diff mbox series

[v3,1/3] block: move .bd_inode into 1st cacheline of block_device

Message ID 20231122103103.1104589-2-yukuai1@huaweicloud.com (mailing list archive)
State New, archived
Headers show
Series block: warn once for each partition in bio_check_ro() | expand

Commit Message

Yu Kuai Nov. 22, 2023, 10:31 a.m. UTC
From: Ming Lei <ming.lei@redhat.com>

The .bd_inode field of block_device is used in IO fast path of
blkdev_write_iter() and blkdev_llseek(), so it is more efficient to keep
it into the 1st cacheline.

.bd_openers is only touched in open()/close(), and .bd_size_lock is only
for updating bdev capacity, which is in slow path too.

So swap .bd_inode layout with .bd_openers & .bd_size_lock to move
.bd_inode into the 1st cache line.

Cc: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 include/linux/blk_types.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

Comments

Christoph Hellwig Nov. 22, 2023, 7:23 a.m. UTC | #1
Looks good:

Reviewed-by: Christoph Hellwig <hch@lst.de>
Yu Kuai Nov. 22, 2023, 11:17 a.m. UTC | #2
Hi,

在 2023/11/22 18:31, Yu Kuai 写道:
> From: Ming Lei <ming.lei@redhat.com>
> 
> The .bd_inode field of block_device is used in IO fast path of
> blkdev_write_iter() and blkdev_llseek(), so it is more efficient to keep
> it into the 1st cacheline.
> 
> .bd_openers is only touched in open()/close(), and .bd_size_lock is only
> for updating bdev capacity, which is in slow path too.
> 
> So swap .bd_inode layout with .bd_openers & .bd_size_lock to move
> .bd_inode into the 1st cache line.
> 
> Cc: Yu Kuai <yukuai3@huawei.com>
> Signed-off-by: Ming Lei <ming.lei@redhat.com>
> Signed-off-by: Yu Kuai <yukuai3@huawei.com>
> ---
>   include/linux/blk_types.h | 3 ++-
>   1 file changed, 2 insertions(+), 1 deletion(-)
> 
> diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
> index d5c5e59ddbd2..f7d40692dd94 100644
> --- a/include/linux/blk_types.h
> +++ b/include/linux/blk_types.h
> @@ -49,9 +49,10 @@ struct block_device {
>   	bool			bd_write_holder;
>   	bool			bd_has_submit_bio;
>   	dev_t			bd_dev;
> +	struct inode		*bd_inode;	/* will die */

Now that we're here, and bdev->bd_inode is always point to the
field inode of struct bdev_inode, which is next to the field bdev,
and the comment "will die" have been exist for a long time.

Maybe I can try to replace all the reference of bdev->bd_inode with
a helper, and then remove this field, then it'll be acceptable to add
a new field "unsigned long bd_flags".

Thanks,
Kuai


> +
>   	atomic_t		bd_openers;
>   	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
> -	struct inode *		bd_inode;	/* will die */
>   	void *			bd_claiming;
>   	void *			bd_holder;
>   	const struct blk_holder_ops *bd_holder_ops;
>
diff mbox series

Patch

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d5c5e59ddbd2..f7d40692dd94 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -49,9 +49,10 @@  struct block_device {
 	bool			bd_write_holder;
 	bool			bd_has_submit_bio;
 	dev_t			bd_dev;
+	struct inode		*bd_inode;	/* will die */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
 	void *			bd_claiming;
 	void *			bd_holder;
 	const struct blk_holder_ops *bd_holder_ops;