Message-Id: <20250422122739.2230121-14-john.g.garry@oracle.com>
Date: Tue, 22 Apr 2025 12:27:37 +0000
From: John Garry <john.g.garry@...cle.com>
To: brauner@...nel.org, djwong@...nel.org, hch@....de, viro@...iv.linux.org.uk,
        jack@...e.cz, cem@...nel.org
Cc: linux-fsdevel@...r.kernel.org, dchinner@...hat.com,
        linux-xfs@...r.kernel.org, linux-kernel@...r.kernel.org,
        ojaswin@...ux.ibm.com, ritesh.list@...il.com,
        martin.petersen@...cle.com, linux-ext4@...r.kernel.org,
        linux-block@...r.kernel.org, catherine.hoang@...cle.com,
        linux-api@...r.kernel.org, John Garry <john.g.garry@...cle.com>
Subject: [PATCH v8 13/15] xfs: add xfs_compute_atomic_write_unit_max()

Now that CoW-based atomic writes are supported, update the max size of an
atomic write for the data device.

The limit of a CoW-based atomic write will be the limit of the number of
logitems which can fit into a single transaction.

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.

Function xfs_atomic_write_logitems() is added to find the limit the number
of log items which can fit in a single transaction.

Amend the max atomic write computation to create a new transaction
reservation type, and compute the maximum size of an atomic write
completion (in fsblocks) based on this new transaction reservation.
Initially, tr_atomic_write is a clone of tr_itruncate, which provides a
reasonable level of parallelism.  In the next patch, we'll add a mount
option so that sysadmins can configure their own limits.

Signed-off-by: John Garry <john.g.garry@...cle.com>
[djwong: use a new reservation type for atomic write ioends, refactor
group limit calculations]
Reviewed-by: "Darrick J. Wong" <djwong@...nel.org>
Signed-off-by: "Darrick J. Wong" <djwong@...nel.org>
[jpg: update xfs_calc_perag_awu_max() ddev check]
---
 fs/xfs/libxfs/xfs_trans_resv.c | 94 ++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_trans_resv.h |  2 +
 fs/xfs/xfs_mount.c             | 81 +++++++++++++++++++++++++++++
 fs/xfs/xfs_mount.h             |  6 +++
 fs/xfs/xfs_reflink.c           | 16 ++++++
 fs/xfs/xfs_reflink.h           |  2 +
 fs/xfs/xfs_trace.h             | 60 ++++++++++++++++++++++
 7 files changed, 261 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 6c74f47f980a..708cfb4be661 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -22,6 +22,12 @@
 #include "xfs_rtbitmap.h"
 #include "xfs_attr_item.h"
 #include "xfs_log.h"
+#include "xfs_defer.h"
+#include "xfs_bmap_item.h"
+#include "xfs_extfree_item.h"
+#include "xfs_rmap_item.h"
+#include "xfs_refcount_item.h"
+#include "xfs_trace.h"
 
 #define _ALLOC	true
 #define _FREE	false
@@ -1397,3 +1403,91 @@ xfs_trans_resv_calc(
 	 */
 	xfs_calc_default_atomic_ioend_reservation(mp, resp);
 }
+
+/*
+ * Return the per-extent and fixed transaction reservation sizes needed to
+ * complete an atomic write.
+ */
+STATIC unsigned int
+xfs_calc_atomic_write_ioend_geometry(
+	struct xfs_mount	*mp,
+	unsigned int		*step_size)
+{
+	const unsigned int	efi = xfs_efi_log_space(1);
+	const unsigned int	efd = xfs_efd_log_space(1);
+	const unsigned int	rui = xfs_rui_log_space(1);
+	const unsigned int	rud = xfs_rud_log_space();
+	const unsigned int	cui = xfs_cui_log_space(1);
+	const unsigned int	cud = xfs_cud_log_space();
+	const unsigned int	bui = xfs_bui_log_space(1);
+	const unsigned int	bud = xfs_bud_log_space();
+
+	/*
+	 * Maximum overhead to complete an atomic write ioend in software:
+	 * remove data fork extent + remove cow fork extent + map extent into
+	 * data fork.
+	 *
+	 * tx0: Creates a BUI and a CUI and that's all it needs.
+	 *
+	 * tx1: Roll to finish the BUI.  Need space for the BUD, an RUI, and
+	 * enough space to relog the CUI (== CUI + CUD).
+	 *
+	 * tx2: Roll again to finish the RUI.  Need space for the RUD and space
+	 * to relog the CUI.
+	 *
+	 * tx3: Roll again, need space for the CUD and possibly a new EFI.
+	 *
+	 * tx4: Roll again, need space for an EFD.
+	 *
+	 * If the extent referenced by the pair of BUI/CUI items is not the one
+	 * being currently processed, then we need to reserve space to relog
+	 * both items.
+	 */
+	const unsigned int	tx0 = bui + cui;
+	const unsigned int	tx1 = bud + rui + cui + cud;
+	const unsigned int	tx2 = rud + cui + cud;
+	const unsigned int	tx3 = cud + efi;
+	const unsigned int	tx4 = efd;
+	const unsigned int	relog = bui + bud + cui + cud;
+
+	const unsigned int	per_intent = max(max3(tx0, tx1, tx2),
+						 max3(tx3, tx4, relog));
+
+	/* Overhead to finish one step of each intent item type */
+	const unsigned int	f1 = xfs_calc_finish_efi_reservation(mp, 1);
+	const unsigned int	f2 = xfs_calc_finish_rui_reservation(mp, 1);
+	const unsigned int	f3 = xfs_calc_finish_cui_reservation(mp, 1);
+	const unsigned int	f4 = xfs_calc_finish_bui_reservation(mp, 1);
+
+	/* We only finish one item per transaction in a chain */
+	*step_size = max(f4, max3(f1, f2, f3));
+
+	return per_intent;
+}
+
+/*
+ * Compute the maximum size (in fsblocks) of atomic writes that we can complete
+ * given the existing log reservations.
+ */
+xfs_extlen_t
+xfs_calc_max_atomic_write_fsblocks(
+	struct xfs_mount		*mp)
+{
+	const struct xfs_trans_res	*resv = &M_RES(mp)->tr_atomic_ioend;
+	unsigned int			per_intent = 0;
+	unsigned int			step_size = 0;
+	unsigned int			ret = 0;
+
+	if (resv->tr_logres > 0) {
+		per_intent = xfs_calc_atomic_write_ioend_geometry(mp,
+				&step_size);
+
+		if (resv->tr_logres >= step_size)
+			ret = (resv->tr_logres - step_size) / per_intent;
+	}
+
+	trace_xfs_calc_max_atomic_write_fsblocks(mp, per_intent, step_size,
+			resv->tr_logres, ret);
+
+	return ret;
+}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.h b/fs/xfs/libxfs/xfs_trans_resv.h
index 670045d417a6..a6d303b83688 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.h
+++ b/fs/xfs/libxfs/xfs_trans_resv.h
@@ -121,4 +121,6 @@ unsigned int xfs_calc_itruncate_reservation_minlogsize(struct xfs_mount *mp);
 unsigned int xfs_calc_write_reservation_minlogsize(struct xfs_mount *mp);
 unsigned int xfs_calc_qm_dqalloc_reservation_minlogsize(struct xfs_mount *mp);
 
+xfs_extlen_t xfs_calc_max_atomic_write_fsblocks(struct xfs_mount *mp);
+
 #endif	/* __XFS_TRANS_RESV_H__ */
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index ee68c026e6cd..eb5ed61b6f99 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -666,6 +666,80 @@ xfs_agbtree_compute_maxlevels(
 	mp->m_agbtree_maxlevels = max(levels, mp->m_refc_maxlevels);
 }
 
+/* Maximum atomic write IO size that the kernel allows. */
+static inline xfs_extlen_t xfs_calc_atomic_write_max(struct xfs_mount *mp)
+{
+	return rounddown_pow_of_two(XFS_B_TO_FSB(mp, MAX_RW_COUNT));
+}
+
+static inline unsigned int max_pow_of_two_factor(const unsigned int nr)
+{
+	return 1 << (ffs(nr) - 1);
+}
+
+/*
+ * If the data device advertises atomic write support, limit the size of data
+ * device atomic writes to the greatest power-of-two factor of the AG size so
+ * that every atomic write unit aligns with the start of every AG.  This is
+ * required so that the per-AG allocations for an atomic write will always be
+ * aligned compatibly with the alignment requirements of the storage.
+ *
+ * If the data device doesn't advertise atomic writes, then there are no
+ * alignment restrictions and the largest out-of-place write we can do
+ * ourselves is the number of blocks that user files can allocate from any AG.
+ */
+static inline xfs_extlen_t xfs_calc_perag_awu_max(struct xfs_mount *mp)
+{
+	if (mp->m_dd_awu_hw_max)
+		return max_pow_of_two_factor(mp->m_sb.sb_agblocks);
+	return mp->m_ag_max_usable;
+}
+
+/*
+ * Reflink on the realtime device requires rtgroups, and atomic writes require
+ * reflink.
+ *
+ * If the realtime device advertises atomic write support, limit the size of
+ * data device atomic writes to the greatest power-of-two factor of the rtgroup
+ * size so that every atomic write unit aligns with the start of every rtgroup.
+ * This is required so that the per-rtgroup allocations for an atomic write
+ * will always be aligned compatibly with the alignment requirements of the
+ * storage.
+ *
+ * If the rt device doesn't advertise atomic writes, then there are no
+ * alignment restrictions and the largest out-of-place write we can do
+ * ourselves is the number of blocks that user files can allocate from any
+ * rtgroup.
+ */
+static inline xfs_extlen_t xfs_calc_rtgroup_awu_max(struct xfs_mount *mp)
+{
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev_awu_min > 0)
+		return max_pow_of_two_factor(rgs->blocks);
+	return rgs->blocks;
+}
+
+/* Compute the maximum atomic write unit size for each section. */
+static inline void
+xfs_calc_atomic_write_unit_max(
+	struct xfs_mount	*mp)
+{
+	struct xfs_groups	*ags = &mp->m_groups[XG_TYPE_AG];
+	struct xfs_groups	*rgs = &mp->m_groups[XG_TYPE_RTG];
+
+	const xfs_extlen_t	max_write = xfs_calc_atomic_write_max(mp);
+	const xfs_extlen_t	max_ioend = xfs_reflink_max_atomic_cow(mp);
+	const xfs_extlen_t	max_agsize = xfs_calc_perag_awu_max(mp);
+	const xfs_extlen_t	max_rgsize = xfs_calc_rtgroup_awu_max(mp);
+
+	ags->awu_max = min3(max_write, max_ioend, max_agsize);
+	rgs->awu_max = min3(max_write, max_ioend, max_rgsize);
+
+	trace_xfs_calc_atomic_write_unit_max(mp, max_write, max_ioend,
+			max_agsize, max_rgsize);
+}
+
 /* Compute maximum possible height for realtime btree types for this fs. */
 static inline void
 xfs_rtbtree_compute_maxlevels(
@@ -1096,6 +1170,13 @@ xfs_mountfs(
 	    mp->m_rtdev_targp->bt_bdev_awu_max >= mp->m_sb.sb_blocksize)
 		mp->m_rt_awu_hw_max = mp->m_rtdev_targp->bt_bdev_awu_max;
 
+	/*
+	 * Pre-calculate atomic write unit max.  This involves computations
+	 * derived from transaction reservations, so we must do this after the
+	 * log is fully initialized.
+	 */
+	xfs_calc_atomic_write_unit_max(mp);
+
 	return 0;
 
  out_agresv:
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 2819e160f0e9..ba55fa1d9594 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -119,6 +119,12 @@ struct xfs_groups {
 	 * SMR hard drives.
 	 */
 	xfs_fsblock_t		start_fsb;
+
+	/*
+	 * Maximum length of an atomic write for files stored in this
+	 * collection of allocation groups, in fsblocks.
+	 */
+	xfs_extlen_t		awu_max;
 };
 
 struct xfs_freecounter {
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 218dee76768b..8c47af705f79 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1040,6 +1040,22 @@ xfs_reflink_end_atomic_cow(
 	return error;
 }
 
+/* Compute the largest atomic write that we can complete through software. */
+xfs_extlen_t
+xfs_reflink_max_atomic_cow(
+	struct xfs_mount	*mp)
+{
+	/* We cannot do any atomic writes without out of place writes. */
+	if (!xfs_has_reflink(mp))
+		return 0;
+
+	/*
+	 * Atomic write limits must always be a power-of-2, according to
+	 * generic_atomic_write_valid.
+	 */
+	return rounddown_pow_of_two(xfs_calc_max_atomic_write_fsblocks(mp));
+}
+
 /*
  * Free all CoW staging blocks that are still referenced by the ondisk refcount
  * metadata.  The ondisk metadata does not track which inode created the
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 412e9b6f2082..36cda724da89 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -68,4 +68,6 @@ extern int xfs_reflink_update_dest(struct xfs_inode *dest, xfs_off_t newlen,
 
 bool xfs_reflink_supports_rextsize(struct xfs_mount *mp, unsigned int rextsize);
 
+xfs_extlen_t xfs_reflink_max_atomic_cow(struct xfs_mount *mp);
+
 #endif /* __XFS_REFLINK_H */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 9554578c6da4..d5ae00f8e04c 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -170,6 +170,66 @@ DEFINE_ATTR_LIST_EVENT(xfs_attr_list_notfound);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list);
 DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list);
 
+TRACE_EVENT(xfs_calc_atomic_write_unit_max,
+	TP_PROTO(struct xfs_mount *mp, unsigned int max_write,
+		 unsigned int max_ioend, unsigned int max_agsize,
+		 unsigned int max_rgsize),
+	TP_ARGS(mp, max_write, max_ioend, max_agsize, max_rgsize),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, max_write)
+		__field(unsigned int, max_ioend)
+		__field(unsigned int, max_agsize)
+		__field(unsigned int, max_rgsize)
+		__field(unsigned int, data_awu_max)
+		__field(unsigned int, rt_awu_max)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->max_write = max_write;
+		__entry->max_ioend = max_ioend;
+		__entry->max_agsize = max_agsize;
+		__entry->max_rgsize = max_rgsize;
+		__entry->data_awu_max = mp->m_groups[XG_TYPE_AG].awu_max;
+		__entry->rt_awu_max = mp->m_groups[XG_TYPE_RTG].awu_max;
+	),
+	TP_printk("dev %d:%d max_write %u max_ioend %u max_agsize %u max_rgsize %u data_awu_max %u rt_awu_max %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->max_write,
+		  __entry->max_ioend,
+		  __entry->max_agsize,
+		  __entry->max_rgsize,
+		  __entry->data_awu_max,
+		  __entry->rt_awu_max)
+);
+
+TRACE_EVENT(xfs_calc_max_atomic_write_fsblocks,
+	TP_PROTO(struct xfs_mount *mp, unsigned int per_intent,
+		 unsigned int step_size, unsigned int logres,
+		 unsigned int blockcount),
+	TP_ARGS(mp, per_intent, step_size, logres, blockcount),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, per_intent)
+		__field(unsigned int, step_size)
+		__field(unsigned int, logres)
+		__field(unsigned int, blockcount)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->per_intent = per_intent;
+		__entry->step_size = step_size;
+		__entry->logres = logres;
+		__entry->blockcount = blockcount;
+	),
+	TP_printk("dev %d:%d per_intent %u step_size %u logres %u blockcount %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->per_intent,
+		  __entry->step_size,
+		  __entry->logres,
+		  __entry->blockcount)
+);
+
 TRACE_EVENT(xlog_intent_recovery_failed,
 	TP_PROTO(struct xfs_mount *mp, const struct xfs_defer_op_type *ops,
 		 int error),
-- 
2.31.1

Powered by blists - more mailing lists