xfs: patchset for 3.11

cover

---
 Documentation/filesystems/xfs.txt |  317 ++++++++++++++++++++++++-------------
 1 file changed, 209 insertions(+), 108 deletions(-)
index 83577f0..12525b1 100644
@@ -18,6 +18,8 @@ Mount Options
 =============
 
 When mounting an XFS filesystem, the following options are accepted.
+For boolean mount options, the names with the (*) suffix is the
+default behaviour.
 
   allocsize=size
 	Sets the buffered I/O end-of-file preallocation size when

@@ -25,97 +27,128 @@ When mounting an XFS filesystem, the following options are accepted.
 	Valid values for this option are page size (typically 4KiB)
 	through to 1GiB, inclusive, in power-of-2 increments.
 
-  attr2/noattr2
-	The options enable/disable (default is disabled for backward
-	compatibility on-disk) an "opportunistic" improvement to be
-	made in the way inline extended attributes are stored on-disk.
-	When the new form is used for the first time (by setting or
-	removing extended attributes) the on-disk superblock feature
-	bit field will be updated to reflect this format being in use.
+	The default behaviour is for dynamic end-of-file
+	preallocation size, which uses a set of heuristics to
+	optimise the preallocation size based on the current
+	allocation patterns within the file and the access patterns
+	to the file. Specifying a fixed allocsize value turns off
+	the dynamic behaviour.
+
+  attr2
+  noattr2
+	The options enable/disable an "opportunistic" improvement to
+	be made in the way inline extended attributes are stored
+	on-disk.  When the new form is used for the first time when
+	attr2 is selected (either when setting or removing extended
+	attributes) the on-disk superblock feature bit field will be
+	updated to reflect this format being in use.
+
+	The default behaviour is determined by the on-disk feature
+	bit indicating that attr2 behaviour is active. If either
+	mount option it set, then that becomes the new default used
+	by the filesystem.
 
 	CRC enabled filesystems always use the attr2 format, and so
 	will reject the noattr2 mount option if it is set.
 
-  barrier
-	Enables the use of block layer write barriers for writes into
-	the journal and unwritten extent conversion.  This allows for
-	drive level write caching to be enabled, for devices that
-	support write barriers.
+  barrier (*)
+  nobarrier
+	Enables/disables the use of block layer write barriers for
+	writes into the journal and for data integrity operations.
+	This allows for drive level write caching to be enabled, for
+	devices that support write barriers.
 
   discard
-	Issue command to let the block device reclaim space freed by the
-	filesystem.  This is useful for SSD devices, thinly provisioned
-	LUNs and virtual machine images, but may have a performance
-	impact.
-
-  dmapi
-	Enable the DMAPI (Data Management API) event callouts.
-	Use with the "mtpt" option.
-
-  grpid/bsdgroups and nogrpid/sysvgroups
-	These options define what group ID a newly created file gets.
-	When grpid is set, it takes the group ID of the directory in
-	which it is created; otherwise (the default) it takes the fsgid
-	of the current process, unless the directory has the setgid bit
-	set, in which case it takes the gid from the parent directory,
-	and also gets the setgid bit set if it is a directory itself.
-
-  ihashsize=value
-	In memory inode hashes have been removed, so this option has
-	no function as of August 2007. Option is deprecated.
-
-  ikeep/noikeep
-	When ikeep is specified, XFS does not delete empty inode clusters
-	and keeps them around on disk. ikeep is the traditional XFS
-	behaviour. When noikeep is specified, empty inode clusters
-	are returned to the free space pool. The default is noikeep for
-	non-DMAPI mounts, while ikeep is the default when DMAPI is in use.
-
-  inode64
-	Indicates that XFS is allowed to create inodes at any location
-	in the filesystem, including those which will result in inode
-	numbers occupying more than 32 bits of significance.  This is
-	the default allocation option. Applications which do not handle
-	inode numbers bigger than 32 bits, should use inode32 option.
+  nodiscard (*)
+	Enable/disable the issuing of commands to let the block
+	device reclaim space freed by the filesystem.  This is
+	useful for SSD devices, thinly provisioned LUNs and virtual
+	machine images, but may have a performance impact.
+
+	Note: It is currently recommended that you use the fstrim
+	application to discard unused blocks rather than the discard
+	mount option because the performance impact of this option
+	is quite severe.
+
+  grpid/bsdgroups
+  nogrpid/sysvgroups (*)
+	These options define what group ID a newly created file
+	gets.  When grpid is set, it takes the group ID of the
+	directory in which it is created; otherwise it takes the
+	fsgid of the current process, unless the directory has the
+	setgid bit set, in which case it takes the gid from the
+	parent directory, and also gets the setgid bit set if it is
+	a directory itself.
+
+  filestreams
+	Make the data allocator use the filestreams allocation mode
+	across the entire filesystem rather than just on directories
+	configured to use it.
+
+  ikeep
+  noikeep (*)
+	When ikeep is specified, XFS does not delete empty inode
+	clusters and keeps them around on disk.  When noikeep is
+	specified, empty inode clusters are returned to the free
+	space pool.
 
   inode32
-	Indicates that XFS is limited to create inodes at locations which
-	will not result in inode numbers with more than 32 bits of
-	significance. This is provided for backwards compatibility, since
-	64 bits inode numbers might cause problems for some applications
-	that cannot handle large inode numbers.
-
-  largeio/nolargeio
+  inode64 (*)
+	When inode32 is specified, it indicates that XFS limits
+	inode creation to locations which will not result in inode
+	numbers with more than 32 bits of significance.
+
+	When inode64 is specified, it indicates that XFS is allowed
+	to create inodes at any location in the filesystem,
+	including those which will result in inode numbers occupying
+	more than 32 bits of significance. 
+
+	inode32 is provided for backwards compatibility with older
+	systems and applications, since 64 bits inode numbers might
+	cause problems for some applications that cannot handle
+	large inode numbers.  If applications are in use which do
+	not handle inode numbers bigger than 32 bits, the inode32
+	option should be specified.
+
+
+  largeio
+  nolargeio (*)
 	If "nolargeio" is specified, the optimal I/O reported in
-	st_blksize by stat(2) will be as small as possible to allow user
-	applications to avoid inefficient read/modify/write I/O.
-	If "largeio" specified, a filesystem that has a "swidth" specified
-	will return the "swidth" value (in bytes) in st_blksize. If the
-	filesystem does not have a "swidth" specified but does specify
-	an "allocsize" then "allocsize" (in bytes) will be returned
-	instead.
-	If neither of these two options are specified, then filesystem
-	will behave as if "nolargeio" was specified.
+	st_blksize by stat(2) will be as small as possible to allow
+	user applications to avoid inefficient read/modify/write
+	I/O.  This is typically the page size of the machine, as
+	this is the granularity of the page cache.
+
+	If "largeio" specified, a filesystem that was created with a
+	"swidth" specified will return the "swidth" value (in bytes)
+	in st_blksize. If the filesystem does not have a "swidth"
+	specified but does specify an "allocsize" then "allocsize"
+	(in bytes) will be returned instead. Otherwise the behaviour
+	is the same as if "nolargeio" was specified.
 
   logbufs=value
-	Set the number of in-memory log buffers.  Valid numbers range
-	from 2-8 inclusive.
-	The default value is 8 buffers for filesystems with a
-	blocksize of 64KiB, 4 buffers for filesystems with a blocksize
-	of 32KiB, 3 buffers for filesystems with a blocksize of 16KiB
-	and 2 buffers for all other configurations.  Increasing the
-	number of buffers may increase performance on some workloads
-	at the cost of the memory used for the additional log buffers
-	and their associated control structures.
+	Set the number of in-memory log buffers.  Valid numbers
+	range from 2-8 inclusive.
+
+	The default value is 8 buffers.
+
+	If the memory cost of 8 log buffers is too high on small
+	systems, then it may be reduced at some cost to performance
+	on metadata intensive workloads. The logbsize option below
+	controls the size of each buffer and so is also relevent to
+	this case.
 
   logbsize=value
-	Set the size of each in-memory log buffer.
-	Size may be specified in bytes, or in kilobytes with a "k" suffix.
-	Valid sizes for version 1 and version 2 logs are 16384 (16k) and
-	32768 (32k).  Valid sizes for version 2 logs also include
-	65536 (64k), 131072 (128k) and 262144 (256k).
-	The default value for machines with more than 32MiB of memory
-	is 32768, machines with less memory use 16384 by default.
+	Set the size of each in-memory log buffer.  The size may be
+	specified in bytes, or in kilobytes with a "k" suffix.
+	Valid sizes for version 1 and version 2 logs are 16384 (16k)
+	and 32768 (32k).  Valid sizes for version 2 logs also
+	include 65536 (64k), 131072 (128k) and 262144 (256k). The
+	logbsize must be an integer multiple of the log
+	stripe unit configured at mkfs time.
+
+	The default value for for version 1 logs is 32768, while the
+	default value for version 2 logs is MAX(32768, log_sunit).
 
   logdev=device and rtdev=device
 	Use an external log (metadata journal) and/or real-time device.

@@ -124,16 +157,11 @@ When mounting an XFS filesystem, the following options are accepted.
 	optional, and the log section can be separate from the data
 	section or contained within it.
 
-  mtpt=mountpoint
-	Use with the "dmapi" option.  The value specified here will be
-	included in the DMAPI mount event, and should be the path of
-	the actual mountpoint that is used.
-
   noalign
-	Data allocations will not be aligned at stripe unit boundaries.
-
-  noatime
-	Access timestamps are not updated when a file is read.
+	Data allocations will not be aligned at stripe unit
+	boundaries. This is only relevant to filesystems created
+	with non-zero data alignment parameters (sunit, swidth) by
+	mkfs.
 
   norecovery
 	The filesystem will be mounted without running log recovery.

@@ -144,8 +172,14 @@ When mounting an XFS filesystem, the following options are accepted.
 	the mount will fail.
 
   nouuid
-	Don't check for double mounted file systems using the file system uuid.
-	This is useful to mount LVM snapshot volumes.
+	Don't check for double mounted file systems using the file
+	system uuid.  This is useful to mount LVM snapshot volumes,
+	and often used in combination with "norecovery" for mounting
+	read-only snapshots.
+
+  noquota
+	Forcibly turns off all quota accounting and enforcement
+	within the filesystem.
 
   uquota/usrquota/uqnoenforce/quota
 	User disk quota accounting enabled, and limits (optionally)

@@ -160,24 +194,64 @@ When mounting an XFS filesystem, the following options are accepted.
 	enforced.  Refer to xfs_quota(8) for further details.
 
   sunit=value and swidth=value
-	Used to specify the stripe unit and width for a RAID device or
-	a stripe volume.  "value" must be specified in 512-byte block
-	units.
-	If this option is not specified and the filesystem was made on
-	a stripe volume or the stripe width or unit were specified for
-	the RAID device at mkfs time, then the mount system call will
-	restore the value from the superblock.  For filesystems that
-	are made directly on RAID devices, these options can be used
-	to override the information in the superblock if the underlying
-	disk layout changes after the filesystem has been created.
-	The "swidth" option is required if the "sunit" option has been
-	specified, and must be a multiple of the "sunit" value.
+	Used to specify the stripe unit and width for a RAID device
+	or a stripe volume.  "value" must be specified in 512-byte
+	block units. These options are only relevant to filesystems
+	that were created with non-zero data alignment parameters.
+
+	The sunit and swidth parameters specified must be compatible
+	with the existing filesystem alignment characteristics.  In
+	general, that means the only valid changes to sunit are
+	increasing it by a power-of-2 multiple. Valid swidth values
+	are any integer multiple of a valid sunit value.
+
+	Typically the only time these mount options are necessary if
+	after an underlying RAID device has had it's geometry
+	modified, such as adding a new disk to a RAID5 lun and
+	reshaping it.
 
   swalloc
 	Data allocations will be rounded up to stripe width boundaries
 	when the current end of file is being extended and the file
 	size is larger than the stripe width size.
 
+  wsync
+	When specified, all filesystem namespace operations are
+	executed synchronously. This ensures that when the namespace
+	operation (create, unlink, etc) completes, the change to the
+	namespace is on stable storage. This is useful in HA setups
+	where failover must not result in clients seeing
+	inconsistent namespace presentation during or after a
+	failover event.
+
+
+Deprecated Mount Options
+========================
+
+  delaylog/nodelaylog
+	Delayed logging is the only logging method that XFS supports
+	now, so these mount options are now ignored.
+
+	Due for removal in 3.12.
+
+  ihashsize=value
+	In memory inode hashes have been removed, so this option has
+	no function as of August 2007. Option is deprecated.
+
+	Due for removal in 3.12.
+
+  irixsgid
+	This behaviour is now controlled by a sysctl, so the mount
+	option is ignored.
+
+	Due for removal in 3.12.
+
+  osyncisdsync
+  osyncisosync
+	O_SYNC and O_DSYNC are fully supported, so there is no need
+	for these options any more.
+
+	Due for removal in 3.12.
 
 sysctls
 =======

@@ -189,15 +263,20 @@ The following sysctls are available for the XFS filesystem:
 	in /proc/fs/xfs/stat.  It then immediately resets to "0".
 
   fs.xfs.xfssyncd_centisecs	(Min: 100  Default: 3000  Max: 720000)
-  	The interval at which the xfssyncd thread flushes metadata
-  	out to disk.  This thread will flush log activity out, and
-  	do some processing on unlinked inodes.
+	The interval at which the filesystem flushes metadata
+	out to disk and runs internal cache cleanup routines.
 
-  fs.xfs.xfsbufd_centisecs	(Min: 50  Default: 100	Max: 3000)
-	The interval at which xfsbufd scans the dirty metadata buffers list.
+  fs.xfs.filestream_centisecs	(Min: 1  Default: 3000  Max: 360000)
+	The interval at which the filesystem ages filestreams cache
+	references and returns timed-out AGs back to the free stream
+	pool.
 
-  fs.xfs.age_buffer_centisecs	(Min: 100  Default: 1500  Max: 720000)
-	The age at which xfsbufd flushes dirty metadata buffers to disk.
+  fs.xfs.speculative_prealloc_lifetime
+		(Units: seconds   Min: 1  Default: 300  Max: 86400)
+	The interval at which the background scanning for inodes
+	with unused speculative preallocation runs. The scan
+	removes unused preallocation from clean inodes and releases
+	the unused space back to the free pool.
 
   fs.xfs.error_level		(Min: 0  Default: 3  Max: 11)
 	A volume knob for error reporting when internal errors occur.

@@ -254,9 +333,31 @@ The following sysctls are available for the XFS filesystem:
 	by the xfs_io(8) chattr command on a directory to be
 	inherited by files in that directory.
 
+  fs.xfs.inherit_nodefrag	(Min: 0  Default: 1  Max: 1)
+	Setting this to "1" will cause the "nodefrag" flag set
+	by the xfs_io(8) chattr command on a directory to be
+	inherited by files in that directory.
+
   fs.xfs.rotorstep		(Min: 1  Default: 1  Max: 256)
 	In "inode32" allocation mode, this option determines how many
 	files the allocator attempts to allocate in the same allocation
 	group before moving to the next allocation group.  The intent
 	is to control the rate at which the allocator moves between
 	allocation groups when allocating extents for new files.
+
+Deprecated Sysctls
+==================
+
+  fs.xfs.xfsbufd_centisecs	(Min: 50  Default: 100	Max: 3000)
+	Dirty metadata is now tracked by the log subsystem and
+	flushing is driven by log space and idling demands. The
+	xfsbufd no longer exists, so this syctl does nothing.
+
+	Due for removal in 3.14.
+
+  fs.xfs.age_buffer_centisecs	(Min: 100  Default: 1500  Max: 720000)
+	Dirty metadata is now tracked by the log subsystem and
+	flushing is driven by log space and idling demands. The
+	xfsbufd no longer exists, so this syctl does nothing.
+
+	Due for removal in 3.14.

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
| On Fri, Jun 28, 2013 at 12:09:12PM +1000, Dave Chinner wrote:
| > Mount options are perfectly fine to be removed - they've been given
| > deprecated warnings for quite some time now (the most recent is the
| > delaylog which has been doing that since 3.1 IIRC). So they are all
| > fine to actually remove - 12 months warning is usually considered
| > sufficient.
| > As to the sysctls - they haven't had any effect since 3.5 when the
| > xfsbufd was removed, so it's time to mark them deprecated so we can
| > remove them in a year's time. That gives anyone using them
| > (including distros) plenty of time to fix whatever is using them
| > before they get removed.
| > 
| > > I'm thinking of the 3.3 glusterfs and 3.8 pulseaudio reakeage.  And I would
| > > really like to have a nice holiday weekend. ;)
| > 
| > I think you're being overly paranoid here - I'm simply following the
| > normal deprecation protocol here....
| 
| Documenation/ABI/README:
| 
| We have four different levels of ABI stability, as shown by the four
| different subdirectories in this location.  Interfaces may change levels
| of stability according to the rules described below.
| ....
|  obsolete/
|          This directory documents interfaces that are still remaining in
| 	 the kernel, but are marked to be removed at some later point in
| 	 time.  The description of the interface will document the reason
| 	 why it is obsolete and when it can be expected to be removed.
| I think you'll find that what I done follows this policy. If you
| really want, I'll move them to Documenation/ABI/obsolete.  And, of
| course, if removing them proves to be a problem, as Eric said we can
| always reinstate them or remove the deprecation notices.
Geoffrey Wehrman  651-683-5496  [email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
| On Fri, Jun 28, 2013 at 12:09:12PM +1000, Dave Chinner wrote:
| > Mount options are perfectly fine to be removed - they've been given
| > deprecated warnings for quite some time now (the most recent is the
| > delaylog which has been doing that since 3.1 IIRC). So they are all
| > fine to actually remove - 12 months warning is usually considered
| > sufficient.
| > As to the sysctls - they haven't had any effect since 3.5 when the
| > xfsbufd was removed, so it's time to mark them deprecated so we can
| > remove them in a year's time. That gives anyone using them
| > (including distros) plenty of time to fix whatever is using them
| > before they get removed.
| > 
| > > I'm thinking of the 3.3 glusterfs and 3.8 pulseaudio reakeage.  And I would
| > > really like to have a nice holiday weekend. ;)
| > 
| > I think you're being overly paranoid here - I'm simply following the
| > normal deprecation protocol here....
| 
| Documenation/ABI/README:
| 
| We have four different levels of ABI stability, as shown by the four
| different subdirectories in this location.  Interfaces may change levels
| of stability according to the rules described below.
| ....
|  obsolete/
|          This directory documents interfaces that are still remaining in
| 	 the kernel, but are marked to be removed at some later point in
| 	 time.  The description of the interface will document the reason
| 	 why it is obsolete and when it can be expected to be removed.
| I think you'll find that what I done follows this policy. If you
| really want, I'll move them to Documenation/ABI/obsolete.  And, of
| course, if removing them proves to be a problem, as Eric said we can
| always reinstate them or remove the deprecation notices.
| On 6/28/13 11:39 AM, Geoffrey Wehrman wrote:
| > On Fri, Jun 28, 2013 at 12:32:04PM +1000, Dave Chinner wrote:
| > | On Fri, Jun 28, 2013 at 12:09:12PM +1000, Dave Chinner wrote:
| > | > Mount options are perfectly fine to be removed - they've been given
| > | > deprecated warnings for quite some time now (the most recent is the
| > | > delaylog which has been doing that since 3.1 IIRC). So they are all
| > | > fine to actually remove - 12 months warning is usually considered
| > | > sufficient.
| > 
| > I hardly consider 12 years to be sufficient.  I have no problem with
| 
| 12 years, really?  Maybe you meant months.  I hope you meant months!
| > | > I think you're being overly paranoid here - I'm simply following the
| > | > normal deprecation protocol here....
| > | 
| > | Documenation/ABI/README:
| > | 
| > | We have four different levels of ABI stability, as shown by the four
| > | different subdirectories in this location.  Interfaces may change levels
| > | of stability according to the rules described below.
| > | ....
| > |  obsolete/
| > |          This directory documents interfaces that are still remaining in
| > | 	 the kernel, but are marked to be removed at some later point in
| > | 	 time.  The description of the interface will document the reason
| > | 	 why it is obsolete and when it can be expected to be removed.
| > 
| > 
| > | I think you'll find that what I done follows this policy. If you
| > | really want, I'll move them to Documenation/ABI/obsolete.  And, of
| > | course, if removing them proves to be a problem, as Eric said we can
| > | always reinstate them or remove the deprecation notices.
Geoffrey Wehrman  651-683-5496  [email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
| On Fri, Jun 28, 2013 at 12:09:12PM +1000, Dave Chinner wrote:
| > Mount options are perfectly fine to be removed - they've been given
| > deprecated warnings for quite some time now (the most recent is the
| > delaylog which has been doing that since 3.1 IIRC). So they are all
| > fine to actually remove - 12 months warning is usually considered
| > sufficient.
| > As to the sysctls - they haven't had any effect since 3.5 when the
| > xfsbufd was removed, so it's time to mark them deprecated so we can
| > remove them in a year's time. That gives anyone using them
| > (including distros) plenty of time to fix whatever is using them
| > before they get removed.
| >
| > > I'm thinking of the 3.3 glusterfs and 3.8 pulseaudio reakeage.  And I would
| > > really like to have a nice holiday weekend. ;)
| >
| > I think you're being overly paranoid here - I'm simply following the
| > normal deprecation protocol here....
|
| Documenation/ABI/README:
|
| We have four different levels of ABI stability, as shown by the four
| different subdirectories in this location.  Interfaces may change levels
| of stability according to the rules described below.
| ....
|  obsolete/
|          This directory documents interfaces that are still remaining in
| 	 the kernel, but are marked to be removed at some later point in
| 	 time.  The description of the interface will document the reason
| 	 why it is obsolete and when it can be expected to be removed.
| I think you'll find that what I done follows this policy. If you
| really want, I'll move them to Documenation/ABI/obsolete.  And, of
| course, if removing them proves to be a problem, as Eric said we can
| always reinstate them or remove the deprecation notices.
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_itable.c |    3 +++
 1 file changed, 3 insertions(+)
index 2ea7d40..06d004d 100644
@@ -383,11 +383,13 @@ xfs_bulkstat(
 			 * Also start read-ahead now for this chunk.
 			 */
 			if (r.ir_freecount < XFS_INODES_PER_CHUNK) {
+				struct blk_plug	plug;
 				/*
 				 * Loop over all clusters in the next chunk.
 				 * Do a readahead if there are any allocated
 				 * inodes in that cluster.
 				 */
+				blk_start_plug(&plug);
 				agbno = XFS_AGINO_TO_AGBNO(mp, r.ir_startino);
 				for (chunkidx = 0;
 				     chunkidx < XFS_INODES_PER_CHUNK;

@@ -399,6 +401,7 @@ xfs_bulkstat(
 							agbno, nbcluster,
 							&xfs_inode_buf_ops);
 				}
+				blk_finish_plug(&plug);
 				irbp->ir_startino = r.ir_startino;
 				irbp->ir_freecount = r.ir_freecount;
 				irbp->ir_free = r.ir_free;

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_dir2_leaf.c |    3 +++
 1 file changed, 3 insertions(+)
index da71a18..bb22aac 100644
@@ -1108,6 +1108,7 @@ xfs_dir2_leaf_readbuf(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*bp = *bpp;
 	struct xfs_bmbt_irec	*map = mip->map;
+	struct blk_plug		plug;
 	int			error = 0;
 	int			length;
 	int			i;

@@ -1236,6 +1237,7 @@ xfs_dir2_leaf_readbuf(
 	/*
 	 * Do we need more readahead?
 	 */
+	blk_start_plug(&plug);
 	for (mip->ra_index = mip->ra_offset = i = 0;
 	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
 	     i += mp->m_dirblkfsbs) {

@@ -1287,6 +1289,7 @@ xfs_dir2_leaf_readbuf(
 			}
 		}
 	}
+	blk_finish_plug(&plug);
 
 out:
 	*bpp = bp;

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_iomap.c |   13 +++++++++++++
 1 file changed, 13 insertions(+)
index 8f8aaee..6a70964 100644
@@ -284,6 +284,15 @@ xfs_iomap_eof_want_preallocate(
 		return 0;
 
 	/*
+	 * If the file is smaller than the minimum prealloc and we are using
+	 * dynamic preallocation, don't do any preallocation at all as it is
+	 * likely this is the only write to the file that is going to be done.
+	 */
+	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) &&
+	    XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_writeio_blocks))
+		return 0;
+
+	/*
 	 * If there are any real blocks past eof, then don't
 	 * do any speculative allocation.
 	 */

@@ -345,6 +354,10 @@ xfs_iomap_eof_prealloc_initial_size(
 	if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
 		return 0;
 
+	/* If the file is small, then use the minimum prealloc */
+	if (XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign))
+		return 0;
+
 	/*
 	 * As we write multiple pages, the offset will always align to the
 	 * start of a page and hence point to a hole at EOF. i.e. if the size is

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_inode.c |   36 ++++++++++++++++++++++++++++--------
 1 file changed, 28 insertions(+), 8 deletions(-)
index 7f7be5f..d1f76da 100644
@@ -1028,6 +1028,11 @@ xfs_dinode_calc_crc(
 
 /*
  * Read the disk inode attributes into the in-core inode structure.
+ *
+ * If we are initialising a new inode and we are not utilising the
+ * XFS_MOUNT_IKEEP inode cluster mode, we can simple build the new inode core
+ * with a random generation number. If we are keeping inodes around, we need to
+ * read the inode cluster to get the existing generation number off disk.
  */
 int
 xfs_iread(

@@ -1047,6 +1052,22 @@ xfs_iread(
 	if (error)
 		return error;
 
+	/* shortcut IO on inode allocation if possible */
+	if ((iget_flags & XFS_IGET_CREATE) &&
+	    !(mp->m_flags & XFS_MOUNT_IKEEP)) {
+		/* initialise the on-disk inode core */
+		memset(&ip->i_d, 0, sizeof(ip->i_d));
+		ip->i_d.di_magic = XFS_DINODE_MAGIC;
+		ip->i_d.di_gen = prandom_u32();
+		if (xfs_sb_version_hascrc(&mp->m_sb)) {
+			ip->i_d.di_version = 3;
+			ip->i_d.di_ino = ip->i_ino;
+			uuid_copy(&ip->i_d.di_uuid, &mp->m_sb.sb_uuid);
+		} else
+			ip->i_d.di_version = 2;
+		return 0;
+	}
+
 	/*
 	 * Get pointers to the on-disk inode and the buffer containing it.
 	 */

@@ -1133,17 +1154,16 @@ xfs_iread(
 	xfs_buf_set_ref(bp, XFS_INO_REF);
 
 	/*
-	 * Use xfs_trans_brelse() to release the buffer containing the
-	 * on-disk inode, because it was acquired with xfs_trans_read_buf()
-	 * in xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
+	 * Use xfs_trans_brelse() to release the buffer containing the on-disk
+	 * inode, because it was acquired with xfs_trans_read_buf() in
+	 * xfs_imap_to_bp() above.  If tp is NULL, this is just a normal
 	 * brelse().  If we're within a transaction, then xfs_trans_brelse()
 	 * will only release the buffer if it is not dirty within the
 	 * transaction.  It will be OK to release the buffer in this case,
-	 * because inodes on disk are never destroyed and we will be
-	 * locking the new in-core inode before putting it in the hash
-	 * table where other processes can find it.  Thus we don't have
-	 * to worry about the inode being changed just because we released
-	 * the buffer.
+	 * because inodes on disk are never destroyed and we will be locking the
+	 * new in-core inode before putting it in the cache where other
+	 * processes can find it.  Thus we don't have to worry about the inode
+	 * being changed just because we released the buffer.
 	 */
  out_brelse:
 	xfs_trans_brelse(tp, bp);

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_inode.c |   32 ++++----------------------------
 1 file changed, 4 insertions(+), 28 deletions(-)
index d1f76da..9ecfe1e 100644
@@ -2048,8 +2048,6 @@ xfs_ifree(
 	int			error;
 	int			delete;
 	xfs_ino_t		first_ino;
-	xfs_dinode_t    	*dip;
-	xfs_buf_t       	*ibp;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(ip->i_d.di_nlink == 0);

@@ -2062,14 +2060,13 @@ xfs_ifree(
 	 * Pull the on-disk inode from the AGI unlinked list.
 	 */
 	error = xfs_iunlink_remove(tp, ip);
-	if (error != 0) {
+	if (error)
 		return error;
-	}
 
 	error = xfs_difree(tp, ip->i_ino, flist, &delete, &first_ino);
-	if (error != 0) {
+	if (error)
 		return error;
-	}
+
 	ip->i_d.di_mode = 0;		/* mark incore inode as free */
 	ip->i_d.di_flags = 0;
 	ip->i_d.di_dmevmask = 0;

@@ -2081,31 +2078,10 @@ xfs_ifree(
 	 * by reincarnations of this inode.
 	 */
 	ip->i_d.di_gen++;
-
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
-	error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &dip, &ibp,
-			       0, 0);
-	if (error)
-		return error;
-
-        /*
-	* Clear the on-disk di_mode. This is to prevent xfs_bulkstat
-	* from picking up this inode when it is reclaimed (its incore state
-	* initialzed but not flushed to disk yet). The in-core di_mode is
-	* already cleared  and a corresponding transaction logged.
-	* The hack here just synchronizes the in-core to on-disk
-	* di_mode value in advance before the actual inode sync to disk.
-	* This is OK because the inode is already unlinked and would never
-	* change its di_mode again for this inode generation.
-	* This is a temporary hack that would require a proper fix
-	* in the future.
-	*/
-	dip->di_mode = 0;
-
-	if (delete) {
+	if (delete)
 		error = xfs_ifree_cluster(ip, tp, first_ino);
-	}
 
 	return error;
 }

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_log.c     |   22 ++++++++++++---
 fs/xfs/xfs_log.h     |    2 ++
 fs/xfs/xfs_log_cil.c |   75 ++++++++++++++++++++++++++++++++++----------------
 3 files changed, 71 insertions(+), 28 deletions(-)
index b345a7c..d852a2b 100644
@@ -1963,6 +1963,10 @@ xlog_write_calc_vec_length(
 		headers++;
 
 	for (lv = log_vector; lv; lv = lv->lv_next) {
+		/* we don't write ordered log vectors */
+		if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED)
+			continue;
+
 		headers += lv->lv_niovecs;
 
 		for (i = 0; i < lv->lv_niovecs; i++) {

@@ -2216,7 +2220,7 @@ xlog_write(
 	index = 0;
 	lv = log_vector;
 	vecp = lv->lv_iovecp;
-	while (lv && index < lv->lv_niovecs) {
+	while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
 		void		*ptr;
 		int		log_offset;
 

@@ -2236,13 +2240,22 @@ xlog_write(
 		 * This loop writes out as many regions as can fit in the amount
 		 * of space which was allocated by xlog_state_get_iclog_space().
 		 */
-		while (lv && index < lv->lv_niovecs) {
-			struct xfs_log_iovec	*reg = &vecp[index];
+		while (lv && (!lv->lv_niovecs || index < lv->lv_niovecs)) {
+			struct xfs_log_iovec	*reg;
 			struct xlog_op_header	*ophdr;
 			int			start_rec_copy;
 			int			copy_len;
 			int			copy_off;
+			bool			ordered = false;
+
+			/* ordered log vectors have no regions to write */
+			if (lv->lv_buf_len == XFS_LOG_VEC_ORDERED) {
+				ASSERT(lv->lv_niovecs == 0);
+				ordered = true;
+				goto next_lv;
+			}
 
+			reg = &vecp[index];
 			ASSERT(reg->i_len % sizeof(__int32_t) == 0);
 			ASSERT((unsigned long)ptr % sizeof(__int32_t) == 0);
 

@@ -2302,12 +2315,13 @@ xlog_write(
 				break;
 
 			if (++index == lv->lv_niovecs) {
+next_lv:
 				lv = lv->lv_next;
 				index = 0;
 				if (lv)
 					vecp = lv->lv_iovecp;
 			}
-			if (record_cnt == 0) {
+			if (record_cnt == 0 && ordered == false) {
 				if (!lv)
 					return 0;
 				break;

index 5caee96..b20918c 100644
@@ -105,6 +105,8 @@ struct xfs_log_vec {
 	int			lv_buf_len;	/* size of formatted buffer */
 };
 
+#define XFS_LOG_VEC_ORDERED	(-1)
+
 /*
  * Structure used to pass callback function and the function's argument
  * to the log manager.

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_buf_item.c  |   75 +++++++++++++++++++++++++++++++-----------------
 fs/xfs/xfs_buf_item.h  |    4 ++-
 fs/xfs/xfs_trace.h     |    4 +++
 fs/xfs/xfs_trans.h     |    1 +
 fs/xfs/xfs_trans_buf.c |   34 ++++++++++++++++++++--
 5 files changed, 87 insertions(+), 31 deletions(-)
index 4ec4317..61f6876 100644
@@ -140,6 +140,16 @@ xfs_buf_item_size(
 
 	ASSERT(bip->bli_flags & XFS_BLI_LOGGED);
 
+	if (bip->bli_flags & XFS_BLI_ORDERED) {
+		/*
+		 * The buffer has been logged just to order it.
+		 * It is not being included in the transaction
+		 * commit, so no vectors are used at all.
+		 */
+		trace_xfs_buf_item_size_ordered(bip);
+		return XFS_LOG_VEC_ORDERED;
+	}
+
 	/*
 	 * the vector count is based on the number of buffer vectors we have
 	 * dirty bits in. This will only be greater than one when we have a

@@ -212,6 +222,7 @@ xfs_buf_item_format_segment(
 		goto out;
 	}
 
+
 	/*
 	 * Fill in an iovec for each set of contiguous chunks.
 	 */

@@ -311,6 +322,16 @@ xfs_buf_item_format(
 		bip->bli_flags &= ~XFS_BLI_INODE_BUF;
 	}
 
+	if ((bip->bli_flags & (XFS_BLI_ORDERED|XFS_BLI_STALE)) ==
+							XFS_BLI_ORDERED) {
+		/*
+		 * The buffer has been logged just to order it.  It is not being
+		 * included in the transaction commit, so don't format it.
+		 */
+		trace_xfs_buf_item_format_ordered(bip);
+		return;
+	}
+
 	for (i = 0; i < bip->bli_format_count; i++) {
 		vecp = xfs_buf_item_format_segment(bip, vecp, offset,
 						&bip->bli_formats[i]);

@@ -340,6 +361,7 @@ xfs_buf_item_pin(
 
 	ASSERT(atomic_read(&bip->bli_refcount) > 0);
 	ASSERT((bip->bli_flags & XFS_BLI_LOGGED) ||
+	       (bip->bli_flags & XFS_BLI_ORDERED) ||
 	       (bip->bli_flags & XFS_BLI_STALE));
 
 	trace_xfs_buf_item_pin(bip);

@@ -512,8 +534,9 @@ xfs_buf_item_unlock(
 {
 	struct xfs_buf_log_item	*bip = BUF_ITEM(lip);
 	struct xfs_buf		*bp = bip->bli_buf;
-	int			aborted, clean, i;
-	uint			hold;
+	bool			clean;
+	bool			aborted;
+	int			flags;
 
 	/* Clear the buffer's association with this transaction. */
 	bp->b_transp = NULL;

@@ -524,23 +547,21 @@ xfs_buf_item_unlock(
 	 * (cancelled) buffers at unpin time, but we'll never go through the
 	 * pin/unpin cycle if we abort inside commit.
 	 */
-	aborted = (lip->li_flags & XFS_LI_ABORTED) != 0;
-
+	aborted = (lip->li_flags & XFS_LI_ABORTED) ? true : false;
 	/*
-	 * Before possibly freeing the buf item, determine if we should
-	 * release the buffer at the end of this routine.
+	 * Before possibly freeing the buf item, copy the per-transaction state
+	 * so we can reference it safely later after clearing it from the
+	 * buffer log item.
 	 */
-	hold = bip->bli_flags & XFS_BLI_HOLD;
-
-	/* Clear the per transaction state. */
-	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD);
+	flags = bip->bli_flags;
+	bip->bli_flags &= ~(XFS_BLI_LOGGED | XFS_BLI_HOLD | XFS_BLI_ORDERED);
 
 	/*
 	 * If the buf item is marked stale, then don't do anything.  We'll
 	 * unlock the buffer and free the buf item when the buffer is unpinned
 	 * for the last time.
 	 */
-	if (bip->bli_flags & XFS_BLI_STALE) {
+	if (flags & XFS_BLI_STALE) {
 		trace_xfs_buf_item_unlock_stale(bip);
 		ASSERT(bip->__bli_format.blf_flags & XFS_BLF_CANCEL);
 		if (!aborted) {

@@ -557,13 +578,19 @@ xfs_buf_item_unlock(
 	 * be the only reference to the buf item, so we free it anyway
 	 * regardless of whether it is dirty or not. A dirty abort implies a
 	 * shutdown, anyway.
+	 *
+	 * Ordered buffers are dirty but may have no recorded changes, so ensure
+	 * we only release clean items here.
 	 */
-	clean = 1;
-	for (i = 0; i < bip->bli_format_count; i++) {
-		if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
-			     bip->bli_formats[i].blf_map_size)) {
-			clean = 0;
-			break;
+	clean = (flags & XFS_BLI_DIRTY) ? false : true;
+	if (clean) {
+		int i;
+		for (i = 0; i < bip->bli_format_count; i++) {
+			if (!xfs_bitmap_empty(bip->bli_formats[i].blf_data_map,
+				     bip->bli_formats[i].blf_map_size)) {
+				clean = false;
+				break;
+			}
 		}
 	}
 	if (clean)

@@ -576,7 +603,7 @@ xfs_buf_item_unlock(
 	} else
 		atomic_dec(&bip->bli_refcount);
 
-	if (!hold)
+	if (!(flags & XFS_BLI_HOLD))
 		xfs_buf_relse(bp);
 }
 

@@ -842,12 +869,6 @@ xfs_buf_item_log(
 	struct xfs_buf		*bp = bip->bli_buf;
 
 	/*
-	 * Mark the item as having some dirty data for
-	 * quick reference in xfs_buf_item_dirty.
-	 */
-	bip->bli_flags |= XFS_BLI_DIRTY;
-
-	/*
 	 * walk each buffer segment and mark them dirty appropriately.
 	 */
 	start = 0;

@@ -873,7 +894,7 @@ xfs_buf_item_log(
 
 
 /*
- * Return 1 if the buffer has some data that has been logged (at any
+ * Return 1 if the buffer has been logged or ordered in a transaction (at any
  * point, not just the current transaction) and 0 if not.
  */
 uint

@@ -907,11 +928,11 @@ void
 xfs_buf_item_relse(
 	xfs_buf_t	*bp)
 {
-	xfs_buf_log_item_t	*bip;
+	xfs_buf_log_item_t	*bip = bp->b_fspriv;
 
 	trace_xfs_buf_item_relse(bp, _RET_IP_);
+	ASSERT(!(bip->bli_item.li_flags & XFS_LI_IN_AIL));
 
-	bip = bp->b_fspriv;
 	bp->b_fspriv = bip->bli_item.li_bio_list;
 	if (bp->b_fspriv == NULL)
 		bp->b_iodone = NULL;

index 2573d2a..0f1c247 100644
@@ -120,6 +120,7 @@ xfs_blft_from_flags(struct xfs_buf_log_format *blf)
 #define	XFS_BLI_INODE_ALLOC_BUF	0x10
 #define XFS_BLI_STALE_INODE	0x20
 #define	XFS_BLI_INODE_BUF	0x40
+#define	XFS_BLI_ORDERED		0x80
 
 #define XFS_BLI_FLAGS \
 	{ XFS_BLI_HOLD,		"HOLD" }, \

@@ -128,7 +129,8 @@ xfs_blft_from_flags(struct xfs_buf_log_format *blf)
 	{ XFS_BLI_LOGGED,	"LOGGED" }, \
 	{ XFS_BLI_INODE_ALLOC_BUF, "INODE_ALLOC" }, \
 	{ XFS_BLI_STALE_INODE,	"STALE_INODE" }, \
-	{ XFS_BLI_INODE_BUF,	"INODE_BUF" }
+	{ XFS_BLI_INODE_BUF,	"INODE_BUF" }, \
+	{ XFS_BLI_ORDERED,	"ORDERED" }
 
 
 #ifdef __KERNEL__

index e318672..ee8b3a3 100644
@@ -486,9 +486,12 @@ DEFINE_EVENT(xfs_buf_item_class, name, \
 	TP_PROTO(struct xfs_buf_log_item *bip), \
 	TP_ARGS(bip))
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size);
+DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format);
+DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale);
+DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin);
 DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale);

@@ -508,6 +511,7 @@ DEFINE_BUF_ITEM_EVENT(xfs_trans_bjoin);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release);
 DEFINE_BUF_ITEM_EVENT(xfs_trans_binval);
+DEFINE_BUF_ITEM_EVENT(xfs_trans_buf_ordered);
 
 DECLARE_EVENT_CLASS(xfs_lock_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned lock_flags,

index 6d52656..822570e 100644
@@ -498,6 +498,7 @@ void		xfs_trans_bhold_release(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_binval(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_inode_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_stale_inode_buf(xfs_trans_t *, struct xfs_buf *);
+void		xfs_trans_ordered_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_dquot_buf(xfs_trans_t *, struct xfs_buf *, uint);
 void		xfs_trans_inode_alloc_buf(xfs_trans_t *, struct xfs_buf *);
 void		xfs_trans_ichgtime(struct xfs_trans *, struct xfs_inode *, int);

index 73a5fa4..aa5a04b 100644
@@ -397,7 +397,6 @@ shutdown_abort:
 	return XFS_ERROR(EIO);
 }
 
-
 /*
  * Release the buffer bp which was previously acquired with one of the
  * xfs_trans_... buffer allocation routines if the buffer has not

@@ -603,8 +602,14 @@ xfs_trans_log_buf(xfs_trans_t	*tp,
 
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	bip->bli_item.li_desc->lid_flags |= XFS_LID_DIRTY;
-	bip->bli_flags |= XFS_BLI_LOGGED;
-	xfs_buf_item_log(bip, first, last);
+
+	/*
+	 * If we have an ordered buffer we are not logging any dirty range but
+	 * it still needs to be marked dirty and that it has been logged.
+	 */
+	bip->bli_flags |= XFS_BLI_DIRTY | XFS_BLI_LOGGED;
+	if (!(bip->bli_flags & XFS_BLI_ORDERED))
+		xfs_buf_item_log(bip, first, last);
 }
 
 

@@ -757,6 +762,29 @@ xfs_trans_inode_alloc_buf(
 }
 
 /*
+ * Mark the buffer as ordered for this transaction. This means
+ * that the contents of the buffer are not recorded in the transaction
+ * but it is tracked in the AIL as though it was. This allows us
+ * to record logical changes in transactions rather than the physical
+ * changes we make to the buffer without changing writeback ordering
+ * constraints of metadata buffers.
+ */
+void
+xfs_trans_ordered_buf(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+
+	ASSERT(bp->b_transp == tp);
+	ASSERT(bip != NULL);
+	ASSERT(atomic_read(&bip->bli_refcount) > 0);
+
+	bip->bli_flags |= XFS_BLI_ORDERED;
+	trace_xfs_buf_item_ordered(bip);
+}
+
+/*
  * Set the type of the buffer for log recovery so that it can correctly identify
  * and hence attach the correct buffer ops to the buffer after replay.
  */

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/Makefile           |    1 +
 fs/xfs/xfs_icreate_item.c |  195 +++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/xfs_icreate_item.h |   52 ++++++++++++
 fs/xfs/xfs_log.h          |    3 +-
 fs/xfs/xfs_super.c        |    8 ++
 fs/xfs/xfs_trans.h        |    4 +-
 6 files changed, 261 insertions(+), 2 deletions(-)
 create mode 100644 fs/xfs/xfs_icreate_item.c
 create mode 100644 fs/xfs/xfs_icreate_item.h
index 6313b69..4a45080 100644
@@ -71,6 +71,7 @@ xfs-y				+= xfs_alloc.o \
 				   xfs_dir2_sf.o \
 				   xfs_ialloc.o \
 				   xfs_ialloc_btree.o \
+				   xfs_icreate_item.o \
 				   xfs_inode.o \
 				   xfs_log_recover.o \
 				   xfs_mount.o \

index b20918c..fb630e4 100644
@@ -88,7 +88,8 @@ static inline xfs_lsn_t	_lsn_cmp(xfs_lsn_t lsn1, xfs_lsn_t lsn2)
 #define XLOG_REG_TYPE_UNMOUNT		17
 #define XLOG_REG_TYPE_COMMIT		18
 #define XLOG_REG_TYPE_TRANSHDR		19
-#define XLOG_REG_TYPE_MAX		19
+#define XLOG_REG_TYPE_ICREATE		20
+#define XLOG_REG_TYPE_MAX		20
 
 typedef struct xfs_log_iovec {
 	void		*i_addr;	/* beginning address of region */

index 3033ba5..f59e27f 100644
@@ -51,6 +51,7 @@
 #include "xfs_inode_item.h"
 #include "xfs_icache.h"
 #include "xfs_trace.h"
+#include "xfs_icreate_item.h"
 
 #include <linux/namei.h>
 #include <linux/init.h>

@@ -1655,9 +1656,15 @@ xfs_init_zones(void)
 					KM_ZONE_SPREAD, NULL);
 	if (!xfs_ili_zone)
 		goto out_destroy_inode_zone;
+	xfs_icreate_zone = kmem_zone_init(sizeof(struct xfs_icreate_item),
+					"xfs_icr");
+	if (!xfs_icreate_zone)
+		goto out_destroy_ili_zone;
 
 	return 0;
 
+ out_destroy_ili_zone:
+	kmem_zone_destroy(xfs_ili_zone);
  out_destroy_inode_zone:
 	kmem_zone_destroy(xfs_inode_zone);
  out_destroy_efi_zone:

@@ -1696,6 +1703,7 @@ xfs_destroy_zones(void)
 	 * destroy caches.
 	 */
 	rcu_barrier();
+	kmem_zone_destroy(xfs_icreate_zone);
 	kmem_zone_destroy(xfs_ili_zone);
 	kmem_zone_destroy(xfs_inode_zone);
 	kmem_zone_destroy(xfs_efi_zone);

index 822570e..2b49463 100644
@@ -48,6 +48,7 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_BUF		0x123c	/* v2 bufs, variable sized inode bufs */
 #define	XFS_LI_DQUOT		0x123d
 #define	XFS_LI_QUOTAOFF		0x123e
+#define	XFS_LI_ICREATE		0x123f
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \

@@ -107,7 +108,8 @@ typedef struct xfs_trans_header {
 #define	XFS_TRANS_SWAPEXT		40
 #define	XFS_TRANS_SB_COUNT		41
 #define	XFS_TRANS_CHECKPOINT		42
-#define	XFS_TRANS_TYPE_MAX		42
+#define	XFS_TRANS_ICREATE		43
+#define	XFS_TRANS_TYPE_MAX		43
 /* new transaction types need to be reflected in xfs_logprint(8) */
 
 #define XFS_TRANS_TYPES \

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_trans.c |  118 ++++++++++++++++++++++++++++++++++------------------
 1 file changed, 77 insertions(+), 41 deletions(-)
index 2fd7c1f..35a2299 100644
@@ -234,71 +234,93 @@ xfs_calc_remove_reservation(
 }
 
 /*
- * For symlink we can modify:
+ * For create, break it in to the two cases that the transaction
+ * covers. We start with the modify case - allocation done by modification
+ * of the state of existing inodes - and the allocation case.
+ */
+
+/*
+ * For create we can modify:
  *    the parent directory inode: inode size
  *    the new inode: inode size
- *    the inode btree entry: 1 block
+ *    the inode btree entry: block size
+ *    the superblock for the nlink flag: sector size
  *    the directory btree: (max depth + v2) * dir block size
  *    the directory inode's bmap btree: (max depth + v2) * block size
- *    the blocks for the symlink: 1 kB
- * Or in the first xact we allocate some inodes giving:
+ */
+STATIC uint
+xfs_calc_create_resv_modify(
+	struct xfs_mount	*mp)
+{
+	return xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
+		xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
+		(uint)XFS_FSB_TO_B(mp, 1) +
+		xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp), XFS_FSB_TO_B(mp, 1));
+}
+
+/*
+ * For create we can allocate some inodes giving:
  *    the agi and agf of the ag getting the new inodes: 2 * sectorsize
+ *    the superblock for the nlink flag: sector size
  *    the inode blocks allocated: XFS_IALLOC_BLOCKS * blocksize
  *    the inode btree: max depth * blocksize
- *    the allocation btrees: 2 trees * (2 * max depth - 1) * block size
+ *    the allocation btrees: 2 trees * (max depth - 1) * block size
  */
 STATIC uint
-xfs_calc_symlink_reservation(
+xfs_calc_create_resv_alloc(
+	struct xfs_mount	*mp)
+{
+	return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+		mp->m_sb.sb_sectsize +
+		xfs_calc_buf_res(XFS_IALLOC_BLOCKS(mp), XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+				 XFS_FSB_TO_B(mp, 1));
+}
+
+STATIC uint
+__xfs_calc_create_reservation(
 	struct xfs_mount	*mp)
 {
 	return XFS_DQUOT_LOGRES(mp) +
-		MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
-		     xfs_calc_buf_res(1, XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
-				      XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(1, 1024)),
-		    (xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
-		     xfs_calc_buf_res(XFS_IALLOC_BLOCKS(mp),
-				      XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(mp->m_in_maxlevels,
-				      XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				      XFS_FSB_TO_B(mp, 1))));
+		MAX(xfs_calc_create_resv_alloc(mp),
+		    xfs_calc_create_resv_modify(mp));
 }
 
 /*
- * For create we can modify:
- *    the parent directory inode: inode size
- *    the new inode: inode size
- *    the inode btree entry: block size
- *    the superblock for the nlink flag: sector size
- *    the directory btree: (max depth + v2) * dir block size
- *    the directory inode's bmap btree: (max depth + v2) * block size
- * Or in the first xact we allocate some inodes giving:
+ * For icreate we can allocate some inodes giving:
  *    the agi and agf of the ag getting the new inodes: 2 * sectorsize
  *    the superblock for the nlink flag: sector size
- *    the inode blocks allocated: XFS_IALLOC_BLOCKS * blocksize
  *    the inode btree: max depth * blocksize
  *    the allocation btrees: 2 trees * (max depth - 1) * block size
  */
 STATIC uint
-xfs_calc_create_reservation(
+xfs_calc_icreate_resv_alloc(
 	struct xfs_mount	*mp)
 {
+	return xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
+		mp->m_sb.sb_sectsize +
+		xfs_calc_buf_res(mp->m_in_maxlevels, XFS_FSB_TO_B(mp, 1)) +
+		xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
+				 XFS_FSB_TO_B(mp, 1));
+}
+
+STATIC uint
+xfs_calc_icreate_reservation(xfs_mount_t *mp)
+{
 	return XFS_DQUOT_LOGRES(mp) +
-		MAX((xfs_calc_buf_res(2, mp->m_sb.sb_inodesize) +
-		     xfs_calc_buf_res(1, mp->m_sb.sb_sectsize) +
-		     (uint)XFS_FSB_TO_B(mp, 1) +
-		     xfs_calc_buf_res(XFS_DIROP_LOG_COUNT(mp),
-				      XFS_FSB_TO_B(mp, 1))),
-		    (xfs_calc_buf_res(2, mp->m_sb.sb_sectsize) +
-		     mp->m_sb.sb_sectsize +
-		     xfs_calc_buf_res(XFS_IALLOC_BLOCKS(mp),
-				      XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(mp->m_in_maxlevels,
-				      XFS_FSB_TO_B(mp, 1)) +
-		     xfs_calc_buf_res(XFS_ALLOCFREE_LOG_COUNT(mp, 1),
-				      XFS_FSB_TO_B(mp, 1))));
+		MAX(xfs_calc_icreate_resv_alloc(mp),
+		    xfs_calc_create_resv_modify(mp));
+}
+
+STATIC uint
+xfs_calc_create_reservation(
+	struct xfs_mount	*mp)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return xfs_calc_icreate_reservation(mp);
+	return __xfs_calc_create_reservation(mp);
+
 }
 
 /*

@@ -311,6 +333,20 @@ xfs_calc_mkdir_reservation(
 	return xfs_calc_create_reservation(mp);
 }
 
+
+/*
+ * Making a new symplink is the same as creating a new file, but
+ * with the added blocks for remote symlink data which can be up to 1kB in
+ * length (MAXPATHLEN).
+ */
+STATIC uint
+xfs_calc_symlink_reservation(
+	struct xfs_mount	*mp)
+{
+	return xfs_calc_create_reservation(mp) +
+	       xfs_calc_buf_res(1, MAXPATHLEN);
+}
+
 /*
  * In freeing an inode we can modify:
  *    the inode being freed: inode size

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_ialloc.c      |   37 +++++++++++----
 fs/xfs/xfs_ialloc.h      |    8 ++++
 fs/xfs/xfs_log_recover.c |  114 ++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 145 insertions(+), 14 deletions(-)
index c8f5ae1..d5ef81a 100644
@@ -150,12 +150,16 @@ xfs_check_agi_freecount(
 #endif
 
 /*
- * Initialise a new set of inodes.
+ * Initialise a new set of inodes. When called without a transaction context
+ * (e.g. from recovery) we initiate a delayed write of the inode buffers rather
+ * than logging them (which in a transaction context puts them into the AIL
+ * for writeback rather than the xfsbufd queue).
  */
 STATIC int
 xfs_ialloc_inode_init(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
+	struct list_head	*buffer_list,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		agbno,
 	xfs_agblock_t		length,

@@ -247,18 +251,33 @@ xfs_ialloc_inode_init(
 				ino++;
 				uuid_copy(&free->di_uuid, &mp->m_sb.sb_uuid);
 				xfs_dinode_calc_crc(mp, free);
-			} else {
+			} else if (tp) {
 				/* just log the inode core */
 				xfs_trans_log_buf(tp, fbuf, ioffset,
 						  ioffset + isize - 1);
 			}
 		}
-		if (version == 3) {
-			/* need to log the entire buffer */
-			xfs_trans_log_buf(tp, fbuf, 0,
-					  BBTOB(fbuf->b_length) - 1);
+
+		if (tp) {
+			/*
+			 * Mark the buffer as an inode allocation buffer so it
+			 * sticks in AIL at the point of this allocation
+			 * transaction. This ensures the they are on disk before
+			 * the tail of the log can be moved past this
+			 * transaction (i.e. by preventing relogging from moving
+			 * it forward in the log).
+			 */
+			xfs_trans_inode_alloc_buf(tp, fbuf);
+			if (version == 3) {
+				/* need to log the entire buffer */
+				xfs_trans_log_buf(tp, fbuf, 0,
+						  BBTOB(fbuf->b_length) - 1);
+			}
+		} else {
+			fbuf->b_flags |= XBF_DONE;
+			xfs_buf_delwri_queue(fbuf, buffer_list);
+			xfs_buf_relse(fbuf);
 		}
-		xfs_trans_inode_alloc_buf(tp, fbuf);
 	}
 	return 0;
 }

@@ -303,7 +322,7 @@ xfs_ialloc_ag_alloc(
 	 * First try to allocate inodes contiguous with the last-allocated
 	 * chunk of inodes.  If the filesystem is striped, this will fill
 	 * an entire stripe unit with inodes.
- 	 */
+	 */
 	agi = XFS_BUF_TO_AGI(agbp);
 	newino = be32_to_cpu(agi->agi_newino);
 	agno = be32_to_cpu(agi->agi_seqno);

@@ -402,7 +421,7 @@ xfs_ialloc_ag_alloc(
 	 * rather than a linear progression to prevent the next generation
 	 * number from being easily guessable.
 	 */
-	error = xfs_ialloc_inode_init(args.mp, tp, agno, args.agbno,
+	error = xfs_ialloc_inode_init(args.mp, tp, NULL, agno, args.agbno,
 			args.len, prandom_u32());
 
 	if (error)

index c8da3df..68c0732 100644
@@ -150,6 +150,14 @@ int xfs_inobt_lookup(struct xfs_btree_cur *cur, xfs_agino_t ino,
 int xfs_inobt_get_rec(struct xfs_btree_cur *cur,
 		xfs_inobt_rec_incore_t *rec, int *stat);
 
+/*
+ * Inode chunk initialisation routine
+ */
+int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
+			  struct list_head *buffer_list,
+			  xfs_agnumber_t agno, xfs_agblock_t agbno,
+			  xfs_agblock_t length, unsigned int gen);
+
 extern const struct xfs_buf_ops xfs_agi_buf_ops;
 
 #endif	/* __XFS_IALLOC_H__ */

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_buf_item.c |   12 ++++++++++--
 fs/xfs/xfs_ialloc.c   |   32 +++++++++++++++++++++++---------
 2 files changed, 33 insertions(+), 11 deletions(-)
index 61f6876..bfc4e0c 100644
@@ -310,13 +310,21 @@ xfs_buf_item_format(
 
 	/*
 	 * If it is an inode buffer, transfer the in-memory state to the
-	 * format flags and clear the in-memory state. We do not transfer
+	 * format flags and clear the in-memory state.
+	 *
+	 * For buffer based inode allocation, we do not transfer
 	 * this state if the inode buffer allocation has not yet been committed
 	 * to the log as setting the XFS_BLI_INODE_BUF flag will prevent
 	 * correct replay of the inode allocation.
+	 *
+	 * For icreate item based inode allocation, the buffers aren't written
+	 * to the journal during allocation, and hence we should always tag the
+	 * buffer as an inode buffer so that the correct unlinked list replay
+	 * occurs during recovery.
 	 */
 	if (bip->bli_flags & XFS_BLI_INODE_BUF) {
-		if (!((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
+		if (xfs_sb_version_hascrc(&lip->li_mountp->m_sb) ||
+		    !((bip->bli_flags & XFS_BLI_INODE_ALLOC_BUF) &&
 		      xfs_log_item_in_current_chkpt(lip)))
 			bip->__bli_format.blf_flags |= XFS_BLF_INODE_BUF;
 		bip->bli_flags &= ~XFS_BLI_INODE_BUF;

index d5ef81a..319d9e4 100644
@@ -38,6 +38,7 @@
 #include "xfs_bmap.h"
 #include "xfs_cksum.h"
 #include "xfs_buf_item.h"
+#include "xfs_icreate_item.h"
 
 
 /*

@@ -155,7 +156,7 @@ xfs_check_agi_freecount(
  * than logging them (which in a transaction context puts them into the AIL
  * for writeback rather than the xfsbufd queue).
  */
-STATIC int
+int
 xfs_ialloc_inode_init(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,

@@ -212,6 +213,18 @@ xfs_ialloc_inode_init(
 		version = 3;
 		ino = XFS_AGINO_TO_INO(mp, agno,
 				       XFS_OFFBNO_TO_AGINO(mp, agbno, 0));
+
+		/*
+		 * log the initialisation that is about to take place as an
+		 * logical operation. This means the transaction does not
+		 * need to log the physical changes to the inode buffers as log
+		 * recovery will know what initialisation is actually needed.
+		 * Hence we only need to log the buffers as "ordered" buffers so
+		 * they track in the AIL as if they were physically logged.
+		 */
+		if (tp)
+			xfs_icreate_log(tp, agno, agbno, XFS_IALLOC_INODES(mp),
+					mp->m_sb.sb_inodesize, length, gen);
 	} else if (xfs_sb_version_hasnlink(&mp->m_sb))
 		version = 2;
 	else

@@ -227,13 +240,8 @@ xfs_ialloc_inode_init(
 					 XBF_UNMAPPED);
 		if (!fbuf)
 			return ENOMEM;
-		/*
-		 * Initialize all inodes in this buffer and then log them.
-		 *
-		 * XXX: It would be much better if we had just one transaction
-		 *	to log a whole cluster of inodes instead of all the
-		 *	individual transactions causing a lot of log traffic.
-		 */
+
+		/* Initialize the inode buffers and log them appropriately. */
 		fbuf->b_ops = &xfs_inode_buf_ops;
 		xfs_buf_zero(fbuf, 0, BBTOB(fbuf->b_length));
 		for (i = 0; i < ninodes; i++) {

@@ -269,7 +277,13 @@ xfs_ialloc_inode_init(
 			 */
 			xfs_trans_inode_alloc_buf(tp, fbuf);
 			if (version == 3) {
-				/* need to log the entire buffer */
+				/*
+				 * Mark the buffer as ordered so that they are
+				 * not physically logged in the transaction but
+				 * still tracked in the AIL as part of the
+				 * transaction and pin the log appropriately.
+				 */
+				xfs_trans_ordered_buf(tp, fbuf);
 				xfs_trans_log_buf(tp, fbuf, 0,
 						  BBTOB(fbuf->b_length) - 1);
 			}

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_attr_leaf.c  |    2 +
 fs/xfs/xfs_bmap.c       |  199 ++++++++++++++++++++---------------------------
 fs/xfs/xfs_bmap.h       |    1 +
 fs/xfs/xfs_dir2_block.c |   20 +++--
 4 files changed, 98 insertions(+), 124 deletions(-)
index 31d3cd1..b800fbc 100644
@@ -690,6 +690,8 @@ xfs_attr_shortform_to_leaf(xfs_da_args_t *args)
 	sf = (xfs_attr_shortform_t *)tmpbuffer;
 
 	xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
+	xfs_bmap_local_to_extents_empty(dp, XFS_ATTR_FORK);
+
 	bp = NULL;
 	error = xfs_da_grow_inode(args, &blkno);
 	if (error) {

index 5f469c3..1cf1292 100644
@@ -172,6 +172,7 @@ void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 #endif
 
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
+void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(xfs_fsblock_t bno, xfs_filblks_t len,
 		struct xfs_bmap_free *flist, struct xfs_mount *mp);
 void	xfs_bmap_cancel(struct xfs_bmap_free *flist);

index e59f5fc..53b9aa2 100644
@@ -29,6 +29,7 @@
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
 #include "xfs_inode_item.h"
+#include "xfs_bmap.h"
 #include "xfs_buf_item.h"
 #include "xfs_dir2.h"
 #include "xfs_dir2_format.h"

@@ -1167,13 +1168,15 @@ xfs_dir2_sf_to_block(
 	__be16			*tagp;		/* end of data entry */
 	xfs_trans_t		*tp;		/* transaction pointer */
 	struct xfs_name		name;
+	struct xfs_ifork	*ifp;
 
 	trace_xfs_dir2_sf_to_block(args);
 
 	dp = args->dp;
 	tp = args->trans;
 	mp = dp->i_mount;
-	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
+	ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+	ASSERT(ifp->if_flags & XFS_IFINLINE);
 	/*
 	 * Bomb out if the shortform directory is way too short.
 	 */

@@ -1182,22 +1185,23 @@ xfs_dir2_sf_to_block(
 		return XFS_ERROR(EIO);
 	}
 
-	oldsfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
+	oldsfp = (xfs_dir2_sf_hdr_t *)ifp->if_u1.if_data;
 
-	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
-	ASSERT(dp->i_df.if_u1.if_data != NULL);
+	ASSERT(ifp->if_bytes == dp->i_d.di_size);
+	ASSERT(ifp->if_u1.if_data != NULL);
 	ASSERT(dp->i_d.di_size >= xfs_dir2_sf_hdr_size(oldsfp->i8count));
+	ASSERT(dp->i_d.di_nextents == 0);
 
 	/*
 	 * Copy the directory into a temporary buffer.
 	 * Then pitch the incore inode data so we can make extents.
 	 */
-	sfp = kmem_alloc(dp->i_df.if_bytes, KM_SLEEP);
-	memcpy(sfp, oldsfp, dp->i_df.if_bytes);
+	sfp = kmem_alloc(ifp->if_bytes, KM_SLEEP);
+	memcpy(sfp, oldsfp, ifp->if_bytes);
 
-	xfs_idata_realloc(dp, -dp->i_df.if_bytes, XFS_DATA_FORK);
+	xfs_idata_realloc(dp, -ifp->if_bytes, XFS_DATA_FORK);
+	xfs_bmap_local_to_extents_empty(dp, XFS_DATA_FORK);
 	dp->i_d.di_size = 0;
-	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
 	/*
 	 * Add block 0 to the inode.

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_quota.h       |   26 ++++++++++++++++++++++----
 fs/xfs/xfs_trans_dquot.c |    9 ++++-----
 2 files changed, 26 insertions(+), 9 deletions(-)
index c38068f..aa4ec5a 100644
@@ -108,11 +108,29 @@ typedef struct xfs_dqblk {
 	{ XFS_DQ_FREEING,	"FREEING" }
 
 /*
- * In the worst case, when both user and group quotas are on,
- * we can have a max of three dquots changing in a single transaction.
+ * We have the possibility of all three quota types being active at once,
+ * and hence free space modification requires modify all three current dquots in
+ * a single transaction.  For this case, we need to have a reservation of at
+ * least 3 dquots.
+ *
+ * However, a chmod operation can change both UID and GID in the one
+ * transaction, resulting in requiring {old, new} x {uid, gid} dquots to be
+ * modified. This means we need to reserve space for at least 4 dquots are the
+ * worst case reservation.
+ *
+ * And in the worst case, there's a rename operation that can be modifying up to
+ * 4 inodes with dquots attached to them. In reality, the only inodes that can
+ * have their dquots modified are the source and destination directory inodes
+ * due to directory name creation and removal. That can require space allocation
+ * and/or freeing on both directory inodes, and hence all three dquots on each
+ * inode can be modified. And if the directories are world writeable, all the
+ * dquots can be unique and so 6 dquots can be modified....
+ *
+ * And, of course, we also need to take into account the dquot log format item
+ * used to describe each dquot.
  */
-#define XFS_DQUOT_LOGRES(mp)	(sizeof(xfs_disk_dquot_t) * 3)
-
+#define XFS_DQUOT_LOGRES(mp)	\
+	((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6)
 
 /*
  * These are the structures used to lay out dquots and quotaoff

index fec75d0..076cc25 100644
@@ -292,11 +292,10 @@ xfs_trans_mod_dquot(
 
 
 /*
- * Given an array of dqtrx structures, lock all the dquots associated
- * and join them to the transaction, provided they have been modified.
- * We know that the highest number of dquots (of one type - usr OR grp),
- * involved in a transaction is 2 and that both usr and grp combined - 3.
- * So, we don't attempt to make this very generic.
+ * Given an array of dqtrx structures, lock all the dquots associated and join
+ * them to the transaction, provided they have been modified.  We know that the
+ * highest number of dquots of one type - usr, grp OR prj - involved in a
+ * transaction is 2 so we don't need to make this very generic.
  */
 STATIC void
 xfs_trans_dqlockedjoin(

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_quota.h       |   26 ++++++++++++++++++++++----
 fs/xfs/xfs_trans_dquot.c |    9 ++++-----
 2 files changed, 26 insertions(+), 9 deletions(-)
index c38068f..aa4ec5a 100644

@@ -108,11 +108,29 @@ typedef struct xfs_dqblk {
 	{ XFS_DQ_FREEING,	"FREEING" }
 
 /*
- * In the worst case, when both user and group quotas are on,
- * we can have a max of three dquots changing in a single transaction.
+ * We have the possibility of all three quota types being active at once,
+ * and hence free space modification requires modify all three current dquots in

+ * a single transaction.  For this case, we need to have a reservation of at
+ * least 3 dquots.
+ *
+ * However, a chmod operation can change both UID and GID in the one

+ * transaction, resulting in requiring {old, new} x {uid, gid} dquots to be
+ * modified. This means we need to reserve space for at least 4 dquots are the

+ * worst case reservation.

+ *
+ * And in the worst case, there's a rename operation that can be modifying up to
+ * 4 inodes with dquots attached to them. In reality, the only inodes that can
+ * have their dquots modified are the source and destination directory inodes
+ * due to directory name creation and removal. That can require space allocation
+ * and/or freeing on both directory inodes, and hence all three dquots on each
+ * inode can be modified. And if the directories are world writeable, all the
+ * dquots can be unique and so 6 dquots can be modified....
+ *
+ * And, of course, we also need to take into account the dquot log format item
+ * used to describe each dquot.
  */
-#define XFS_DQUOT_LOGRES(mp)	(sizeof(xfs_disk_dquot_t) * 3)
-
+#define XFS_DQUOT_LOGRES(mp)	\
+	((sizeof(struct xfs_dq_logformat) + sizeof(struct xfs_disk_dquot)) * 6)
 
 /*
  * These are the structures used to lay out dquots and quotaoff

index fec75d0..076cc25 100644
@@ -292,11 +292,10 @@ xfs_trans_mod_dquot(
 
 

 /*
- * Given an array of dqtrx structures, lock all the dquots associated
- * and join them to the transaction, provided they have been modified.
- * We know that the highest number of dquots (of one type - usr OR grp),
- * involved in a transaction is 2 and that both usr and grp combined - 3.
- * So, we don't attempt to make this very generic.
+ * Given an array of dqtrx structures, lock all the dquots associated and join
+ * them to the transaction, provided they have been modified.  We know that the
+ * highest number of dquots of one type - usr, grp OR prj - involved in a
+ * transaction is 2 so we don't need to make this very generic.

  */
 STATIC void
 xfs_trans_dqlockedjoin(

Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
Dave Chinner
[email protected]

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_super.c       |    4 ++++
 fs/xfs/xfs_trans_inode.c |   11 +++++++++++
 2 files changed, 15 insertions(+)
index f59e27f..a1587f9 100644
@@ -1482,6 +1482,10 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
+	/* version 5 superblocks support inode version counters. */
+	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+		sb->s_flags |= MS_I_VERSION;
+
 	error = xfs_mountfs(mp);
 	if (error)
 		goto out_filestream_unmount;

index ac6d567..53dfe46 100644
@@ -112,6 +112,17 @@ xfs_trans_log_inode(
 	ASSERT(ip->i_itemp != NULL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
+	/*
+	 * First time we log the inode in a transaction, bump the inode change
+	 * counter if it is configured for this to occur.
+	 */
+	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
+	    IS_I_VERSION(VFS_I(ip))) {
+		inode_inc_iversion(VFS_I(ip));
+		ip->i_d.di_changecount = VFS_I(ip)->i_version;
+		flags |= XFS_ILOG_CORE;
+	}
+
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
 

1.7.10.4

_______________________________________________
xfs mailing list
[email protected]
http://oss.sgi.com/mailman/listinfo/xfs
---
 fs/xfs/xfs_super.c       |    4 ++++
 fs/xfs/xfs_trans_inode.c |   11 +++++++++++
 2 files changed, 15 insertions(+)
index f59e27f..a1587f9 100644
@@ -1482,6 +1482,10 @@ xfs_fs_fill_super(
 	sb->s_time_gran = 1;
 	set_posix_acl_flag(sb);
 
+	/* version 5 superblocks support inode version counters. */
+	if (XFS_SB_VERSION_NUM(&mp->m_sb) == XFS_SB_VERSION_5)
+		sb->s_flags |= MS_I_VERSION;
+
 	error = xfs_mountfs(mp);
 	if (error)
 		goto out_filestream_unmount;

index ac6d567..53dfe46 100644
@@ -112,6 +112,17 @@ xfs_trans_log_inode(
 	ASSERT(ip->i_itemp != NULL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
+	/*
+	 * First time we log the inode in a transaction, bump the inode change
+	 * counter if it is configured for this to occur.
+	 */

+	if (!(ip->i_itemp->ili_item.li_desc->lid_flags & XFS_LID_DIRTY) &&
+	    IS_I_VERSION(VFS_I(ip))) {
+		inode_inc_iversion(VFS_I(ip));
+		ip->i_d.di_changecount = VFS_I(ip)->i_version;
+		flags |= XFS_ILOG_CORE;
+	}
+
 	tp->t_flags |= XFS_TRANS_DIRTY;
 	ip->i_itemp->ili_item.li_desc->lid_flags |= XFS_LID_DIRTY;
 


xfs: patchset for 3.11

Dave Chinner

Dave Chinner

Ben Myers

Ben Myers

Dave Chinner

Dave Chinner

Geoffrey Wehrman

Eric Sandeen

Geoffrey Wehrman

Ric Wheeler

Ben Myers

Dave Chinner

Eric Sandeen

Ben Myers

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Dave Chinner

Mark Tinguely

Chandra Seetharaman

Dave Chinner

Ben Myers

Dave Chinner

Ben Myers

Dave Chinner

Mark Tinguely

Chandra Seetharaman

Ben Myers

Ben Myers