Received-SPF: pass (google.com: domain of linux-kernel+bounces-138854-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
From: Zhang Yi <yi.zhang@huaweicloud.com>
To: linux-ext4@vger.kernel.org
Cc: linux-fsdevel@vger.kernel.org,
	linux-mm@kvack.org,
	linux-kernel@vger.kernel.org,
	tytso@mit.edu,
	adilger.kernel@dilger.ca,
	jack@suse.cz,
	ritesh.list@gmail.com,
	hch@infradead.org,
	djwong@kernel.org,
	david@fromorbit.com,
	willy@infradead.org,
	zokeefe@google.com,
	yi.zhang@huawei.com,
	yi.zhang@huaweicloud.com,
	chengzhihao1@huawei.com,
	yukuai3@huawei.com,
	wangkefeng.wang@huawei.com
Subject: [RFC PATCH v4 32/34] ext4: enable large folio for regular file with iomap buffered IO path
Date: Wed, 10 Apr 2024 23:03:11 +0800
Message-Id: <20240410150313.2820364-4-yi.zhang@huaweicloud.com>
In-Reply-To: <20240410142948.2817554-1-yi.zhang@huaweicloud.com>
References: <20240410142948.2817554-1-yi.zhang@huaweicloud.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

From: Zhang Yi <yi.zhang@huawei.com>

Since we've convert buffered IO path to iomap for regular files, we can
enable large foilo together, that should be able to bring a lot of
performance gains for large IO. These are fio tests with psync on Intel
Xeon Gold 6240 CPU with 400GB system ram, 200GB ramdisk and 1TB nvme ssd
disk.

 buffer read:

                buffer head        iomap + large folio
 type     bs    IOPS    BW(MiB/s)  IOPS    BW(MiB/s)
 ----------------------------------------------------
 hole     64K   45.1k   2820       78.1k   4879
 hole     1M    2744    2744       4890    4891
 ramdisk  64K   29.6k   1848       44.0k   2747
 ramdisk  1M    1994    1995       2809    2809
 nvme     64K   19.3k   1208       24.3k   1517
 nvme     1M    1694    1694       2256    2256

 buffer write:

                                      buffer head   iomap + large folio
 type   Overwrite Sync Writeback bs   IOPS   BW     IOPS   BW
 -------------------------------------------------------------
 cache    N       N    N         64K  30.8k  1928   80.1k  5005
 cache    N       N    N         1M   1963   1963   5641   5642
 cache    Y       N    N         64K  33.0k  2063   80.8k  5051
 cache    Y       N    N         1M   2103   2103   5588   5589
 ramdisk  N       N    Y         64K  22.4k  1399   64.8k  4050
 ramdisk  N       N    Y         1M   1670   1670   4559   4560
 ramdisk  N       Y    N         64K  5834   365    10.1k  629
 ramdisk  N       Y    N         1M   1011   1011   2064   2064
 ramdisk  Y       N    Y         64K  29.2k  1827   73.6k  4597
 ramdisk  Y       N    Y         1M   1837   1837   4985   4985
 ramdisk  Y       Y    N         64K  17.7k  1109   33.7k  2105
 ramdisk  Y       Y    N         1M   1128   1129   1790   1791
 nvme     N       N    Y         64K  21.5k  1343   57.4k  3590
 nvme     N       N    Y         1M   1308   1308   3664   3664
 nvme     N       Y    N         64K  5962   373    8598   537
 nvme     N       Y    N         1M   676    677    1417   1418
 nvme     Y       N    Y         64K  26.7k  1670   56.8k  3547
 nvme     Y       N    Y         1M   1745   1746   3586   3586
 nvme     Y       Y    N         64K  13.0k  813    21.0k  1311
 nvme     Y       Y    N         1M   683    683    1368   1369

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
---
 fs/ext4/ialloc.c      | 4 +++-
 fs/ext4/inode.c       | 4 +++-
 fs/ext4/move_extent.c | 1 +
 3 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 956b9d69c559..5a22fe5aa46b 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1336,8 +1336,10 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
 		}
 	}
 
-	if (ext4_should_use_buffered_iomap(inode))
+	if (ext4_should_use_buffered_iomap(inode)) {
 		ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+		mapping_set_large_folios(inode->i_mapping);
+	}
 
 	if (ext4_handle_valid(handle)) {
 		ei->i_sync_tid = handle->h_transaction->t_tid;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 624eac0cc705..1cb219d347af 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -5400,8 +5400,10 @@ struct inode *__ext4_iget(struct super_block *sb, unsigned long ino,
 	if (ret)
 		goto bad_inode;
 
-	if (ext4_should_use_buffered_iomap(inode))
+	if (ext4_should_use_buffered_iomap(inode)) {
 		ext4_set_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+		mapping_set_large_folios(inode->i_mapping);
+	}
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = &ext4_file_inode_operations;
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 3db255385367..6722b39049cf 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -560,6 +560,7 @@ static int ext4_disable_buffered_iomap_aops(struct inode *inode)
 	truncate_inode_pages(inode->i_mapping, 0);
 
 	ext4_clear_inode_state(inode, EXT4_STATE_BUFFERED_IOMAP);
+	mapping_clear_large_folios(inode->i_mapping);
 	ext4_set_aops(inode);
 	filemap_invalidate_unlock(inode->i_mapping);
 
-- 
2.39.2