mirror_zfs/module/zfs/dmu_diff.c

238 lines
6.3 KiB
C
Raw Normal View History

/*
* 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) 2010, Oracle and/or its affiliates. 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) 2012, 2018 by Delphix. All rights reserved.
* Copyright (c) 2019, loli10K <ezomori.nozomu@gmail.com>. All rights reserved.
*/
#include <sys/dmu.h>
#include <sys/dmu_impl.h>
#include <sys/dmu_tx.h>
#include <sys/dbuf.h>
#include <sys/dnode.h>
#include <sys/zfs_context.h>
#include <sys/dmu_objset.h>
#include <sys/dmu_traverse.h>
#include <sys/dsl_dataset.h>
#include <sys/dsl_dir.h>
#include <sys/dsl_pool.h>
#include <sys/dsl_synctask.h>
#include <sys/zfs_ioctl.h>
#include <sys/zap.h>
#include <sys/zio_checksum.h>
#include <sys/zfs_znode.h>
struct diffarg {
struct vnode *da_vp; /* file to which we are reporting */
offset_t *da_offp;
int da_err; /* error that stopped diff search */
dmu_diff_record_t da_ddr;
};
static int
write_record(struct diffarg *da)
{
ssize_t resid; /* have to get resid to get detailed errno */
if (da->da_ddr.ddr_type == DDR_NONE) {
da->da_err = 0;
return (0);
}
da->da_err = vn_rdwr(UIO_WRITE, da->da_vp, (caddr_t)&da->da_ddr,
sizeof (da->da_ddr), 0, UIO_SYSSPACE, FAPPEND,
RLIM64_INFINITY, CRED(), &resid);
*da->da_offp += sizeof (da->da_ddr);
return (da->da_err);
}
static int
report_free_dnode_range(struct diffarg *da, uint64_t first, uint64_t last)
{
ASSERT(first <= last);
if (da->da_ddr.ddr_type != DDR_FREE ||
first != da->da_ddr.ddr_last + 1) {
if (write_record(da) != 0)
return (da->da_err);
da->da_ddr.ddr_type = DDR_FREE;
da->da_ddr.ddr_first = first;
da->da_ddr.ddr_last = last;
return (0);
}
da->da_ddr.ddr_last = last;
return (0);
}
static int
report_dnode(struct diffarg *da, uint64_t object, dnode_phys_t *dnp)
{
ASSERT(dnp != NULL);
if (dnp->dn_type == DMU_OT_NONE)
return (report_free_dnode_range(da, object, object));
if (da->da_ddr.ddr_type != DDR_INUSE ||
object != da->da_ddr.ddr_last + 1) {
if (write_record(da) != 0)
return (da->da_err);
da->da_ddr.ddr_type = DDR_INUSE;
da->da_ddr.ddr_first = da->da_ddr.ddr_last = object;
return (0);
}
da->da_ddr.ddr_last = object;
return (0);
}
#define DBP_SPAN(dnp, level) \
(((uint64_t)dnp->dn_datablkszsec) << (SPA_MINBLOCKSHIFT + \
(level) * (dnp->dn_indblkshift - SPA_BLKPTRSHIFT)))
/* ARGSUSED */
static int
diff_cb(spa_t *spa, zilog_t *zilog, const blkptr_t *bp,
const zbookmark_phys_t *zb, const dnode_phys_t *dnp, void *arg)
{
struct diffarg *da = arg;
int err = 0;
if (issig(JUSTLOOKING) && issig(FORREAL))
return (SET_ERROR(EINTR));
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
if (zb->zb_level == ZB_DNODE_LEVEL ||
zb->zb_object != DMU_META_DNODE_OBJECT)
return (0);
if (BP_IS_HOLE(bp)) {
uint64_t span = DBP_SPAN(dnp, zb->zb_level);
uint64_t dnobj = (zb->zb_blkid * span) >> DNODE_SHIFT;
err = report_free_dnode_range(da, dnobj,
dnobj + (span >> DNODE_SHIFT) - 1);
if (err)
return (err);
} else if (zb->zb_level == 0) {
dnode_phys_t *blk;
arc_buf_t *abuf;
arc_flags_t aflags = ARC_FLAG_WAIT;
int epb = BP_GET_LSIZE(bp) >> DNODE_SHIFT;
int zio_flags = ZIO_FLAG_CANFAIL;
int i;
if (BP_IS_PROTECTED(bp))
zio_flags |= ZIO_FLAG_RAW;
if (arc_read(NULL, spa, bp, arc_getbuf_func, &abuf,
ZIO_PRIORITY_ASYNC_READ, zio_flags, &aflags, zb) != 0)
return (SET_ERROR(EIO));
blk = abuf->b_data;
for (i = 0; i < epb; i += blk[i].dn_extra_slots + 1) {
uint64_t dnobj = (zb->zb_blkid <<
(DNODE_BLOCK_SHIFT - DNODE_SHIFT)) + i;
err = report_dnode(da, dnobj, blk+i);
if (err)
break;
}
OpenZFS 6950 - ARC should cache compressed data Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Matt Ahrens <mahrens@delphix.com> Reviewed by: Paul Dagnelie <pcd@delphix.com> Reviewed by: Tom Caputi <tcaputi@datto.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Ported by: David Quigley <david.quigley@intel.com> This review covers the reading and writing of compressed arc headers, sharing data between the arc_hdr_t and the arc_buf_t, and the implementation of a new dbuf cache to keep frequently access data uncompressed. I've added a new member to l1 arc hdr called b_pdata. The b_pdata always hangs off the arc_buf_hdr_t (if an L1 hdr is in use) and points to the physical block for that DVA. The physical block may or may not be compressed. If compressed arc is enabled and the block on-disk is compressed, then the b_pdata will match the block on-disk and remain compressed in memory. If the block on disk is not compressed, then neither will the b_pdata. Lastly, if compressed arc is disabled, then b_pdata will always be an uncompressed version of the on-disk block. Typically the arc will cache only the arc_buf_hdr_t and will aggressively evict any arc_buf_t's that are no longer referenced. This means that the arc will primarily have compressed blocks as the arc_buf_t's are considered overhead and are always uncompressed. When a consumer reads a block we first look to see if the arc_buf_hdr_t is cached. If the hdr is cached then we allocate a new arc_buf_t and decompress the b_pdata contents into the arc_buf_t's b_data. If the hdr already has a arc_buf_t, then we will allocate an additional arc_buf_t and bcopy the uncompressed contents from the first arc_buf_t to the new one. Writing to the compressed arc requires that we first discard the b_pdata since the physical block is about to be rewritten. The new data contents will be passed in via an arc_buf_t (uncompressed) and during the I/O pipeline stages we will copy the physical block contents to a newly allocated b_pdata. When an l2arc is inuse it will also take advantage of the b_pdata. Now the l2arc will always write the contents of b_pdata to the l2arc. This means that when compressed arc is enabled that the l2arc blocks are identical to those stored in the main data pool. This provides a significant advantage since we can leverage the bp's checksum when reading from the l2arc to determine if the contents are valid. If the compressed arc is disabled, then we must first transform the read block to look like the physical block in the main data pool before comparing the checksum and determining it's valid. OpenZFS-issue: https://www.illumos.org/issues/6950 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7fc10f0 Issue #5078
2016-06-02 07:04:53 +03:00
arc_buf_destroy(abuf, &abuf);
if (err)
return (err);
/* Don't care about the data blocks */
return (TRAVERSE_VISIT_NO_CHILDREN);
}
return (0);
}
int
dmu_diff(const char *tosnap_name, const char *fromsnap_name,
struct vnode *vp, offset_t *offp)
{
struct diffarg da;
dsl_dataset_t *fromsnap;
dsl_dataset_t *tosnap;
dsl_pool_t *dp;
int error;
uint64_t fromtxg;
if (strchr(tosnap_name, '@') == NULL ||
strchr(fromsnap_name, '@') == NULL)
return (SET_ERROR(EINVAL));
error = dsl_pool_hold(tosnap_name, FTAG, &dp);
if (error != 0)
return (error);
error = dsl_dataset_hold(dp, tosnap_name, FTAG, &tosnap);
if (error != 0) {
dsl_pool_rele(dp, FTAG);
return (error);
}
error = dsl_dataset_hold(dp, fromsnap_name, FTAG, &fromsnap);
if (error != 0) {
dsl_dataset_rele(tosnap, FTAG);
dsl_pool_rele(dp, FTAG);
return (error);
}
if (!dsl_dataset_is_before(tosnap, fromsnap, 0)) {
dsl_dataset_rele(fromsnap, FTAG);
dsl_dataset_rele(tosnap, FTAG);
dsl_pool_rele(dp, FTAG);
return (SET_ERROR(EXDEV));
}
fromtxg = dsl_dataset_phys(fromsnap)->ds_creation_txg;
dsl_dataset_rele(fromsnap, FTAG);
dsl_dataset_long_hold(tosnap, FTAG);
dsl_pool_rele(dp, FTAG);
da.da_vp = vp;
da.da_offp = offp;
da.da_ddr.ddr_type = DDR_NONE;
da.da_ddr.ddr_first = da.da_ddr.ddr_last = 0;
da.da_err = 0;
/*
* Since zfs diff only looks at dnodes which are stored in plaintext
* (other than bonus buffers), we don't technically need to decrypt
* the dataset to perform this operation. However, the command line
* utility will still fail if the keys are not loaded because the
* dataset isn't mounted and because it will fail when it attempts to
* call the ZFS_IOC_OBJ_TO_STATS ioctl.
*/
error = traverse_dataset(tosnap, fromtxg,
TRAVERSE_PRE | TRAVERSE_PREFETCH_METADATA | TRAVERSE_NO_DECRYPT,
diff_cb, &da);
if (error != 0) {
da.da_err = error;
} else {
/* we set the da.da_err we return as side-effect */
(void) write_record(&da);
}
dsl_dataset_long_rele(tosnap, FTAG);
dsl_dataset_rele(tosnap, FTAG);
return (da.da_err);
}