On Thu, Feb 13, 2025 at 01:56:18PM +0000, John Garry wrote:
> Now that CoW-based atomic writes are supported, update the max size of an
> atomic write.
>
> For simplicity, limit at the max of what the mounted bdev can support in
> terms of atomic write limits. Maybe in future we will have a better way
> to advertise this optimised limit.
>
> In addition, the max atomic write size needs to be aligned to the agsize.
> Limit the size of atomic writes to the greatest power-of-two factor of the
> agsize so that allocations for an atomic write will always be aligned
> compatibly with the alignment requirements of the storage.
>
> For RT inode, just limit to 1x block, even though larger can be supported
> in future.
>
> Signed-off-by: John Garry <john.g.garry@xxxxxxxxxx>
> ---
> fs/xfs/xfs_iops.c | 13 ++++++++++++-
> fs/xfs/xfs_iops.h | 1 -
> fs/xfs/xfs_mount.c | 28 ++++++++++++++++++++++++++++
> fs/xfs/xfs_mount.h | 1 +
> 4 files changed, 41 insertions(+), 2 deletions(-)
>
> diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
> index ea79fb246e33..d0a537696514 100644
> --- a/fs/xfs/xfs_iops.c
> +++ b/fs/xfs/xfs_iops.c
> @@ -606,12 +606,23 @@ xfs_get_atomic_write_attr(
> unsigned int *unit_min,
> unsigned int *unit_max)
> {
> + struct xfs_buftarg *target = xfs_inode_buftarg(ip);
> + struct xfs_mount *mp = ip->i_mount;
> +
> if (!xfs_inode_can_atomicwrite(ip)) {
> *unit_min = *unit_max = 0;
> return;
> }
>
> - *unit_min = *unit_max = ip->i_mount->m_sb.sb_blocksize;
> + *unit_min = ip->i_mount->m_sb.sb_blocksize;
> +
> + if (XFS_IS_REALTIME_INODE(ip)) {
> + /* For now, set limit at 1x block */
> + *unit_max = ip->i_mount->m_sb.sb_blocksize;
> + } else {
> + *unit_max = min_t(unsigned int, XFS_FSB_TO_B(mp, mp->awu_max),
> + target->bt_bdev_awu_max);
> + }
> }
>
> static void
> diff --git a/fs/xfs/xfs_iops.h b/fs/xfs/xfs_iops.h
> index ce7bdeb9a79c..d95a543f3ab0 100644
> --- a/fs/xfs/xfs_iops.h
> +++ b/fs/xfs/xfs_iops.h
> @@ -22,5 +22,4 @@ extern void xfs_diflags_to_iflags(struct xfs_inode *ip, bool init);
> void xfs_get_atomic_write_attr(struct xfs_inode *ip,
> unsigned int *unit_min, unsigned int *unit_max);
>
> -
No need to remove a blank line.
> #endif /* __XFS_IOPS_H__ */
> diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
> index 477c5262cf91..af3ed135be4d 100644
> --- a/fs/xfs/xfs_mount.c
> +++ b/fs/xfs/xfs_mount.c
> @@ -651,6 +651,32 @@ xfs_agbtree_compute_maxlevels(
> levels = max(levels, mp->m_rmap_maxlevels);
> mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
> }
> +static inline void
> +xfs_compute_awu_max(
> + struct xfs_mount *mp)
> +{
> + xfs_agblock_t agsize = mp->m_sb.sb_agblocks;
> + xfs_agblock_t awu_max;
> +
> + if (!xfs_has_reflink(mp)) {
> + mp->awu_max = 1;
> + return;
> + }
> +
> + /*
> + * Find highest power-of-2 evenly divisible into agsize and which
> + * also fits into an unsigned int field.
> + */
> + awu_max = 1;
> + while (1) {
> + if (agsize % (awu_max * 2))
> + break;
> + if (XFS_FSB_TO_B(mp, awu_max * 2) > UINT_MAX)
> + break;
> + awu_max *= 2;
> + }
> + mp->awu_max = awu_max;
> +}
>
> /* Compute maximum possible height for realtime btree types for this fs. */
> static inline void
> @@ -736,6 +762,8 @@ xfs_mountfs(
> xfs_agbtree_compute_maxlevels(mp);
> xfs_rtbtree_compute_maxlevels(mp);
>
> + xfs_compute_awu_max(mp);
> +
> /*
> * Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks
> * is NOT aligned turn off m_dalign since allocator alignment is within
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index fbed172d6770..34286c87ac4a 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -198,6 +198,7 @@ typedef struct xfs_mount {
> bool m_fail_unmount;
> bool m_finobt_nores; /* no per-AG finobt resv. */
> bool m_update_sb; /* sb needs update in mount */
> + xfs_extlen_t awu_max; /* max atomic write */
Might want to clarify that this is for the *data* device.
/* max atomic write to datadev */
With those two things fixed,
Reviewed-by: "Darrick J. Wong" <djwong@xxxxxxxxxx>
--D
>
> /*
> * Bitsets of per-fs metadata that have been checked and/or are sick.
> --
> 2.31.1
>
>
