public inbox for linux-ext4@vger.kernel.org
 help / color / mirror / Atom feed
From: Baokun Li <libaokun1@huawei.com>
To: <linux-ext4@vger.kernel.org>
Cc: <tytso@mit.edu>, <jack@suse.cz>, <adilger.kernel@dilger.ca>,
	<ojaswin@linux.ibm.com>, <linux-kernel@vger.kernel.org>,
	<yi.zhang@huawei.com>, <yangerkun@huawei.com>,
	<libaokun1@huawei.com>
Subject: [PATCH v2 07/16] ext4: convert sbi->s_mb_free_pending to atomic_t
Date: Mon, 23 Jun 2025 15:32:55 +0800	[thread overview]
Message-ID: <20250623073304.3275702-8-libaokun1@huawei.com> (raw)
In-Reply-To: <20250623073304.3275702-1-libaokun1@huawei.com>

Previously, s_md_lock was used to protect s_mb_free_pending during
modifications, while smp_mb() ensured fresh reads, so s_md_lock just
guarantees the atomicity of s_mb_free_pending. Thus we optimized it by
converting s_mb_free_pending into an atomic variable, thereby eliminating
s_md_lock and minimizing lock contention. This also prepares for future
lockless merging of free extents.

Following this modification, s_md_lock is exclusively responsible for
managing insertions and deletions within s_freed_data_list, along with
operations involving list_splice.

Performance test data follows:

Test: Running will-it-scale/fallocate2 on CPU-bound containers.
Observation: Average fallocate operations per container per second.

                   | Kunpeng 920 / 512GB -P80|  AMD 9654 / 1536GB -P96 |
 Disk: 960GB SSD   |-------------------------|-------------------------|
                   | base  |    patched      | base  |    patched      |
-------------------|-------|-----------------|-------|-----------------|
mb_optimize_scan=0 | 19699 | 20982 (+6.5%)   | 53093 | 50629 (-4.6%)   |
mb_optimize_scan=1 | 9862  | 10703 (+8.5%)   | 14401 | 14856 (+3.1%)   |

Signed-off-by: Baokun Li <libaokun1@huawei.com>
---
 fs/ext4/balloc.c  | 2 +-
 fs/ext4/ext4.h    | 2 +-
 fs/ext4/mballoc.c | 9 +++------
 3 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index c48fd36b2d74..c9329ed5c094 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -703,7 +703,7 @@ int ext4_should_retry_alloc(struct super_block *sb, int *retries)
 	 * possible we just missed a transaction commit that did so
 	 */
 	smp_mb();
-	if (sbi->s_mb_free_pending == 0) {
+	if (atomic_read(&sbi->s_mb_free_pending) == 0) {
 		if (test_opt(sb, DISCARD)) {
 			atomic_inc(&sbi->s_retry_alloc_pending);
 			flush_work(&sbi->s_discard_work);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 294198c05cdd..003b8d3726e8 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1602,7 +1602,7 @@ struct ext4_sb_info {
 	unsigned short *s_mb_offsets;
 	unsigned int *s_mb_maxs;
 	unsigned int s_group_info_size;
-	unsigned int s_mb_free_pending;
+	atomic_t s_mb_free_pending;
 	struct list_head s_freed_data_list[2];	/* List of blocks to be freed
 						   after commit completed */
 	struct list_head s_discard_list;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 216b332a5054..5410fb3688ee 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3680,7 +3680,7 @@ int ext4_mb_init(struct super_block *sb)
 	}
 
 	spin_lock_init(&sbi->s_md_lock);
-	sbi->s_mb_free_pending = 0;
+	atomic_set(&sbi->s_mb_free_pending, 0);
 	INIT_LIST_HEAD(&sbi->s_freed_data_list[0]);
 	INIT_LIST_HEAD(&sbi->s_freed_data_list[1]);
 	INIT_LIST_HEAD(&sbi->s_discard_list);
@@ -3894,10 +3894,7 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
 	/* we expect to find existing buddy because it's pinned */
 	BUG_ON(err != 0);
 
-	spin_lock(&EXT4_SB(sb)->s_md_lock);
-	EXT4_SB(sb)->s_mb_free_pending -= entry->efd_count;
-	spin_unlock(&EXT4_SB(sb)->s_md_lock);
-
+	atomic_sub(entry->efd_count, &EXT4_SB(sb)->s_mb_free_pending);
 	db = e4b.bd_info;
 	/* there are blocks to put in buddy to make them really free */
 	count += entry->efd_count;
@@ -6392,7 +6389,7 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 
 	spin_lock(&sbi->s_md_lock);
 	list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list[new_entry->efd_tid & 1]);
-	sbi->s_mb_free_pending += clusters;
+	atomic_add(clusters, &sbi->s_mb_free_pending);
 	spin_unlock(&sbi->s_md_lock);
 }
 
-- 
2.46.1


  parent reply	other threads:[~2025-06-23  7:47 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-06-23  7:32 [PATCH v2 00/16] ext4: better scalability for ext4 block allocation Baokun Li
2025-06-23  7:32 ` [PATCH v2 01/16] ext4: add ext4_try_lock_group() to skip busy groups Baokun Li
2025-06-27 18:06   ` Jan Kara
2025-07-14  6:53   ` Ojaswin Mujoo
2025-06-23  7:32 ` [PATCH v2 02/16] ext4: remove unnecessary s_mb_last_start Baokun Li
2025-06-27 18:15   ` Jan Kara
2025-06-30  3:32     ` Baokun Li
2025-06-30  7:31       ` Jan Kara
2025-06-30  7:52         ` Baokun Li
2025-07-14  7:00           ` Ojaswin Mujoo
2025-06-23  7:32 ` [PATCH v2 03/16] ext4: remove unnecessary s_md_lock on update s_mb_last_group Baokun Li
2025-06-27 18:19   ` Jan Kara
2025-06-30  3:48     ` Baokun Li
2025-06-30  7:47       ` Jan Kara
2025-06-30  9:21         ` Baokun Li
2025-06-30 16:32           ` Jan Kara
2025-07-01  2:39             ` Baokun Li
2025-07-01 12:21               ` Jan Kara
2025-07-01 13:17                 ` Baokun Li
2025-07-08 13:08                 ` Baokun Li
2025-07-10 14:38                   ` Jan Kara
2025-07-14  3:01                     ` Theodore Ts'o
2025-07-14  7:00                       ` Baokun Li
2025-07-01  2:57   ` kernel test robot
2025-06-23  7:32 ` [PATCH v2 04/16] ext4: utilize multiple global goals to reduce contention Baokun Li
2025-06-27 18:31   ` Jan Kara
2025-06-30  6:50     ` Baokun Li
2025-06-30  8:38       ` Jan Kara
2025-06-30 10:02         ` Baokun Li
2025-06-30 17:41           ` Jan Kara
2025-07-01  3:32             ` Baokun Li
2025-07-01 11:53               ` Jan Kara
2025-07-01 12:12                 ` Baokun Li
2025-06-23  7:32 ` [PATCH v2 05/16] ext4: get rid of some obsolete EXT4_MB_HINT flags Baokun Li
2025-06-23  7:32 ` [PATCH v2 06/16] ext4: fix typo in CR_GOAL_LEN_SLOW comment Baokun Li
2025-06-23  7:32 ` Baokun Li [this message]
2025-06-27 18:33   ` [PATCH v2 07/16] ext4: convert sbi->s_mb_free_pending to atomic_t Jan Kara
2025-06-23  7:32 ` [PATCH v2 08/16] ext4: merge freed extent with existing extents before insertion Baokun Li
2025-06-27 19:11   ` Jan Kara
2025-06-23  7:32 ` [PATCH v2 09/16] ext4: fix zombie groups in average fragment size lists Baokun Li
2025-06-27 19:14   ` Jan Kara
2025-06-30  6:53     ` Baokun Li
2025-06-23  7:32 ` [PATCH v2 10/16] ext4: fix largest free orders lists corruption on mb_optimize_scan switch Baokun Li
2025-06-27 19:34   ` Jan Kara
2025-06-30  7:34     ` Baokun Li
2025-06-23  7:32 ` [PATCH v2 11/16] ext4: factor out __ext4_mb_scan_group() Baokun Li
2025-06-23  7:33 ` [PATCH v2 12/16] ext4: factor out ext4_mb_might_prefetch() Baokun Li
2025-06-23  7:33 ` [PATCH v2 13/16] ext4: factor out ext4_mb_scan_group() Baokun Li
2025-06-23  7:33 ` [PATCH v2 14/16] ext4: convert free group lists to ordered xarrays Baokun Li
2025-06-23  7:33 ` [PATCH v2 15/16] ext4: refactor choose group to scan group Baokun Li
2025-06-23  7:33 ` [PATCH v2 16/16] ext4: ensure global ordered traversal across all free groups xarrays Baokun Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250623073304.3275702-8-libaokun1@huawei.com \
    --to=libaokun1@huawei.com \
    --cc=adilger.kernel@dilger.ca \
    --cc=jack@suse.cz \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=ojaswin@linux.ibm.com \
    --cc=tytso@mit.edu \
    --cc=yangerkun@huawei.com \
    --cc=yi.zhang@huawei.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox