- Gates real-time block device fallocation's to rtfallocmin bytes
- Use case: Allows developers to send files to the SSD with ease simply
by fallocating them, if they are below rtfallocmin XFS will allocate the
blocks from the non-RT device (e.g. an SSD)
- Useful to automagically store small files on the SSD vs. RT device
(HDD) for tiered XFS setups without having to rely on XFS specific
ioctl calls. Userland tools such as rsync can also use fallocation
behavior to migrate files between SSD and RT (HDD) device without
modifiction (e.g. w/ --preallocate flag).
Signed-off-by: Richard Wareing <rwareing@xxxxxx>
---
fs/xfs/xfs_file.c | 16 ++++++++++++++++
fs/xfs/xfs_mount.h | 1 +
fs/xfs/xfs_super.c | 15 ++++++++++++++-
3 files changed, 31 insertions(+), 1 deletion(-)
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 5fb5a09..a29f6e8 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -730,6 +730,7 @@ xfs_file_fallocate(
{
struct inode *inode = file_inode(file);
struct xfs_inode *ip = XFS_I(inode);
+ struct xfs_mount *mp = ip->i_mount;
long error;
enum xfs_prealloc_flags flags = 0;
uint iolock = XFS_IOLOCK_EXCL;
@@ -749,6 +750,21 @@ xfs_file_fallocate(
xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
iolock |= XFS_MMAPLOCK_EXCL;
+ /*
+ * If fallocating a file < rtfallocmin store it on the non RT device.
+ * In a tiered storage setup, this device might be a device suitable
+ * for better small file storage/performance (e.g. SSD).
+ */
+ if (mp->m_rtdev_targp && mp->m_rtfallocmin && !offset &&
+ !inode->i_size) {
+ if (len >= mp->m_rtfallocmin) {
+ ip->i_d.di_flags |= XFS_DIFLAG_REALTIME;
+ /* Clear flag if inheritence or rtdefault is being used */
+ } else {
+ ip->i_d.di_flags &= ~XFS_DIFLAG_REALTIME;
+ }
+ }
+
if (mode & FALLOC_FL_PUNCH_HOLE) {
error = xfs_free_file_space(ip, offset, len);
if (error)
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 8016ddb..f5593bb 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -84,6 +84,7 @@ typedef struct xfs_mount {
char *m_fsname; /* filesystem name */
int m_fsname_len; /* strlen of fs name */
char *m_rtname; /* realtime device name */
+ int m_rtfallocmin; /* Min size for RT fallocate */
char *m_logname; /* external log device name */
int m_bsize; /* fs logical block size */
xfs_agnumber_t m_agfrotor; /* last ag where space found */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index a1d6968..01a2ab4 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -83,7 +83,8 @@ enum {
Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
Opt_uquota, Opt_gquota, Opt_pquota,
Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
- Opt_discard, Opt_nodiscard, Opt_dax, Opt_rtdisable, Opt_err,
+ Opt_discard, Opt_nodiscard, Opt_dax, Opt_rtdisable, Opt_rtfallocmin,
+ Opt_err,
};
static const match_table_t tokens = {
@@ -135,6 +136,9 @@ static const match_table_t tokens = {
#ifdef CONFIG_XFS_RT
{Opt_rtdisable, "rtdisable"}, /* Ignore real-time flags */
+ {Opt_rtfallocmin, "rtfallocmin=%u"}, /* Min fallocation required
+ * for rt device
+ */
#endif
/* Deprecated mount options scheduled for removal */
{Opt_barrier, "barrier"}, /* use writer barriers for log write and
@@ -374,6 +378,10 @@ xfs_parseargs(
case Opt_rtdisable:
mp->m_flags |= XFS_MOUNT_RTDISABLE;
break;
+ case Opt_rtfallocmin:
+ if (match_int(args, &mp->m_rtfallocmin))
+ return -EINVAL;
+ break;
#endif
#ifdef CONFIG_FS_DAX
case Opt_dax:
@@ -538,6 +546,11 @@ xfs_showargs(
if (mp->m_rtname)
seq_show_option(m, "rtdev", mp->m_rtname);
+#ifdef CONFIG_XFS_RT
+ if (mp->m_rtfallocmin > 0)
+ seq_printf(m, ",rtfallocmin=%d", mp->m_rtfallocmin);
+#endif
+
if (mp->m_dalign > 0)
seq_printf(m, ",sunit=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
--
2.9.3
--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
