XFS realtime device tweaks

index 044fb0e..fe46e71 100644
@@ -280,8 +280,10 @@ static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
 
 #ifdef CONFIG_XFS_RT
 #define XFS_IS_REALTIME_INODE(ip) ((ip)->i_d.di_flags & XFS_DIFLAG_REALTIME)
+#define XFS_IS_REALTIME_MOUNT(mp) ((mp)->m_rtdev_targp ? 1 : 0)
 #else
 #define XFS_IS_REALTIME_INODE(ip) (0)
+#define XFS_IS_REALTIME_MOUNT(mp) (0)
 #endif
 
 #endif /* __XFS_LINUX__ */

index 455a575..6d33a5e 100644
@@ -1136,6 +1136,14 @@ xfs_fs_statfs(
 	    ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) ==
 			      (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))
 		xfs_qm_statvfs(ip, statp);
+
+	if (XFS_IS_REALTIME_MOUNT(mp) &&
+	    (ip->i_d.di_flags & XFS_DIFLAG_RTINHERIT)) {
+		statp->f_blocks = sbp->sb_rblocks;
+		statp->f_bavail = statp->f_bfree =
+			sbp->sb_frextents * sbp->sb_rextsize;
+	}
+
 	return 0;
 }
 

index a7048eaf..deb9ffd 100644
@@ -4185,6 +4185,39 @@ xfs_bmapi_reserve_delalloc(
 	return error;
 }
 
+/*
+ * This function will set the XFS_DIFLAG_REALTIME flag on the inode if
+ * the XFS_BMAPI_RTDATA flag is set on the xfs_bmalloca struct.
+ *
+ * This function is only valid for realtime mounts, and only on the initial
+ * allocation for the file.
+ *
+ */
+void
+xfs_bmapi_rt_data_flag(
+	struct xfs_mount	*mp,
+	struct xfs_bmalloca	*bma)
+{
+
+	/* Only valid if this is a realtime mount */
+	if (!XFS_IS_REALTIME_MOUNT(mp))
+		return;
+
+	/* Only valid if file is empty */
+	if (!(bma->datatype & XFS_ALLOC_INITIAL_USER_DATA))
+		return;
+
+	/* Nothing to do, realtime flag already set */
+	if (bma->ip->i_d.di_flags & XFS_DIFLAG_REALTIME)
+		return;
+
+	/* Set realtime flag and log it if RTDATA flag is set */
+	if (bma->flags & XFS_BMAPI_RTDATA) {
+		bma->ip->i_d.di_flags |= XFS_DIFLAG_REALTIME;
+		bma->logflags |= XFS_ILOG_CORE;
+	}
+}
+
 static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)

@@ -4235,6 +4268,8 @@ xfs_bmapi_allocate(
 
 	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;
 
+	xfs_bmapi_rt_data_flag(mp, bma);
+
 	/*
 	 * Only want to do the alignment at the eof if it is userdata and
 	 * allocation length is larger than a stripe unit.

index c35a14f..57bf954 100644
@@ -113,6 +113,9 @@ struct xfs_extent_free_item
 /* Only convert delalloc space, don't allocate entirely new extents */
 #define XFS_BMAPI_DELALLOC	0x400
 
+/* Allocate to realtime device */
+#define XFS_BMAPI_RTDATA	0x800
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \

index 9e3cc21..7c07ec9 100644
@@ -1027,6 +1027,9 @@ xfs_alloc_file_space(
 		return -EINVAL;
 
 	rt = XFS_IS_REALTIME_INODE(ip);
+	if (!rt && (rt = xfs_inode_select_rt_target(ip, len)))
+		alloc_type |= XFS_BMAPI_RTDATA;
+
 	extsz = xfs_get_extsz_hint(ip);
 
 	count = len;

index ec9826c..f9e2deb 100644
@@ -1620,12 +1620,18 @@ xfs_itruncate_extents(
 	if (error)
 		goto out;
 
-	/*
-	 * Clear the reflink flag if we truncated everything.
-	 */
-	if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) {
-		ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
-		xfs_inode_clear_cowblocks_tag(ip);
+	if (ip->i_d.di_nblocks == 0) {
+		/*
+		 * Clear the reflink flag if we truncated everything.
+		 */
+		if (xfs_is_reflink_inode(ip)) {
+			ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+			xfs_inode_clear_cowblocks_tag(ip);
+		}
+		/* Clear realtime flag if m_rt_alloc_min policy is in place */
+		if (XFS_IS_REALTIME_MOUNT(mp) && mp->m_rt_alloc_min) {
+			ip->i_d.di_flags &= ~XFS_DIFLAG_REALTIME;
+		}
 	}
 
 	/*

index 94e5bdf..4c545c0 100644
@@ -40,6 +40,7 @@
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
 #include "xfs_reflink.h"
+#include "xfs_rtalloc.h"
 
 
 #define XFS_WRITEIO_ALIGN(mp,off)	(((off) >> mp->m_writeio_log) \

@@ -174,7 +175,11 @@ xfs_iomap_write_direct(
 	int		bmapi_flags = XFS_BMAPI_PREALLOC;
 	uint		tflags = 0;
 
+
 	rt = XFS_IS_REALTIME_INODE(ip);
+	if (!rt && (rt = xfs_inode_select_rt_target(ip, count)))
+		bmapi_flags |= XFS_BMAPI_RTDATA;
+
 	extsz = xfs_get_extsz_hint(ip);
 	lockmode = XFS_ILOCK_SHARED;	/* locked by caller */
 

@@ -983,9 +988,17 @@ xfs_file_iomap_begin(
 
 	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
 			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
-		/* Reserve delalloc blocks for regular writeback. */
-		return xfs_file_iomap_begin_delay(inode, offset, length, flags,
-				iomap);
+		/*
+		 * For non-odirect writes, check if this will be allocated to
+		 * realtime, if so we by-pass xfs_file_iomap_begin_delay as if
+		 * the inode was already marked realtime (see xfs_get_extsz_hint).
+		 * The actual setting of the realtime flag on the inode will be
+		 * done later on.
+		 */
+		if (!xfs_inode_select_rt_target(ip, XFS_FSB_TO_B(mp, length)))
+			/* Reserve delalloc blocks for regular writeback. */
+			return xfs_file_iomap_begin_delay(inode, offset, length,
+					flags, iomap);
 	}
 
 	if (need_excl_ilock(ip, flags)) {

index 9fa312a..e64936f 100644
@@ -197,6 +197,7 @@ typedef struct xfs_mount {
 	__uint32_t		m_generation;
 
 	bool			m_fail_unmount;
+	xfs_off_t		m_rt_alloc_min; /* Min RT allocation */
 #ifdef DEBUG
 	/*
 	 * DEBUG mode instrumentation to test and/or trigger delayed allocation

53 lines not on this page · raw message

index f13133e..76868d2 100644
@@ -136,6 +136,7 @@ int xfs_rtalloc_query_range(struct xfs_trans *tp,
 int xfs_rtalloc_query_all(struct xfs_trans *tp,
 			  xfs_rtalloc_query_range_fn fn,
 			  void *priv);
+bool xfs_inode_select_rt_target(struct xfs_inode *ip, xfs_off_t len);
 #else
 # define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb)    (ENOSYS)
 # define xfs_rtfree_extent(t,b,l)                       (ENOSYS)

@@ -155,6 +156,7 @@ xfs_rtmount_init(
 }
 # define xfs_rtmount_inodes(m)  (((mp)->m_sb.sb_rblocks == 0)? 0 : (ENOSYS))
 # define xfs_rtunmount_inodes(m)
+# define xfs_inode_select_rt_target(i,l)		(0)
 #endif	/* CONFIG_XFS_RT */
 
 #endif	/* __XFS_RTALLOC_H__ */

52 lines not on this page · raw message

index 6ccaae9..80ccb14 100644
@@ -610,6 +610,8 @@ xfs_growfs_data_private(
 	xfs_set_low_space_thresholds(mp);
 	mp->m_alloc_set_aside = xfs_alloc_set_aside(mp);
 
+	mp->m_rt_min_free_dblocks = xfs_rt_calc_min_free_dblocks(mp);
+
 	/*
 	 * If we expanded the last AG, free the per-AG reservation
 	 * so we can reinitialize it with the new size.

index 2eaf818..c91e6c4 100644
@@ -1396,3 +1396,27 @@ xfs_dev_is_read_only(
 	}
 	return 0;
 }
+
+/*
+ * precalculate minimum of data blocks required, if we fall
+ * below this value, we will fallback to the real-time device.
+ *
+ * m_rt_fallback_pct can only be non-zero if a real-time device
+ * is configured.
+ */
+uint64_t
+xfs_rt_calc_min_free_dblocks(
+	struct xfs_mount	*mp)
+{
+	xfs_rfsblock_t		min_free_dblocks = 0;
+
+	if (!XFS_IS_REALTIME_MOUNT(mp))
+		return 0;
+
+	/* Pre-compute minimum data blocks required before
+	 * falling back to RT device for allocations
+	 */
+	min_free_dblocks = mp->m_sb.sb_dblocks * (100 - mp->m_rt_fallback_pct);
+	do_div(min_free_dblocks, 100);
+	return min_free_dblocks;
+}

index e64936f..318bacc 100644
@@ -198,6 +198,12 @@ typedef struct xfs_mount {
 
 	bool			m_fail_unmount;
 	xfs_off_t		m_rt_alloc_min; /* Min RT allocation */
+	/* Fallback to realtime device if data device usage above rt_fallback_pct */
+	uint			m_rt_fallback_pct;
+	/* Use realtime device if free data device blocks falls below this; computed
+	 * from m_rt_fallback_pct.
+	 */
+	xfs_rfsblock_t		m_rt_min_free_dblocks;
 #ifdef DEBUG
 	/*
 	 * DEBUG mode instrumentation to test and/or trigger delayed allocation

@@ -463,4 +469,5 @@ int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
 struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
 		int error_class, int error);
 
+uint64_t	xfs_rt_calc_min_free_dblocks(struct xfs_mount *mp);
 #endif	/* __XFS_MOUNT_H__ */

52 lines not on this page · raw message

index 954398d..f8c3523 100644
@@ -166,6 +166,43 @@ rt_alloc_min_show(
 	return snprintf(buf, PAGE_SIZE, "%lld\n", mp->m_rt_alloc_min);
 }
 XFS_SYSFS_ATTR_RW(rt_alloc_min);
+
+STATIC ssize_t
+rt_fallback_pct_store(
+	struct kobject		*kobject,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	int			ret;
+	int			val;
+
+	ret = kstrtoint(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	if (!XFS_IS_REALTIME_MOUNT(mp))
+		return -EINVAL;
+
+	if (val < 0 || val > 100)
+		return -EINVAL;
+
+	/* Only valid if using a real-time device */
+	mp->m_rt_fallback_pct = val;
+	mp->m_rt_min_free_dblocks = xfs_rt_calc_min_free_dblocks(mp);
+	return count;
+}
+
+STATIC ssize_t
+rt_fallback_pct_show(
+	struct kobject          *kobject,
+	char                    *buf)
+{
+	struct xfs_mount        *mp = to_mp(kobject);
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_rt_fallback_pct);
+}
+XFS_SYSFS_ATTR_RW(rt_fallback_pct);
 #endif
 
 static struct attribute *xfs_mp_attrs[] = {

@@ -174,6 +211,7 @@ static struct attribute *xfs_mp_attrs[] = {
 #endif
 #ifdef CONFIG_XFS_RT
 	ATTR_LIST(rt_alloc_min),
+	ATTR_LIST(rt_fallback_pct),
 #endif
 	NULL,
 };