Re: [PATCH] xfs: update BDI {io,ra}_pages values based on the RT device limits

On Mon, Jul 20, 2026 at 04:08:47PM +0200, Christoph Hellwig wrote:
> When using XFS with a main device on an SSD that stores metadata and a RT
> device to store data on a HDD, we fail to take the I/O sizes for the RT
> device into accounting, leading to up to 5% slower read performance when
> using an SSD for metadata vs storing data and metadata on the HDD.
> 
> Fix this up by taking the RT settings into account at mount an restoring
> the old settings at unmount time, unless the BDI settings have changed
> from those set by XFS.
> 
> Reported-by: Filip Blagojevic <[email protected]>
> Signed-off-by: Christoph Hellwig <[email protected]>

Reviewed-by: Carlos Maiolino <[email protected]>


> ---
>  fs/xfs/xfs_mount.h |  7 ++++++
>  fs/xfs/xfs_super.c | 53 +++++++++++++++++++++++++++++++++++++++++++++-
>  2 files changed, 59 insertions(+), 1 deletion(-)
> 
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index 66a02d1b9ad7..216a38a354e7 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -349,6 +349,13 @@ typedef struct xfs_mount {
>  
>  	/* Index of uuid record in the uuid xarray. */
>  	unsigned int		m_uuid_table_index;
> +
> +	/*
> +	 * Old io_pages/ra_pages valued in the main bdev BDI, and our initial
> +	 * calculated values.
> +	 */
> +	unsigned long		m_old_io_pages, m_initial_io_pages;
> +	unsigned long		m_old_ra_pages, m_initial_ra_pages;
>  } xfs_mount_t;
>  
>  #define M_IGEO(mp)		(&(mp)->m_ino_geo)
> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
> index 8531d526fc44..63c4bcbe6c2b 100644
> --- a/fs/xfs/xfs_super.c
> +++ b/fs/xfs/xfs_super.c
> @@ -548,6 +548,52 @@ xfs_open_devices(
>  	return error;
>  }
>  
> +/*
> + * When using a RT device some or all data I/O is using the RT device, but
> + * the BDI is inherited from the main data device.  When the underlying block
> + * device for the RT device has larger I/O sizes, the BDI settings might be
> + * incorrect, which is especially bad if the main device is a SSD and the
> + * RT device is a HDD, as the io_opt fixup in blk_apply_bdi_limits is missing
> + * for this case.
> + *
> + * Update the BDI values to the max of the data and RT device to cover our
> + * bases.
> + */
> +static void
> +xfs_update_bdi_rahead(
> +	struct xfs_mount	*mp)
> +{
> +	struct backing_dev_info	*rt_bdi =
> +		mp->m_rtdev_targp->bt_bdev->bd_disk->bdi;
> +	struct backing_dev_info	*sb_bdi = mp->m_super->s_bdi;
> +
> +	mp->m_old_io_pages = sb_bdi->io_pages;
> +	mp->m_old_ra_pages = sb_bdi->ra_pages;
> +
> +	sb_bdi->io_pages = mp->m_initial_io_pages =
> +		max(sb_bdi->io_pages, rt_bdi->io_pages);
> +	sb_bdi->ra_pages = mp->m_initial_ra_pages =
> +		max(sb_bdi->ra_pages, rt_bdi->ra_pages);
> +}
> +
> +static void
> +xfs_restore_bdi_rahead(
> +	struct xfs_mount	*mp)
> +{
> +	struct backing_dev_info	*sb_bdi = mp->m_super->s_bdi;
> +
> +	if (sb_bdi->io_pages == mp->m_initial_io_pages)
> +		sb_bdi->io_pages = mp->m_old_io_pages;
> +	else
> +		xfs_info(mp, "io_pages changed from %lu to %lu, not restoring.",
> +				mp->m_initial_io_pages, sb_bdi->io_pages);
> +	if (sb_bdi->ra_pages == mp->m_initial_ra_pages)
> +		sb_bdi->ra_pages = mp->m_old_ra_pages;
> +	else
> +		xfs_info(mp, "ra_pages changed from %lu to %lu, not restoring.",
> +				mp->m_initial_ra_pages, sb_bdi->ra_pages);
> +}
> +
>  /*
>   * Setup xfs_mount buffer target pointers based on superblock
>   */
> @@ -585,6 +631,7 @@ xfs_setup_devices(
>  				mp->m_sb.sb_sectsize, mp->m_sb.sb_rblocks);
>  		if (error)
>  			return error;
> +		xfs_update_bdi_rahead(mp);
>  	}
>  
>  	return 0;
> @@ -2283,8 +2330,12 @@ static void
>  xfs_kill_sb(
>  	struct super_block		*sb)
>  {
> +	struct xfs_mount		*mp = XFS_M(sb);
> +
> +	if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp)
> +		xfs_restore_bdi_rahead(mp);
>  	kill_block_super(sb);
> -	xfs_mount_free(XFS_M(sb));
> +	xfs_mount_free(mp);
>  }
>  
>  static struct file_system_type xfs_fs_type = {
> -- 
> 2.53.0
> 
>