mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 11:29:36 +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
92 lines
2.9 KiB
C
92 lines
2.9 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.
|
|
* Copyright 2011 Nexenta Systems, Inc. All rights reserved.
|
|
* Copyright (c) 2013, Joyent, Inc. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _DMU_RECV_H
|
|
#define _DMU_RECV_H
|
|
|
|
#include <sys/inttypes.h>
|
|
#include <sys/dsl_bookmark.h>
|
|
#include <sys/dsl_dataset.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/objlist.h>
|
|
#include <sys/dsl_bookmark.h>
|
|
|
|
extern const char *recv_clone_name;
|
|
|
|
typedef struct dmu_recv_cookie {
|
|
struct dsl_dataset *drc_ds;
|
|
struct dmu_replay_record *drc_drr_begin;
|
|
struct drr_begin *drc_drrb;
|
|
const char *drc_tofs;
|
|
const char *drc_tosnap;
|
|
boolean_t drc_newfs;
|
|
boolean_t drc_byteswap;
|
|
uint64_t drc_featureflags;
|
|
boolean_t drc_force;
|
|
boolean_t drc_resumable;
|
|
boolean_t drc_raw;
|
|
boolean_t drc_clone;
|
|
boolean_t drc_spill;
|
|
struct avl_tree *drc_guid_to_ds_map;
|
|
nvlist_t *drc_keynvl;
|
|
uint64_t drc_fromsnapobj;
|
|
uint64_t drc_newsnapobj;
|
|
uint64_t drc_ivset_guid;
|
|
void *drc_owner;
|
|
cred_t *drc_cred;
|
|
nvlist_t *drc_begin_nvl;
|
|
|
|
objset_t *drc_os;
|
|
vnode_t *drc_vp; /* The vnode to read the stream from */
|
|
uint64_t drc_voff; /* The current offset in the stream */
|
|
uint64_t drc_bytes_read;
|
|
/*
|
|
* A record that has had its payload read in, but hasn't yet been handed
|
|
* off to the worker thread.
|
|
*/
|
|
struct receive_record_arg *drc_rrd;
|
|
/* A record that has had its header read in, but not its payload. */
|
|
struct receive_record_arg *drc_next_rrd;
|
|
zio_cksum_t drc_cksum;
|
|
zio_cksum_t drc_prev_cksum;
|
|
int drc_err;
|
|
/* Sorted list of objects not to issue prefetches for. */
|
|
objlist_t *drc_ignore_objlist;
|
|
} dmu_recv_cookie_t;
|
|
|
|
int dmu_recv_begin(char *tofs, char *tosnap, dmu_replay_record_t *drr_begin,
|
|
boolean_t force, boolean_t resumable, nvlist_t *localprops,
|
|
nvlist_t *hidden_args, char *origin, dmu_recv_cookie_t *drc,
|
|
vnode_t *vp, offset_t *voffp);
|
|
int dmu_recv_stream(dmu_recv_cookie_t *drc, int cleanup_fd,
|
|
uint64_t *action_handlep, offset_t *voffp);
|
|
int dmu_recv_end(dmu_recv_cookie_t *drc, void *owner);
|
|
boolean_t dmu_objset_is_receiving(objset_t *os);
|
|
|
|
#endif /* _DMU_RECV_H */
|