c/mirror_zfs
1
0
Fork 0
mirror of https://git.proxmox.com/git/mirror_zfs.git synced 2026-05-25 19:57:43 +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
module/zfs/dbuf.c
+98 -5
View File
@@ -1359,6 +1359,20 @@ dbuf_read_impl(dmu_buf_impl_t *db, zio_t *zio, uint32_t flags)
return (0);
}
/*
* Any attempt to read a redacted block should result in an error. This
* will never happen under normal conditions, but can be useful for
* debugging purposes.
*/
if (BP_IS_REDACTED(db->db_blkptr)) {
ASSERT(dsl_dataset_feature_is_active(
db->db_objset->os_dsl_dataset,
SPA_FEATURE_REDACTED_DATASETS));
DB_DNODE_EXIT(db);
mutex_exit(&db->db_mtx);
return (SET_ERROR(EIO));
}
SET_BOOKMARK(&zb, dmu_objset_id(db->db_objset),
db->db.db_object, db->db_level, db->db_blkid);
@@ -2395,11 +2409,23 @@ dmu_buf_set_crypt_params(dmu_buf_t *db_fake, boolean_t byteorder,
bcopy(mac, dr->dt.dl.dr_mac, ZIO_DATA_MAC_LEN);
}
#pragma weak dmu_buf_fill_done = dbuf_fill_done
static void
dbuf_override_impl(dmu_buf_impl_t *db, const blkptr_t *bp, dmu_tx_t *tx)
{
struct dirty_leaf *dl;
ASSERT3U(db->db_last_dirty->dr_txg, ==, tx->tx_txg);
dl = &db->db_last_dirty->dt.dl;
dl->dr_overridden_by = *bp;
dl->dr_override_state = DR_OVERRIDDEN;
dl->dr_overridden_by.blk_birth = db->db_last_dirty->dr_txg;
}
/* ARGSUSED */
void
dbuf_fill_done(dmu_buf_impl_t *db, dmu_tx_t *tx)
dmu_buf_fill_done(dmu_buf_t *dbuf, dmu_tx_t *tx)
{
dmu_buf_impl_t *db = (dmu_buf_impl_t *)dbuf;
mutex_enter(&db->db_mtx);
DBUF_VERIFY(db);
@@ -2454,6 +2480,31 @@ dmu_buf_write_embedded(dmu_buf_t *dbuf, void *data,
dl->dr_overridden_by.blk_birth = db->db_last_dirty->dr_txg;
}
void
dmu_buf_redact(dmu_buf_t *dbuf, dmu_tx_t *tx)
{
dmu_buf_impl_t *db = (dmu_buf_impl_t *)dbuf;
dmu_object_type_t type;
ASSERT(dsl_dataset_feature_is_active(db->db_objset->os_dsl_dataset,
SPA_FEATURE_REDACTED_DATASETS));
DB_DNODE_ENTER(db);
type = DB_DNODE(db)->dn_type;
DB_DNODE_EXIT(db);
ASSERT0(db->db_level);
dmu_buf_will_not_fill(dbuf, tx);
blkptr_t bp = { { { {0} } } };
BP_SET_TYPE(&bp, type);
BP_SET_LEVEL(&bp, 0);
BP_SET_BIRTH(&bp, tx->tx_txg, 0);
BP_SET_REDACTED(&bp);
BPE_SET_LSIZE(&bp, dbuf->db_size);
dbuf_override_impl(db, &bp, tx);
}
/*
* Directly assign a provided arc buf to a given dbuf if it's not referenced
* by anybody except our caller. Otherwise copy arcbuf's contents to dbuf.
@@ -2820,6 +2871,36 @@ dbuf_create(dnode_t *dn, uint8_t level, uint64_t blkid,
return (db);
}
/*
* This function returns a block pointer and information about the object,
* given a dnode and a block. This is a publicly accessible version of
* dbuf_findbp that only returns some information, rather than the
* dbuf. Note that the dnode passed in must be held, and the dn_struct_rwlock
* should be locked as (at least) a reader.
*/
int
dbuf_dnode_findbp(dnode_t *dn, uint64_t level, uint64_t blkid,
blkptr_t *bp, uint16_t *datablkszsec, uint8_t *indblkshift)
{
dmu_buf_impl_t *dbp = NULL;
blkptr_t *bp2;
int err = 0;
ASSERT(RW_LOCK_HELD(&dn->dn_struct_rwlock));
err = dbuf_findbp(dn, level, blkid, B_FALSE, &dbp, &bp2);
if (err == 0) {
*bp = *bp2;
if (dbp != NULL)
dbuf_rele(dbp, NULL);
if (datablkszsec != NULL)
*datablkszsec = dn->dn_phys->dn_datablkszsec;
if (indblkshift != NULL)
*indblkshift = dn->dn_phys->dn_indblkshift;
}
return (err);
}
typedef struct dbuf_prefetch_arg {
spa_t *dpa_spa; /* The spa to issue the prefetch in. */
zbookmark_phys_t dpa_zb; /* The target block to prefetch. */
@@ -2837,7 +2918,12 @@ typedef struct dbuf_prefetch_arg {
static void
dbuf_issue_final_prefetch(dbuf_prefetch_arg_t *dpa, blkptr_t *bp)
{
if (BP_IS_HOLE(bp) || BP_IS_EMBEDDED(bp))
ASSERT(!BP_IS_REDACTED(bp) ||
dsl_dataset_feature_is_active(
dpa->dpa_dnode->dn_objset->os_dsl_dataset,
SPA_FEATURE_REDACTED_DATASETS));
if (BP_IS_HOLE(bp) || BP_IS_EMBEDDED(bp) || BP_IS_REDACTED(bp))
return;
int zio_flags = ZIO_FLAG_CANFAIL | ZIO_FLAG_SPECULATIVE;
@@ -2921,7 +3007,11 @@ dbuf_prefetch_indirect_done(zio_t *zio, const zbookmark_phys_t *zb,
blkptr_t *bp = ((blkptr_t *)abuf->b_data) +
P2PHASE(nextblkid, 1ULL << dpa->dpa_epbs);
if (BP_IS_HOLE(bp)) {
ASSERT(!BP_IS_REDACTED(bp) ||
dsl_dataset_feature_is_active(
dpa->dpa_dnode->dn_objset->os_dsl_dataset,
SPA_FEATURE_REDACTED_DATASETS));
if (BP_IS_HOLE(bp) || BP_IS_REDACTED(bp)) {
kmem_free(dpa, sizeof (*dpa));
} else if (dpa->dpa_curlevel == dpa->dpa_zb.zb_level) {
ASSERT3U(nextblkid, ==, dpa->dpa_zb.zb_blkid);
@@ -3025,7 +3115,10 @@ dbuf_prefetch(dnode_t *dn, int64_t level, uint64_t blkid, zio_priority_t prio,
ASSERT3U(curblkid, <, dn->dn_phys->dn_nblkptr);
bp = dn->dn_phys->dn_blkptr[curblkid];
}
if (BP_IS_HOLE(&bp))
ASSERT(!BP_IS_REDACTED(&bp) ||
dsl_dataset_feature_is_active(dn->dn_objset->os_dsl_dataset,
SPA_FEATURE_REDACTED_DATASETS));
if (BP_IS_HOLE(&bp) || BP_IS_REDACTED(&bp))
return;
ASSERT3U(curlevel, ==, BP_GET_LEVEL(&bp));