2010-05-29 00:45:14 +04:00
|
|
|
/*
|
|
|
|
|
* CDDL HEADER START
|
|
|
|
|
*
|
|
|
|
|
* The contents of this file are subject to the terms of the
|
|
|
|
|
* Common Development and Distribution License (the "License").
|
|
|
|
|
* You may not use this file except in compliance with the License.
|
|
|
|
|
*
|
|
|
|
|
* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
|
|
|
|
|
* or http://www.opensolaris.org/os/licensing.
|
|
|
|
|
* See the License for the specific language governing permissions
|
|
|
|
|
* and limitations under the License.
|
|
|
|
|
*
|
|
|
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
|
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
|
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
|
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
|
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
|
|
|
*
|
|
|
|
|
* CDDL HEADER END
|
|
|
|
|
*/
|
|
|
|
|
/*
|
|
|
|
|
* Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved.
|
|
|
|
|
*/
|
|
|
|
|
|
2015-04-02 06:44:32 +03:00
|
|
|
#include <sys/zfs_context.h>
|
2010-05-29 00:45:14 +04:00
|
|
|
#include <sys/vnode.h>
|
|
|
|
|
#include <sys/sa.h>
|
|
|
|
|
#include <sys/zfs_acl.h>
|
|
|
|
|
#include <sys/zfs_sa.h>
|
|
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* ZPL attribute registration table.
|
|
|
|
|
* Order of attributes doesn't matter
|
|
|
|
|
* a unique value will be assigned for each
|
|
|
|
|
* attribute that is file system specific
|
|
|
|
|
*
|
|
|
|
|
* This is just the set of ZPL attributes that this
|
|
|
|
|
* version of ZFS deals with natively. The file system
|
|
|
|
|
* could have other attributes stored in files, but they will be
|
|
|
|
|
* ignored. The SA framework will preserve them, just that
|
|
|
|
|
* this version of ZFS won't change or delete them.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
sa_attr_reg_t zfs_attr_table[ZPL_END+1] = {
|
|
|
|
|
{"ZPL_ATIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 0},
|
|
|
|
|
{"ZPL_MTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 1},
|
|
|
|
|
{"ZPL_CTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 2},
|
|
|
|
|
{"ZPL_CRTIME", sizeof (uint64_t) * 2, SA_UINT64_ARRAY, 3},
|
|
|
|
|
{"ZPL_GEN", sizeof (uint64_t), SA_UINT64_ARRAY, 4},
|
|
|
|
|
{"ZPL_MODE", sizeof (uint64_t), SA_UINT64_ARRAY, 5},
|
|
|
|
|
{"ZPL_SIZE", sizeof (uint64_t), SA_UINT64_ARRAY, 6},
|
|
|
|
|
{"ZPL_PARENT", sizeof (uint64_t), SA_UINT64_ARRAY, 7},
|
|
|
|
|
{"ZPL_LINKS", sizeof (uint64_t), SA_UINT64_ARRAY, 8},
|
|
|
|
|
{"ZPL_XATTR", sizeof (uint64_t), SA_UINT64_ARRAY, 9},
|
|
|
|
|
{"ZPL_RDEV", sizeof (uint64_t), SA_UINT64_ARRAY, 10},
|
|
|
|
|
{"ZPL_FLAGS", sizeof (uint64_t), SA_UINT64_ARRAY, 11},
|
|
|
|
|
{"ZPL_UID", sizeof (uint64_t), SA_UINT64_ARRAY, 12},
|
|
|
|
|
{"ZPL_GID", sizeof (uint64_t), SA_UINT64_ARRAY, 13},
|
|
|
|
|
{"ZPL_PAD", sizeof (uint64_t) * 4, SA_UINT64_ARRAY, 14},
|
|
|
|
|
{"ZPL_ZNODE_ACL", 88, SA_UINT8_ARRAY, 15},
|
|
|
|
|
{"ZPL_DACL_COUNT", sizeof (uint64_t), SA_UINT64_ARRAY, 0},
|
|
|
|
|
{"ZPL_SYMLINK", 0, SA_UINT8_ARRAY, 0},
|
|
|
|
|
{"ZPL_SCANSTAMP", 32, SA_UINT8_ARRAY, 0},
|
|
|
|
|
{"ZPL_DACL_ACES", 0, SA_ACL, 0},
|
2011-10-25 03:55:20 +04:00
|
|
|
{"ZPL_DXATTR", 0, SA_UINT8_ARRAY, 0},
|
2010-05-29 00:45:14 +04:00
|
|
|
{NULL, 0, 0, 0}
|
|
|
|
|
};
|
|
|
|
|
|
|
|
|
|
#ifdef _KERNEL
|
|
|
|
|
int
|
|
|
|
|
zfs_sa_readlink(znode_t *zp, uio_t *uio)
|
|
|
|
|
{
|
|
|
|
|
dmu_buf_t *db = sa_get_db(zp->z_sa_hdl);
|
|
|
|
|
size_t bufsz;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
bufsz = zp->z_size;
|
|
|
|
|
if (bufsz + ZFS_OLD_ZNODE_PHYS_SIZE <= db->db_size) {
|
|
|
|
|
error = uiomove((caddr_t)db->db_data +
|
|
|
|
|
ZFS_OLD_ZNODE_PHYS_SIZE,
|
|
|
|
|
MIN((size_t)bufsz, uio->uio_resid), UIO_READ, uio);
|
|
|
|
|
} else {
|
|
|
|
|
dmu_buf_t *dbp;
|
2011-02-08 22:16:06 +03:00
|
|
|
if ((error = dmu_buf_hold(ZTOZSB(zp)->z_os, zp->z_id,
|
2010-05-29 00:45:14 +04:00
|
|
|
0, FTAG, &dbp, DMU_READ_NO_PREFETCH)) == 0) {
|
|
|
|
|
error = uiomove(dbp->db_data,
|
|
|
|
|
MIN((size_t)bufsz, uio->uio_resid), UIO_READ, uio);
|
|
|
|
|
dmu_buf_rele(dbp, FTAG);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
return (error);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
zfs_sa_symlink(znode_t *zp, char *link, int len, dmu_tx_t *tx)
|
|
|
|
|
{
|
|
|
|
|
dmu_buf_t *db = sa_get_db(zp->z_sa_hdl);
|
|
|
|
|
|
|
|
|
|
if (ZFS_OLD_ZNODE_PHYS_SIZE + len <= dmu_bonus_max()) {
|
Implement large_dnode pool feature
Justification
-------------
This feature adds support for variable length dnodes. Our motivation is
to eliminate the overhead associated with using spill blocks. Spill
blocks are used to store system attribute data (i.e. file metadata) that
does not fit in the dnode's bonus buffer. By allowing a larger bonus
buffer area the use of a spill block can be avoided. Spill blocks
potentially incur an additional read I/O for every dnode in a dnode
block. As a worst case example, reading 32 dnodes from a 16k dnode block
and all of the spill blocks could issue 33 separate reads. Now suppose
those dnodes have size 1024 and therefore don't need spill blocks. Then
the worst case number of blocks read is reduced to from 33 to two--one
per dnode block. In practice spill blocks may tend to be co-located on
disk with the dnode blocks so the reduction in I/O would not be this
drastic. In a badly fragmented pool, however, the improvement could be
significant.
ZFS-on-Linux systems that make heavy use of extended attributes would
benefit from this feature. In particular, ZFS-on-Linux supports the
xattr=sa dataset property which allows file extended attribute data
to be stored in the dnode bonus buffer as an alternative to the
traditional directory-based format. Workloads such as SELinux and the
Lustre distributed filesystem often store enough xattr data to force
spill bocks when xattr=sa is in effect. Large dnodes may therefore
provide a performance benefit to such systems.
Other use cases that may benefit from this feature include files with
large ACLs and symbolic links with long target names. Furthermore,
this feature may be desirable on other platforms in case future
applications or features are developed that could make use of a
larger bonus buffer area.
Implementation
--------------
The size of a dnode may be a multiple of 512 bytes up to the size of
a dnode block (currently 16384 bytes). A dn_extra_slots field was
added to the current on-disk dnode_phys_t structure to describe the
size of the physical dnode on disk. The 8 bits for this field were
taken from the zero filled dn_pad2 field. The field represents how
many "extra" dnode_phys_t slots a dnode consumes in its dnode block.
This convention results in a value of 0 for 512 byte dnodes which
preserves on-disk format compatibility with older software.
Similarly, the in-memory dnode_t structure has a new dn_num_slots field
to represent the total number of dnode_phys_t slots consumed on disk.
Thus dn->dn_num_slots is 1 greater than the corresponding
dnp->dn_extra_slots. This difference in convention was adopted
because, unlike on-disk structures, backward compatibility is not a
concern for in-memory objects, so we used a more natural way to
represent size for a dnode_t.
The default size for newly created dnodes is determined by the value of
a new "dnodesize" dataset property. By default the property is set to
"legacy" which is compatible with older software. Setting the property
to "auto" will allow the filesystem to choose the most suitable dnode
size. Currently this just sets the default dnode size to 1k, but future
code improvements could dynamically choose a size based on observed
workload patterns. Dnodes of varying sizes can coexist within the same
dataset and even within the same dnode block. For example, to enable
automatically-sized dnodes, run
# zfs set dnodesize=auto tank/fish
The user can also specify literal values for the dnodesize property.
These are currently limited to powers of two from 1k to 16k. The
power-of-2 limitation is only for simplicity of the user interface.
Internally the implementation can handle any multiple of 512 up to 16k,
and consumers of the DMU API can specify any legal dnode value.
The size of a new dnode is determined at object allocation time and
stored as a new field in the znode in-memory structure. New DMU
interfaces are added to allow the consumer to specify the dnode size
that a newly allocated object should use. Existing interfaces are
unchanged to avoid having to update every call site and to preserve
compatibility with external consumers such as Lustre. The new
interfaces names are given below. The versions of these functions that
don't take a dnodesize parameter now just call the _dnsize() versions
with a dnodesize of 0, which means use the legacy dnode size.
New DMU interfaces:
dmu_object_alloc_dnsize()
dmu_object_claim_dnsize()
dmu_object_reclaim_dnsize()
New ZAP interfaces:
zap_create_dnsize()
zap_create_norm_dnsize()
zap_create_flags_dnsize()
zap_create_claim_norm_dnsize()
zap_create_link_dnsize()
The constant DN_MAX_BONUSLEN is renamed to DN_OLD_MAX_BONUSLEN. The
spa_maxdnodesize() function should be used to determine the maximum
bonus length for a pool.
These are a few noteworthy changes to key functions:
* The prototype for dnode_hold_impl() now takes a "slots" parameter.
When the DNODE_MUST_BE_FREE flag is set, this parameter is used to
ensure the hole at the specified object offset is large enough to
hold the dnode being created. The slots parameter is also used
to ensure a dnode does not span multiple dnode blocks. In both of
these cases, if a failure occurs, ENOSPC is returned. Keep in mind,
these failure cases are only possible when using DNODE_MUST_BE_FREE.
If the DNODE_MUST_BE_ALLOCATED flag is set, "slots" must be 0.
dnode_hold_impl() will check if the requested dnode is already
consumed as an extra dnode slot by an large dnode, in which case
it returns ENOENT.
* The function dmu_object_alloc() advances to the next dnode block
if dnode_hold_impl() returns an error for a requested object.
This is because the beginning of the next dnode block is the only
location it can safely assume to either be a hole or a valid
starting point for a dnode.
* dnode_next_offset_level() and other functions that iterate
through dnode blocks may no longer use a simple array indexing
scheme. These now use the current dnode's dn_num_slots field to
advance to the next dnode in the block. This is to ensure we
properly skip the current dnode's bonus area and don't interpret it
as a valid dnode.
zdb
---
The zdb command was updated to display a dnode's size under the
"dnsize" column when the object is dumped.
For ZIL create log records, zdb will now display the slot count for
the object.
ztest
-----
Ztest chooses a random dnodesize for every newly created object. The
random distribution is more heavily weighted toward small dnodes to
better simulate real-world datasets.
Unused bonus buffer space is filled with non-zero values computed from
the object number, dataset id, offset, and generation number. This
helps ensure that the dnode traversal code properly skips the interior
regions of large dnodes, and that these interior regions are not
overwritten by data belonging to other dnodes. A new test visits each
object in a dataset. It verifies that the actual dnode size matches what
was stored in the ztest block tag when it was created. It also verifies
that the unused bonus buffer space is filled with the expected data
patterns.
ZFS Test Suite
--------------
Added six new large dnode-specific tests, and integrated the dnodesize
property into existing tests for zfs allow and send/recv.
Send/Receive
------------
ZFS send streams for datasets containing large dnodes cannot be received
on pools that don't support the large_dnode feature. A send stream with
large dnodes sets a DMU_BACKUP_FEATURE_LARGE_DNODE flag which will be
unrecognized by an incompatible receiving pool so that the zfs receive
will fail gracefully.
While not implemented here, it may be possible to generate a
backward-compatible send stream from a dataset containing large
dnodes. The implementation may be tricky, however, because the send
object record for a large dnode would need to be resized to a 512
byte dnode, possibly kicking in a spill block in the process. This
means we would need to construct a new SA layout and possibly
register it in the SA layout object. The SA layout is normally just
sent as an ordinary object record. But if we are constructing new
layouts while generating the send stream we'd have to build the SA
layout object dynamically and send it at the end of the stream.
For sending and receiving between pools that do support large dnodes,
the drr_object send record type is extended with a new field to store
the dnode slot count. This field was repurposed from unused padding
in the structure.
ZIL Replay
----------
The dnode slot count is stored in the uppermost 8 bits of the lr_foid
field. The bits were unused as the object id is currently capped at
48 bits.
Resizing Dnodes
---------------
It should be possible to resize a dnode when it is dirtied if the
current dnodesize dataset property differs from the dnode's size, but
this functionality is not currently implemented. Clearly a dnode can
only grow if there are sufficient contiguous unused slots in the
dnode block, but it should always be possible to shrink a dnode.
Growing dnodes may be useful to reduce fragmentation in a pool with
many spill blocks in use. Shrinking dnodes may be useful to allow
sending a dataset to a pool that doesn't support the large_dnode
feature.
Feature Reference Counting
--------------------------
The reference count for the large_dnode pool feature tracks the
number of datasets that have ever contained a dnode of size larger
than 512 bytes. The first time a large dnode is created in a dataset
the dataset is converted to an extensible dataset. This is a one-way
operation and the only way to decrement the feature count is to
destroy the dataset, even if the dataset no longer contains any large
dnodes. The complexity of reference counting on a per-dnode basis was
too high, so we chose to track it on a per-dataset basis similarly to
the large_block feature.
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3542
2016-03-17 04:25:34 +03:00
|
|
|
VERIFY0(dmu_set_bonus(db, len + ZFS_OLD_ZNODE_PHYS_SIZE, tx));
|
2010-05-29 00:45:14 +04:00
|
|
|
if (len) {
|
|
|
|
|
bcopy(link, (caddr_t)db->db_data +
|
|
|
|
|
ZFS_OLD_ZNODE_PHYS_SIZE, len);
|
|
|
|
|
}
|
|
|
|
|
} else {
|
|
|
|
|
dmu_buf_t *dbp;
|
|
|
|
|
|
|
|
|
|
zfs_grow_blocksize(zp, len, tx);
|
Implement large_dnode pool feature
Justification
-------------
This feature adds support for variable length dnodes. Our motivation is
to eliminate the overhead associated with using spill blocks. Spill
blocks are used to store system attribute data (i.e. file metadata) that
does not fit in the dnode's bonus buffer. By allowing a larger bonus
buffer area the use of a spill block can be avoided. Spill blocks
potentially incur an additional read I/O for every dnode in a dnode
block. As a worst case example, reading 32 dnodes from a 16k dnode block
and all of the spill blocks could issue 33 separate reads. Now suppose
those dnodes have size 1024 and therefore don't need spill blocks. Then
the worst case number of blocks read is reduced to from 33 to two--one
per dnode block. In practice spill blocks may tend to be co-located on
disk with the dnode blocks so the reduction in I/O would not be this
drastic. In a badly fragmented pool, however, the improvement could be
significant.
ZFS-on-Linux systems that make heavy use of extended attributes would
benefit from this feature. In particular, ZFS-on-Linux supports the
xattr=sa dataset property which allows file extended attribute data
to be stored in the dnode bonus buffer as an alternative to the
traditional directory-based format. Workloads such as SELinux and the
Lustre distributed filesystem often store enough xattr data to force
spill bocks when xattr=sa is in effect. Large dnodes may therefore
provide a performance benefit to such systems.
Other use cases that may benefit from this feature include files with
large ACLs and symbolic links with long target names. Furthermore,
this feature may be desirable on other platforms in case future
applications or features are developed that could make use of a
larger bonus buffer area.
Implementation
--------------
The size of a dnode may be a multiple of 512 bytes up to the size of
a dnode block (currently 16384 bytes). A dn_extra_slots field was
added to the current on-disk dnode_phys_t structure to describe the
size of the physical dnode on disk. The 8 bits for this field were
taken from the zero filled dn_pad2 field. The field represents how
many "extra" dnode_phys_t slots a dnode consumes in its dnode block.
This convention results in a value of 0 for 512 byte dnodes which
preserves on-disk format compatibility with older software.
Similarly, the in-memory dnode_t structure has a new dn_num_slots field
to represent the total number of dnode_phys_t slots consumed on disk.
Thus dn->dn_num_slots is 1 greater than the corresponding
dnp->dn_extra_slots. This difference in convention was adopted
because, unlike on-disk structures, backward compatibility is not a
concern for in-memory objects, so we used a more natural way to
represent size for a dnode_t.
The default size for newly created dnodes is determined by the value of
a new "dnodesize" dataset property. By default the property is set to
"legacy" which is compatible with older software. Setting the property
to "auto" will allow the filesystem to choose the most suitable dnode
size. Currently this just sets the default dnode size to 1k, but future
code improvements could dynamically choose a size based on observed
workload patterns. Dnodes of varying sizes can coexist within the same
dataset and even within the same dnode block. For example, to enable
automatically-sized dnodes, run
# zfs set dnodesize=auto tank/fish
The user can also specify literal values for the dnodesize property.
These are currently limited to powers of two from 1k to 16k. The
power-of-2 limitation is only for simplicity of the user interface.
Internally the implementation can handle any multiple of 512 up to 16k,
and consumers of the DMU API can specify any legal dnode value.
The size of a new dnode is determined at object allocation time and
stored as a new field in the znode in-memory structure. New DMU
interfaces are added to allow the consumer to specify the dnode size
that a newly allocated object should use. Existing interfaces are
unchanged to avoid having to update every call site and to preserve
compatibility with external consumers such as Lustre. The new
interfaces names are given below. The versions of these functions that
don't take a dnodesize parameter now just call the _dnsize() versions
with a dnodesize of 0, which means use the legacy dnode size.
New DMU interfaces:
dmu_object_alloc_dnsize()
dmu_object_claim_dnsize()
dmu_object_reclaim_dnsize()
New ZAP interfaces:
zap_create_dnsize()
zap_create_norm_dnsize()
zap_create_flags_dnsize()
zap_create_claim_norm_dnsize()
zap_create_link_dnsize()
The constant DN_MAX_BONUSLEN is renamed to DN_OLD_MAX_BONUSLEN. The
spa_maxdnodesize() function should be used to determine the maximum
bonus length for a pool.
These are a few noteworthy changes to key functions:
* The prototype for dnode_hold_impl() now takes a "slots" parameter.
When the DNODE_MUST_BE_FREE flag is set, this parameter is used to
ensure the hole at the specified object offset is large enough to
hold the dnode being created. The slots parameter is also used
to ensure a dnode does not span multiple dnode blocks. In both of
these cases, if a failure occurs, ENOSPC is returned. Keep in mind,
these failure cases are only possible when using DNODE_MUST_BE_FREE.
If the DNODE_MUST_BE_ALLOCATED flag is set, "slots" must be 0.
dnode_hold_impl() will check if the requested dnode is already
consumed as an extra dnode slot by an large dnode, in which case
it returns ENOENT.
* The function dmu_object_alloc() advances to the next dnode block
if dnode_hold_impl() returns an error for a requested object.
This is because the beginning of the next dnode block is the only
location it can safely assume to either be a hole or a valid
starting point for a dnode.
* dnode_next_offset_level() and other functions that iterate
through dnode blocks may no longer use a simple array indexing
scheme. These now use the current dnode's dn_num_slots field to
advance to the next dnode in the block. This is to ensure we
properly skip the current dnode's bonus area and don't interpret it
as a valid dnode.
zdb
---
The zdb command was updated to display a dnode's size under the
"dnsize" column when the object is dumped.
For ZIL create log records, zdb will now display the slot count for
the object.
ztest
-----
Ztest chooses a random dnodesize for every newly created object. The
random distribution is more heavily weighted toward small dnodes to
better simulate real-world datasets.
Unused bonus buffer space is filled with non-zero values computed from
the object number, dataset id, offset, and generation number. This
helps ensure that the dnode traversal code properly skips the interior
regions of large dnodes, and that these interior regions are not
overwritten by data belonging to other dnodes. A new test visits each
object in a dataset. It verifies that the actual dnode size matches what
was stored in the ztest block tag when it was created. It also verifies
that the unused bonus buffer space is filled with the expected data
patterns.
ZFS Test Suite
--------------
Added six new large dnode-specific tests, and integrated the dnodesize
property into existing tests for zfs allow and send/recv.
Send/Receive
------------
ZFS send streams for datasets containing large dnodes cannot be received
on pools that don't support the large_dnode feature. A send stream with
large dnodes sets a DMU_BACKUP_FEATURE_LARGE_DNODE flag which will be
unrecognized by an incompatible receiving pool so that the zfs receive
will fail gracefully.
While not implemented here, it may be possible to generate a
backward-compatible send stream from a dataset containing large
dnodes. The implementation may be tricky, however, because the send
object record for a large dnode would need to be resized to a 512
byte dnode, possibly kicking in a spill block in the process. This
means we would need to construct a new SA layout and possibly
register it in the SA layout object. The SA layout is normally just
sent as an ordinary object record. But if we are constructing new
layouts while generating the send stream we'd have to build the SA
layout object dynamically and send it at the end of the stream.
For sending and receiving between pools that do support large dnodes,
the drr_object send record type is extended with a new field to store
the dnode slot count. This field was repurposed from unused padding
in the structure.
ZIL Replay
----------
The dnode slot count is stored in the uppermost 8 bits of the lr_foid
field. The bits were unused as the object id is currently capped at
48 bits.
Resizing Dnodes
---------------
It should be possible to resize a dnode when it is dirtied if the
current dnodesize dataset property differs from the dnode's size, but
this functionality is not currently implemented. Clearly a dnode can
only grow if there are sufficient contiguous unused slots in the
dnode block, but it should always be possible to shrink a dnode.
Growing dnodes may be useful to reduce fragmentation in a pool with
many spill blocks in use. Shrinking dnodes may be useful to allow
sending a dataset to a pool that doesn't support the large_dnode
feature.
Feature Reference Counting
--------------------------
The reference count for the large_dnode pool feature tracks the
number of datasets that have ever contained a dnode of size larger
than 512 bytes. The first time a large dnode is created in a dataset
the dataset is converted to an extensible dataset. This is a one-way
operation and the only way to decrement the feature count is to
destroy the dataset, even if the dataset no longer contains any large
dnodes. The complexity of reference counting on a per-dnode basis was
too high, so we chose to track it on a per-dataset basis similarly to
the large_block feature.
Signed-off-by: Ned Bass <bass6@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #3542
2016-03-17 04:25:34 +03:00
|
|
|
VERIFY0(dmu_buf_hold(ZTOZSB(zp)->z_os, zp->z_id, 0, FTAG, &dbp,
|
|
|
|
|
DMU_READ_NO_PREFETCH));
|
2010-05-29 00:45:14 +04:00
|
|
|
|
|
|
|
|
dmu_buf_will_dirty(dbp, tx);
|
|
|
|
|
|
|
|
|
|
ASSERT3U(len, <=, dbp->db_size);
|
|
|
|
|
bcopy(link, dbp->db_data, len);
|
|
|
|
|
dmu_buf_rele(dbp, FTAG);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
zfs_sa_get_scanstamp(znode_t *zp, xvattr_t *xvap)
|
|
|
|
|
{
|
2017-03-08 03:21:37 +03:00
|
|
|
zfsvfs_t *zfsvfs = ZTOZSB(zp);
|
2010-05-29 00:45:14 +04:00
|
|
|
xoptattr_t *xoap;
|
|
|
|
|
|
2010-08-27 01:24:34 +04:00
|
|
|
ASSERT(MUTEX_HELD(&zp->z_lock));
|
2010-05-29 00:45:14 +04:00
|
|
|
VERIFY((xoap = xva_getxoptattr(xvap)) != NULL);
|
|
|
|
|
if (zp->z_is_sa) {
|
2017-03-08 03:21:37 +03:00
|
|
|
if (sa_lookup(zp->z_sa_hdl, SA_ZPL_SCANSTAMP(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
&xoap->xoa_av_scanstamp,
|
|
|
|
|
sizeof (xoap->xoa_av_scanstamp)) != 0)
|
|
|
|
|
return;
|
|
|
|
|
} else {
|
|
|
|
|
dmu_object_info_t doi;
|
|
|
|
|
dmu_buf_t *db = sa_get_db(zp->z_sa_hdl);
|
|
|
|
|
int len;
|
|
|
|
|
|
|
|
|
|
if (!(zp->z_pflags & ZFS_BONUS_SCANSTAMP))
|
|
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
sa_object_info(zp->z_sa_hdl, &doi);
|
|
|
|
|
len = sizeof (xoap->xoa_av_scanstamp) +
|
|
|
|
|
ZFS_OLD_ZNODE_PHYS_SIZE;
|
|
|
|
|
|
|
|
|
|
if (len <= doi.doi_bonus_size) {
|
|
|
|
|
(void) memcpy(xoap->xoa_av_scanstamp,
|
|
|
|
|
(caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE,
|
|
|
|
|
sizeof (xoap->xoa_av_scanstamp));
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
XVA_SET_RTN(xvap, XAT_AV_SCANSTAMP);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
zfs_sa_set_scanstamp(znode_t *zp, xvattr_t *xvap, dmu_tx_t *tx)
|
|
|
|
|
{
|
2017-03-08 03:21:37 +03:00
|
|
|
zfsvfs_t *zfsvfs = ZTOZSB(zp);
|
2010-05-29 00:45:14 +04:00
|
|
|
xoptattr_t *xoap;
|
|
|
|
|
|
2010-08-27 01:24:34 +04:00
|
|
|
ASSERT(MUTEX_HELD(&zp->z_lock));
|
2010-05-29 00:45:14 +04:00
|
|
|
VERIFY((xoap = xva_getxoptattr(xvap)) != NULL);
|
|
|
|
|
if (zp->z_is_sa)
|
2017-03-08 03:21:37 +03:00
|
|
|
VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_SCANSTAMP(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
&xoap->xoa_av_scanstamp,
|
|
|
|
|
sizeof (xoap->xoa_av_scanstamp), tx));
|
|
|
|
|
else {
|
|
|
|
|
dmu_object_info_t doi;
|
|
|
|
|
dmu_buf_t *db = sa_get_db(zp->z_sa_hdl);
|
|
|
|
|
int len;
|
|
|
|
|
|
|
|
|
|
sa_object_info(zp->z_sa_hdl, &doi);
|
|
|
|
|
len = sizeof (xoap->xoa_av_scanstamp) +
|
|
|
|
|
ZFS_OLD_ZNODE_PHYS_SIZE;
|
|
|
|
|
if (len > doi.doi_bonus_size)
|
|
|
|
|
VERIFY(dmu_set_bonus(db, len, tx) == 0);
|
|
|
|
|
(void) memcpy((caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE,
|
|
|
|
|
xoap->xoa_av_scanstamp, sizeof (xoap->xoa_av_scanstamp));
|
|
|
|
|
|
|
|
|
|
zp->z_pflags |= ZFS_BONUS_SCANSTAMP;
|
2017-03-08 03:21:37 +03:00
|
|
|
VERIFY(0 == sa_update(zp->z_sa_hdl, SA_ZPL_FLAGS(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
&zp->z_pflags, sizeof (uint64_t), tx));
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2011-10-25 03:55:20 +04:00
|
|
|
int
|
|
|
|
|
zfs_sa_get_xattr(znode_t *zp)
|
|
|
|
|
{
|
2017-03-08 03:21:37 +03:00
|
|
|
zfsvfs_t *zfsvfs = ZTOZSB(zp);
|
2011-10-25 03:55:20 +04:00
|
|
|
char *obj;
|
|
|
|
|
int size;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
ASSERT(RW_LOCK_HELD(&zp->z_xattr_lock));
|
|
|
|
|
ASSERT(!zp->z_xattr_cached);
|
|
|
|
|
ASSERT(zp->z_is_sa);
|
|
|
|
|
|
2017-03-08 03:21:37 +03:00
|
|
|
error = sa_size(zp->z_sa_hdl, SA_ZPL_DXATTR(zfsvfs), &size);
|
2011-10-25 03:55:20 +04:00
|
|
|
if (error) {
|
|
|
|
|
if (error == ENOENT)
|
|
|
|
|
return nvlist_alloc(&zp->z_xattr_cached,
|
|
|
|
|
NV_UNIQUE_NAME, KM_SLEEP);
|
|
|
|
|
else
|
|
|
|
|
return (error);
|
|
|
|
|
}
|
|
|
|
|
|
2016-12-01 02:18:20 +03:00
|
|
|
obj = vmem_alloc(size, KM_SLEEP);
|
2011-10-25 03:55:20 +04:00
|
|
|
|
2017-03-08 03:21:37 +03:00
|
|
|
error = sa_lookup(zp->z_sa_hdl, SA_ZPL_DXATTR(zfsvfs), obj, size);
|
2011-10-25 03:55:20 +04:00
|
|
|
if (error == 0)
|
|
|
|
|
error = nvlist_unpack(obj, size, &zp->z_xattr_cached, KM_SLEEP);
|
|
|
|
|
|
2016-12-01 02:18:20 +03:00
|
|
|
vmem_free(obj, size);
|
2011-10-25 03:55:20 +04:00
|
|
|
|
|
|
|
|
return (error);
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
int
|
|
|
|
|
zfs_sa_set_xattr(znode_t *zp)
|
|
|
|
|
{
|
2017-03-08 03:21:37 +03:00
|
|
|
zfsvfs_t *zfsvfs = ZTOZSB(zp);
|
2011-10-25 03:55:20 +04:00
|
|
|
dmu_tx_t *tx;
|
|
|
|
|
char *obj;
|
|
|
|
|
size_t size;
|
|
|
|
|
int error;
|
|
|
|
|
|
|
|
|
|
ASSERT(RW_WRITE_HELD(&zp->z_xattr_lock));
|
|
|
|
|
ASSERT(zp->z_xattr_cached);
|
|
|
|
|
ASSERT(zp->z_is_sa);
|
|
|
|
|
|
|
|
|
|
error = nvlist_size(zp->z_xattr_cached, &size, NV_ENCODE_XDR);
|
2015-12-30 05:41:22 +03:00
|
|
|
if ((error == 0) && (size > SA_ATTR_MAX_LEN))
|
|
|
|
|
error = EFBIG;
|
2011-10-25 03:55:20 +04:00
|
|
|
if (error)
|
|
|
|
|
goto out;
|
|
|
|
|
|
2016-12-01 02:18:20 +03:00
|
|
|
obj = vmem_alloc(size, KM_SLEEP);
|
2011-10-25 03:55:20 +04:00
|
|
|
|
|
|
|
|
error = nvlist_pack(zp->z_xattr_cached, &obj, &size,
|
|
|
|
|
NV_ENCODE_XDR, KM_SLEEP);
|
|
|
|
|
if (error)
|
|
|
|
|
goto out_free;
|
|
|
|
|
|
2017-03-08 03:21:37 +03:00
|
|
|
tx = dmu_tx_create(zfsvfs->z_os);
|
2011-10-25 03:55:20 +04:00
|
|
|
dmu_tx_hold_sa_create(tx, size);
|
2012-08-24 07:46:38 +04:00
|
|
|
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE);
|
2011-10-25 03:55:20 +04:00
|
|
|
|
|
|
|
|
error = dmu_tx_assign(tx, TXG_WAIT);
|
|
|
|
|
if (error) {
|
|
|
|
|
dmu_tx_abort(tx);
|
|
|
|
|
} else {
|
2017-09-13 22:20:07 +03:00
|
|
|
int count = 0;
|
|
|
|
|
sa_bulk_attr_t bulk[2];
|
|
|
|
|
uint64_t ctime[2];
|
|
|
|
|
|
|
|
|
|
zfs_tstamp_update_setup(zp, STATE_CHANGED, NULL, ctime);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_DXATTR(zfsvfs),
|
|
|
|
|
NULL, obj, size);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs),
|
|
|
|
|
NULL, &ctime, 16);
|
|
|
|
|
VERIFY0(sa_bulk_update(zp->z_sa_hdl, bulk, count, tx));
|
|
|
|
|
|
2015-12-30 05:41:22 +03:00
|
|
|
dmu_tx_commit(tx);
|
2011-10-25 03:55:20 +04:00
|
|
|
}
|
|
|
|
|
out_free:
|
2016-12-01 02:18:20 +03:00
|
|
|
vmem_free(obj, size);
|
2011-10-25 03:55:20 +04:00
|
|
|
out:
|
|
|
|
|
return (error);
|
|
|
|
|
}
|
|
|
|
|
|
2010-05-29 00:45:14 +04:00
|
|
|
/*
|
|
|
|
|
* I'm not convinced we should do any of this upgrade.
|
|
|
|
|
* since the SA code can read both old/new znode formats
|
2013-06-11 21:12:34 +04:00
|
|
|
* with probably little to no performance difference.
|
2010-05-29 00:45:14 +04:00
|
|
|
*
|
|
|
|
|
* All new files will be created with the new format.
|
|
|
|
|
*/
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
zfs_sa_upgrade(sa_handle_t *hdl, dmu_tx_t *tx)
|
|
|
|
|
{
|
|
|
|
|
dmu_buf_t *db = sa_get_db(hdl);
|
|
|
|
|
znode_t *zp = sa_get_userdata(hdl);
|
2017-03-08 03:21:37 +03:00
|
|
|
zfsvfs_t *zfsvfs = ZTOZSB(zp);
|
2010-05-29 00:45:14 +04:00
|
|
|
int count = 0;
|
2010-12-18 01:21:46 +03:00
|
|
|
sa_bulk_attr_t *bulk, *sa_attrs;
|
2010-05-29 00:45:14 +04:00
|
|
|
zfs_acl_locator_cb_t locate = { 0 };
|
2016-04-18 22:08:53 +03:00
|
|
|
uint64_t uid, gid, mode, rdev, xattr, parent, tmp_gen;
|
Fix atime handling and relatime
The problem for atime:
We have 3 places for atime: inode->i_atime, znode->z_atime and SA. And its
handling is a mess. A huge part of mess regarding atime comes from
zfs_tstamp_update_setup, zfs_inode_update, and zfs_getattr, which behave
inconsistently with those three values.
zfs_tstamp_update_setup clears z_atime_dirty unconditionally as long as you
don't pass ATTR_ATIME. Which means every write(2) operation which only updates
ctime and mtime will cause atime changes to not be written to disk.
Also zfs_inode_update from write(2) will replace inode->i_atime with what's
inside SA(stale). But doesn't touch z_atime. So after read(2) and write(2).
You'll have i_atime(stale), z_atime(new), SA(stale) and z_atime_dirty=0.
Now, if you do stat(2), zfs_getattr will actually replace i_atime with what's
inside, z_atime. So you will have now you'll have i_atime(new), z_atime(new),
SA(stale) and z_atime_dirty=0. These will all gone after umount. And you'll
leave with a stale atime.
The problem for relatime:
We do have a relatime config inside ZFS dataset, but how it should interact
with the mount flag MS_RELATIME is not well defined. It seems it wanted
relatime mount option to override the dataset config by showing it as
temporary in `zfs get`. But at the same time, `zfs set relatime=on|off` would
also seems to want to override the mount option. Not to mention that
MS_RELATIME flag is actually never passed into ZFS, so it never really worked.
How Linux handles atime:
The Linux kernel actually handles atime completely in VFS, except for writing
it to disk. So if we remove the atime handling in ZFS, things would just work,
no matter it's strictatime, relatime, noatime, or even O_NOATIME. And whenever
VFS updates the i_atime, it will notify the underlying filesystem via
sb->dirty_inode().
And also there's one thing to note about atime flags like MS_RELATIME and
other flags like MS_NODEV, etc. They are mount point flags rather than
filesystem(sb) flags. Since native linux filesystem can be mounted at multiple
places at the same time, they can all have different atime settings. So these
flags are never passed down to filesystem drivers.
What this patch tries to do:
We remove znode->z_atime, since we won't gain anything from it. We remove most
of the atime handling and leave it to VFS. The only thing we do with atime is
to write it when dirty_inode() or setattr() is called. We also add
file_accessed() in zpl_read() since it's not provided in vfs_read().
After this patch, only the MS_RELATIME flag will have effect. The setting in
dataset won't do anything. We will make zfstuil to mount ZFS with MS_RELATIME
set according to the setting in dataset in future patch.
Signed-off-by: Chunwei Chen <david.chen@osnexus.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #4482
2016-03-30 03:53:34 +03:00
|
|
|
uint64_t crtime[2], mtime[2], ctime[2], atime[2];
|
2016-07-14 17:44:38 +03:00
|
|
|
uint64_t links;
|
2010-05-29 00:45:14 +04:00
|
|
|
zfs_acl_phys_t znode_acl;
|
|
|
|
|
char scanstamp[AV_SCANSTAMP_SZ];
|
2010-08-27 01:24:34 +04:00
|
|
|
boolean_t drop_lock = B_FALSE;
|
2010-05-29 00:45:14 +04:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* No upgrade if ACL isn't cached
|
|
|
|
|
* since we won't know which locks are held
|
|
|
|
|
* and ready the ACL would require special "locked"
|
|
|
|
|
* interfaces that would be messy
|
|
|
|
|
*/
|
2011-02-08 22:16:06 +03:00
|
|
|
if (zp->z_acl_cached == NULL || S_ISLNK(ZTOI(zp)->i_mode))
|
2010-05-29 00:45:14 +04:00
|
|
|
return;
|
|
|
|
|
|
2010-08-27 01:24:34 +04:00
|
|
|
/*
|
|
|
|
|
* If the z_lock is held and we aren't the owner
|
|
|
|
|
* the just return since we don't want to deadlock
|
|
|
|
|
* trying to update the status of z_is_sa. This
|
|
|
|
|
* file can then be upgraded at a later time.
|
|
|
|
|
*
|
|
|
|
|
* Otherwise, we know we are doing the
|
|
|
|
|
* sa_update() that caused us to enter this function.
|
|
|
|
|
*/
|
|
|
|
|
if (mutex_owner(&zp->z_lock) != curthread) {
|
|
|
|
|
if (mutex_tryenter(&zp->z_lock) == 0)
|
|
|
|
|
return;
|
|
|
|
|
else
|
|
|
|
|
drop_lock = B_TRUE;
|
|
|
|
|
}
|
|
|
|
|
|
2010-05-29 00:45:14 +04:00
|
|
|
/* First do a bulk query of the attributes that aren't cached */
|
2013-11-01 23:26:11 +04:00
|
|
|
bulk = kmem_alloc(sizeof (sa_bulk_attr_t) * 20, KM_SLEEP);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ATIME(zfsvfs), NULL, &atime, 16);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MTIME(zfsvfs), NULL, &mtime, 16);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CTIME(zfsvfs), NULL, &ctime, 16);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_CRTIME(zfsvfs), NULL, &crtime, 16);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_MODE(zfsvfs), NULL, &mode, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_PARENT(zfsvfs), NULL, &parent, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_XATTR(zfsvfs), NULL, &xattr, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_RDEV(zfsvfs), NULL, &rdev, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_UID(zfsvfs), NULL, &uid, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GID(zfsvfs), NULL, &gid, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_GEN(zfsvfs), NULL, &tmp_gen, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(bulk, count, SA_ZPL_ZNODE_ACL(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&znode_acl, 88);
|
|
|
|
|
|
2010-12-18 01:21:46 +03:00
|
|
|
if (sa_bulk_lookup_locked(hdl, bulk, count) != 0) {
|
2013-11-01 23:26:11 +04:00
|
|
|
kmem_free(bulk, sizeof (sa_bulk_attr_t) * 20);
|
2010-08-27 01:24:34 +04:00
|
|
|
goto done;
|
2010-12-18 01:21:46 +03:00
|
|
|
}
|
2010-05-29 00:45:14 +04:00
|
|
|
|
|
|
|
|
/*
|
|
|
|
|
* While the order here doesn't matter its best to try and organize
|
|
|
|
|
* it is such a way to pick up an already existing layout number
|
|
|
|
|
*/
|
|
|
|
|
count = 0;
|
2013-11-01 23:26:11 +04:00
|
|
|
sa_attrs = kmem_zalloc(sizeof (sa_bulk_attr_t) * 20, KM_SLEEP);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_MODE(zfsvfs), NULL, &mode, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_SIZE(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&zp->z_size, 8);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_GEN(zfsvfs),
|
|
|
|
|
NULL, &tmp_gen, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_UID(zfsvfs), NULL, &uid, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_GID(zfsvfs), NULL, &gid, 8);
|
|
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_PARENT(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
NULL, &parent, 8);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_FLAGS(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&zp->z_pflags, 8);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_ATIME(zfsvfs), NULL,
|
Fix atime handling and relatime
The problem for atime:
We have 3 places for atime: inode->i_atime, znode->z_atime and SA. And its
handling is a mess. A huge part of mess regarding atime comes from
zfs_tstamp_update_setup, zfs_inode_update, and zfs_getattr, which behave
inconsistently with those three values.
zfs_tstamp_update_setup clears z_atime_dirty unconditionally as long as you
don't pass ATTR_ATIME. Which means every write(2) operation which only updates
ctime and mtime will cause atime changes to not be written to disk.
Also zfs_inode_update from write(2) will replace inode->i_atime with what's
inside SA(stale). But doesn't touch z_atime. So after read(2) and write(2).
You'll have i_atime(stale), z_atime(new), SA(stale) and z_atime_dirty=0.
Now, if you do stat(2), zfs_getattr will actually replace i_atime with what's
inside, z_atime. So you will have now you'll have i_atime(new), z_atime(new),
SA(stale) and z_atime_dirty=0. These will all gone after umount. And you'll
leave with a stale atime.
The problem for relatime:
We do have a relatime config inside ZFS dataset, but how it should interact
with the mount flag MS_RELATIME is not well defined. It seems it wanted
relatime mount option to override the dataset config by showing it as
temporary in `zfs get`. But at the same time, `zfs set relatime=on|off` would
also seems to want to override the mount option. Not to mention that
MS_RELATIME flag is actually never passed into ZFS, so it never really worked.
How Linux handles atime:
The Linux kernel actually handles atime completely in VFS, except for writing
it to disk. So if we remove the atime handling in ZFS, things would just work,
no matter it's strictatime, relatime, noatime, or even O_NOATIME. And whenever
VFS updates the i_atime, it will notify the underlying filesystem via
sb->dirty_inode().
And also there's one thing to note about atime flags like MS_RELATIME and
other flags like MS_NODEV, etc. They are mount point flags rather than
filesystem(sb) flags. Since native linux filesystem can be mounted at multiple
places at the same time, they can all have different atime settings. So these
flags are never passed down to filesystem drivers.
What this patch tries to do:
We remove znode->z_atime, since we won't gain anything from it. We remove most
of the atime handling and leave it to VFS. The only thing we do with atime is
to write it when dirty_inode() or setattr() is called. We also add
file_accessed() in zpl_read() since it's not provided in vfs_read().
After this patch, only the MS_RELATIME flag will have effect. The setting in
dataset won't do anything. We will make zfstuil to mount ZFS with MS_RELATIME
set according to the setting in dataset in future patch.
Signed-off-by: Chunwei Chen <david.chen@osnexus.com>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Issue #4482
2016-03-30 03:53:34 +03:00
|
|
|
&atime, 16);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_MTIME(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&mtime, 16);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_CTIME(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&ctime, 16);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_CRTIME(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&crtime, 16);
|
2016-07-14 17:44:38 +03:00
|
|
|
links = ZTOI(zp)->i_nlink;
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_LINKS(zfsvfs), NULL,
|
2016-07-14 17:44:38 +03:00
|
|
|
&links, 8);
|
2011-02-08 22:16:06 +03:00
|
|
|
if (S_ISBLK(ZTOI(zp)->i_mode) || S_ISCHR(ZTOI(zp)->i_mode))
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_RDEV(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&rdev, 8);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_DACL_COUNT(zfsvfs), NULL,
|
2010-05-29 00:45:14 +04:00
|
|
|
&zp->z_acl_cached->z_acl_count, 8);
|
|
|
|
|
|
|
|
|
|
if (zp->z_acl_cached->z_version < ZFS_ACL_VERSION_FUID)
|
|
|
|
|
zfs_acl_xform(zp, zp->z_acl_cached, CRED());
|
|
|
|
|
|
|
|
|
|
locate.cb_aclp = zp->z_acl_cached;
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_DACL_ACES(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
zfs_acl_data_locator, &locate, zp->z_acl_cached->z_acl_bytes);
|
2010-08-27 01:24:34 +04:00
|
|
|
|
2010-05-29 00:45:14 +04:00
|
|
|
if (xattr)
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_XATTR(zfsvfs),
|
2010-08-27 01:24:34 +04:00
|
|
|
NULL, &xattr, 8);
|
2010-05-29 00:45:14 +04:00
|
|
|
|
|
|
|
|
/* if scanstamp then add scanstamp */
|
|
|
|
|
|
|
|
|
|
if (zp->z_pflags & ZFS_BONUS_SCANSTAMP) {
|
|
|
|
|
bcopy((caddr_t)db->db_data + ZFS_OLD_ZNODE_PHYS_SIZE,
|
|
|
|
|
scanstamp, AV_SCANSTAMP_SZ);
|
2017-03-08 03:21:37 +03:00
|
|
|
SA_ADD_BULK_ATTR(sa_attrs, count, SA_ZPL_SCANSTAMP(zfsvfs),
|
2010-05-29 00:45:14 +04:00
|
|
|
NULL, scanstamp, AV_SCANSTAMP_SZ);
|
|
|
|
|
zp->z_pflags &= ~ZFS_BONUS_SCANSTAMP;
|
|
|
|
|
}
|
|
|
|
|
|
|
|
|
|
VERIFY(dmu_set_bonustype(db, DMU_OT_SA, tx) == 0);
|
|
|
|
|
VERIFY(sa_replace_all_by_template_locked(hdl, sa_attrs,
|
|
|
|
|
count, tx) == 0);
|
|
|
|
|
if (znode_acl.z_acl_extern_obj)
|
2017-03-08 03:21:37 +03:00
|
|
|
VERIFY(0 == dmu_object_free(zfsvfs->z_os,
|
2010-05-29 00:45:14 +04:00
|
|
|
znode_acl.z_acl_extern_obj, tx));
|
|
|
|
|
|
|
|
|
|
zp->z_is_sa = B_TRUE;
|
2013-11-01 23:26:11 +04:00
|
|
|
kmem_free(sa_attrs, sizeof (sa_bulk_attr_t) * 20);
|
|
|
|
|
kmem_free(bulk, sizeof (sa_bulk_attr_t) * 20);
|
2010-08-27 01:24:34 +04:00
|
|
|
done:
|
|
|
|
|
if (drop_lock)
|
|
|
|
|
mutex_exit(&zp->z_lock);
|
2010-05-29 00:45:14 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
|
|
void
|
|
|
|
|
zfs_sa_upgrade_txholds(dmu_tx_t *tx, znode_t *zp)
|
|
|
|
|
{
|
2011-02-08 22:16:06 +03:00
|
|
|
if (!ZTOZSB(zp)->z_use_sa || zp->z_is_sa)
|
2010-05-29 00:45:14 +04:00
|
|
|
return;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
dmu_tx_hold_sa(tx, zp->z_sa_hdl, B_TRUE);
|
|
|
|
|
|
2010-08-27 01:24:34 +04:00
|
|
|
if (zfs_external_acl(zp)) {
|
|
|
|
|
dmu_tx_hold_free(tx, zfs_external_acl(zp), 0,
|
2010-05-29 00:45:14 +04:00
|
|
|
DMU_OBJECT_END);
|
|
|
|
|
}
|
|
|
|
|
}
|
|
|
|
|
|
2012-01-27 21:15:42 +04:00
|
|
|
EXPORT_SYMBOL(zfs_attr_table);
|
2011-09-30 21:33:26 +04:00
|
|
|
EXPORT_SYMBOL(zfs_sa_readlink);
|
|
|
|
|
EXPORT_SYMBOL(zfs_sa_symlink);
|
|
|
|
|
EXPORT_SYMBOL(zfs_sa_get_scanstamp);
|
|
|
|
|
EXPORT_SYMBOL(zfs_sa_set_scanstamp);
|
2011-10-25 03:55:20 +04:00
|
|
|
EXPORT_SYMBOL(zfs_sa_get_xattr);
|
|
|
|
|
EXPORT_SYMBOL(zfs_sa_set_xattr);
|
2011-09-30 21:33:26 +04:00
|
|
|
EXPORT_SYMBOL(zfs_sa_upgrade);
|
|
|
|
|
EXPORT_SYMBOL(zfs_sa_upgrade_txholds);
|
|
|
|
|
|
2010-05-29 00:45:14 +04:00
|
|
|
#endif
|