In ext4_mb_regular_allocator(), after the call to ext4_mb_find_by_goal()
fails to achieve the inode goal, allocation continues with the stream
allocation global goal. Currently, hits for both are combined in
sbi->s_bal_goals, hindering accurate optimization.

This commit separates global goal hits into sbi->s_bal_stream_goals. Since
stream allocation doesn't use ac->ac_g_ex.fe_start, set fe_start to -1.
This prevents stream allocations from being counted in s_bal_goals. Also
clear EXT4_MB_HINT_TRY_GOAL to avoid calling ext4_mb_find_by_goal again.

After adding `stream_goal_hits`, `/proc/fs/ext4/sdx/mb_stats` will show:

mballoc:
	reqs: 840347
	success: 750992
	groups_scanned: 1230506
	cr_p2_aligned_stats:
		hits: 21531
		groups_considered: 411664
		extents_scanned: 21531
		useless_loops: 0
		bad_suggestions: 6
	cr_goal_fast_stats:
		hits: 111222
		groups_considered: 1806728
		extents_scanned: 467908
		useless_loops: 0
		bad_suggestions: 13
	cr_best_avail_stats:
		hits: 36267
		groups_considered: 1817631
		extents_scanned: 156143
		useless_loops: 0
		bad_suggestions: 204
	cr_goal_slow_stats:
		hits: 106396
		groups_considered: 5671710
		extents_scanned: 22540056
		useless_loops: 123747
	cr_any_free_stats:
		hits: 138071
		groups_considered: 724692
		extents_scanned: 23615593
		useless_loops: 585
	extents_scanned: 46804261
		goal_hits: 1307
		stream_goal_hits: 236317
		len_goal_hits: 155549
		2^n_hits: 21531
		breaks: 225096
		lost: 35062
	buddies_generated: 40/40
	buddies_time_used: 48004
	preallocated: 5962467
	discarded: 4847560

Signed-off-by: Baokun Li <libaokun1@huawei.com>
---
 fs/ext4/ext4.h    |  1 +
 fs/ext4/mballoc.c | 11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 9df74123e7e6..8750ace12935 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1646,6 +1646,7 @@ struct ext4_sb_info {
 	atomic_t s_bal_cX_ex_scanned[EXT4_MB_NUM_CRS];	/* total extents scanned */
 	atomic_t s_bal_groups_scanned;	/* number of groups scanned */
 	atomic_t s_bal_goals;	/* goal hits */
+	atomic_t s_bal_stream_goals;	/* stream allocation global goal hits */
 	atomic_t s_bal_len_goals;	/* len goal hits */
 	atomic_t s_bal_breaks;	/* too long searches */
 	atomic_t s_bal_2orders;	/* 2^order hits */
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 336d65c4f6a2..f56ac477c464 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -2849,8 +2849,9 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		/* TBD: may be hot point */
 		spin_lock(&sbi->s_md_lock);
 		ac->ac_g_ex.fe_group = sbi->s_mb_last_group;
-		ac->ac_g_ex.fe_start = sbi->s_mb_last_start;
 		spin_unlock(&sbi->s_md_lock);
+		ac->ac_g_ex.fe_start = -1;
+		ac->ac_flags &= ~EXT4_MB_HINT_TRY_GOAL;
 	}
 
 	/*
@@ -3000,8 +3001,12 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		}
 	}
 
-	if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND)
+	if (sbi->s_mb_stats && ac->ac_status == AC_STATUS_FOUND) {
 		atomic64_inc(&sbi->s_bal_cX_hits[ac->ac_criteria]);
+		if (ac->ac_flags & EXT4_MB_STREAM_ALLOC &&
+		    ac->ac_b_ex.fe_group == ac->ac_g_ex.fe_group)
+			atomic_inc(&sbi->s_bal_stream_goals);
+	}
 out:
 	if (!err && ac->ac_status != AC_STATUS_FOUND && first_err)
 		err = first_err;
@@ -3194,6 +3199,8 @@ int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset)
 	seq_printf(seq, "\textents_scanned: %u\n",
 		   atomic_read(&sbi->s_bal_ex_scanned));
 	seq_printf(seq, "\t\tgoal_hits: %u\n", atomic_read(&sbi->s_bal_goals));
+	seq_printf(seq, "\t\tstream_goal_hits: %u\n",
+		   atomic_read(&sbi->s_bal_stream_goals));
 	seq_printf(seq, "\t\tlen_goal_hits: %u\n",
 		   atomic_read(&sbi->s_bal_len_goals));
 	seq_printf(seq, "\t\t2^n_hits: %u\n", atomic_read(&sbi->s_bal_2orders));
-- 
2.46.1