mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-18 18:31:00 +03:00
30af21b025
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
93 lines
3.0 KiB
C
93 lines
3.0 KiB
C
/*
|
|
* 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) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
|
* Copyright (c) 2012, 2018 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_DMU_TRAVERSE_H
|
|
#define _SYS_DMU_TRAVERSE_H
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/zio.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
struct dnode_phys;
|
|
struct dsl_dataset;
|
|
struct zilog;
|
|
struct arc_buf;
|
|
|
|
typedef int (blkptr_cb_t)(spa_t *spa, zilog_t *zilog, const blkptr_t *bp,
|
|
const zbookmark_phys_t *zb, const struct dnode_phys *dnp, void *arg);
|
|
|
|
#define TRAVERSE_PRE (1<<0)
|
|
#define TRAVERSE_POST (1<<1)
|
|
#define TRAVERSE_PREFETCH_METADATA (1<<2)
|
|
#define TRAVERSE_PREFETCH_DATA (1<<3)
|
|
#define TRAVERSE_PREFETCH (TRAVERSE_PREFETCH_METADATA | TRAVERSE_PREFETCH_DATA)
|
|
#define TRAVERSE_HARD (1<<4)
|
|
|
|
/*
|
|
* Encrypted dnode blocks have encrypted bonus buffers while the rest
|
|
* of the dnode is left unencrypted. Callers can specify the
|
|
* TRAVERSE_NO_DECRYPT flag to indicate to the traversal code that
|
|
* they wish to receive the raw encrypted dnodes instead of attempting
|
|
* to read the logical data.
|
|
*/
|
|
#define TRAVERSE_NO_DECRYPT (1<<5)
|
|
|
|
/* Special traverse error return value to indicate skipping of children */
|
|
#define TRAVERSE_VISIT_NO_CHILDREN -1
|
|
|
|
int traverse_dataset(struct dsl_dataset *ds,
|
|
uint64_t txg_start, int flags, blkptr_cb_t func, void *arg);
|
|
int traverse_dataset_resume(struct dsl_dataset *ds, uint64_t txg_start,
|
|
zbookmark_phys_t *resume, int flags, blkptr_cb_t func, void *arg);
|
|
int traverse_dataset_destroyed(spa_t *spa, blkptr_t *blkptr,
|
|
uint64_t txg_start, zbookmark_phys_t *resume, int flags,
|
|
blkptr_cb_t func, void *arg);
|
|
int traverse_pool(spa_t *spa,
|
|
uint64_t txg_start, int flags, blkptr_cb_t func, void *arg);
|
|
|
|
/*
|
|
* Note that this calculation cannot overflow with the current maximum indirect
|
|
* block size (128k). If that maximum is increased to 1M, however, this
|
|
* calculation can overflow, and handling would need to be added to ensure
|
|
* continued correctness.
|
|
*/
|
|
static inline uint64_t
|
|
bp_span_in_blocks(uint8_t indblkshift, uint64_t level)
|
|
{
|
|
unsigned int shift = level * (indblkshift - SPA_BLKPTRSHIFT);
|
|
ASSERT3U(shift, <, 64);
|
|
return (1ULL << shift);
|
|
}
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_DMU_TRAVERSE_H */
|