zfs/lib/libzfs/libzfs_iter.c

595 lines
14 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) 2005, 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 16:48:13 +00:00
* Copyright (c) 2013, 2019 by Delphix. All rights reserved.
* Copyright 2014 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2019 Datto Inc.
*/
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <unistd.h>
#include <stddef.h>
#include <libintl.h>
#include <libzfs.h>
#include <libzutil.h>
#include <sys/mntent.h>
#include "libzfs_impl.h"
static int
zfs_iter_clones(zfs_handle_t *zhp, zfs_iter_f func, void *data)
{
nvlist_t *nvl = zfs_get_clones_nvl(zhp);
nvpair_t *pair;
if (nvl == NULL)
return (0);
for (pair = nvlist_next_nvpair(nvl, NULL); pair != NULL;
pair = nvlist_next_nvpair(nvl, pair)) {
zfs_handle_t *clone = zfs_open(zhp->zfs_hdl, nvpair_name(pair),
ZFS_TYPE_FILESYSTEM | ZFS_TYPE_VOLUME);
if (clone != NULL) {
int err = func(clone, data);
if (err != 0)
return (err);
}
}
return (0);
}
static int
zfs_do_list_ioctl(zfs_handle_t *zhp, int arg, zfs_cmd_t *zc)
{
int rc;
uint64_t orig_cookie;
orig_cookie = zc->zc_cookie;
top:
(void) strlcpy(zc->zc_name, zhp->zfs_name, sizeof (zc->zc_name));
rc = zfs_ioctl(zhp->zfs_hdl, arg, zc);
if (rc == -1) {
switch (errno) {
case ENOMEM:
/* expand nvlist memory and try again */
zcmd_expand_dst_nvlist(zhp->zfs_hdl, zc);
zc->zc_cookie = orig_cookie;
goto top;
/*
* An errno value of ESRCH indicates normal completion.
* If ENOENT is returned, then the underlying dataset
* has been removed since we obtained the handle.
*/
case ESRCH:
case ENOENT:
rc = 1;
break;
default:
rc = zfs_standard_error(zhp->zfs_hdl, errno,
dgettext(TEXT_DOMAIN,
"cannot iterate filesystems"));
break;
}
}
return (rc);
}
/*
* Iterate over all child filesystems
*/
int
zfs_iter_filesystems(zfs_handle_t *zhp, zfs_iter_f func, void *data)
{
zfs_cmd_t zc = {"\0"};
zfs_handle_t *nzhp;
int ret;
if (zhp->zfs_type != ZFS_TYPE_FILESYSTEM)
return (0);
zcmd_alloc_dst_nvlist(zhp->zfs_hdl, &zc, 0);
while ((ret = zfs_do_list_ioctl(zhp, ZFS_IOC_DATASET_LIST_NEXT,
&zc)) == 0) {
/*
* Silently ignore errors, as the only plausible explanation is
* that the pool has since been removed.
*/
if ((nzhp = make_dataset_handle_zc(zhp->zfs_hdl,
&zc)) == NULL) {
continue;
}
if ((ret = func(nzhp, data)) != 0) {
zcmd_free_nvlists(&zc);
return (ret);
}
}
zcmd_free_nvlists(&zc);
return ((ret < 0) ? ret : 0);
}
/*
* Iterate over all snapshots
*/
int
zfs_iter_snapshots(zfs_handle_t *zhp, boolean_t simple, zfs_iter_f func,
void *data, uint64_t min_txg, uint64_t max_txg)
{
zfs_cmd_t zc = {"\0"};
zfs_handle_t *nzhp;
int ret;
nvlist_t *range_nvl = NULL;
if (zhp->zfs_type == ZFS_TYPE_SNAPSHOT ||
zhp->zfs_type == ZFS_TYPE_BOOKMARK)
return (0);
zc.zc_simple = simple;
zcmd_alloc_dst_nvlist(zhp->zfs_hdl, &zc, 0);
if (min_txg != 0) {
range_nvl = fnvlist_alloc();
fnvlist_add_uint64(range_nvl, SNAP_ITER_MIN_TXG, min_txg);
}
if (max_txg != 0) {
if (range_nvl == NULL)
range_nvl = fnvlist_alloc();
fnvlist_add_uint64(range_nvl, SNAP_ITER_MAX_TXG, max_txg);
}
if (range_nvl != NULL)
zcmd_write_src_nvlist(zhp->zfs_hdl, &zc, range_nvl);
while ((ret = zfs_do_list_ioctl(zhp, ZFS_IOC_SNAPSHOT_LIST_NEXT,
&zc)) == 0) {
if (simple)
nzhp = make_dataset_simple_handle_zc(zhp, &zc);
else
nzhp = make_dataset_handle_zc(zhp->zfs_hdl, &zc);
if (nzhp == NULL)
continue;
if ((ret = func(nzhp, data)) != 0) {
zcmd_free_nvlists(&zc);
fnvlist_free(range_nvl);
return (ret);
}
}
zcmd_free_nvlists(&zc);
fnvlist_free(range_nvl);
return ((ret < 0) ? ret : 0);
}
/*
* Iterate over all bookmarks
*/
int
zfs_iter_bookmarks(zfs_handle_t *zhp, zfs_iter_f func, void *data)
{
zfs_handle_t *nzhp;
nvlist_t *props = NULL;
nvlist_t *bmarks = NULL;
int err;
nvpair_t *pair;
if ((zfs_get_type(zhp) & (ZFS_TYPE_SNAPSHOT | ZFS_TYPE_BOOKMARK)) != 0)
return (0);
/* Setup the requested properties nvlist. */
props = fnvlist_alloc();
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 16:48:13 +00:00
for (zfs_prop_t p = 0; p < ZFS_NUM_PROPS; p++) {
if (zfs_prop_valid_for_type(p, ZFS_TYPE_BOOKMARK, B_FALSE)) {
fnvlist_add_boolean(props, zfs_prop_to_name(p));
}
}
fnvlist_add_boolean(props, "redact_complete");
if ((err = lzc_get_bookmarks(zhp->zfs_name, props, &bmarks)) != 0)
goto out;
for (pair = nvlist_next_nvpair(bmarks, NULL);
pair != NULL; pair = nvlist_next_nvpair(bmarks, pair)) {
char name[ZFS_MAX_DATASET_NAME_LEN];
char *bmark_name;
nvlist_t *bmark_props;
bmark_name = nvpair_name(pair);
bmark_props = fnvpair_value_nvlist(pair);
if (snprintf(name, sizeof (name), "%s#%s", zhp->zfs_name,
bmark_name) >= sizeof (name)) {
err = EINVAL;
goto out;
}
nzhp = make_bookmark_handle(zhp, name, bmark_props);
if (nzhp == NULL)
continue;
if ((err = func(nzhp, data)) != 0)
goto out;
}
out:
fnvlist_free(props);
fnvlist_free(bmarks);
return (err);
}
/*
* Routines for dealing with the sorted snapshot functionality
*/
typedef struct zfs_node {
zfs_handle_t *zn_handle;
avl_node_t zn_avlnode;
} zfs_node_t;
static int
zfs_sort_snaps(zfs_handle_t *zhp, void *data)
{
avl_tree_t *avl = data;
zfs_node_t *node;
zfs_node_t search;
search.zn_handle = zhp;
node = avl_find(avl, &search, NULL);
if (node) {
/*
* If this snapshot was renamed while we were creating the
* AVL tree, it's possible that we already inserted it under
* its old name. Remove the old handle before adding the new
* one.
*/
zfs_close(node->zn_handle);
avl_remove(avl, node);
free(node);
}
node = zfs_alloc(zhp->zfs_hdl, sizeof (zfs_node_t));
node->zn_handle = zhp;
avl_add(avl, node);
return (0);
}
static int
zfs_snapshot_compare(const void *larg, const void *rarg)
{
zfs_handle_t *l = ((zfs_node_t *)larg)->zn_handle;
zfs_handle_t *r = ((zfs_node_t *)rarg)->zn_handle;
uint64_t lcreate, rcreate;
/*
* Sort them according to creation time. We use the hidden
* CREATETXG property to get an absolute ordering of snapshots.
*/
lcreate = zfs_prop_get_int(l, ZFS_PROP_CREATETXG);
rcreate = zfs_prop_get_int(r, ZFS_PROP_CREATETXG);
Reduce loaded range tree memory usage This patch implements a new tree structure for ZFS, and uses it to store range trees more efficiently. The new structure is approximately a B-tree, though there are some small differences from the usual characterizations. The tree has core nodes and leaf nodes; each contain data elements, which the elements in the core nodes acting as separators between its children. The difference between core and leaf nodes is that the core nodes have an array of children, while leaf nodes don't. Every node in the tree may be only partially full; in most cases, they are all at least 50% full (in terms of element count) except for the root node, which can be less full. Underfull nodes will steal from their neighbors or merge to remain full enough, while overfull nodes will split in two. The data elements are contained in tree-controlled buffers; they are copied into these on insertion, and overwritten on deletion. This means that the elements are not independently allocated, which reduces overhead, but also means they can't be shared between trees (and also that pointers to them are only valid until a side-effectful tree operation occurs). The overhead varies based on how dense the tree is, but is usually on the order of about 50% of the element size; the per-node overheads are very small, and so don't make a significant difference. The trees can accept arbitrary records; they accept a size and a comparator to allow them to be used for a variety of purposes. The new trees replace the AVL trees used in the range trees today. Currently, the range_seg_t structure contains three 8 byte integers of payload and two 24 byte avl_tree_node_ts to handle its storage in both an offset-sorted tree and a size-sorted tree (total size: 64 bytes). In the new model, the range seg structures are usually two 4 byte integers, but a separate one needs to exist for the size-sorted and offset-sorted tree. Between the raw size, the 50% overhead, and the double storage, the new btrees are expected to use 8*1.5*2 = 24 bytes per record, or 33.3% as much memory as the AVL trees (this is for the purposes of storing metaslab range trees; for other purposes, like scrubs, they use ~50% as much memory). We reduced the size of the payload in the range segments by teaching range trees about starting offsets and shifts; since metaslabs have a fixed starting offset, and they all operate in terms of disk sectors, we can store the ranges using 4-byte integers as long as the size of the metaslab divided by the sector size is less than 2^32. For 512-byte sectors, this is a 2^41 (or 2TB) metaslab, which with the default settings corresponds to a 256PB disk. 4k sector disks can handle metaslabs up to 2^46 bytes, or 2^63 byte disks. Since we do not anticipate disks of this size in the near future, there should be almost no cases where metaslabs need 64-byte integers to store their ranges. We do still have the capability to store 64-byte integer ranges to account for cases where we are storing per-vdev (or per-dnode) trees, which could reasonably go above the limits discussed. We also do not store fill information in the compact version of the node, since it is only used for sorted scrub. We also optimized the metaslab loading process in various other ways to offset some inefficiencies in the btree model. While individual operations (find, insert, remove_from) are faster for the btree than they are for the avl tree, remove usually requires a find operation, while in the AVL tree model the element itself suffices. Some clever changes actually caused an overall speedup in metaslab loading; we use approximately 40% less cpu to load metaslabs in our tests on Illumos. Another memory and performance optimization was achieved by changing what is stored in the size-sorted trees. When a disk is heavily fragmented, the df algorithm used by default in ZFS will almost always find a number of small regions in its initial cursor-based search; it will usually only fall back to the size-sorted tree to find larger regions. If we increase the size of the cursor-based search slightly, and don't store segments that are smaller than a tunable size floor in the size-sorted tree, we can further cut memory usage down to below 20% of what the AVL trees store. This also results in further reductions in CPU time spent loading metaslabs. The 16KiB size floor was chosen because it results in substantial memory usage reduction while not usually resulting in situations where we can't find an appropriate chunk with the cursor and are forced to use an oversized chunk from the size-sorted tree. In addition, even if we do have to use an oversized chunk from the size-sorted tree, the chunk would be too small to use for ZIL allocations, so it isn't as big of a loss as it might otherwise be. And often, more small allocations will follow the initial one, and the cursor search will now find the remainder of the chunk we didn't use all of and use it for subsequent allocations. Practical testing has shown little or no change in fragmentation as a result of this change. If the size-sorted tree becomes empty while the offset sorted one still has entries, it will load all the entries from the offset sorted tree and disregard the size floor until it is unloaded again. This operation occurs rarely with the default setting, only on incredibly thoroughly fragmented pools. There are some other small changes to zdb to teach it to handle btrees, but nothing major. Reviewed-by: George Wilson <gwilson@delphix.com> Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed by: Sebastien Roy seb@delphix.com Reviewed-by: Igor Kozhukhov <igor@dilos.org> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Paul Dagnelie <pcd@delphix.com> Closes #9181
2019-10-09 17:36:03 +00:00
return (TREE_CMP(lcreate, rcreate));
}
int
zfs_iter_snapshots_sorted(zfs_handle_t *zhp, zfs_iter_f callback, void *data,
uint64_t min_txg, uint64_t max_txg)
{
int ret = 0;
zfs_node_t *node;
avl_tree_t avl;
void *cookie = NULL;
avl_create(&avl, zfs_snapshot_compare,
sizeof (zfs_node_t), offsetof(zfs_node_t, zn_avlnode));
ret = zfs_iter_snapshots(zhp, B_FALSE, zfs_sort_snaps, &avl, min_txg,
max_txg);
for (node = avl_first(&avl); node != NULL; node = AVL_NEXT(&avl, node))
ret |= callback(node->zn_handle, data);
while ((node = avl_destroy_nodes(&avl, &cookie)) != NULL)
free(node);
avl_destroy(&avl);
return (ret);
}
typedef struct {
char *ssa_first;
char *ssa_last;
boolean_t ssa_seenfirst;
boolean_t ssa_seenlast;
zfs_iter_f ssa_func;
void *ssa_arg;
} snapspec_arg_t;
static int
snapspec_cb(zfs_handle_t *zhp, void *arg)
{
snapspec_arg_t *ssa = arg;
const char *shortsnapname;
int err = 0;
if (ssa->ssa_seenlast)
return (0);
shortsnapname = strchr(zfs_get_name(zhp), '@') + 1;
if (!ssa->ssa_seenfirst && strcmp(shortsnapname, ssa->ssa_first) == 0)
ssa->ssa_seenfirst = B_TRUE;
if (strcmp(shortsnapname, ssa->ssa_last) == 0)
ssa->ssa_seenlast = B_TRUE;
if (ssa->ssa_seenfirst) {
err = ssa->ssa_func(zhp, ssa->ssa_arg);
} else {
zfs_close(zhp);
}
return (err);
}
/*
* spec is a string like "A,B%C,D"
*
* <snaps>, where <snaps> can be:
* <snap> (single snapshot)
* <snap>%<snap> (range of snapshots, inclusive)
* %<snap> (range of snapshots, starting with earliest)
* <snap>% (range of snapshots, ending with last)
* % (all snapshots)
* <snaps>[,...] (comma separated list of the above)
*
* If a snapshot can not be opened, continue trying to open the others, but
* return ENOENT at the end.
*/
int
zfs_iter_snapspec(zfs_handle_t *fs_zhp, const char *spec_orig,
zfs_iter_f func, void *arg)
{
Illumos #2882, #2883, #2900 2882 implement libzfs_core 2883 changing "canmount" property to "on" should not always remount dataset 2900 "zfs snapshot" should be able to create multiple, arbitrary snapshots at once Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Chris Siden <christopher.siden@delphix.com> Reviewed by: Garrett D'Amore <garrett@damore.org> Reviewed by: Bill Pijewski <wdp@joyent.com> Reviewed by: Dan Kruchinin <dan.kruchinin@gmail.com> Approved by: Eric Schrock <Eric.Schrock@delphix.com> References: https://www.illumos.org/issues/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1293 Porting notes: WARNING: This patch changes the user/kernel ABI. That means that the zfs/zpool utilities built from master are NOT compatible with the 0.6.2 kernel modules. Ensure you load the matching kernel modules from master after updating the utilities. Otherwise the zfs/zpool commands will be unable to interact with your pool and you will see errors similar to the following: $ zpool list failed to read pool configuration: bad address no pools available $ zfs list no datasets available Add zvol minor device creation to the new zfs_snapshot_nvl function. Remove the logging of the "release" operation in dsl_dataset_user_release_sync(). The logging caused a null dereference because ds->ds_dir is zeroed in dsl_dataset_destroy_sync() and the logging functions try to get the ds name via the dsl_dataset_name() function. I've got no idea why this particular code would have worked in Illumos. This code has subsequently been completely reworked in Illumos commit 3b2aab1 (3464 zfs synctask code needs restructuring). Squash some "may be used uninitialized" warning/erorrs. Fix some printf format warnings for %lld and %llu. Apply a few spa_writeable() changes that were made to Illumos in illumos/illumos-gate.git@cd1c8b8 as part of the 3112, 3113, 3114 and 3115 fixes. Add a missing call to fnvlist_free(nvl) in log_internal() that was added in Illumos to fix issue 3085 but couldn't be ported to ZoL at the time (zfsonlinux/zfs@9e11c73) because it depended on future work.
2013-08-28 11:45:09 +00:00
char *buf, *comma_separated, *cp;
int err = 0;
int ret = 0;
Illumos #2882, #2883, #2900 2882 implement libzfs_core 2883 changing "canmount" property to "on" should not always remount dataset 2900 "zfs snapshot" should be able to create multiple, arbitrary snapshots at once Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Chris Siden <christopher.siden@delphix.com> Reviewed by: Garrett D'Amore <garrett@damore.org> Reviewed by: Bill Pijewski <wdp@joyent.com> Reviewed by: Dan Kruchinin <dan.kruchinin@gmail.com> Approved by: Eric Schrock <Eric.Schrock@delphix.com> References: https://www.illumos.org/issues/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1293 Porting notes: WARNING: This patch changes the user/kernel ABI. That means that the zfs/zpool utilities built from master are NOT compatible with the 0.6.2 kernel modules. Ensure you load the matching kernel modules from master after updating the utilities. Otherwise the zfs/zpool commands will be unable to interact with your pool and you will see errors similar to the following: $ zpool list failed to read pool configuration: bad address no pools available $ zfs list no datasets available Add zvol minor device creation to the new zfs_snapshot_nvl function. Remove the logging of the "release" operation in dsl_dataset_user_release_sync(). The logging caused a null dereference because ds->ds_dir is zeroed in dsl_dataset_destroy_sync() and the logging functions try to get the ds name via the dsl_dataset_name() function. I've got no idea why this particular code would have worked in Illumos. This code has subsequently been completely reworked in Illumos commit 3b2aab1 (3464 zfs synctask code needs restructuring). Squash some "may be used uninitialized" warning/erorrs. Fix some printf format warnings for %lld and %llu. Apply a few spa_writeable() changes that were made to Illumos in illumos/illumos-gate.git@cd1c8b8 as part of the 3112, 3113, 3114 and 3115 fixes. Add a missing call to fnvlist_free(nvl) in log_internal() that was added in Illumos to fix issue 3085 but couldn't be ported to ZoL at the time (zfsonlinux/zfs@9e11c73) because it depended on future work.
2013-08-28 11:45:09 +00:00
buf = zfs_strdup(fs_zhp->zfs_hdl, spec_orig);
cp = buf;
while ((comma_separated = strsep(&cp, ",")) != NULL) {
char *pct = strchr(comma_separated, '%');
if (pct != NULL) {
snapspec_arg_t ssa = { 0 };
ssa.ssa_func = func;
ssa.ssa_arg = arg;
if (pct == comma_separated)
ssa.ssa_seenfirst = B_TRUE;
else
ssa.ssa_first = comma_separated;
*pct = '\0';
ssa.ssa_last = pct + 1;
/*
* If there is a lastname specified, make sure it
* exists.
*/
if (ssa.ssa_last[0] != '\0') {
char snapname[ZFS_MAX_DATASET_NAME_LEN];
(void) snprintf(snapname, sizeof (snapname),
"%s@%s", zfs_get_name(fs_zhp),
ssa.ssa_last);
if (!zfs_dataset_exists(fs_zhp->zfs_hdl,
snapname, ZFS_TYPE_SNAPSHOT)) {
ret = ENOENT;
continue;
}
}
err = zfs_iter_snapshots_sorted(fs_zhp,
snapspec_cb, &ssa, 0, 0);
if (ret == 0)
ret = err;
if (ret == 0 && (!ssa.ssa_seenfirst ||
(ssa.ssa_last[0] != '\0' && !ssa.ssa_seenlast))) {
ret = ENOENT;
}
} else {
char snapname[ZFS_MAX_DATASET_NAME_LEN];
zfs_handle_t *snap_zhp;
(void) snprintf(snapname, sizeof (snapname), "%s@%s",
zfs_get_name(fs_zhp), comma_separated);
snap_zhp = make_dataset_handle(fs_zhp->zfs_hdl,
snapname);
if (snap_zhp == NULL) {
ret = ENOENT;
continue;
}
err = func(snap_zhp, arg);
if (ret == 0)
ret = err;
}
}
Illumos #2882, #2883, #2900 2882 implement libzfs_core 2883 changing "canmount" property to "on" should not always remount dataset 2900 "zfs snapshot" should be able to create multiple, arbitrary snapshots at once Reviewed by: George Wilson <george.wilson@delphix.com> Reviewed by: Chris Siden <christopher.siden@delphix.com> Reviewed by: Garrett D'Amore <garrett@damore.org> Reviewed by: Bill Pijewski <wdp@joyent.com> Reviewed by: Dan Kruchinin <dan.kruchinin@gmail.com> Approved by: Eric Schrock <Eric.Schrock@delphix.com> References: https://www.illumos.org/issues/2882 https://www.illumos.org/issues/2883 https://www.illumos.org/issues/2900 illumos/illumos-gate@4445fffbbb1ea25fd0e9ea68b9380dd7a6709025 Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #1293 Porting notes: WARNING: This patch changes the user/kernel ABI. That means that the zfs/zpool utilities built from master are NOT compatible with the 0.6.2 kernel modules. Ensure you load the matching kernel modules from master after updating the utilities. Otherwise the zfs/zpool commands will be unable to interact with your pool and you will see errors similar to the following: $ zpool list failed to read pool configuration: bad address no pools available $ zfs list no datasets available Add zvol minor device creation to the new zfs_snapshot_nvl function. Remove the logging of the "release" operation in dsl_dataset_user_release_sync(). The logging caused a null dereference because ds->ds_dir is zeroed in dsl_dataset_destroy_sync() and the logging functions try to get the ds name via the dsl_dataset_name() function. I've got no idea why this particular code would have worked in Illumos. This code has subsequently been completely reworked in Illumos commit 3b2aab1 (3464 zfs synctask code needs restructuring). Squash some "may be used uninitialized" warning/erorrs. Fix some printf format warnings for %lld and %llu. Apply a few spa_writeable() changes that were made to Illumos in illumos/illumos-gate.git@cd1c8b8 as part of the 3112, 3113, 3114 and 3115 fixes. Add a missing call to fnvlist_free(nvl) in log_internal() that was added in Illumos to fix issue 3085 but couldn't be ported to ZoL at the time (zfsonlinux/zfs@9e11c73) because it depended on future work.
2013-08-28 11:45:09 +00:00
free(buf);
return (ret);
}
/*
* Iterate over all children, snapshots and filesystems
* Process snapshots before filesystems because they are nearer the input
* handle: this is extremely important when used with zfs_iter_f functions
* looking for data, following the logic that we would like to find it as soon
* and as close as possible.
*/
int
zfs_iter_children(zfs_handle_t *zhp, zfs_iter_f func, void *data)
{
int ret;
if ((ret = zfs_iter_snapshots(zhp, B_FALSE, func, data, 0, 0)) != 0)
return (ret);
return (zfs_iter_filesystems(zhp, func, data));
}
typedef struct iter_stack_frame {
struct iter_stack_frame *next;
zfs_handle_t *zhp;
} iter_stack_frame_t;
typedef struct iter_dependents_arg {
boolean_t first;
boolean_t allowrecursion;
iter_stack_frame_t *stack;
zfs_iter_f func;
void *data;
} iter_dependents_arg_t;
static int
iter_dependents_cb(zfs_handle_t *zhp, void *arg)
{
iter_dependents_arg_t *ida = arg;
int err = 0;
boolean_t first = ida->first;
ida->first = B_FALSE;
if (zhp->zfs_type == ZFS_TYPE_SNAPSHOT) {
err = zfs_iter_clones(zhp, iter_dependents_cb, ida);
} else if (zhp->zfs_type != ZFS_TYPE_BOOKMARK) {
iter_stack_frame_t isf;
iter_stack_frame_t *f;
/*
* check if there is a cycle by seeing if this fs is already
* on the stack.
*/
for (f = ida->stack; f != NULL; f = f->next) {
if (f->zhp->zfs_dmustats.dds_guid ==
zhp->zfs_dmustats.dds_guid) {
if (ida->allowrecursion) {
zfs_close(zhp);
return (0);
} else {
zfs_error_aux(zhp->zfs_hdl,
dgettext(TEXT_DOMAIN,
"recursive dependency at '%s'"),
zfs_get_name(zhp));
err = zfs_error(zhp->zfs_hdl,
EZFS_RECURSIVE,
dgettext(TEXT_DOMAIN,
"cannot determine dependent "
"datasets"));
zfs_close(zhp);
return (err);
}
}
}
isf.zhp = zhp;
isf.next = ida->stack;
ida->stack = &isf;
err = zfs_iter_filesystems(zhp, iter_dependents_cb, ida);
if (err == 0)
err = zfs_iter_snapshots(zhp, B_FALSE,
iter_dependents_cb, ida, 0, 0);
ida->stack = isf.next;
}
if (!first && err == 0)
err = ida->func(zhp, ida->data);
else
zfs_close(zhp);
return (err);
}
int
zfs_iter_dependents(zfs_handle_t *zhp, boolean_t allowrecursion,
zfs_iter_f func, void *data)
{
iter_dependents_arg_t ida;
ida.allowrecursion = allowrecursion;
ida.stack = NULL;
ida.func = func;
ida.data = data;
ida.first = B_TRUE;
return (iter_dependents_cb(zfs_handle_dup(zhp), &ida));
}
/*
* Iterate over mounted children of the specified dataset
*/
int
zfs_iter_mounted(zfs_handle_t *zhp, zfs_iter_f func, void *data)
{
char mnt_prop[ZFS_MAXPROPLEN];
struct mnttab entry;
zfs_handle_t *mtab_zhp;
size_t namelen = strlen(zhp->zfs_name);
FILE *mnttab;
int err = 0;
if ((mnttab = fopen(MNTTAB, "re")) == NULL)
return (ENOENT);
while (err == 0 && getmntent(mnttab, &entry) == 0) {
/* Ignore non-ZFS entries */
if (strcmp(entry.mnt_fstype, MNTTYPE_ZFS) != 0)
continue;
/* Ignore datasets not within the provided dataset */
if (strncmp(entry.mnt_special, zhp->zfs_name, namelen) != 0 ||
entry.mnt_special[namelen] != '/')
continue;
/* Skip snapshot of any child dataset */
if (strchr(entry.mnt_special, '@') != NULL)
continue;
if ((mtab_zhp = zfs_open(zhp->zfs_hdl, entry.mnt_special,
ZFS_TYPE_FILESYSTEM)) == NULL)
continue;
/* Ignore legacy mounts as they are user managed */
verify(zfs_prop_get(mtab_zhp, ZFS_PROP_MOUNTPOINT, mnt_prop,
sizeof (mnt_prop), NULL, NULL, 0, B_FALSE) == 0);
if (strcmp(mnt_prop, "legacy") == 0) {
zfs_close(mtab_zhp);
continue;
}
err = func(mtab_zhp, data);
}
fclose(mnttab);
return (err);
}