mirror_zfs/include/sys/dmu_impl.h

265 lines
7.0 KiB
C
Raw Normal View History

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
*/
/*
* Copyright 2010 Sun Microsystems, Inc. All rights reserved.
2008-11-20 23:01:55 +03:00
* Use is subject to license terms.
*/
/*
* Copyright (c) 2012, Joyent, Inc. All rights reserved.
Implement Redacted Send/Receive Redacted send/receive allows users to send subsets of their data to a target system. One possible use case for this feature is to not transmit sensitive information to a data warehousing, test/dev, or analytics environment. Another is to save space by not replicating unimportant data within a given dataset, for example in backup tools like zrepl. Redacted send/receive is a three-stage process. First, a clone (or clones) is made of the snapshot to be sent to the target. In this clone (or clones), all unnecessary or unwanted data is removed or modified. This clone is then snapshotted to create the "redaction snapshot" (or snapshots). Second, the new zfs redact command is used to create a redaction bookmark. The redaction bookmark stores the list of blocks in a snapshot that were modified by the redaction snapshot(s). Finally, the redaction bookmark is passed as a parameter to zfs send. When sending to the snapshot that was redacted, the redaction bookmark is used to filter out blocks that contain sensitive or unwanted information, and those blocks are not included in the send stream. When sending from the redaction bookmark, the blocks it contains are considered as candidate blocks in addition to those blocks in the destination snapshot that were modified since the creation_txg of the redaction bookmark. This step is necessary to allow the target to rehydrate data in the case where some blocks are accidentally or unnecessarily modified in the redaction snapshot. The changes to bookmarks to enable fast space estimation involve adding deadlists to bookmarks. There is also logic to manage the life cycles of these deadlists. The new size estimation process operates in cases where previously an accurate estimate could not be provided. In those cases, a send is performed where no data blocks are read, reducing the runtime significantly and providing a byte-accurate size estimate. Reviewed-by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Prashanth Sreenivasa <pks@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Chris Williamson <chris.williamson@delphix.com> Reviewed-by: Pavel Zhakarov <pavel.zakharov@delphix.com> Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com> Closes #7958
2019-06-19 19:48:13 +03:00
* Copyright (c) 2013, 2018 by Delphix. All rights reserved.
2008-11-20 23:01:55 +03:00
*/
#ifndef _SYS_DMU_IMPL_H
#define _SYS_DMU_IMPL_H
#include <sys/txg_impl.h>
#include <sys/zio.h>
#include <sys/dnode.h>
#include <sys/zfs_context.h>
#include <sys/zfs_ioctl.h>
2008-11-20 23:01:55 +03:00
#ifdef __cplusplus
extern "C" {
#endif
/*
* This is the locking strategy for the DMU. Numbers in parenthesis are
* cases that use that lock order, referenced below:
*
* ARC is self-contained
* bplist is self-contained
* refcount is self-contained
* txg is self-contained (hopefully!)
* zst_lock
* zf_rwlock
*
* XXX try to improve evicting path?
*
* dp_config_rwlock > os_obj_lock > dn_struct_rwlock >
* dn_dbufs_mtx > hash_mutexes > db_mtx > dd_lock > leafs
2008-11-20 23:01:55 +03:00
*
* dp_config_rwlock
* must be held before: everything
* protects dd namespace changes
* protects property changes globally
* held from:
* dsl_dir_open/r:
* dsl_dir_create_sync/w:
* dsl_dir_sync_destroy/w:
* dsl_dir_rename_sync/w:
* dsl_prop_changed_notify/r:
*
* os_obj_lock
* must be held before:
* everything except dp_config_rwlock
* protects os_obj_next
* held from:
* dmu_object_alloc: dn_dbufs_mtx, db_mtx, hash_mutexes, dn_struct_rwlock
*
* dn_struct_rwlock
* must be held before:
* everything except dp_config_rwlock and os_obj_lock
* protects structure of dnode (eg. nlevels)
* db_blkptr can change when syncing out change to nlevels
* dn_maxblkid
* dn_nlevels
* dn_*blksz*
* phys nlevels, maxblkid, physical blkptr_t's (?)
* held from:
* callers of dbuf_read_impl, dbuf_hold[_impl], dbuf_prefetch
* dmu_object_info_from_dnode: dn_dirty_mtx (dn_datablksz)
* dbuf_read_impl: db_mtx, dmu_zfetch()
* dmu_zfetch: zf_rwlock/r, zst_lock, dbuf_prefetch()
* dbuf_new_size: db_mtx
* dbuf_dirty: db_mtx
* dbuf_findbp: (callers, phys? - the real need)
* dbuf_create: dn_dbufs_mtx, hash_mutexes, db_mtx (phys?)
* dbuf_prefetch: dn_dirty_mtx, hash_mutexes, db_mtx, dn_dbufs_mtx
* dbuf_hold_impl: hash_mutexes, db_mtx, dn_dbufs_mtx, dbuf_findbp()
* dnode_sync/w (increase_indirection): db_mtx (phys)
* dnode_set_blksz/w: dn_dbufs_mtx (dn_*blksz*)
* dnode_new_blkid/w: (dn_maxblkid)
* dnode_free_range/w: dn_dirty_mtx (dn_maxblkid)
* dnode_next_offset: (phys)
*
* dn_dbufs_mtx
* must be held before:
* db_mtx, hash_mutexes
* protects:
* dn_dbufs
* dn_evicted
* held from:
* dmu_evict_user: db_mtx (dn_dbufs)
* dbuf_free_range: db_mtx (dn_dbufs)
* dbuf_remove_ref: db_mtx, callees:
* dbuf_hash_remove: hash_mutexes, db_mtx
* dbuf_create: hash_mutexes, db_mtx (dn_dbufs)
* dnode_set_blksz: (dn_dbufs)
*
* hash_mutexes (global)
* must be held before:
* db_mtx
* protects dbuf_hash_table (global) and db_hash_next
* held from:
* dbuf_find: db_mtx
* dbuf_hash_insert: db_mtx
* dbuf_hash_remove: db_mtx
*
* db_mtx (meta-leaf)
* must be held before:
* dn_mtx, dn_dirty_mtx, dd_lock (leaf mutexes)
* protects:
* db_state
* db_holds
* db_buf
* db_changed
* db_data_pending
* db_dirtied
* db_link
* db_dirty_node (??)
* db_dirtycnt
* db_d.*
* db.*
* held from:
* dbuf_dirty: dn_mtx, dn_dirty_mtx
* dbuf_dirty->dsl_dir_willuse_space: dd_lock
* dbuf_dirty->dbuf_new_block->dsl_dataset_block_freeable: dd_lock
* dbuf_undirty: dn_dirty_mtx (db_d)
* dbuf_write_done: dn_dirty_mtx (db_state)
* dbuf_*
* dmu_buf_update_user: none (db_d)
* dmu_evict_user: none (db_d) (maybe can eliminate)
* dbuf_find: none (db_holds)
* dbuf_hash_insert: none (db_holds)
* dmu_buf_read_array_impl: none (db_state, db_changed)
* dmu_sync: none (db_dirty_node, db_d)
* dnode_reallocate: none (db)
*
* dn_mtx (leaf)
* protects:
* dn_dirty_dbufs
* dn_ranges
* phys accounting
* dn_allocated_txg
* dn_free_txg
* dn_assigned_txg
* dn_dirty_txg
2008-11-20 23:01:55 +03:00
* dd_assigned_tx
* dn_notxholds
* dn_nodnholds
2008-11-20 23:01:55 +03:00
* dn_dirtyctx
* dn_dirtyctx_firstset
* (dn_phys copy fields?)
* (dn_phys contents?)
* held from:
* dnode_*
* dbuf_dirty: none
* dbuf_sync: none (phys accounting)
* dbuf_undirty: none (dn_ranges, dn_dirty_dbufs)
* dbuf_write_done: none (phys accounting)
* dmu_object_info_from_dnode: none (accounting)
* dmu_tx_commit: none
* dmu_tx_hold_object_impl: none
* dmu_tx_try_assign: dn_notxholds(cv)
* dmu_tx_unassign: none
*
* dd_lock
* must be held before:
* ds_lock
* ancestors' dd_lock
2008-11-20 23:01:55 +03:00
* protects:
* dd_prop_cbs
* dd_sync_*
* dd_used_bytes
* dd_tempreserved
* dd_space_towrite
* dd_myname
* dd_phys accounting?
* held from:
* dsl_dir_*
* dsl_prop_changed_notify: none (dd_prop_cbs)
* dsl_prop_register: none (dd_prop_cbs)
* dsl_prop_unregister: none (dd_prop_cbs)
*
* os_lock (leaf)
* protects:
* os_dirty_dnodes
* os_free_dnodes
* os_dnodes
* os_downgraded_dbufs
* dn_dirtyblksz
* dn_dirty_link
* held from:
* dnode_create: none (os_dnodes)
* dnode_destroy: none (os_dnodes)
* dnode_setdirty: none (dn_dirtyblksz, os_*_dnodes)
* dnode_free: none (dn_dirtyblksz, os_*_dnodes)
*
* ds_lock
2008-11-20 23:01:55 +03:00
* protects:
* ds_objset
2008-11-20 23:01:55 +03:00
* ds_open_refcount
* ds_snapname
* ds_phys accounting
2009-08-18 22:43:27 +04:00
* ds_phys userrefs zapobj
* ds_reserved
2008-11-20 23:01:55 +03:00
* held from:
* dsl_dataset_*
*
* dr_mtx (leaf)
* protects:
* dr_children
* held from:
* dbuf_dirty
* dbuf_undirty
* dbuf_sync_indirect
* dnode_new_blkid
*/
struct objset;
struct dmu_pool;
typedef struct dmu_xuio {
int next;
int cnt;
struct arc_buf **bufs;
iovec_t *iovp;
} dmu_xuio_t;
Implement Redacted Send/Receive Redacted send/receive allows users to send subsets of their data to a target system. One possible use case for this feature is to not transmit sensitive information to a data warehousing, test/dev, or analytics environment. Another is to save space by not replicating unimportant data within a given dataset, for example in backup tools like zrepl. Redacted send/receive is a three-stage process. First, a clone (or clones) is made of the snapshot to be sent to the target. In this clone (or clones), all unnecessary or unwanted data is removed or modified. This clone is then snapshotted to create the "redaction snapshot" (or snapshots). Second, the new zfs redact command is used to create a redaction bookmark. The redaction bookmark stores the list of blocks in a snapshot that were modified by the redaction snapshot(s). Finally, the redaction bookmark is passed as a parameter to zfs send. When sending to the snapshot that was redacted, the redaction bookmark is used to filter out blocks that contain sensitive or unwanted information, and those blocks are not included in the send stream. When sending from the redaction bookmark, the blocks it contains are considered as candidate blocks in addition to those blocks in the destination snapshot that were modified since the creation_txg of the redaction bookmark. This step is necessary to allow the target to rehydrate data in the case where some blocks are accidentally or unnecessarily modified in the redaction snapshot. The changes to bookmarks to enable fast space estimation involve adding deadlists to bookmarks. There is also logic to manage the life cycles of these deadlists. The new size estimation process operates in cases where previously an accurate estimate could not be provided. In those cases, a send is performed where no data blocks are read, reducing the runtime significantly and providing a byte-accurate size estimate. Reviewed-by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: Prashanth Sreenivasa <pks@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Chris Williamson <chris.williamson@delphix.com> Reviewed-by: Pavel Zhakarov <pavel.zakharov@delphix.com> Reviewed-by: Sebastien Roy <sebastien.roy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com> Closes #7958
2019-06-19 19:48:13 +03:00
typedef struct dmu_sendstatus {
list_node_t dss_link;
int dss_outfd;
proc_t *dss_proc;
offset_t *dss_off;
uint64_t dss_blocks; /* blocks visited during the sending process */
} dmu_sendstatus_t;
void dmu_object_zapify(objset_t *, uint64_t, dmu_object_type_t, dmu_tx_t *);
void dmu_object_free_zapified(objset_t *, uint64_t, dmu_tx_t *);
int dmu_buf_hold_noread(objset_t *, uint64_t, uint64_t,
void *, dmu_buf_t **);
2008-11-20 23:01:55 +03:00
#ifdef __cplusplus
}
#endif
#endif /* _SYS_DMU_IMPL_H */