c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-22 10:37:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Implement Redacted Send/Receive

Browse Source 
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
This commit is contained in:
Paul Dagnelie
2019-06-19 09:48:13 -07:00
committed by Brian Behlendorf
parent c1b5801bb5
commit 30af21b025
103 changed files with 11513 additions and 2668 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/sys/spa.h
+24 -2
View File
@@ -94,13 +94,19 @@ _NOTE(CONSTCOND) } while (0)
#define BF64_GET_SB(x, low, len, shift, bias) \
((BF64_GET(x, low, len) + (bias)) << (shift))
/*
* We use ASSERT3U instead of ASSERT in these macros to prevent a lint error in
* the case where val is a constant. We can't fix ASSERT because it's used as
* an expression in several places in the kernel; as a result, changing it to
* the do{} while() syntax to allow us to _NOTE the CONSTCOND is not an option.
*/
#define BF32_SET_SB(x, low, len, shift, bias, val) do { \
ASSERT(IS_P2ALIGNED(val, 1U << shift)); \
ASSERT3U(IS_P2ALIGNED(val, 1U << shift), !=, B_FALSE); \
ASSERT3S((val) >> (shift), >=, bias); \
BF32_SET(x, low, len, ((val) >> (shift)) - (bias)); \
_NOTE(CONSTCOND) } while (0)
#define BF64_SET_SB(x, low, len, shift, bias, val) do { \
ASSERT(IS_P2ALIGNED(val, 1ULL << shift)); \
ASSERT3U(IS_P2ALIGNED(val, 1ULL << shift), !=, B_FALSE); \
ASSERT3S((val) >> (shift), >=, bias); \
BF64_SET(x, low, len, ((val) >> (shift)) - (bias)); \
_NOTE(CONSTCOND) } while (0)
@@ -402,6 +408,7 @@ _NOTE(CONSTCOND) } while (0)
typedef enum bp_embedded_type {
BP_EMBEDDED_TYPE_DATA,
BP_EMBEDDED_TYPE_RESERVED, /* Reserved for an unintegrated feature. */
BP_EMBEDDED_TYPE_REDACTED,
NUM_BP_EMBEDDED_TYPES = BP_EMBEDDED_TYPE_RESERVED
} bp_embedded_type_t;
@@ -602,6 +609,14 @@ _NOTE(CONSTCOND) } while (0)
#define BP_IS_HOLE(bp) \
(!BP_IS_EMBEDDED(bp) && DVA_IS_EMPTY(BP_IDENTITY(bp)))
#define BP_SET_REDACTED(bp) \
{ \
BP_SET_EMBEDDED(bp, B_TRUE); \
BPE_SET_ETYPE(bp, BP_EMBEDDED_TYPE_REDACTED); \
}
#define BP_IS_REDACTED(bp) \
(BP_IS_EMBEDDED(bp) && BPE_GET_ETYPE(bp) == BP_EMBEDDED_TYPE_REDACTED)
/* BP_IS_RAIDZ(bp) assumes no block compression */
#define BP_IS_RAIDZ(bp) (DVA_GET_ASIZE(&(bp)->blk_dva[0]) > \
BP_GET_PSIZE(bp))
@@ -678,6 +693,13 @@ _NOTE(CONSTCOND) } while (0)
(u_longlong_t)BPE_GET_LSIZE(bp), \
(u_longlong_t)BPE_GET_PSIZE(bp), \
(u_longlong_t)bp->blk_birth); \
} else if (BP_IS_REDACTED(bp)) { \
len += func(buf + len, size - len, \
"REDACTED [L%llu %s] size=%llxL birth=%lluL", \
(u_longlong_t)BP_GET_LEVEL(bp), \
type, \
(u_longlong_t)BP_GET_LSIZE(bp), \
(u_longlong_t)bp->blk_birth); \
} else { \
for (int d = 0; d < BP_GET_NDVAS(bp); d++) { \
const dva_t *dva = &bp->blk_dva[d]; \