XFS real-time device tweaks
v3 cover XFS real-time device tweaks
Patch 1: Same, per v2 cover letter.
Patch 2:
- Style updated per Christoph Hellwig's comment
- Fixed bug: statp->f_bavail = statp->f_bfree
Patch 3: Same, per v2 cover letter. I'm going to try my hand and putting this into the allocator itself per suggestions, perhaps there's some non-obvious way I'm not thinking of which can reduce the risk that folks hit the non-RT accidentally.
Richard Wareing (3):
fs/xfs: Add rtdisable option
fs/xfs: Add real-time device support to statfs
fs/xfs: Add rtfallocmin mount option
fs/xfs/xfs_file.c | 16 ++++++++++++++++ fs/xfs/xfs_inode.c | 6 ++++-- fs/xfs/xfs_ioctl.c | 7 +++++-- fs/xfs/xfs_mount.h | 2 ++ fs/xfs/xfs_super.c | 33 ++++++++++++++++++++++++++++++++- 5 files changed, 59 insertions(+), 5 deletions(-)
Signature · 1 line
2.9.3
PATCH v3 1/3 fs/xfs: Add rtdisable option
- Adds rtdisable mount option to ignore any real-time inheritance flag set on directories. Designed to be used as a "kill-switch" for this behavior, negating the need to walk/kill flags on FS.
Signed-off-by Richard Wareing <[email protected]>
--- fs/xfs/xfs_inode.c | 6 ++++-- fs/xfs/xfs_ioctl.c | 7 +++++-- fs/xfs/xfs_mount.h | 1 + fs/xfs/xfs_super.c | 14 +++++++++++++- 4 files changed, 23 insertions(+), 5 deletions(-)
fs/xfs/xfs_inode.c +4 -2
@@ -878,7 +878,8 @@ xfs_ialloc(uint di_flags =0 ;if (S_ISDIR (mode)) { -if (pip->i_d.di_flags &XFS_DIFLAG_RTINHERIT ) +if (!(mp->m_flags &XFS_MOUNT_RTDISABLE ) && + pip->i_d.di_flags &XFS_DIFLAG_RTINHERIT ) di_flags |=XFS_DIFLAG_RTINHERIT ;if (pip->i_d.di_flags &XFS_DIFLAG_EXTSZINHERIT ) { di_flags |=XFS_DIFLAG_EXTSZINHERIT ;
@@ -887,7 +888,8 @@ xfs_ialloc(if (pip->i_d.di_flags &XFS_DIFLAG_PROJINHERIT ) di_flags |=XFS_DIFLAG_PROJINHERIT ; }else if (S_ISREG (mode)) { -if (pip->i_d.di_flags &XFS_DIFLAG_RTINHERIT ) +if (!(mp->m_flags &XFS_MOUNT_RTDISABLE ) && + pip->i_d.di_flags &XFS_DIFLAG_RTINHERIT ) di_flags |=XFS_DIFLAG_REALTIME ;if (pip->i_d.di_flags &XFS_DIFLAG_EXTSZINHERIT ) { di_flags |=XFS_DIFLAG_EXTSIZE ;
fs/xfs/xfs_ioctl.c +5 -2
@@ -937,6 +937,7 @@ xfs_set_diflags( struct xfs_inode *ip, unsigned int xflags) { +struct xfs_mount *mp = ip->i_mount;unsigned int di_flags;uint64_t di_flags2;
@@ -957,7 +958,8 @@ xfs_set_diflags(if (xflags &FS_XFLAG_FILESTREAM ) di_flags |=XFS_DIFLAG_FILESTREAM ;if (S_ISDIR (VFS_I (ip)->i_mode)) { -if (xflags &FS_XFLAG_RTINHERIT ) +if (!(mp->m_flags &XFS_MOUNT_RTDISABLE ) && + xflags &FS_XFLAG_RTINHERIT ) di_flags |=XFS_DIFLAG_RTINHERIT ;if (xflags &FS_XFLAG_NOSYMLINKS ) di_flags |=XFS_DIFLAG_NOSYMLINKS ;
@@ -966,7 +968,8 @@ xfs_set_diflags(if (xflags &FS_XFLAG_PROJINHERIT ) di_flags |=XFS_DIFLAG_PROJINHERIT ; }else if (S_ISREG (VFS_I (ip)->i_mode)) { -if (xflags &FS_XFLAG_REALTIME ) +if (!(mp->m_flags &XFS_MOUNT_RTDISABLE ) && + xflags &FS_XFLAG_REALTIME ) di_flags |=XFS_DIFLAG_REALTIME ;if (xflags &FS_XFLAG_EXTSIZE ) di_flags |=XFS_DIFLAG_EXTSIZE ;
fs/xfs/xfs_mount.h +1 -0
@@ -243,6 +243,7 @@ typedef struct xfs_mount {allocator */ #define XFS_MOUNT_NOATTR2 (1ULL << 25)/* disable use of attr2 format */ +#define XFS_MOUNT_RTDISABLE (1ULL << 61)/* Ignore RT flags */ #define XFS_MOUNT_DAX (1ULL << 62)/* TEST ONLY! */
fs/xfs/xfs_super.c +13 -1
@@ -83,7 +83,7 @@ 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_err, + Opt_discard, Opt_nodiscard, Opt_dax, Opt_rtdisable, Opt_err, }; static const match_table_t tokens = {
@@ -133,6 +133,9 @@ static const match_table_t tokens = { {Opt_dax, "dax"}, /* Enable direct access to bdev pages */ +#ifdef CONFIG_XFS_RT + {Opt_rtdisable, "rtdisable"}, /* Ignore real-time flags */ +#endif /* Deprecated mount options scheduled for removal */ {Opt_barrier, "barrier"}, /* use writer barriers for log write and * unwritten extent conversion */
@@ -367,6 +370,11 @@ xfs_parseargs(case Opt_nodiscard: mp->m_flags &= ~XFS_MOUNT_DISCARD ;break ; +#ifdef CONFIG_XFS_RT +case Opt_rtdisable: + mp->m_flags |=XFS_MOUNT_RTDISABLE ; +break ; +#endif #ifdef CONFIG_FS_DAX case Opt_dax: mp->m_flags |=XFS_MOUNT_DAX ;
@@ -492,6 +500,10 @@ xfs_showargs( { XFS_MOUNT_DISCARD, ",discard" }, { XFS_MOUNT_SMALL_INUMS, ",inode32" }, { XFS_MOUNT_DAX, ",dax" }, +#ifdef CONFIG_XFS_RT + { XFS_MOUNT_RTDISABLE, ",rtdisable" }, +#endif + { 0, NULL } }; static struct proc_xfs_info xfs_info_unset[] = {
Signature · 1 line
2.9.3
PATCH v3 2/3 fs/xfs: Add real-time device support to statfs
In reply to Richard Wareing- Reports real-time device free blocks in statfs calls if inheritance bit is set on the inode of directory. This is a bit more intuitive, especially for use-cases which are using a much larger device for the real-time device.
Signed-off-by Richard Wareing <[email protected]>
--- fs/xfs/xfs_super.c | 6 ++++++ 1 file changed, 6 insertions(+)
fs/xfs/xfs_super.c +6 -0
@@ -1148,6 +1148,12 @@ xfs_fs_statfs( ((mp->m_qflags & (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))) == (XFS_PQUOTA_ACCT|XFS_PQUOTA_ENFD))xfs_qm_statvfs (ip, statp); +if ((ip->i_d.di_flags &XFS_DIFLAG_RTINHERIT ) && mp->m_rtdev_targp) { + statp->f_blocks = sbp->sb_rblocks; + statp->f_bavail = statp->f_bfree = + sbp->sb_frextents * sbp->sb_rextsize - + mp->m_alloc_set_aside; + }return 0 ; }
Signature · 1 line
2.9.3
PATCH v3 3/3 fs/xfs: Add rtfallocmin mount option
In reply to Richard Wareing- 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 <[email protected]>
--- 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(-)
fs/xfs/xfs_file.c +16 -0
@@ -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)
fs/xfs/xfs_mount.h +1 -0
@@ -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 */
fs/xfs/xfs_super.c +14 -1
@@ -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));
Signature · 1 line
2.9.3