From mboxrd@z Thu Jan 1 00:00:00 1970 From: Tao Ma Subject: [PATCH 4/4] ext4: Speed up FITRIM by recording flags in ext4_group_info. Date: Thu, 30 Jun 2011 22:50:39 +0800 Message-ID: <1309445439-3753-4-git-send-email-tm@tao.ma> References: <4E0C8B6C.8030403@tao.ma> Cc: tytso@mit.edu To: linux-ext4@vger.kernel.org Return-path: Received: from oproxy4-pub.bluehost.com ([69.89.21.11]:41908 "HELO oproxy4-pub.bluehost.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1751611Ab1F3OvC (ORCPT ); Thu, 30 Jun 2011 10:51:02 -0400 In-Reply-To: <4E0C8B6C.8030403@tao.ma> Sender: linux-ext4-owner@vger.kernel.org List-ID: From: Tao Ma 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 Reviewed-by: Andreas Dilger Signed-off-by: Tao Ma --- fs/ext4/ext4.h | 13 ++++++++++++- fs/ext4/mballoc.c | 20 ++++++++++++++++++++ fs/ext4/super.c | 2 ++ 3 files changed, 34 insertions(+), 1 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 1921392..5878a22 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1214,6 +1214,9 @@ 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) @@ -2067,11 +2070,19 @@ 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 a822f2a..afdd869 100644 --- 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() @@ -4840,6 +4849,10 @@ 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; @@ -4871,6 +4884,10 @@ 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); @@ -4960,6 +4977,9 @@ 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; } diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 9ea71aa..080e9f9 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -3086,6 +3086,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) sbi->s_sectors_written_start = part_stat_read(sb->s_bdev->bd_part, sectors[1]); + atomic_set(&sbi->s_last_trim_minblks, 0); + /* Cleanup superblock name */ for (cp = sb->s_id; (cp = strchr(cp, '/'));) *cp = '!'; -- 1.7.4