[PATCH v7 3/3] xfs: Add realtime fallback if data device full

[Richard Wareing <rwareing@fb.com>]

- For FSes which have a realtime device configured, rt_fallback_pct forces
  allocations to the realtime device after data device usage reaches
  rt_fallback_pct.
- Useful for realtime device users to help prevent ENOSPC errors when
  selectively storing some files (e.g. small files) on data device, while
  others are stored on realtime block device.
- Set via the "rt_fallback_pct" sysfs value which is available if
  the kernel is compiled with CONFIG_XFS_RT.

Signed-off-by: Richard Wareing <rwareing@fb.com>
---
Changes since v6:
* None

Changes since v5:
* Minor change to work with XFS_BMAPI_RTDATA method described
  in rt_alloc_min patch
* Fixed bounds checks on sysfs option
* Documentation

Changes since v4:
* Refactored to align with xfs_inode_select_target change
* Fallback percentage reworked to trigger on % space used on data device.
  I find this a bit more intuitive as it aligns well with "df" output.
* mp->m_rt_min_fdblocks now assigned via function call
* Better consistency on sysfs options

Changes since v3:
* None, new patch to patch set

 Documentation/filesystems/xfs.txt |  6 ++++++
 fs/xfs/xfs_fsops.c                |  2 ++
 fs/xfs/xfs_mount.c                | 24 ++++++++++++++++++++++
 fs/xfs/xfs_mount.h                |  7 +++++++
 fs/xfs/xfs_rtalloc.c              | 42 ++++++++++++++++++++++++++++++++++++++-
 fs/xfs/xfs_sysfs.c                | 38 +++++++++++++++++++++++++++++++++++
 6 files changed, 118 insertions(+), 1 deletion(-)

diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 0763972..ed6f6e2 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -486,3 +486,9 @@ When using a realtime sub-volume, the following sysfs options are supported:
 	Buffered, direct IO and pre-allocation are supported.
 
 	Setting the value to "0" disables this behavior.
+
+  /sys/fs/xfs/<dev>/rt_fallback_pct
+  (Units: percentage  Min: 0  Default: 0,  Max: 100)
+	When set, the file will be allocated blocks from the realtime device if the
+	data device space utilization rises above rt_fallback_pct.  Setting the
+	value to "0" disables this behavior.
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 8f22fc5..89713f1 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -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.
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index e9727d0..3905e57 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -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;
+}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 0db9731..9dc17b8 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -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
 	/*
 	 * Frequency with which errors are injected.  Replaces xfs_etest; the
@@ -447,4 +453,5 @@ 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__ */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 145007b..3abd403 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1304,6 +1304,37 @@ xfs_rt_alloc_min(
 }
 
 /*
+ * m_rt_min_free_dblocks is a pre-computed threshold, which controls target
+ * selection based on how many free blocks are available on the data device.
+ *
+ * If the number of free data device blocks falls below
+ * mp->m_rt_min_free_dblocks, the realtime device is selected as the target
+ * device.  If this value is not set, this target policy is in-active.
+ *
+ */
+bool
+xfs_rt_min_free_dblocks(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*ip,
+	xfs_off_t		len)
+{
+	/* Disabled */
+	if (!mp->m_rt_fallback_pct)
+		return false;
+
+	/* If inode target is already realtime device, nothing to do here */
+	if (!XFS_IS_REALTIME_INODE(ip)) {
+		uint64_t	free_dblocks;
+		free_dblocks = percpu_counter_sum(&mp->m_fdblocks) -
+			mp->m_alloc_set_aside;
+		if (free_dblocks < mp->m_rt_min_free_dblocks) {
+			return true;
+		}
+	}
+	return false;
+}
+
+/*
 * Select the target device for the inode based on either the size of the
 * initial allocation, or the amount of space available on the data device.
 *
@@ -1332,5 +1363,14 @@ xfs_inode_select_rt_target(
 	/* Select realtime device as our target based on the value of
 	 * mp->m_rt_alloc_min.  Target selection code if not valid if not set.
 	 */
-	return xfs_rt_alloc_min(mp, len);
+	if (xfs_rt_alloc_min(mp, len))
+		return true;
+
+	/* Check if data device has enough space, if not fallback to realtime
+	 * device.  Valid only if mp->m_rt_fallback_pct is set.
+	 */
+	if (xfs_rt_min_free_dblocks(mp, ip, len))
+		return true;
+
+	return false;
 }
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 8b425be..64f29b6 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -127,11 +127,49 @@ 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[] = {
 #ifdef CONFIG_XFS_RT
 	ATTR_LIST(rt_alloc_min),
+	ATTR_LIST(rt_fallback_pct),
 #endif
 	NULL,
 };
-- 
2.9.5