2008-11-20 23:01:55 +03:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
*/
|
|
|
|
/*
|
2010-05-29 00:45:14 +04:00
|
|
|
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
2015-07-24 19:53:55 +03:00
|
|
|
* Copyright (c) 2011, 2015 by Delphix. All rights reserved.
|
2015-12-22 04:31:57 +03:00
|
|
|
* Copyright (c) 2011, 2014 by Delphix. All rights reserved.
|
2013-05-25 06:06:23 +04:00
|
|
|
* Copyright (c) 2013 Steven Hartland. All rights reserved.
|
2015-04-02 06:44:32 +03:00
|
|
|
* Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
|
2008-11-20 23:01:55 +03:00
|
|
|
*/
|
|
|
|
|
|
|
|
#ifndef _SYS_DSL_DATASET_H
|
|
|
|
#define _SYS_DSL_DATASET_H
|
|
|
|
|
|
|
|
#include <sys/dmu.h>
|
|
|
|
#include <sys/spa.h>
|
|
|
|
#include <sys/txg.h>
|
|
|
|
#include <sys/zio.h>
|
|
|
|
#include <sys/bplist.h>
|
|
|
|
#include <sys/dsl_synctask.h>
|
|
|
|
#include <sys/zfs_context.h>
|
2010-05-29 00:45:14 +04:00
|
|
|
#include <sys/dsl_deadlist.h>
|
2013-09-04 16:00:57 +04:00
|
|
|
#include <sys/refcount.h>
|
2017-01-27 22:43:42 +03:00
|
|
|
#include <sys/rrwlock.h>
|
2015-07-24 19:53:55 +03:00
|
|
|
#include <zfeature_common.h>
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
extern "C" {
|
|
|
|
#endif
|
|
|
|
|
|
|
|
struct dsl_dataset;
|
|
|
|
struct dsl_dir;
|
|
|
|
struct dsl_pool;
|
|
|
|
|
|
|
|
#define DS_FLAG_INCONSISTENT (1ULL<<0)
|
2008-12-03 23:09:06 +03:00
|
|
|
#define DS_IS_INCONSISTENT(ds) \
|
2015-04-01 18:14:34 +03:00
|
|
|
(dsl_dataset_phys(ds)->ds_flags & DS_FLAG_INCONSISTENT)
|
2013-10-08 21:13:05 +04:00
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
/*
|
2013-10-08 21:13:05 +04:00
|
|
|
* Do not allow this dataset to be promoted.
|
2008-11-20 23:01:55 +03:00
|
|
|
*/
|
|
|
|
#define DS_FLAG_NOPROMOTE (1ULL<<1)
|
|
|
|
|
|
|
|
/*
|
|
|
|
* DS_FLAG_UNIQUE_ACCURATE is set if ds_unique_bytes has been correctly
|
|
|
|
* calculated for head datasets (starting with SPA_VERSION_UNIQUE_ACCURATE,
|
|
|
|
* refquota/refreservations).
|
|
|
|
*/
|
|
|
|
#define DS_FLAG_UNIQUE_ACCURATE (1ULL<<2)
|
|
|
|
|
2009-08-18 22:43:27 +04:00
|
|
|
/*
|
|
|
|
* DS_FLAG_DEFER_DESTROY is set after 'zfs destroy -d' has been called
|
|
|
|
* on a dataset. This allows the dataset to be destroyed using 'zfs release'.
|
|
|
|
*/
|
|
|
|
#define DS_FLAG_DEFER_DESTROY (1ULL<<3)
|
|
|
|
#define DS_IS_DEFER_DESTROY(ds) \
|
2015-04-01 18:14:34 +03:00
|
|
|
(dsl_dataset_phys(ds)->ds_flags & DS_FLAG_DEFER_DESTROY)
|
2009-08-18 22:43:27 +04:00
|
|
|
|
2013-10-08 21:13:05 +04:00
|
|
|
/*
|
|
|
|
* DS_FIELD_* are strings that are used in the "extensified" dataset zap object.
|
|
|
|
* They should be of the format <reverse-dns>:<field>.
|
|
|
|
*/
|
|
|
|
|
2013-12-12 02:33:41 +04:00
|
|
|
/*
|
|
|
|
* This field's value is the object ID of a zap object which contains the
|
|
|
|
* bookmarks of this dataset. If it is present, then this dataset is counted
|
|
|
|
* in the refcount of the SPA_FEATURES_BOOKMARKS feature.
|
|
|
|
*/
|
|
|
|
#define DS_FIELD_BOOKMARK_NAMES "com.delphix:bookmarks"
|
|
|
|
|
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
|
|
|
/*
|
|
|
|
* This field is present (with value=0) if this dataset may contain large
|
|
|
|
* dnodes (>512B). If it is present, then this dataset is counted in the
|
|
|
|
* refcount of the SPA_FEATURE_LARGE_DNODE feature.
|
|
|
|
*/
|
|
|
|
#define DS_FIELD_LARGE_DNODE "org.zfsonlinux:large_dnode"
|
|
|
|
|
2016-01-07 00:22:48 +03:00
|
|
|
/*
|
|
|
|
* These fields are set on datasets that are in the middle of a resumable
|
|
|
|
* receive, and allow the sender to resume the send if it is interrupted.
|
|
|
|
*/
|
|
|
|
#define DS_FIELD_RESUME_FROMGUID "com.delphix:resume_fromguid"
|
|
|
|
#define DS_FIELD_RESUME_TONAME "com.delphix:resume_toname"
|
|
|
|
#define DS_FIELD_RESUME_TOGUID "com.delphix:resume_toguid"
|
|
|
|
#define DS_FIELD_RESUME_OBJECT "com.delphix:resume_object"
|
|
|
|
#define DS_FIELD_RESUME_OFFSET "com.delphix:resume_offset"
|
|
|
|
#define DS_FIELD_RESUME_BYTES "com.delphix:resume_bytes"
|
2016-07-11 20:45:52 +03:00
|
|
|
#define DS_FIELD_RESUME_LARGEBLOCK "com.delphix:resume_largeblockok"
|
2016-01-07 00:22:48 +03:00
|
|
|
#define DS_FIELD_RESUME_EMBEDOK "com.delphix:resume_embedok"
|
2016-07-11 20:45:52 +03:00
|
|
|
#define DS_FIELD_RESUME_COMPRESSOK "com.delphix:resume_compressok"
|
2016-01-07 00:22:48 +03:00
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
/*
|
|
|
|
* DS_FLAG_CI_DATASET is set if the dataset contains a file system whose
|
|
|
|
* name lookups should be performed case-insensitively.
|
|
|
|
*/
|
|
|
|
#define DS_FLAG_CI_DATASET (1ULL<<16)
|
|
|
|
|
2013-09-04 16:00:57 +04:00
|
|
|
#define DS_CREATE_FLAG_NODIRTY (1ULL<<24)
|
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
typedef struct dsl_dataset_phys {
|
2008-12-03 23:09:06 +03:00
|
|
|
uint64_t ds_dir_obj; /* DMU_OT_DSL_DIR */
|
|
|
|
uint64_t ds_prev_snap_obj; /* DMU_OT_DSL_DATASET */
|
2008-11-20 23:01:55 +03:00
|
|
|
uint64_t ds_prev_snap_txg;
|
2008-12-03 23:09:06 +03:00
|
|
|
uint64_t ds_next_snap_obj; /* DMU_OT_DSL_DATASET */
|
|
|
|
uint64_t ds_snapnames_zapobj; /* DMU_OT_DSL_DS_SNAP_MAP 0 for snaps */
|
2008-11-20 23:01:55 +03:00
|
|
|
uint64_t ds_num_children; /* clone/snap children; ==0 for head */
|
|
|
|
uint64_t ds_creation_time; /* seconds since 1970 */
|
|
|
|
uint64_t ds_creation_txg;
|
2010-05-29 00:45:14 +04:00
|
|
|
uint64_t ds_deadlist_obj; /* DMU_OT_DEADLIST */
|
2012-12-14 03:24:15 +04:00
|
|
|
/*
|
|
|
|
* ds_referenced_bytes, ds_compressed_bytes, and ds_uncompressed_bytes
|
|
|
|
* include all blocks referenced by this dataset, including those
|
|
|
|
* shared with any other datasets.
|
|
|
|
*/
|
|
|
|
uint64_t ds_referenced_bytes;
|
2008-11-20 23:01:55 +03:00
|
|
|
uint64_t ds_compressed_bytes;
|
|
|
|
uint64_t ds_uncompressed_bytes;
|
|
|
|
uint64_t ds_unique_bytes; /* only relevant to snapshots */
|
|
|
|
/*
|
|
|
|
* The ds_fsid_guid is a 56-bit ID that can change to avoid
|
|
|
|
* collisions. The ds_guid is a 64-bit ID that will never
|
|
|
|
* change, so there is a small probability that it will collide.
|
|
|
|
*/
|
|
|
|
uint64_t ds_fsid_guid;
|
|
|
|
uint64_t ds_guid;
|
2008-12-03 23:09:06 +03:00
|
|
|
uint64_t ds_flags; /* DS_FLAG_* */
|
2008-11-20 23:01:55 +03:00
|
|
|
blkptr_t ds_bp;
|
2008-12-03 23:09:06 +03:00
|
|
|
uint64_t ds_next_clones_obj; /* DMU_OT_DSL_CLONES */
|
|
|
|
uint64_t ds_props_obj; /* DMU_OT_DSL_PROPS for snaps */
|
2009-08-18 22:43:27 +04:00
|
|
|
uint64_t ds_userrefs_obj; /* DMU_OT_USERREFS */
|
|
|
|
uint64_t ds_pad[5]; /* pad out to 320 bytes for good measure */
|
2008-11-20 23:01:55 +03:00
|
|
|
} dsl_dataset_phys_t;
|
|
|
|
|
|
|
|
typedef struct dsl_dataset {
|
2015-04-02 06:44:32 +03:00
|
|
|
dmu_buf_user_t ds_dbu;
|
2017-01-27 22:43:42 +03:00
|
|
|
rrwlock_t ds_bp_rwlock; /* Protects ds_phys->ds_bp */
|
2015-04-02 06:44:32 +03:00
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
/* Immutable: */
|
|
|
|
struct dsl_dir *ds_dir;
|
|
|
|
dmu_buf_t *ds_dbuf;
|
|
|
|
uint64_t ds_object;
|
|
|
|
uint64_t ds_fsid_guid;
|
2015-04-02 06:44:32 +03:00
|
|
|
boolean_t ds_is_snapshot;
|
2008-11-20 23:01:55 +03:00
|
|
|
|
2008-12-03 23:09:06 +03:00
|
|
|
/* only used in syncing context, only valid for non-snapshots: */
|
|
|
|
struct dsl_dataset *ds_prev;
|
2013-12-12 02:33:41 +04:00
|
|
|
uint64_t ds_bookmarks; /* DMU_OTN_ZAP_METADATA */
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
/* has internal locking: */
|
2010-05-29 00:45:14 +04:00
|
|
|
dsl_deadlist_t ds_deadlist;
|
|
|
|
bplist_t ds_pending_deadlist;
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
/* protected by lock on pool's dp_dirty_datasets list */
|
|
|
|
txg_node_t ds_dirty_link;
|
|
|
|
list_node_t ds_synced_link;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* ds_phys->ds_<accounting> is also protected by ds_lock.
|
|
|
|
* Protected by ds_lock:
|
|
|
|
*/
|
|
|
|
kmutex_t ds_lock;
|
2010-05-29 00:45:14 +04:00
|
|
|
objset_t *ds_objset;
|
2009-08-18 22:43:27 +04:00
|
|
|
uint64_t ds_userrefs;
|
2013-09-04 16:00:57 +04:00
|
|
|
void *ds_owner;
|
2008-12-03 23:09:06 +03:00
|
|
|
|
|
|
|
/*
|
2013-09-04 16:00:57 +04:00
|
|
|
* Long holds prevent the ds from being destroyed; they allow the
|
|
|
|
* ds to remain held even after dropping the dp_config_rwlock.
|
|
|
|
* Owning counts as a long hold. See the comments above
|
|
|
|
* dsl_pool_hold() for details.
|
2008-12-03 23:09:06 +03:00
|
|
|
*/
|
2013-09-04 16:00:57 +04:00
|
|
|
refcount_t ds_longholds;
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
/* no locking; only for making guesses */
|
|
|
|
uint64_t ds_trysnap_txg;
|
|
|
|
|
|
|
|
/* for objset_open() */
|
|
|
|
kmutex_t ds_opening_lock;
|
|
|
|
|
|
|
|
uint64_t ds_reserved; /* cached refreservation */
|
|
|
|
uint64_t ds_quota; /* cached refquota */
|
|
|
|
|
2012-05-10 02:05:14 +04:00
|
|
|
kmutex_t ds_sendstream_lock;
|
|
|
|
list_t ds_sendstreams;
|
|
|
|
|
2016-01-07 00:22:48 +03:00
|
|
|
/*
|
|
|
|
* When in the middle of a resumable receive, tracks how much
|
|
|
|
* progress we have made.
|
|
|
|
*/
|
|
|
|
uint64_t ds_resume_object[TXG_SIZE];
|
|
|
|
uint64_t ds_resume_offset[TXG_SIZE];
|
|
|
|
uint64_t ds_resume_bytes[TXG_SIZE];
|
|
|
|
|
2015-11-05 02:00:58 +03:00
|
|
|
/* Protected by our dsl_dir's dd_lock */
|
|
|
|
list_t ds_prop_cbs;
|
|
|
|
|
2015-07-24 19:53:55 +03:00
|
|
|
/*
|
|
|
|
* For ZFEATURE_FLAG_PER_DATASET features, set if this dataset
|
|
|
|
* uses this feature.
|
|
|
|
*/
|
|
|
|
uint8_t ds_feature_inuse[SPA_FEATURES];
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Set if we need to activate the feature on this dataset this txg
|
|
|
|
* (used only in syncing context).
|
|
|
|
*/
|
|
|
|
uint8_t ds_feature_activation_needed[SPA_FEATURES];
|
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
/* Protected by ds_lock; keep at end of struct for better locality */
|
2016-06-16 00:28:36 +03:00
|
|
|
char ds_snapname[ZFS_MAX_DATASET_NAME_LEN];
|
2008-11-20 23:01:55 +03:00
|
|
|
} dsl_dataset_t;
|
|
|
|
|
2015-04-01 18:14:34 +03:00
|
|
|
static inline dsl_dataset_phys_t *
|
|
|
|
dsl_dataset_phys(dsl_dataset_t *ds)
|
|
|
|
{
|
|
|
|
return (ds->ds_dbuf->db_data);
|
|
|
|
}
|
|
|
|
|
2010-08-27 01:24:34 +04:00
|
|
|
/*
|
|
|
|
* The max length of a temporary tag prefix is the number of hex digits
|
|
|
|
* required to express UINT64_MAX plus one for the hyphen.
|
|
|
|
*/
|
|
|
|
#define MAX_TAG_PREFIX_LEN 17
|
|
|
|
|
2015-04-08 21:37:13 +03:00
|
|
|
#define dsl_dataset_is_snapshot(ds) \
|
|
|
|
(dsl_dataset_phys(ds)->ds_num_children != 0)
|
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
#define DS_UNIQUE_IS_ACCURATE(ds) \
|
2015-04-01 18:14:34 +03:00
|
|
|
((dsl_dataset_phys(ds)->ds_flags & DS_FLAG_UNIQUE_ACCURATE) != 0)
|
2008-11-20 23:01:55 +03:00
|
|
|
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_hold(struct dsl_pool *dp, const char *name, void *tag,
|
|
|
|
dsl_dataset_t **dsp);
|
2015-04-02 14:59:15 +03:00
|
|
|
boolean_t dsl_dataset_try_add_ref(struct dsl_pool *dp, dsl_dataset_t *ds,
|
|
|
|
void *tag);
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_hold_obj(struct dsl_pool *dp, uint64_t dsobj, void *tag,
|
|
|
|
dsl_dataset_t **);
|
|
|
|
void dsl_dataset_rele(dsl_dataset_t *ds, void *tag);
|
|
|
|
int dsl_dataset_own(struct dsl_pool *dp, const char *name,
|
2010-05-29 00:45:14 +04:00
|
|
|
void *tag, dsl_dataset_t **dsp);
|
2008-12-03 23:09:06 +03:00
|
|
|
int dsl_dataset_own_obj(struct dsl_pool *dp, uint64_t dsobj,
|
2013-09-04 16:00:57 +04:00
|
|
|
void *tag, dsl_dataset_t **dsp);
|
2010-05-29 00:45:14 +04:00
|
|
|
void dsl_dataset_disown(dsl_dataset_t *ds, void *tag);
|
2013-09-04 16:00:57 +04:00
|
|
|
void dsl_dataset_name(dsl_dataset_t *ds, char *name);
|
|
|
|
boolean_t dsl_dataset_tryown(dsl_dataset_t *ds, void *tag);
|
2016-06-16 00:28:36 +03:00
|
|
|
int dsl_dataset_namelen(dsl_dataset_t *ds);
|
2016-01-07 00:22:48 +03:00
|
|
|
boolean_t dsl_dataset_has_owner(dsl_dataset_t *ds);
|
2008-12-03 23:09:06 +03:00
|
|
|
uint64_t dsl_dataset_create_sync(dsl_dir_t *pds, const char *lastname,
|
|
|
|
dsl_dataset_t *origin, uint64_t flags, cred_t *, dmu_tx_t *);
|
|
|
|
uint64_t dsl_dataset_create_sync_dd(dsl_dir_t *dd, dsl_dataset_t *origin,
|
2008-11-20 23:01:55 +03:00
|
|
|
uint64_t flags, dmu_tx_t *tx);
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_snapshot(nvlist_t *snaps, nvlist_t *props, nvlist_t *errors);
|
2010-05-29 00:45:14 +04:00
|
|
|
int dsl_dataset_promote(const char *name, char *conflsnap);
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_rename_snapshot(const char *fsname,
|
|
|
|
const char *oldsnapname, const char *newsnapname, boolean_t recursive);
|
|
|
|
int dsl_dataset_snapshot_tmp(const char *fsname, const char *snapname,
|
|
|
|
minor_t cleanup_minor, const char *htag);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
blkptr_t *dsl_dataset_get_blkptr(dsl_dataset_t *ds);
|
|
|
|
|
|
|
|
spa_t *dsl_dataset_get_spa(dsl_dataset_t *ds);
|
|
|
|
|
2013-07-29 22:55:16 +04:00
|
|
|
boolean_t dsl_dataset_modified_since_snap(dsl_dataset_t *ds,
|
|
|
|
dsl_dataset_t *snap);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
void dsl_dataset_sync(dsl_dataset_t *os, zio_t *zio, dmu_tx_t *tx);
|
2016-11-22 02:09:54 +03:00
|
|
|
void dsl_dataset_sync_done(dsl_dataset_t *os, dmu_tx_t *tx);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
2010-05-29 00:45:14 +04:00
|
|
|
void dsl_dataset_block_born(dsl_dataset_t *ds, const blkptr_t *bp,
|
2008-11-20 23:01:55 +03:00
|
|
|
dmu_tx_t *tx);
|
2010-05-29 00:45:14 +04:00
|
|
|
int dsl_dataset_block_kill(dsl_dataset_t *ds, const blkptr_t *bp,
|
|
|
|
dmu_tx_t *tx, boolean_t async);
|
2013-01-26 02:57:53 +04:00
|
|
|
int dsl_dataset_snap_lookup(dsl_dataset_t *ds, const char *name,
|
|
|
|
uint64_t *value);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
void dsl_dataset_dirty(dsl_dataset_t *ds, dmu_tx_t *tx);
|
|
|
|
void dsl_dataset_stats(dsl_dataset_t *os, nvlist_t *nv);
|
|
|
|
void dsl_dataset_fast_stat(dsl_dataset_t *ds, dmu_objset_stats_t *stat);
|
|
|
|
void dsl_dataset_space(dsl_dataset_t *ds,
|
|
|
|
uint64_t *refdbytesp, uint64_t *availbytesp,
|
|
|
|
uint64_t *usedobjsp, uint64_t *availobjsp);
|
|
|
|
uint64_t dsl_dataset_fsid_guid(dsl_dataset_t *ds);
|
2011-11-17 22:14:36 +04:00
|
|
|
int dsl_dataset_space_written(dsl_dataset_t *oldsnap, dsl_dataset_t *new,
|
|
|
|
uint64_t *usedp, uint64_t *compp, uint64_t *uncompp);
|
|
|
|
int dsl_dataset_space_wouldfree(dsl_dataset_t *firstsnap, dsl_dataset_t *last,
|
|
|
|
uint64_t *usedp, uint64_t *compp, uint64_t *uncompp);
|
2012-08-24 18:12:46 +04:00
|
|
|
boolean_t dsl_dataset_is_dirty(dsl_dataset_t *ds);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
|
|
|
int dsl_dsobj_to_dsname(char *pname, uint64_t obj, char *buf);
|
|
|
|
|
|
|
|
int dsl_dataset_check_quota(dsl_dataset_t *ds, boolean_t check_quota,
|
|
|
|
uint64_t asize, uint64_t inflight, uint64_t *used,
|
|
|
|
uint64_t *ref_rsrv);
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_set_refquota(const char *dsname, zprop_source_t source,
|
2010-05-29 00:45:14 +04:00
|
|
|
uint64_t quota);
|
2013-09-04 16:00:57 +04:00
|
|
|
int dsl_dataset_set_refreservation(const char *dsname, zprop_source_t source,
|
2010-05-29 00:45:14 +04:00
|
|
|
uint64_t reservation);
|
|
|
|
|
2013-12-12 02:33:41 +04:00
|
|
|
boolean_t dsl_dataset_is_before(dsl_dataset_t *later, dsl_dataset_t *earlier,
|
|
|
|
uint64_t earlier_txg);
|
2013-09-04 16:00:57 +04:00
|
|
|
void dsl_dataset_long_hold(dsl_dataset_t *ds, void *tag);
|
|
|
|
void dsl_dataset_long_rele(dsl_dataset_t *ds, void *tag);
|
|
|
|
boolean_t dsl_dataset_long_held(dsl_dataset_t *ds);
|
|
|
|
|
|
|
|
int dsl_dataset_clone_swap_check_impl(dsl_dataset_t *clone,
|
2013-07-27 21:50:07 +04:00
|
|
|
dsl_dataset_t *origin_head, boolean_t force, void *owner, dmu_tx_t *tx);
|
2013-09-04 16:00:57 +04:00
|
|
|
void dsl_dataset_clone_swap_sync_impl(dsl_dataset_t *clone,
|
|
|
|
dsl_dataset_t *origin_head, dmu_tx_t *tx);
|
|
|
|
int dsl_dataset_snapshot_check_impl(dsl_dataset_t *ds, const char *snapname,
|
2015-04-01 16:07:48 +03:00
|
|
|
dmu_tx_t *tx, boolean_t recv, uint64_t cnt, cred_t *cr);
|
2013-09-04 16:00:57 +04:00
|
|
|
void dsl_dataset_snapshot_sync_impl(dsl_dataset_t *ds, const char *snapname,
|
|
|
|
dmu_tx_t *tx);
|
|
|
|
|
|
|
|
void dsl_dataset_remove_from_next_clones(dsl_dataset_t *ds, uint64_t obj,
|
|
|
|
dmu_tx_t *tx);
|
|
|
|
void dsl_dataset_recalc_head_uniq(dsl_dataset_t *ds);
|
|
|
|
int dsl_dataset_get_snapname(dsl_dataset_t *ds);
|
|
|
|
int dsl_dataset_snap_lookup(dsl_dataset_t *ds, const char *name,
|
|
|
|
uint64_t *value);
|
2015-04-01 16:07:48 +03:00
|
|
|
int dsl_dataset_snap_remove(dsl_dataset_t *ds, const char *name, dmu_tx_t *tx,
|
|
|
|
boolean_t adj_cnt);
|
2013-09-04 16:00:57 +04:00
|
|
|
void dsl_dataset_set_refreservation_sync_impl(dsl_dataset_t *ds,
|
|
|
|
zprop_source_t source, uint64_t value, dmu_tx_t *tx);
|
2013-12-12 02:33:41 +04:00
|
|
|
void dsl_dataset_zapify(dsl_dataset_t *ds, dmu_tx_t *tx);
|
2016-01-07 00:22:48 +03:00
|
|
|
boolean_t dsl_dataset_is_zapified(dsl_dataset_t *ds);
|
|
|
|
boolean_t dsl_dataset_has_resume_receive_state(dsl_dataset_t *ds);
|
2013-08-14 23:42:31 +04:00
|
|
|
int dsl_dataset_rollback(const char *fsname, void *owner, nvlist_t *result);
|
2008-11-20 23:01:55 +03:00
|
|
|
|
2015-07-24 19:53:55 +03:00
|
|
|
void dsl_dataset_deactivate_feature(uint64_t dsobj,
|
|
|
|
spa_feature_t f, dmu_tx_t *tx);
|
|
|
|
|
2008-11-20 23:01:55 +03:00
|
|
|
#ifdef ZFS_DEBUG
|
|
|
|
#define dprintf_ds(ds, fmt, ...) do { \
|
|
|
|
if (zfs_flags & ZFS_DEBUG_DPRINTF) { \
|
2016-06-16 00:28:36 +03:00
|
|
|
char *__ds_name = kmem_alloc(ZFS_MAX_DATASET_NAME_LEN, KM_SLEEP); \
|
2008-11-20 23:01:55 +03:00
|
|
|
dsl_dataset_name(ds, __ds_name); \
|
|
|
|
dprintf("ds=%s " fmt, __ds_name, __VA_ARGS__); \
|
2016-06-16 00:28:36 +03:00
|
|
|
kmem_free(__ds_name, ZFS_MAX_DATASET_NAME_LEN); \
|
2008-11-20 23:01:55 +03:00
|
|
|
} \
|
|
|
|
_NOTE(CONSTCOND) } while (0)
|
|
|
|
#else
|
|
|
|
#define dprintf_ds(dd, fmt, ...)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifdef __cplusplus
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#endif /* _SYS_DSL_DATASET_H */
|