[PATCH v3 v3 2/2] ext4: allow clearing mballoc stats through mb_stats

From: Baolin Liu

Date: Tue Apr 21 2026 - 21:54:46 EST


From: Baolin Liu <liubaolin@xxxxxxxxxx>

Make /proc/fs/ext4/<dev>/mb_stats writable and clear the runtime
mballoc statistics when 0 is written.
Update the related documentation accordingly.

Reviewed-by: Ojaswin Mujoo <ojaswin@xxxxxxxxxxxxx>
Reviewed-by: Andreas Dilger <adilger@xxxxxxxxx>
Reviewed-by: Ritesh Harjani (IBM) <ritesh.list@xxxxxxxxx>
Reviewed-by: Zhang Yi <yi.zhang@xxxxxxxxxx>
Signed-off-by: Baolin Liu <liubaolin@xxxxxxxxxx>
---
Documentation/admin-guide/ext4.rst | 5 ++++
Documentation/filesystems/proc.rst | 3 +++
fs/ext4/ext4.h | 1 +
fs/ext4/mballoc.c | 29 ++++++++++++++++++++++
fs/ext4/sysfs.c | 40 ++++++++++++++++++++++++++++--
5 files changed, 76 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/ext4.rst b/Documentation/admin-guide/ext4.rst
index ac0c709ea9e7..fb3887cd5e44 100644
--- a/Documentation/admin-guide/ext4.rst
+++ b/Documentation/admin-guide/ext4.rst
@@ -436,6 +436,11 @@ Files in /proc/fs/ext4/<devname>
mb_groups
details of multiblock allocator buddy cache of free blocks

+ mb_stats
+ reports runtime statistics from the multiblock allocator
+ (mballoc). Writing 0 to this file clears the current
+ statistics.
+
/sys entries
============

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index b0c0d1b45b99..7ce02573a3d9 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -1634,6 +1634,9 @@ directory are shown in Table 1-12, below.
============== ==========================================================
File Content
mb_groups details of multiblock allocator buddy cache of free blocks
+ mb_stats reports runtime statistics from the multiblock allocator
+ (mballoc). Writing 0 to this file clears the current
+ statistics.
============== ==========================================================

1.9 /proc/consoles
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 293f698b7042..3223e73612ae 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2994,6 +2994,7 @@ int ext4_fc_record_regions(struct super_block *sb, int ino,
extern const struct seq_operations ext4_mb_seq_groups_ops;
extern const struct seq_operations ext4_mb_seq_structs_summary_ops;
extern int ext4_seq_mb_stats_show(struct seq_file *seq, void *offset);
+extern void ext4_mb_stats_clear(struct ext4_sb_info *sbi);
extern int ext4_mb_init(struct super_block *);
extern void ext4_mb_release(struct super_block *);
extern ext4_fsblk_t ext4_mb_new_blocks(handle_t *,
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 1e13ef62cb9d..79ddfa935813 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4723,6 +4723,35 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
trace_ext4_mballoc_prealloc(ac);
}

+void ext4_mb_stats_clear(struct ext4_sb_info *sbi)
+{
+ int i;
+
+ atomic_set(&sbi->s_bal_reqs, 0);
+ atomic_set(&sbi->s_bal_success, 0);
+ atomic_set(&sbi->s_bal_allocated, 0);
+ atomic_set(&sbi->s_bal_groups_scanned, 0);
+
+ for (i = 0; i < EXT4_MB_NUM_CRS; i++) {
+ atomic64_set(&sbi->s_bal_cX_hits[i], 0);
+ atomic64_set(&sbi->s_bal_cX_groups_considered[i], 0);
+ atomic_set(&sbi->s_bal_cX_ex_scanned[i], 0);
+ atomic64_set(&sbi->s_bal_cX_failed[i], 0);
+ }
+
+ atomic_set(&sbi->s_bal_ex_scanned, 0);
+ atomic_set(&sbi->s_bal_goals, 0);
+ atomic_set(&sbi->s_bal_stream_goals, 0);
+ atomic_set(&sbi->s_bal_len_goals, 0);
+ atomic_set(&sbi->s_bal_2orders, 0);
+ atomic_set(&sbi->s_bal_breaks, 0);
+ atomic_set(&sbi->s_mb_lost_chunks, 0);
+ atomic_set(&sbi->s_mb_buddies_generated, 0);
+ atomic64_set(&sbi->s_mb_generation_time, 0);
+ atomic_set(&sbi->s_mb_preallocated, 0);
+ atomic_set(&sbi->s_mb_discarded, 0);
+}
+
/*
* Called on failure; free up any blocks from the inode PA for this
* context. We don't need this for MB_GROUP_PA because we only change
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index b87d7bdab06a..e90885d470ab 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -52,6 +52,42 @@ typedef enum {
static const char proc_dirname[] = "fs/ext4";
static struct proc_dir_entry *ext4_proc_root;

+static int ext4_mb_stats_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, ext4_seq_mb_stats_show, pde_data(inode));
+}
+
+static ssize_t ext4_mb_stats_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *ppos)
+{
+ struct super_block *sb = pde_data(file_inode(file));
+ char kbuf[2];
+
+ if (count == 0 || count > sizeof(kbuf))
+ return -EINVAL;
+
+ if (copy_from_user(kbuf, buf, count))
+ return -EFAULT;
+
+ if (count == 2) {
+ if (kbuf[0] != '0' || kbuf[1] != '\n')
+ return -EINVAL;
+ } else if (kbuf[0] != '0') {
+ return -EINVAL;
+ }
+
+ ext4_mb_stats_clear(EXT4_SB(sb));
+ return count;
+}
+
+static const struct proc_ops ext4_mb_stats_proc_ops = {
+ .proc_open = ext4_mb_stats_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ .proc_write = ext4_mb_stats_write,
+};
+
struct ext4_attr {
struct attribute attr;
short attr_id;
@@ -630,8 +666,8 @@ int ext4_register_sysfs(struct super_block *sb)
ext4_fc_info_show, sb);
proc_create_seq_data("mb_groups", S_IRUGO, sbi->s_proc,
&ext4_mb_seq_groups_ops, sb);
- proc_create_single_data("mb_stats", 0444, sbi->s_proc,
- ext4_seq_mb_stats_show, sb);
+ proc_create_data("mb_stats", 0644, sbi->s_proc,
+ &ext4_mb_stats_proc_ops, sb);
proc_create_seq_data("mb_structs_summary", 0444, sbi->s_proc,
&ext4_mb_seq_structs_summary_ops, sb);
}
--
2.51.0