete some big image files, it is still much
faster than iterating the whole disk.

[root@boyu-tm test]# time ./ftrim /mnt/ext4/a
real	0m1.217s
user	0m0.000s
sys	0m0.196s

Cc: Lukas Czerner <lczerner@redhat.com>
Reviewed-by: Andreas Dilger <adilger.kernel@dilger.ca>
Signed-off-by: Tao Ma <boyu.mt@taobao.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index d13f3b5098866ceb9f3589a2e52ae0158acf1c8d..62cee2b6fe799a42bb7ca16dc1aeb73dc0e02e70 100644 (file)
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1215,6 +1215,9 @@ struct ext4_sb_info {
 
        /* Kernel thread for multiple mount protection */
        struct task_struct *s_mmp_tsk;
+
+       /* record the last minlen when FITRIM is called. */
+       atomic_t s_last_trim_minblks;
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -2080,11 +2083,19 @@ struct ext4_group_info {
                                         * 5 free 8-block regions. */
 };
 
-#define EXT4_GROUP_INFO_NEED_INIT_BIT  0
+#define EXT4_GROUP_INFO_NEED_INIT_BIT          0
+#define EXT4_GROUP_INFO_WAS_TRIMMED_BIT                1
 
 #define EXT4_MB_GRP_NEED_INIT(grp)     \
        (test_bit(EXT4_GROUP_INFO_NEED_INIT_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_MAX_CONTENTION            8
 #define EXT4_CONTENTION_THRESHOLD      2
 

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7aa4c16caca1efa99608bceeb961085470b097dc..73c254085a41cea875c3a32ce31dcce4311d166c 100644 (file)
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2628,6 +2628,15 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
                rb_erase(&entry->node, &(db->bb_free_root));
                mb_free_blocks(NULL, &e4b, entry->start_blk, entry->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()
@@ -4838,6 +4847,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
        bitmap = e4b.bd_bitmap;
 
        ext4_lock_group(sb, group);
+       if (EXT4_MB_GRP_WAS_TRIMMED(e4b.bd_info) &&
+           minblocks >= atomic_read(&EXT4_SB(sb)->s_last_trim_minblks))
+               goto out;
+
        start = (e4b.bd_info->bb_first_free > start) ?
                e4b.bd_info->bb_first_free : start;
 
@@ -4869,6 +4882,10 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
                if ((e4b.bd_info->bb_free - free_count) < minblocks)
                        break;
        }
+
+       if (!ret)
+               EXT4_MB_GRP_SET_TRIMMED(e4b.bd_info);
+out:
        ext4_unlock_group(sb, group);
        ext4_mb_unload_buddy(&e4b);
 
@@ -4957,6 +4974,9 @@ int ext4_trim_fs(struct super_block *sb, struct fstrim_range *range)
        }
        range->len = trimmed * sb->s_blocksize;
 
+       if (!ret)
+               atomic_set(&EXT4_SB(sb)->s_last_trim_minblks, minlen);
+
 out:
        return ret;
 }