zfs/lib/libzfs/libzfs_util.c

2079 lines
50 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* 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
*/
2008-11-20 20:01:55 +00:00
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright 2020 Joyent, Inc. All rights reserved.
Remove dependency on sharetab file and refactor sharing logic == Motivation and Context The current implementation of 'sharenfs' and 'sharesmb' relies on the use of the sharetab file. The use of this file is os-specific and not required by linux or freebsd. Currently the code must maintain updates to this file which adds complexity and presents a significant performance impact when sharing many datasets. In addition, concurrently running 'zfs sharenfs' command results in missing entries in the sharetab file leading to unexpected failures. == Description This change removes the sharetab logic from the linux and freebsd implementation of 'sharenfs' and 'sharesmb'. It still preserves an os-specific library which contains the logic required for sharing NFS or SMB. The following entry points exist in the vastly simplified libshare library: - sa_enable_share -- shares a dataset but may not commit the change - sa_disable_share -- unshares a dataset but may not commit the change - sa_is_shared -- determine if a dataset is shared - sa_commit_share -- notify NFS/SMB subsystem to commit the shares - sa_validate_shareopts -- determine if sharing options are valid The sa_commit_share entry point is provided as a performance enhancement and is not required. The sa_enable_share/sa_disable_share may commit the share as part of the implementation. Libshare provides a framework for both NFS and SMB but some operating systems may not fully support these protocols or all features of the protocol. NFS Operation: For linux, libshare updates /etc/exports.d/zfs.exports to add and remove shares and then commits the changes by invoking 'exportfs -r'. This file, is automatically read by the kernel NFS implementation which makes for better integration with the NFS systemd service. For FreeBSD, libshare updates /etc/zfs/exports to add and remove shares and then commits the changes by sending a SIGHUP to mountd. SMB Operation: For linux, libshare adds and removes files in /var/lib/samba/usershares by calling the 'net' command directly. There is no need to commit the changes. FreeBSD does not support SMB. == Performance Results To test sharing performance we created a pool with an increasing number of datasets and invoked various zfs actions that would enable and disable sharing. The performance testing was limited to NFS sharing. The following tests were performed on an 8 vCPU system with 128GB and a pool comprised of 4 50GB SSDs: Scale testing: - Share all filesystems in parallel -- zfs sharenfs=on <dataset> & - Unshare all filesystems in parallel -- zfs sharenfs=off <dataset> & Functional testing: - share each filesystem serially -- zfs share -a - unshare each filesystem serially -- zfs unshare -a - reset sharenfs property and unshare -- zfs inherit -r sharenfs <pool> For 'zfs sharenfs=on' scale testing we saw an average reduction in time of 89.43% and for 'zfs sharenfs=off' we saw an average reduction in time of 83.36%. Functional testing also shows a huge improvement: - zfs share -- 97.97% reduction in time - zfs unshare -- 96.47% reduction in time - zfs inhert -r sharenfs -- 99.01% reduction in time Reviewed-by: Matt Ahrens <matt@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Ryan Moeller <ryan@ixsystems.com> Reviewed-by: Bryant G. Ly <bryangly@gmail.com> Signed-off-by: George Wilson <gwilson@delphix.com> External-Issue: DLPX-68690 Closes #1603 Closes #7692 Closes #7943 Closes #10300
2020-07-13 16:19:18 +00:00
* Copyright (c) 2011, 2020 by Delphix. All rights reserved.
* Copyright 2016 Igor Kozhukhov <ikozhukhov@gmail.com>
* Copyright (c) 2017 Datto Inc.
* Copyright (c) 2020 The FreeBSD Foundation
*
* Portions of this software were developed by Allan Jude
* under sponsorship from the FreeBSD Foundation.
2008-11-20 20:01:55 +00:00
*/
/*
* Internal utility routines for the ZFS library.
*/
#include <errno.h>
#include <fcntl.h>
#include <libintl.h>
#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <strings.h>
#include <unistd.h>
#include <math.h>
#include <sys/stat.h>
2008-11-20 20:01:55 +00:00
#include <sys/mnttab.h>
#include <sys/mntent.h>
#include <sys/types.h>
#include <sys/wait.h>
2008-11-20 20:01:55 +00:00
#include <libzfs.h>
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
#include <libzfs_core.h>
2008-11-20 20:01:55 +00:00
#include "libzfs_impl.h"
#include "zfs_prop.h"
#include "zfeature_common.h"
#include <zfs_fletcher.h>
#include <libzutil.h>
2008-11-20 20:01:55 +00:00
/*
* We only care about the scheme in order to match the scheme
* with the handler. Each handler should validate the full URI
* as necessary.
*/
#define URI_REGEX "^\\([A-Za-z][A-Za-z0-9+.\\-]*\\):"
2008-11-20 20:01:55 +00:00
int
libzfs_errno(libzfs_handle_t *hdl)
{
return (hdl->libzfs_error);
}
const char *
libzfs_error_action(libzfs_handle_t *hdl)
{
return (hdl->libzfs_action);
}
const char *
libzfs_error_description(libzfs_handle_t *hdl)
{
if (hdl->libzfs_desc[0] != '\0')
return (hdl->libzfs_desc);
switch (hdl->libzfs_error) {
case EZFS_NOMEM:
return (dgettext(TEXT_DOMAIN, "out of memory"));
case EZFS_BADPROP:
return (dgettext(TEXT_DOMAIN, "invalid property value"));
case EZFS_PROPREADONLY:
return (dgettext(TEXT_DOMAIN, "read-only property"));
2008-11-20 20:01:55 +00:00
case EZFS_PROPTYPE:
return (dgettext(TEXT_DOMAIN, "property doesn't apply to "
"datasets of this type"));
case EZFS_PROPNONINHERIT:
return (dgettext(TEXT_DOMAIN, "property cannot be inherited"));
case EZFS_PROPSPACE:
return (dgettext(TEXT_DOMAIN, "invalid quota or reservation"));
case EZFS_BADTYPE:
return (dgettext(TEXT_DOMAIN, "operation not applicable to "
"datasets of this type"));
case EZFS_BUSY:
return (dgettext(TEXT_DOMAIN, "pool or dataset is busy"));
case EZFS_EXISTS:
return (dgettext(TEXT_DOMAIN, "pool or dataset exists"));
case EZFS_NOENT:
return (dgettext(TEXT_DOMAIN, "no such pool or dataset"));
case EZFS_BADSTREAM:
return (dgettext(TEXT_DOMAIN, "invalid backup stream"));
case EZFS_DSREADONLY:
return (dgettext(TEXT_DOMAIN, "dataset is read-only"));
2008-11-20 20:01:55 +00:00
case EZFS_VOLTOOBIG:
return (dgettext(TEXT_DOMAIN, "volume size exceeds limit for "
"this system"));
case EZFS_INVALIDNAME:
return (dgettext(TEXT_DOMAIN, "invalid name"));
case EZFS_BADRESTORE:
return (dgettext(TEXT_DOMAIN, "unable to restore to "
"destination"));
case EZFS_BADBACKUP:
return (dgettext(TEXT_DOMAIN, "backup failed"));
case EZFS_BADTARGET:
return (dgettext(TEXT_DOMAIN, "invalid target vdev"));
case EZFS_NODEVICE:
return (dgettext(TEXT_DOMAIN, "no such device in pool"));
case EZFS_BADDEV:
return (dgettext(TEXT_DOMAIN, "invalid device"));
case EZFS_NOREPLICAS:
return (dgettext(TEXT_DOMAIN, "no valid replicas"));
case EZFS_RESILVERING:
return (dgettext(TEXT_DOMAIN, "currently resilvering"));
case EZFS_BADVERSION:
return (dgettext(TEXT_DOMAIN, "unsupported version or "
"feature"));
2008-11-20 20:01:55 +00:00
case EZFS_POOLUNAVAIL:
return (dgettext(TEXT_DOMAIN, "pool is unavailable"));
case EZFS_DEVOVERFLOW:
return (dgettext(TEXT_DOMAIN, "too many devices in one vdev"));
case EZFS_BADPATH:
return (dgettext(TEXT_DOMAIN, "must be an absolute path"));
case EZFS_CROSSTARGET:
return (dgettext(TEXT_DOMAIN, "operation crosses datasets or "
"pools"));
case EZFS_ZONED:
return (dgettext(TEXT_DOMAIN, "dataset in use by local zone"));
case EZFS_MOUNTFAILED:
return (dgettext(TEXT_DOMAIN, "mount failed"));
case EZFS_UMOUNTFAILED:
return (dgettext(TEXT_DOMAIN, "unmount failed"));
2008-11-20 20:01:55 +00:00
case EZFS_UNSHARENFSFAILED:
return (dgettext(TEXT_DOMAIN, "NFS share removal failed"));
2008-11-20 20:01:55 +00:00
case EZFS_SHARENFSFAILED:
return (dgettext(TEXT_DOMAIN, "NFS share creation failed"));
2008-11-20 20:01:55 +00:00
case EZFS_UNSHARESMBFAILED:
return (dgettext(TEXT_DOMAIN, "SMB share removal failed"));
2008-11-20 20:01:55 +00:00
case EZFS_SHARESMBFAILED:
return (dgettext(TEXT_DOMAIN, "SMB share creation failed"));
2008-11-20 20:01:55 +00:00
case EZFS_PERM:
return (dgettext(TEXT_DOMAIN, "permission denied"));
case EZFS_NOSPC:
return (dgettext(TEXT_DOMAIN, "out of space"));
case EZFS_FAULT:
return (dgettext(TEXT_DOMAIN, "bad address"));
2008-11-20 20:01:55 +00:00
case EZFS_IO:
return (dgettext(TEXT_DOMAIN, "I/O error"));
case EZFS_INTR:
return (dgettext(TEXT_DOMAIN, "signal received"));
case EZFS_ISSPARE:
return (dgettext(TEXT_DOMAIN, "device is reserved as a hot "
"spare"));
case EZFS_INVALCONFIG:
return (dgettext(TEXT_DOMAIN, "invalid vdev configuration"));
case EZFS_RECURSIVE:
return (dgettext(TEXT_DOMAIN, "recursive dataset dependency"));
case EZFS_NOHISTORY:
return (dgettext(TEXT_DOMAIN, "no history available"));
case EZFS_POOLPROPS:
return (dgettext(TEXT_DOMAIN, "failed to retrieve "
"pool properties"));
case EZFS_POOL_NOTSUP:
return (dgettext(TEXT_DOMAIN, "operation not supported "
"on this type of pool"));
case EZFS_POOL_INVALARG:
return (dgettext(TEXT_DOMAIN, "invalid argument for "
"this pool operation"));
case EZFS_NAMETOOLONG:
return (dgettext(TEXT_DOMAIN, "dataset name is too long"));
case EZFS_OPENFAILED:
return (dgettext(TEXT_DOMAIN, "open failed"));
case EZFS_NOCAP:
return (dgettext(TEXT_DOMAIN,
"disk capacity information could not be retrieved"));
case EZFS_LABELFAILED:
return (dgettext(TEXT_DOMAIN, "write of label failed"));
case EZFS_BADWHO:
return (dgettext(TEXT_DOMAIN, "invalid user/group"));
case EZFS_BADPERM:
return (dgettext(TEXT_DOMAIN, "invalid permission"));
case EZFS_BADPERMSET:
return (dgettext(TEXT_DOMAIN, "invalid permission set name"));
case EZFS_NODELEGATION:
return (dgettext(TEXT_DOMAIN, "delegated administration is "
"disabled on pool"));
case EZFS_BADCACHE:
return (dgettext(TEXT_DOMAIN, "invalid or missing cache file"));
case EZFS_ISL2CACHE:
return (dgettext(TEXT_DOMAIN, "device is in use as a cache"));
case EZFS_VDEVNOTSUP:
return (dgettext(TEXT_DOMAIN, "vdev specification is not "
"supported"));
case EZFS_NOTSUP:
return (dgettext(TEXT_DOMAIN, "operation not supported "
"on this dataset"));
case EZFS_IOC_NOTSUPPORTED:
return (dgettext(TEXT_DOMAIN, "operation not supported by "
"zfs kernel module"));
case EZFS_ACTIVE_SPARE:
return (dgettext(TEXT_DOMAIN, "pool has active shared spare "
"device"));
2009-07-02 22:44:48 +00:00
case EZFS_UNPLAYED_LOGS:
return (dgettext(TEXT_DOMAIN, "log device has unplayed intent "
"logs"));
2009-08-18 18:43:27 +00:00
case EZFS_REFTAG_RELE:
return (dgettext(TEXT_DOMAIN, "no such tag on this dataset"));
case EZFS_REFTAG_HOLD:
return (dgettext(TEXT_DOMAIN, "tag already exists on this "
"dataset"));
case EZFS_TAGTOOLONG:
return (dgettext(TEXT_DOMAIN, "tag too long"));
case EZFS_PIPEFAILED:
return (dgettext(TEXT_DOMAIN, "pipe create failed"));
case EZFS_THREADCREATEFAILED:
return (dgettext(TEXT_DOMAIN, "thread create failed"));
case EZFS_POSTSPLIT_ONLINE:
return (dgettext(TEXT_DOMAIN, "disk was split from this pool "
"into a new one"));
case EZFS_SCRUB_PAUSED:
return (dgettext(TEXT_DOMAIN, "scrub is paused; "
"use 'zpool scrub' to resume"));
case EZFS_SCRUBBING:
return (dgettext(TEXT_DOMAIN, "currently scrubbing; "
"use 'zpool scrub -s' to cancel current scrub"));
case EZFS_NO_SCRUB:
return (dgettext(TEXT_DOMAIN, "there is no active scrub"));
case EZFS_DIFF:
return (dgettext(TEXT_DOMAIN, "unable to generate diffs"));
case EZFS_DIFFDATA:
return (dgettext(TEXT_DOMAIN, "invalid diff data"));
case EZFS_POOLREADONLY:
return (dgettext(TEXT_DOMAIN, "pool is read-only"));
OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Alex Reece <alex@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Richard Laager <rlaager@wiktel.com> Reviewed by: Tim Chase <tim@chase2k.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Garrett D'Amore <garrett@damore.org> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900
2016-09-22 16:30:13 +00:00
case EZFS_NO_PENDING:
return (dgettext(TEXT_DOMAIN, "operation is not "
"in progress"));
OpenZFS 9166 - zfs storage pool checkpoint Details about the motivation of this feature and its usage can be found in this blogpost: https://sdimitro.github.io/post/zpool-checkpoint/ A lightning talk of this feature can be found here: https://www.youtube.com/watch?v=fPQA8K40jAM Implementation details can be found in big block comment of spa_checkpoint.c Side-changes that are relevant to this commit but not explained elsewhere: * renames members of "struct metaslab trees to be shorter without losing meaning * space_map_{alloc,truncate}() accept a block size as a parameter. The reason is that in the current state all space maps that we allocate through the DMU use a global tunable (space_map_blksz) which defauls to 4KB. This is ok for metaslab space maps in terms of bandwirdth since they are scattered all over the disk. But for other space maps this default is probably not what we want. Examples are device removal's vdev_obsolete_sm or vdev_chedkpoint_sm from this review. Both of these have a 1:1 relationship with each vdev and could benefit from a bigger block size. Porting notes: * The part of dsl_scan_sync() which handles async destroys has been moved into the new dsl_process_async_destroys() function. * Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write to block device backed pools. * ZTS: * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg". * Don't use large dd block sizes on /dev/urandom under Linux in checkpoint_capacity. * Adopt Delphix-OS's setting of 4 (spa_asize_inflation = SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed its attempts to fill the pool * Create the base and nested pools with sync=disabled to speed up the "setup" phase. * Clear labels in test pool between checkpoint tests to avoid duplicate pool issues. * The import_rewind_device_replaced test has been marked as "known to fail" for the reasons listed in its DISCLAIMER. * New module parameters: zfs_spa_discard_memory_limit, zfs_remove_max_bytes_pause (not documented - debugging only) vdev_max_ms_count (formerly metaslabs_per_vdev) vdev_min_ms_count Authored by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Richard Lowe <richlowe@richlowe.net> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://illumos.org/issues/9166 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8 Closes #7570
2016-12-16 22:11:29 +00:00
case EZFS_CHECKPOINT_EXISTS:
return (dgettext(TEXT_DOMAIN, "checkpoint exists"));
case EZFS_DISCARDING_CHECKPOINT:
return (dgettext(TEXT_DOMAIN, "currently discarding "
"checkpoint"));
case EZFS_NO_CHECKPOINT:
return (dgettext(TEXT_DOMAIN, "checkpoint does not exist"));
case EZFS_DEVRM_IN_PROGRESS:
return (dgettext(TEXT_DOMAIN, "device removal in progress"));
case EZFS_VDEV_TOO_BIG:
return (dgettext(TEXT_DOMAIN, "device exceeds supported size"));
Multi-modifier protection (MMP) Add multihost=on|off pool property to control MMP. When enabled a new thread writes uberblocks to the last slot in each label, at a set frequency, to indicate to other hosts the pool is actively imported. These uberblocks are the last synced uberblock with an updated timestamp. Property defaults to off. During tryimport, find the "best" uberblock (newest txg and timestamp) repeatedly, checking for change in the found uberblock. Include the results of the activity test in the config returned by tryimport. These results are reported to user in "zpool import". Allow the user to control the period between MMP writes, and the duration of the activity test on import, via a new module parameter zfs_multihost_interval. The period is specified in milliseconds. The activity test duration is calculated from this value, and from the mmp_delay in the "best" uberblock found initially. Add a kstat interface to export statistics about Multiple Modifier Protection (MMP) updates. Include the last synced txg number, the timestamp, the delay since the last MMP update, the VDEV GUID, the VDEV label that received the last MMP update, and the VDEV path. Abbreviated output below. $ cat /proc/spl/kstat/zfs/mypool/multihost 31 0 0x01 10 880 105092382393521 105144180101111 txg timestamp mmp_delay vdev_guid vdev_label vdev_path 20468 261337 250274925 68396651780 3 /dev/sda 20468 261339 252023374 6267402363293 1 /dev/sdc 20468 261340 252000858 6698080955233 1 /dev/sdx 20468 261341 251980635 783892869810 2 /dev/sdy 20468 261342 253385953 8923255792467 3 /dev/sdd 20468 261344 253336622 042125143176 0 /dev/sdab 20468 261345 253310522 1200778101278 2 /dev/sde 20468 261346 253286429 0950576198362 2 /dev/sdt 20468 261347 253261545 96209817917 3 /dev/sds 20468 261349 253238188 8555725937673 3 /dev/sdb Add a new tunable zfs_multihost_history to specify the number of MMP updates to store history for. By default it is set to zero meaning that no MMP statistics are stored. When using ztest to generate activity, for automated tests of the MMP function, some test functions interfere with the test. For example, the pool is exported to run zdb and then imported again. Add a new ztest function, "-M", to alter ztest behavior to prevent this. Add new tests to verify the new functionality. Tests provided by Giuseppe Di Natale. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Giuseppe Di Natale <dinatale2@llnl.gov> Reviewed-by: Ned Bass <bass6@llnl.gov> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Closes #745 Closes #6279
2017-07-08 03:20:35 +00:00
case EZFS_ACTIVE_POOL:
return (dgettext(TEXT_DOMAIN, "pool is imported on a "
"different host"));
Native Encryption for ZFS on Linux This change incorporates three major pieces: The first change is a keystore that manages wrapping and encryption keys for encrypted datasets. These commands mostly involve manipulating the new DSL Crypto Key ZAP Objects that live in the MOS. Each encrypted dataset has its own DSL Crypto Key that is protected with a user's key. This level of indirection allows users to change their keys without re-encrypting their entire datasets. The change implements the new subcommands "zfs load-key", "zfs unload-key" and "zfs change-key" which allow the user to manage their encryption keys and settings. In addition, several new flags and properties have been added to allow dataset creation and to make mounting and unmounting more convenient. The second piece of this patch provides the ability to encrypt, decyrpt, and authenticate protected datasets. Each object set maintains a Merkel tree of Message Authentication Codes that protect the lower layers, similarly to how checksums are maintained. This part impacts the zio layer, which handles the actual encryption and generation of MACs, as well as the ARC and DMU, which need to be able to handle encrypted buffers and protected data. The last addition is the ability to do raw, encrypted sends and receives. The idea here is to send raw encrypted and compressed data and receive it exactly as is on a backup system. This means that the dataset on the receiving system is protected using the same user key that is in use on the sending side. By doing so, datasets can be efficiently backed up to an untrusted system without fear of data being compromised. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Jorgen Lundman <lundman@lundman.net> Signed-off-by: Tom Caputi <tcaputi@datto.com> Closes #494 Closes #5769
2017-08-14 17:36:48 +00:00
case EZFS_CRYPTOFAILED:
return (dgettext(TEXT_DOMAIN, "encryption failure"));
OpenZFS 9102 - zfs should be able to initialize storage devices PROBLEM ======== The first access to a block incurs a performance penalty on some platforms (e.g. AWS's EBS, VMware VMDKs). Therefore we recommend that volumes are "thick provisioned", where supported by the platform (VMware). This can create a large delay in getting a new virtual machines up and running (or adding storage to an existing Engine). If the thick provision step is omitted, write performance will be suboptimal until all blocks on the LUN have been written. SOLUTION ========= This feature introduces a way to 'initialize' the disks at install or in the background to make sure we don't incur this first read penalty. When an entire LUN is added to ZFS, we make all space available immediately, and allow ZFS to find unallocated space and zero it out. This works with concurrent writes to arbitrary offsets, ensuring that we don't zero out something that has been (or is in the middle of being) written. This scheme can also be applied to existing pools (affecting only free regions on the vdev). Detailed design: - new subcommand:zpool initialize [-cs] <pool> [<vdev> ...] - start, suspend, or cancel initialization - Creates new open-context thread for each vdev - Thread iterates through all metaslabs in this vdev - Each metaslab: - select a metaslab - load the metaslab - mark the metaslab as being zeroed - walk all free ranges within that metaslab and translate them to ranges on the leaf vdev - issue a "zeroing" I/O on the leaf vdev that corresponds to a free range on the metaslab we're working on - continue until all free ranges for this metaslab have been "zeroed" - reset/unmark the metaslab being zeroed - if more metaslabs exist, then repeat above tasks. - if no more metaslabs, then we're done. - progress for the initialization is stored on-disk in the vdev’s leaf zap object. The following information is stored: - the last offset that has been initialized - the state of the initialization process (i.e. active, suspended, or canceled) - the start time for the initialization - progress is reported via the zpool status command and shows information for each of the vdevs that are initializing Porting notes: - Added zfs_initialize_value module parameter to set the pattern written by "zpool initialize". - Added zfs_vdev_{initializing,removal}_{min,max}_active module options. Authored by: George Wilson <george.wilson@delphix.com> Reviewed by: John Wren Kennedy <john.kennedy@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Pavel Zakharov <pavel.zakharov@delphix.com> Reviewed by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: loli10K <ezomori.nozomu@gmail.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Richard Lowe <richlowe@richlowe.net> Signed-off-by: Tim Chase <tim@chase2k.com> Ported-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/9102 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/c3963210eb Closes #8230
2018-12-19 14:54:59 +00:00
case EZFS_TOOMANY:
return (dgettext(TEXT_DOMAIN, "argument list too long"));
case EZFS_INITIALIZING:
return (dgettext(TEXT_DOMAIN, "currently initializing"));
case EZFS_NO_INITIALIZE:
return (dgettext(TEXT_DOMAIN, "there is no active "
"initialization"));
case EZFS_WRONG_PARENT:
return (dgettext(TEXT_DOMAIN, "invalid parent dataset"));
Add TRIM support UNMAP/TRIM support is a frequently-requested feature to help prevent performance from degrading on SSDs and on various other SAN-like storage back-ends. By issuing UNMAP/TRIM commands for sectors which are no longer allocated the underlying device can often more efficiently manage itself. This TRIM implementation is modeled on the `zpool initialize` feature which writes a pattern to all unallocated space in the pool. The new `zpool trim` command uses the same vdev_xlate() code to calculate what sectors are unallocated, the same per- vdev TRIM thread model and locking, and the same basic CLI for a consistent user experience. The core difference is that instead of writing a pattern it will issue UNMAP/TRIM commands for those extents. The zio pipeline was updated to accommodate this by adding a new ZIO_TYPE_TRIM type and associated spa taskq. This new type makes is straight forward to add the platform specific TRIM/UNMAP calls to vdev_disk.c and vdev_file.c. These new ZIO_TYPE_TRIM zios are handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs. This makes it possible to largely avoid changing the pipieline, one exception is that TRIM zio's may exceed the 16M block size limit since they contain no data. In addition to the manual `zpool trim` command, a background automatic TRIM was added and is controlled by the 'autotrim' property. It relies on the exact same infrastructure as the manual TRIM. However, instead of relying on the extents in a metaslab's ms_allocatable range tree, a ms_trim tree is kept per metaslab. When 'autotrim=on', ranges added back to the ms_allocatable tree are also added to the ms_free tree. The ms_free tree is then periodically consumed by an autotrim thread which systematically walks a top level vdev's metaslabs. Since the automatic TRIM will skip ranges it considers too small there is value in occasionally running a full `zpool trim`. This may occur when the freed blocks are small and not enough time was allowed to aggregate them. An automatic TRIM and a manual `zpool trim` may be run concurrently, in which case the automatic TRIM will yield to the manual TRIM. Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Tim Chase <tim@chase2k.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Contributions-by: Saso Kiselkov <saso.kiselkov@nexenta.com> Contributions-by: Tim Chase <tim@chase2k.com> Contributions-by: Chunwei Chen <tuxoko@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #8419 Closes #598
2019-03-29 16:13:20 +00:00
case EZFS_TRIMMING:
return (dgettext(TEXT_DOMAIN, "currently trimming"));
case EZFS_NO_TRIM:
return (dgettext(TEXT_DOMAIN, "there is no active trim"));
case EZFS_TRIM_NOTSUP:
return (dgettext(TEXT_DOMAIN, "trim operations are not "
"supported by this device"));
case EZFS_NO_RESILVER_DEFER:
return (dgettext(TEXT_DOMAIN, "this action requires the "
"resilver_defer feature"));
case EZFS_EXPORT_IN_PROGRESS:
return (dgettext(TEXT_DOMAIN, "pool export in progress"));
Add device rebuild feature The device_rebuild feature enables sequential reconstruction when resilvering. Mirror vdevs can be rebuilt in LBA order which may more quickly restore redundancy depending on the pools average block size, overall fragmentation and the performance characteristics of the devices. However, block checksums cannot be verified as part of the rebuild thus a scrub is automatically started after the sequential resilver completes. The new '-s' option has been added to the `zpool attach` and `zpool replace` command to request sequential reconstruction instead of healing reconstruction when resilvering. zpool attach -s <pool> <existing vdev> <new vdev> zpool replace -s <pool> <old vdev> <new vdev> The `zpool status` output has been updated to report the progress of sequential resilvering in the same way as healing resilvering. The one notable difference is that multiple sequential resilvers may be in progress as long as they're operating on different top-level vdevs. The `zpool wait -t resilver` command was extended to wait on sequential resilvers. From this perspective they are no different than healing resilvers. Sequential resilvers cannot be supported for RAIDZ, but are compatible with the dRAID feature being developed. As part of this change the resilver_restart_* tests were moved in to the functional/replacement directory. Additionally, the replacement tests were renamed and extended to verify both resilvering and rebuilding. Original-patch-by: Isaac Huang <he.huang@intel.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: John Poduska <jpoduska@datto.com> Co-authored-by: Mark Maybee <mmaybee@cray.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #10349
2020-07-03 18:05:50 +00:00
case EZFS_REBUILDING:
return (dgettext(TEXT_DOMAIN, "currently sequentially "
"resilvering"));
2008-11-20 20:01:55 +00:00
case EZFS_UNKNOWN:
return (dgettext(TEXT_DOMAIN, "unknown error"));
default:
assert(hdl->libzfs_error == 0);
return (dgettext(TEXT_DOMAIN, "no error"));
}
}
/*PRINTFLIKE2*/
void
zfs_error_aux(libzfs_handle_t *hdl, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
(void) vsnprintf(hdl->libzfs_desc, sizeof (hdl->libzfs_desc),
fmt, ap);
hdl->libzfs_desc_active = 1;
va_end(ap);
}
static void
zfs_verror(libzfs_handle_t *hdl, int error, const char *fmt, va_list ap)
{
(void) vsnprintf(hdl->libzfs_action, sizeof (hdl->libzfs_action),
fmt, ap);
hdl->libzfs_error = error;
if (hdl->libzfs_desc_active)
hdl->libzfs_desc_active = 0;
else
hdl->libzfs_desc[0] = '\0';
if (hdl->libzfs_printerr) {
if (error == EZFS_UNKNOWN) {
(void) fprintf(stderr, dgettext(TEXT_DOMAIN, "internal "
"error: %s: %s\n"), hdl->libzfs_action,
libzfs_error_description(hdl));
2008-11-20 20:01:55 +00:00
abort();
}
(void) fprintf(stderr, "%s: %s\n", hdl->libzfs_action,
libzfs_error_description(hdl));
if (error == EZFS_NOMEM)
exit(1);
}
}
int
zfs_error(libzfs_handle_t *hdl, int error, const char *msg)
{
return (zfs_error_fmt(hdl, error, "%s", msg));
}
/*PRINTFLIKE3*/
int
zfs_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
zfs_verror(hdl, error, fmt, ap);
va_end(ap);
return (-1);
}
static int
zfs_common_error(libzfs_handle_t *hdl, int error, const char *fmt,
va_list ap)
{
switch (error) {
case EPERM:
case EACCES:
zfs_verror(hdl, EZFS_PERM, fmt, ap);
return (-1);
case ECANCELED:
zfs_verror(hdl, EZFS_NODELEGATION, fmt, ap);
return (-1);
case EIO:
zfs_verror(hdl, EZFS_IO, fmt, ap);
return (-1);
case EFAULT:
zfs_verror(hdl, EZFS_FAULT, fmt, ap);
return (-1);
2008-11-20 20:01:55 +00:00
case EINTR:
zfs_verror(hdl, EZFS_INTR, fmt, ap);
return (-1);
}
return (0);
}
int
zfs_standard_error(libzfs_handle_t *hdl, int error, const char *msg)
{
return (zfs_standard_error_fmt(hdl, error, "%s", msg));
}
/*PRINTFLIKE3*/
int
zfs_standard_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
if (zfs_common_error(hdl, error, fmt, ap) != 0) {
va_end(ap);
return (-1);
}
switch (error) {
case ENXIO:
case ENODEV:
case EPIPE:
2008-11-20 20:01:55 +00:00
zfs_verror(hdl, EZFS_IO, fmt, ap);
break;
case ENOENT:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"dataset does not exist"));
zfs_verror(hdl, EZFS_NOENT, fmt, ap);
break;
case ENOSPC:
case EDQUOT:
zfs_verror(hdl, EZFS_NOSPC, fmt, ap);
break;
2008-11-20 20:01:55 +00:00
case EEXIST:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"dataset already exists"));
zfs_verror(hdl, EZFS_EXISTS, fmt, ap);
break;
case EBUSY:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"dataset is busy"));
zfs_verror(hdl, EZFS_BUSY, fmt, ap);
break;
case EROFS:
zfs_verror(hdl, EZFS_POOLREADONLY, fmt, ap);
2008-11-20 20:01:55 +00:00
break;
case ENAMETOOLONG:
zfs_verror(hdl, EZFS_NAMETOOLONG, fmt, ap);
break;
case ENOTSUP:
zfs_verror(hdl, EZFS_BADVERSION, fmt, ap);
break;
2009-07-02 22:44:48 +00:00
case EAGAIN:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool I/O is currently suspended"));
zfs_verror(hdl, EZFS_POOLUNAVAIL, fmt, ap);
break;
Multi-modifier protection (MMP) Add multihost=on|off pool property to control MMP. When enabled a new thread writes uberblocks to the last slot in each label, at a set frequency, to indicate to other hosts the pool is actively imported. These uberblocks are the last synced uberblock with an updated timestamp. Property defaults to off. During tryimport, find the "best" uberblock (newest txg and timestamp) repeatedly, checking for change in the found uberblock. Include the results of the activity test in the config returned by tryimport. These results are reported to user in "zpool import". Allow the user to control the period between MMP writes, and the duration of the activity test on import, via a new module parameter zfs_multihost_interval. The period is specified in milliseconds. The activity test duration is calculated from this value, and from the mmp_delay in the "best" uberblock found initially. Add a kstat interface to export statistics about Multiple Modifier Protection (MMP) updates. Include the last synced txg number, the timestamp, the delay since the last MMP update, the VDEV GUID, the VDEV label that received the last MMP update, and the VDEV path. Abbreviated output below. $ cat /proc/spl/kstat/zfs/mypool/multihost 31 0 0x01 10 880 105092382393521 105144180101111 txg timestamp mmp_delay vdev_guid vdev_label vdev_path 20468 261337 250274925 68396651780 3 /dev/sda 20468 261339 252023374 6267402363293 1 /dev/sdc 20468 261340 252000858 6698080955233 1 /dev/sdx 20468 261341 251980635 783892869810 2 /dev/sdy 20468 261342 253385953 8923255792467 3 /dev/sdd 20468 261344 253336622 042125143176 0 /dev/sdab 20468 261345 253310522 1200778101278 2 /dev/sde 20468 261346 253286429 0950576198362 2 /dev/sdt 20468 261347 253261545 96209817917 3 /dev/sds 20468 261349 253238188 8555725937673 3 /dev/sdb Add a new tunable zfs_multihost_history to specify the number of MMP updates to store history for. By default it is set to zero meaning that no MMP statistics are stored. When using ztest to generate activity, for automated tests of the MMP function, some test functions interfere with the test. For example, the pool is exported to run zdb and then imported again. Add a new ztest function, "-M", to alter ztest behavior to prevent this. Add new tests to verify the new functionality. Tests provided by Giuseppe Di Natale. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Giuseppe Di Natale <dinatale2@llnl.gov> Reviewed-by: Ned Bass <bass6@llnl.gov> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Closes #745 Closes #6279
2017-07-08 03:20:35 +00:00
case EREMOTEIO:
zfs_verror(hdl, EZFS_ACTIVE_POOL, fmt, ap);
break;
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
case ZFS_ERR_UNKNOWN_SEND_STREAM_FEATURE:
case ZFS_ERR_IOC_CMD_UNAVAIL:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "the loaded zfs "
"module does not support this operation. A reboot may "
"be required to enable this operation."));
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
case ZFS_ERR_IOC_ARG_UNAVAIL:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "the loaded zfs "
"module does not support an option for this operation. "
"A reboot may be required to enable this option."));
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
case ZFS_ERR_IOC_ARG_REQUIRED:
case ZFS_ERR_IOC_ARG_BADTYPE:
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
case ZFS_ERR_WRONG_PARENT:
zfs_verror(hdl, EZFS_WRONG_PARENT, fmt, ap);
break;
case ZFS_ERR_BADPROP:
zfs_verror(hdl, EZFS_BADPROP, fmt, ap);
break;
2008-11-20 20:01:55 +00:00
default:
zfs_error_aux(hdl, strerror(error));
2008-11-20 20:01:55 +00:00
zfs_verror(hdl, EZFS_UNKNOWN, fmt, ap);
break;
}
va_end(ap);
return (-1);
}
void
zfs_setprop_error(libzfs_handle_t *hdl, zfs_prop_t prop, int err,
char *errbuf)
{
switch (err) {
case ENOSPC:
/*
* For quotas and reservations, ENOSPC indicates
* something different; setting a quota or reservation
* doesn't use any disk space.
*/
switch (prop) {
case ZFS_PROP_QUOTA:
case ZFS_PROP_REFQUOTA:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"size is less than current used or "
"reserved space"));
(void) zfs_error(hdl, EZFS_PROPSPACE, errbuf);
break;
case ZFS_PROP_RESERVATION:
case ZFS_PROP_REFRESERVATION:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"size is greater than available space"));
(void) zfs_error(hdl, EZFS_PROPSPACE, errbuf);
break;
default:
(void) zfs_standard_error(hdl, err, errbuf);
break;
}
break;
case EBUSY:
(void) zfs_standard_error(hdl, EBUSY, errbuf);
break;
case EROFS:
(void) zfs_error(hdl, EZFS_DSREADONLY, errbuf);
break;
case E2BIG:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property value too long"));
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
break;
case ENOTSUP:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool and or dataset must be upgraded to set this "
"property or value"));
(void) zfs_error(hdl, EZFS_BADVERSION, errbuf);
break;
case ERANGE:
if (prop == ZFS_PROP_COMPRESSION ||
prop == ZFS_PROP_DNODESIZE ||
prop == ZFS_PROP_RECORDSIZE) {
(void) zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property setting is not allowed on "
"bootable datasets"));
(void) zfs_error(hdl, EZFS_NOTSUP, errbuf);
} else if (prop == ZFS_PROP_CHECKSUM ||
prop == ZFS_PROP_DEDUP) {
(void) zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"property setting is not allowed on "
"root pools"));
(void) zfs_error(hdl, EZFS_NOTSUP, errbuf);
} else {
(void) zfs_standard_error(hdl, err, errbuf);
}
break;
case EINVAL:
if (prop == ZPROP_INVAL) {
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
} else {
(void) zfs_standard_error(hdl, err, errbuf);
}
break;
case ZFS_ERR_BADPROP:
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
break;
case EACCES:
if (prop == ZFS_PROP_KEYLOCATION) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"keylocation may only be set on encryption roots"));
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
} else {
(void) zfs_standard_error(hdl, err, errbuf);
}
break;
case EOVERFLOW:
/*
* This platform can't address a volume this big.
*/
#ifdef _ILP32
if (prop == ZFS_PROP_VOLSIZE) {
(void) zfs_error(hdl, EZFS_VOLTOOBIG, errbuf);
break;
}
#endif
/* FALLTHROUGH */
default:
(void) zfs_standard_error(hdl, err, errbuf);
}
}
2008-11-20 20:01:55 +00:00
int
zpool_standard_error(libzfs_handle_t *hdl, int error, const char *msg)
{
return (zpool_standard_error_fmt(hdl, error, "%s", msg));
}
/*PRINTFLIKE3*/
int
zpool_standard_error_fmt(libzfs_handle_t *hdl, int error, const char *fmt, ...)
{
va_list ap;
va_start(ap, fmt);
if (zfs_common_error(hdl, error, fmt, ap) != 0) {
va_end(ap);
return (-1);
}
switch (error) {
case ENODEV:
zfs_verror(hdl, EZFS_NODEVICE, fmt, ap);
break;
case ENOENT:
zfs_error_aux(hdl,
dgettext(TEXT_DOMAIN, "no such pool or dataset"));
zfs_verror(hdl, EZFS_NOENT, fmt, ap);
break;
case EEXIST:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool already exists"));
zfs_verror(hdl, EZFS_EXISTS, fmt, ap);
break;
case EBUSY:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "pool is busy"));
zfs_verror(hdl, EZFS_BUSY, fmt, ap);
2008-11-20 20:01:55 +00:00
break;
OpenZFS 7614, 9064 - zfs device evacuation/removal OpenZFS 7614 - zfs device evacuation/removal OpenZFS 9064 - remove_mirror should wait for device removal to complete This project allows top-level vdevs to be removed from the storage pool with "zpool remove", reducing the total amount of storage in the pool. This operation copies all allocated regions of the device to be removed onto other devices, recording the mapping from old to new location. After the removal is complete, read and free operations to the removed (now "indirect") vdev must be remapped and performed at the new location on disk. The indirect mapping table is kept in memory whenever the pool is loaded, so there is minimal performance overhead when doing operations on the indirect vdev. The size of the in-memory mapping table will be reduced when its entries become "obsolete" because they are no longer used by any block pointers in the pool. An entry becomes obsolete when all the blocks that use it are freed. An entry can also become obsolete when all the snapshots that reference it are deleted, and the block pointers that reference it have been "remapped" in all filesystems/zvols (and clones). Whenever an indirect block is written, all the block pointers in it will be "remapped" to their new (concrete) locations if possible. This process can be accelerated by using the "zfs remap" command to proactively rewrite all indirect blocks that reference indirect (removed) vdevs. Note that when a device is removed, we do not verify the checksum of the data that is copied. This makes the process much faster, but if it were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be possible to copy the wrong data, when we have the correct data on e.g. the other side of the mirror. At the moment, only mirrors and simple top-level vdevs can be removed and no removal is allowed if any of the top-level vdevs are raidz. Porting Notes: * Avoid zero-sized kmem_alloc() in vdev_compact_children(). The device evacuation code adds a dependency that vdev_compact_children() be able to properly empty the vdev_child array by setting it to NULL and zeroing vdev_children. Under Linux, kmem_alloc() and related functions return a sentinel pointer rather than NULL for zero-sized allocations. * Remove comment regarding "mpt" driver where zfs_remove_max_segment is initialized to SPA_MAXBLOCKSIZE. Change zfs_condense_indirect_commit_entry_delay_ticks to zfs_condense_indirect_commit_entry_delay_ms for consistency with most other tunables in which delays are specified in ms. * ZTS changes: Use set_tunable rather than mdb Use zpool sync as appropriate Use sync_pool instead of sync Kill jobs during test_removal_with_operation to allow unmount/export Don't add non-disk names such as "mirror" or "raidz" to $DISKS Use $TEST_BASE_DIR instead of /tmp Increase HZ from 100 to 1000 which is more common on Linux removal_multiple_indirection.ksh Reduce iterations in order to not time out on the code coverage builders. removal_resume_export: Functionally, the test case is correct but there exists a race where the kernel thread hasn't been fully started yet and is not visible. Wait for up to 1 second for the removal thread to be started before giving up on it. Also, increase the amount of data copied in order that the removal not finish before the export has a chance to fail. * MMP compatibility, the concept of concrete versus non-concrete devices has slightly changed the semantics of vdev_writeable(). Update mmp_random_leaf_impl() accordingly. * Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool feature which is not supported by OpenZFS. * Added support for new vdev removal tracepoints. * Test cases removal_with_zdb and removal_condense_export have been intentionally disabled. When run manually they pass as intended, but when running in the automated test environment they produce unreliable results on the latest Fedora release. They may work better once the upstream pool import refectoring is merged into ZoL at which point they will be re-enabled. Authored by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Alex Reece <alex@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: John Kennedy <john.kennedy@delphix.com> Reviewed-by: Prakash Surya <prakash.surya@delphix.com> Reviewed by: Richard Laager <rlaager@wiktel.com> Reviewed by: Tim Chase <tim@chase2k.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Garrett D'Amore <garrett@damore.org> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://www.illumos.org/issues/7614 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb Closes #6900
2016-09-22 16:30:13 +00:00
/* There is no pending operation to cancel */
case ENOTACTIVE:
zfs_verror(hdl, EZFS_NO_PENDING, fmt, ap);
break;
2008-11-20 20:01:55 +00:00
case ENXIO:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"one or more devices is currently unavailable"));
zfs_verror(hdl, EZFS_BADDEV, fmt, ap);
break;
case ENAMETOOLONG:
zfs_verror(hdl, EZFS_DEVOVERFLOW, fmt, ap);
break;
case ENOTSUP:
zfs_verror(hdl, EZFS_POOL_NOTSUP, fmt, ap);
break;
case EINVAL:
zfs_verror(hdl, EZFS_POOL_INVALARG, fmt, ap);
break;
case ENOSPC:
case EDQUOT:
zfs_verror(hdl, EZFS_NOSPC, fmt, ap);
return (-1);
2009-07-02 22:44:48 +00:00
case EAGAIN:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"pool I/O is currently suspended"));
zfs_verror(hdl, EZFS_POOLUNAVAIL, fmt, ap);
break;
2008-11-20 20:01:55 +00:00
case EROFS:
zfs_verror(hdl, EZFS_POOLREADONLY, fmt, ap);
break;
case EDOM:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"block size out of range or does not match"));
zfs_verror(hdl, EZFS_BADPROP, fmt, ap);
break;
Multi-modifier protection (MMP) Add multihost=on|off pool property to control MMP. When enabled a new thread writes uberblocks to the last slot in each label, at a set frequency, to indicate to other hosts the pool is actively imported. These uberblocks are the last synced uberblock with an updated timestamp. Property defaults to off. During tryimport, find the "best" uberblock (newest txg and timestamp) repeatedly, checking for change in the found uberblock. Include the results of the activity test in the config returned by tryimport. These results are reported to user in "zpool import". Allow the user to control the period between MMP writes, and the duration of the activity test on import, via a new module parameter zfs_multihost_interval. The period is specified in milliseconds. The activity test duration is calculated from this value, and from the mmp_delay in the "best" uberblock found initially. Add a kstat interface to export statistics about Multiple Modifier Protection (MMP) updates. Include the last synced txg number, the timestamp, the delay since the last MMP update, the VDEV GUID, the VDEV label that received the last MMP update, and the VDEV path. Abbreviated output below. $ cat /proc/spl/kstat/zfs/mypool/multihost 31 0 0x01 10 880 105092382393521 105144180101111 txg timestamp mmp_delay vdev_guid vdev_label vdev_path 20468 261337 250274925 68396651780 3 /dev/sda 20468 261339 252023374 6267402363293 1 /dev/sdc 20468 261340 252000858 6698080955233 1 /dev/sdx 20468 261341 251980635 783892869810 2 /dev/sdy 20468 261342 253385953 8923255792467 3 /dev/sdd 20468 261344 253336622 042125143176 0 /dev/sdab 20468 261345 253310522 1200778101278 2 /dev/sde 20468 261346 253286429 0950576198362 2 /dev/sdt 20468 261347 253261545 96209817917 3 /dev/sds 20468 261349 253238188 8555725937673 3 /dev/sdb Add a new tunable zfs_multihost_history to specify the number of MMP updates to store history for. By default it is set to zero meaning that no MMP statistics are stored. When using ztest to generate activity, for automated tests of the MMP function, some test functions interfere with the test. For example, the pool is exported to run zdb and then imported again. Add a new ztest function, "-M", to alter ztest behavior to prevent this. Add new tests to verify the new functionality. Tests provided by Giuseppe Di Natale. Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed-by: Giuseppe Di Natale <dinatale2@llnl.gov> Reviewed-by: Ned Bass <bass6@llnl.gov> Reviewed-by: Andreas Dilger <andreas.dilger@intel.com> Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Olaf Faaland <faaland1@llnl.gov> Closes #745 Closes #6279
2017-07-08 03:20:35 +00:00
case EREMOTEIO:
zfs_verror(hdl, EZFS_ACTIVE_POOL, fmt, ap);
break;
OpenZFS 9166 - zfs storage pool checkpoint Details about the motivation of this feature and its usage can be found in this blogpost: https://sdimitro.github.io/post/zpool-checkpoint/ A lightning talk of this feature can be found here: https://www.youtube.com/watch?v=fPQA8K40jAM Implementation details can be found in big block comment of spa_checkpoint.c Side-changes that are relevant to this commit but not explained elsewhere: * renames members of "struct metaslab trees to be shorter without losing meaning * space_map_{alloc,truncate}() accept a block size as a parameter. The reason is that in the current state all space maps that we allocate through the DMU use a global tunable (space_map_blksz) which defauls to 4KB. This is ok for metaslab space maps in terms of bandwirdth since they are scattered all over the disk. But for other space maps this default is probably not what we want. Examples are device removal's vdev_obsolete_sm or vdev_chedkpoint_sm from this review. Both of these have a 1:1 relationship with each vdev and could benefit from a bigger block size. Porting notes: * The part of dsl_scan_sync() which handles async destroys has been moved into the new dsl_process_async_destroys() function. * Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write to block device backed pools. * ZTS: * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg". * Don't use large dd block sizes on /dev/urandom under Linux in checkpoint_capacity. * Adopt Delphix-OS's setting of 4 (spa_asize_inflation = SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed its attempts to fill the pool * Create the base and nested pools with sync=disabled to speed up the "setup" phase. * Clear labels in test pool between checkpoint tests to avoid duplicate pool issues. * The import_rewind_device_replaced test has been marked as "known to fail" for the reasons listed in its DISCLAIMER. * New module parameters: zfs_spa_discard_memory_limit, zfs_remove_max_bytes_pause (not documented - debugging only) vdev_max_ms_count (formerly metaslabs_per_vdev) vdev_min_ms_count Authored by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com> Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: John Kennedy <john.kennedy@delphix.com> Reviewed by: Dan Kimmel <dan.kimmel@delphix.com> Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov> Approved by: Richard Lowe <richlowe@richlowe.net> Ported-by: Tim Chase <tim@chase2k.com> Signed-off-by: Tim Chase <tim@chase2k.com> OpenZFS-issue: https://illumos.org/issues/9166 OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8 Closes #7570
2016-12-16 22:11:29 +00:00
case ZFS_ERR_CHECKPOINT_EXISTS:
zfs_verror(hdl, EZFS_CHECKPOINT_EXISTS, fmt, ap);
break;
case ZFS_ERR_DISCARDING_CHECKPOINT:
zfs_verror(hdl, EZFS_DISCARDING_CHECKPOINT, fmt, ap);
break;
case ZFS_ERR_NO_CHECKPOINT:
zfs_verror(hdl, EZFS_NO_CHECKPOINT, fmt, ap);
break;
case ZFS_ERR_DEVRM_IN_PROGRESS:
zfs_verror(hdl, EZFS_DEVRM_IN_PROGRESS, fmt, ap);
break;
case ZFS_ERR_VDEV_TOO_BIG:
zfs_verror(hdl, EZFS_VDEV_TOO_BIG, fmt, ap);
break;
case ZFS_ERR_EXPORT_IN_PROGRESS:
zfs_verror(hdl, EZFS_EXPORT_IN_PROGRESS, fmt, ap);
break;
Add device rebuild feature The device_rebuild feature enables sequential reconstruction when resilvering. Mirror vdevs can be rebuilt in LBA order which may more quickly restore redundancy depending on the pools average block size, overall fragmentation and the performance characteristics of the devices. However, block checksums cannot be verified as part of the rebuild thus a scrub is automatically started after the sequential resilver completes. The new '-s' option has been added to the `zpool attach` and `zpool replace` command to request sequential reconstruction instead of healing reconstruction when resilvering. zpool attach -s <pool> <existing vdev> <new vdev> zpool replace -s <pool> <old vdev> <new vdev> The `zpool status` output has been updated to report the progress of sequential resilvering in the same way as healing resilvering. The one notable difference is that multiple sequential resilvers may be in progress as long as they're operating on different top-level vdevs. The `zpool wait -t resilver` command was extended to wait on sequential resilvers. From this perspective they are no different than healing resilvers. Sequential resilvers cannot be supported for RAIDZ, but are compatible with the dRAID feature being developed. As part of this change the resilver_restart_* tests were moved in to the functional/replacement directory. Additionally, the replacement tests were renamed and extended to verify both resilvering and rebuilding. Original-patch-by: Isaac Huang <he.huang@intel.com> Reviewed-by: Tony Hutter <hutter2@llnl.gov> Reviewed-by: John Poduska <jpoduska@datto.com> Co-authored-by: Mark Maybee <mmaybee@cray.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #10349
2020-07-03 18:05:50 +00:00
case ZFS_ERR_RESILVER_IN_PROGRESS:
zfs_verror(hdl, EZFS_RESILVERING, fmt, ap);
break;
case ZFS_ERR_REBUILD_IN_PROGRESS:
zfs_verror(hdl, EZFS_REBUILDING, fmt, ap);
break;
case ZFS_ERR_BADPROP:
zfs_verror(hdl, EZFS_BADPROP, fmt, ap);
break;
case ZFS_ERR_IOC_CMD_UNAVAIL:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "the loaded zfs "
"module does not support this operation. A reboot may "
"be required to enable this operation."));
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
case ZFS_ERR_IOC_ARG_UNAVAIL:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN, "the loaded zfs "
"module does not support an option for this operation. "
"A reboot may be required to enable this option."));
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
case ZFS_ERR_IOC_ARG_REQUIRED:
case ZFS_ERR_IOC_ARG_BADTYPE:
zfs_verror(hdl, EZFS_IOC_NOTSUPPORTED, fmt, ap);
break;
2008-11-20 20:01:55 +00:00
default:
zfs_error_aux(hdl, strerror(error));
zfs_verror(hdl, EZFS_UNKNOWN, fmt, ap);
}
va_end(ap);
return (-1);
}
/*
* Display an out of memory error message and abort the current program.
*/
int
no_memory(libzfs_handle_t *hdl)
{
return (zfs_error(hdl, EZFS_NOMEM, "internal error"));
}
/*
* A safe form of malloc() which will die if the allocation fails.
*/
void *
zfs_alloc(libzfs_handle_t *hdl, size_t size)
{
void *data;
if ((data = calloc(1, size)) == NULL)
(void) no_memory(hdl);
return (data);
}
/*
* A safe form of asprintf() which will die if the allocation fails.
*/
/*PRINTFLIKE2*/
char *
zfs_asprintf(libzfs_handle_t *hdl, const char *fmt, ...)
{
va_list ap;
char *ret;
int err;
va_start(ap, fmt);
err = vasprintf(&ret, fmt, ap);
va_end(ap);
if (err < 0)
(void) no_memory(hdl);
return (ret);
}
2008-11-20 20:01:55 +00:00
/*
* A safe form of realloc(), which also zeroes newly allocated space.
*/
void *
zfs_realloc(libzfs_handle_t *hdl, void *ptr, size_t oldsize, size_t newsize)
{
void *ret;
if ((ret = realloc(ptr, newsize)) == NULL) {
(void) no_memory(hdl);
return (NULL);
}
bzero((char *)ret + oldsize, (newsize - oldsize));
return (ret);
}
/*
* A safe form of strdup() which will die if the allocation fails.
*/
char *
zfs_strdup(libzfs_handle_t *hdl, const char *str)
{
char *ret;
if ((ret = strdup(str)) == NULL)
(void) no_memory(hdl);
return (ret);
}
void
libzfs_print_on_error(libzfs_handle_t *hdl, boolean_t printerr)
{
hdl->libzfs_printerr = printerr;
}
2017-04-21 16:27:04 +00:00
/*
* Read lines from an open file descriptor and store them in an array of
* strings until EOF. lines[] will be allocated and populated with all the
* lines read. All newlines are replaced with NULL terminators for
* convenience. lines[] must be freed after use with libzfs_free_str_array().
*
* Returns the number of lines read.
*/
static int
libzfs_read_stdout_from_fd(int fd, char **lines[])
{
FILE *fp;
int lines_cnt = 0;
size_t len = 0;
char *line = NULL;
char **tmp_lines = NULL, **tmp;
char *nl = NULL;
int rc;
fp = fdopen(fd, "r");
if (fp == NULL)
return (0);
while (1) {
rc = getline(&line, &len, fp);
if (rc == -1)
break;
tmp = realloc(tmp_lines, sizeof (*tmp_lines) * (lines_cnt + 1));
if (tmp == NULL) {
/* Return the lines we were able to process */
break;
}
tmp_lines = tmp;
/* Terminate newlines */
if ((nl = strchr(line, '\n')) != NULL)
*nl = '\0';
tmp_lines[lines_cnt] = line;
lines_cnt++;
line = NULL;
}
fclose(fp);
*lines = tmp_lines;
return (lines_cnt);
}
static int
libzfs_run_process_impl(const char *path, char *argv[], char *env[], int flags,
char **lines[], int *lines_cnt)
{
pid_t pid;
int error, devnull_fd;
2017-04-21 16:27:04 +00:00
int link[2];
/*
* Setup a pipe between our child and parent process if we're
* reading stdout.
*/
if ((lines != NULL) && pipe2(link, O_CLOEXEC) == -1)
return (-EPIPE);
pid = vfork();
if (pid == 0) {
2017-04-21 16:27:04 +00:00
/* Child process */
devnull_fd = open("/dev/null", O_WRONLY | O_CLOEXEC);
if (devnull_fd < 0)
_exit(-1);
2017-04-21 16:27:04 +00:00
if (!(flags & STDOUT_VERBOSE) && (lines == NULL))
(void) dup2(devnull_fd, STDOUT_FILENO);
2017-04-21 16:27:04 +00:00
else if (lines != NULL) {
/* Save the output to lines[] */
dup2(link[1], STDOUT_FILENO);
}
if (!(flags & STDERR_VERBOSE))
(void) dup2(devnull_fd, STDERR_FILENO);
2017-04-21 16:27:04 +00:00
if (flags & NO_DEFAULT_PATH) {
if (env == NULL)
execv(path, argv);
else
execve(path, argv, env);
} else {
if (env == NULL)
execvp(path, argv);
else
execvpe(path, argv, env);
}
_exit(-1);
} else if (pid > 0) {
2017-04-21 16:27:04 +00:00
/* Parent process */
int status;
while ((error = waitpid(pid, &status, 0)) == -1 &&
errno == EINTR) { }
if (error < 0 || !WIFEXITED(status))
return (-1);
2017-04-21 16:27:04 +00:00
if (lines != NULL) {
close(link[1]);
*lines_cnt = libzfs_read_stdout_from_fd(link[0], lines);
}
return (WEXITSTATUS(status));
}
return (-1);
}
2017-04-21 16:27:04 +00:00
int
libzfs_run_process(const char *path, char *argv[], int flags)
{
return (libzfs_run_process_impl(path, argv, NULL, flags, NULL, NULL));
}
/*
* Run a command and store its stdout lines in an array of strings (lines[]).
* lines[] is allocated and populated for you, and the number of lines is set in
* lines_cnt. lines[] must be freed after use with libzfs_free_str_array().
* All newlines (\n) in lines[] are terminated for convenience.
*/
int
libzfs_run_process_get_stdout(const char *path, char *argv[], char *env[],
char **lines[], int *lines_cnt)
{
return (libzfs_run_process_impl(path, argv, env, 0, lines, lines_cnt));
}
/*
* Same as libzfs_run_process_get_stdout(), but run without $PATH set. This
* means that *path needs to be the full path to the executable.
*/
int
libzfs_run_process_get_stdout_nopath(const char *path, char *argv[],
char *env[], char **lines[], int *lines_cnt)
{
return (libzfs_run_process_impl(path, argv, env, NO_DEFAULT_PATH,
lines, lines_cnt));
}
/*
* Free an array of strings. Free both the strings contained in the array and
* the array itself.
*/
void
libzfs_free_str_array(char **strs, int count)
{
while (--count >= 0)
free(strs[count]);
free(strs);
}
/*
* Returns 1 if environment variable is set to "YES", "yes", "ON", "on", or
* a non-zero number.
*
* Returns 0 otherwise.
*/
int
libzfs_envvar_is_set(char *envvar)
{
char *env = getenv(envvar);
if (env && (strtoul(env, NULL, 0) > 0 ||
(!strncasecmp(env, "YES", 3) && strnlen(env, 4) == 3) ||
(!strncasecmp(env, "ON", 2) && strnlen(env, 3) == 2)))
return (1);
return (0);
}
2008-11-20 20:01:55 +00:00
libzfs_handle_t *
libzfs_init(void)
{
libzfs_handle_t *hdl;
Wait in libzfs_init() for the /dev/zfs device While module loading itself is synchronous the creation of the /dev/zfs device is not. This is because /dev/zfs is typically created by a udev rule after the module is registered and presented to user space through sysfs. This small window between module loading and device creation can result in spurious failures of libzfs_init(). This patch closes that race by extending libzfs_init() so it can detect that the modules are loaded and only if required wait for the /dev/zfs device to be created. This allows scripts to reliably use the following shell construct without the need for additional error handling. $ /sbin/modprobe zfs && /sbin/zpool import -a To minimize the potential time waiting in libzfs_init() a strategy similar to adaptive mutexes is employed. The function will busy-wait for up to 10ms based on the expectation that the modules were just loaded and therefore the /dev/zfs will be created imminently. If it takes longer than this it will fall back to polling for up to 10 seconds. This behavior can be customized to some degree by setting the following new environment variables. This functionality is provided for backwards compatibility with existing scripts which depend on the module auto-load behavior. By default module auto-loading is now disabled. * ZFS_MODULE_LOADING="YES|yes|ON|on" - Attempt to load modules. * ZFS_MODULE_TIMEOUT="<seconds>" - Seconds to wait for /dev/zfs The zfs-import-* systemd service files have been updated to call '/sbin/modprobe zfs' so they no longer rely on the legacy auto-loading behavior. Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Chris Dunlap <cdunlap@llnl.gov> Signed-off-by: Richard Yao <ryao@gentoo.org> Closes #2556
2015-05-20 21:36:37 +00:00
int error;
char *env;
2008-11-20 20:01:55 +00:00
if ((error = libzfs_load_module()) != 0) {
errno = error;
return (NULL);
}
if ((hdl = calloc(1, sizeof (libzfs_handle_t))) == NULL) {
2008-11-20 20:01:55 +00:00
return (NULL);
}
if (regcomp(&hdl->libzfs_urire, URI_REGEX, 0) != 0) {
free(hdl);
return (NULL);
}
if ((hdl->libzfs_fd = open(ZFS_DEV, O_RDWR|O_EXCL|O_CLOEXEC)) < 0) {
2008-11-20 20:01:55 +00:00
free(hdl);
return (NULL);
}
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
if (libzfs_core_init() != 0) {
(void) close(hdl->libzfs_fd);
free(hdl);
return (NULL);
}
2008-11-20 20:01:55 +00:00
zfs_prop_init();
zpool_prop_init();
zpool_feature_init();
2009-07-02 22:44:48 +00:00
libzfs_mnttab_init(hdl);
fletcher_4_init();
2008-11-20 20:01:55 +00:00
if (getenv("ZFS_PROP_DEBUG") != NULL) {
hdl->libzfs_prop_debug = B_TRUE;
}
if ((env = getenv("ZFS_SENDRECV_MAX_NVLIST")) != NULL) {
if ((error = zfs_nicestrtonum(hdl, env,
&hdl->libzfs_max_nvlist))) {
errno = error;
(void) close(hdl->libzfs_fd);
free(hdl);
return (NULL);
}
} else {
hdl->libzfs_max_nvlist = (SPA_MAXBLOCKSIZE * 4);
}
/*
* For testing, remove some settable properties and features
*/
if (libzfs_envvar_is_set("ZFS_SYSFS_PROP_SUPPORT_TEST")) {
zprop_desc_t *proptbl;
proptbl = zpool_prop_get_table();
proptbl[ZPOOL_PROP_COMMENT].pd_zfs_mod_supported = B_FALSE;
proptbl = zfs_prop_get_table();
proptbl[ZFS_PROP_DNODESIZE].pd_zfs_mod_supported = B_FALSE;
zfeature_info_t *ftbl = spa_feature_table;
ftbl[SPA_FEATURE_LARGE_BLOCKS].fi_zfs_mod_supported = B_FALSE;
}
2008-11-20 20:01:55 +00:00
return (hdl);
}
void
libzfs_fini(libzfs_handle_t *hdl)
{
(void) close(hdl->libzfs_fd);
zpool_free_handles(hdl);
2008-11-20 20:01:55 +00:00
namespace_clear(hdl);
2009-07-02 22:44:48 +00:00
libzfs_mnttab_fini(hdl);
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
libzfs_core_fini();
regfree(&hdl->libzfs_urire);
fletcher_4_fini();
2008-11-20 20:01:55 +00:00
free(hdl);
}
libzfs_handle_t *
zpool_get_handle(zpool_handle_t *zhp)
{
return (zhp->zpool_hdl);
}
libzfs_handle_t *
zfs_get_handle(zfs_handle_t *zhp)
{
return (zhp->zfs_hdl);
}
zpool_handle_t *
zfs_get_pool_handle(const zfs_handle_t *zhp)
{
return (zhp->zpool_hdl);
}
2008-11-20 20:01:55 +00:00
/*
* Given a name, determine whether or not it's a valid path
* (starts with '/' or "./"). If so, walk the mnttab trying
* to match the device number. If not, treat the path as an
* fs/vol/snap/bkmark name.
2008-11-20 20:01:55 +00:00
*/
zfs_handle_t *
zfs_path_to_zhandle(libzfs_handle_t *hdl, const char *path, zfs_type_t argtype)
2008-11-20 20:01:55 +00:00
{
struct stat64 statbuf;
struct extmnttab entry;
if (path[0] != '/' && strncmp(path, "./", strlen("./")) != 0) {
/*
* It's not a valid path, assume it's a name of type 'argtype'.
*/
return (zfs_open(hdl, path, argtype));
}
if (getextmntent(path, &entry, &statbuf) != 0)
2008-11-20 20:01:55 +00:00
return (NULL);
if (strcmp(entry.mnt_fstype, MNTTYPE_ZFS) != 0) {
(void) fprintf(stderr, gettext("'%s': not a ZFS filesystem\n"),
path);
return (NULL);
}
return (zfs_open(hdl, entry.mnt_special, ZFS_TYPE_FILESYSTEM));
}
/*
* Initialize the zc_nvlist_dst member to prepare for receiving an nvlist from
* an ioctl().
*/
int
zcmd_alloc_dst_nvlist(libzfs_handle_t *hdl, zfs_cmd_t *zc, size_t len)
{
if (len == 0)
len = 256 * 1024;
2008-11-20 20:01:55 +00:00
zc->zc_nvlist_dst_size = len;
zc->zc_nvlist_dst =
(uint64_t)(uintptr_t)zfs_alloc(hdl, zc->zc_nvlist_dst_size);
if (zc->zc_nvlist_dst == 0)
2008-11-20 20:01:55 +00:00
return (-1);
return (0);
}
/*
* Called when an ioctl() which returns an nvlist fails with ENOMEM. This will
* expand the nvlist to the size specified in 'zc_nvlist_dst_size', which was
* filled in by the kernel to indicate the actual required size.
*/
int
zcmd_expand_dst_nvlist(libzfs_handle_t *hdl, zfs_cmd_t *zc)
{
free((void *)(uintptr_t)zc->zc_nvlist_dst);
zc->zc_nvlist_dst =
(uint64_t)(uintptr_t)zfs_alloc(hdl, zc->zc_nvlist_dst_size);
if (zc->zc_nvlist_dst == 0)
2008-11-20 20:01:55 +00:00
return (-1);
return (0);
}
/*
* Called to free the src and dst nvlists stored in the command structure.
*/
void
zcmd_free_nvlists(zfs_cmd_t *zc)
{
free((void *)(uintptr_t)zc->zc_nvlist_conf);
free((void *)(uintptr_t)zc->zc_nvlist_src);
free((void *)(uintptr_t)zc->zc_nvlist_dst);
zc->zc_nvlist_conf = 0;
zc->zc_nvlist_src = 0;
zc->zc_nvlist_dst = 0;
2008-11-20 20:01:55 +00:00
}
static int
zcmd_write_nvlist_com(libzfs_handle_t *hdl, uint64_t *outnv, uint64_t *outlen,
nvlist_t *nvl)
{
char *packed;
size_t len;
verify(nvlist_size(nvl, &len, NV_ENCODE_NATIVE) == 0);
if ((packed = zfs_alloc(hdl, len)) == NULL)
return (-1);
verify(nvlist_pack(nvl, &packed, &len, NV_ENCODE_NATIVE, 0) == 0);
*outnv = (uint64_t)(uintptr_t)packed;
*outlen = len;
return (0);
}
int
zcmd_write_conf_nvlist(libzfs_handle_t *hdl, zfs_cmd_t *zc, nvlist_t *nvl)
{
return (zcmd_write_nvlist_com(hdl, &zc->zc_nvlist_conf,
&zc->zc_nvlist_conf_size, nvl));
}
int
zcmd_write_src_nvlist(libzfs_handle_t *hdl, zfs_cmd_t *zc, nvlist_t *nvl)
{
return (zcmd_write_nvlist_com(hdl, &zc->zc_nvlist_src,
&zc->zc_nvlist_src_size, nvl));
}
/*
* Unpacks an nvlist from the ZFS ioctl command structure.
*/
int
zcmd_read_dst_nvlist(libzfs_handle_t *hdl, zfs_cmd_t *zc, nvlist_t **nvlp)
{
if (nvlist_unpack((void *)(uintptr_t)zc->zc_nvlist_dst,
zc->zc_nvlist_dst_size, nvlp, 0) != 0)
return (no_memory(hdl));
return (0);
}
/*
* ================================================================
* API shared by zfs and zpool property management
* ================================================================
*/
static void
zprop_print_headers(zprop_get_cbdata_t *cbp, zfs_type_t type)
{
zprop_list_t *pl = cbp->cb_proplist;
int i;
char *title;
size_t len;
cbp->cb_first = B_FALSE;
if (cbp->cb_scripted)
return;
/*
* Start with the length of the column headers.
*/
cbp->cb_colwidths[GET_COL_NAME] = strlen(dgettext(TEXT_DOMAIN, "NAME"));
cbp->cb_colwidths[GET_COL_PROPERTY] = strlen(dgettext(TEXT_DOMAIN,
"PROPERTY"));
cbp->cb_colwidths[GET_COL_VALUE] = strlen(dgettext(TEXT_DOMAIN,
"VALUE"));
cbp->cb_colwidths[GET_COL_RECVD] = strlen(dgettext(TEXT_DOMAIN,
"RECEIVED"));
2008-11-20 20:01:55 +00:00
cbp->cb_colwidths[GET_COL_SOURCE] = strlen(dgettext(TEXT_DOMAIN,
"SOURCE"));
2009-01-15 21:59:39 +00:00
/* first property is always NAME */
assert(cbp->cb_proplist->pl_prop ==
((type == ZFS_TYPE_POOL) ? ZPOOL_PROP_NAME : ZFS_PROP_NAME));
2008-11-20 20:01:55 +00:00
/*
* Go through and calculate the widths for each column. For the
* 'source' column, we kludge it up by taking the worst-case scenario of
* inheriting from the longest name. This is acceptable because in the
* majority of cases 'SOURCE' is the last column displayed, and we don't
* use the width anyway. Note that the 'VALUE' column can be oversized,
* if the name of the property is much longer than any values we find.
2008-11-20 20:01:55 +00:00
*/
for (pl = cbp->cb_proplist; pl != NULL; pl = pl->pl_next) {
/*
* 'PROPERTY' column
*/
if (pl->pl_prop != ZPROP_INVAL) {
const char *propname = (type == ZFS_TYPE_POOL) ?
zpool_prop_to_name(pl->pl_prop) :
zfs_prop_to_name(pl->pl_prop);
len = strlen(propname);
if (len > cbp->cb_colwidths[GET_COL_PROPERTY])
cbp->cb_colwidths[GET_COL_PROPERTY] = len;
} else {
len = strlen(pl->pl_user_prop);
if (len > cbp->cb_colwidths[GET_COL_PROPERTY])
cbp->cb_colwidths[GET_COL_PROPERTY] = len;
}
/*
2009-01-15 21:59:39 +00:00
* 'VALUE' column. The first property is always the 'name'
* property that was tacked on either by /sbin/zfs's
* zfs_do_get() or when calling zprop_expand_list(), so we
* ignore its width. If the user specified the name property
* to display, then it will be later in the list in any case.
2008-11-20 20:01:55 +00:00
*/
2009-01-15 21:59:39 +00:00
if (pl != cbp->cb_proplist &&
2008-11-20 20:01:55 +00:00
pl->pl_width > cbp->cb_colwidths[GET_COL_VALUE])
cbp->cb_colwidths[GET_COL_VALUE] = pl->pl_width;
/* 'RECEIVED' column. */
if (pl != cbp->cb_proplist &&
pl->pl_recvd_width > cbp->cb_colwidths[GET_COL_RECVD])
cbp->cb_colwidths[GET_COL_RECVD] = pl->pl_recvd_width;
2008-11-20 20:01:55 +00:00
/*
* 'NAME' and 'SOURCE' columns
*/
if (pl->pl_prop == (type == ZFS_TYPE_POOL ? ZPOOL_PROP_NAME :
ZFS_PROP_NAME) &&
pl->pl_width > cbp->cb_colwidths[GET_COL_NAME]) {
cbp->cb_colwidths[GET_COL_NAME] = pl->pl_width;
cbp->cb_colwidths[GET_COL_SOURCE] = pl->pl_width +
strlen(dgettext(TEXT_DOMAIN, "inherited from"));
}
}
/*
* Now go through and print the headers.
*/
for (i = 0; i < ZFS_GET_NCOLS; i++) {
2008-11-20 20:01:55 +00:00
switch (cbp->cb_columns[i]) {
case GET_COL_NAME:
title = dgettext(TEXT_DOMAIN, "NAME");
break;
case GET_COL_PROPERTY:
title = dgettext(TEXT_DOMAIN, "PROPERTY");
break;
case GET_COL_VALUE:
title = dgettext(TEXT_DOMAIN, "VALUE");
break;
case GET_COL_RECVD:
title = dgettext(TEXT_DOMAIN, "RECEIVED");
break;
2008-11-20 20:01:55 +00:00
case GET_COL_SOURCE:
title = dgettext(TEXT_DOMAIN, "SOURCE");
break;
default:
title = NULL;
}
if (title != NULL) {
if (i == (ZFS_GET_NCOLS - 1) ||
cbp->cb_columns[i + 1] == GET_COL_NONE)
2008-11-20 20:01:55 +00:00
(void) printf("%s", title);
else
(void) printf("%-*s ",
cbp->cb_colwidths[cbp->cb_columns[i]],
title);
}
}
(void) printf("\n");
}
/*
* Display a single line of output, according to the settings in the callback
* structure.
*/
void
zprop_print_one_property(const char *name, zprop_get_cbdata_t *cbp,
const char *propname, const char *value, zprop_source_t sourcetype,
const char *source, const char *recvd_value)
2008-11-20 20:01:55 +00:00
{
int i;
const char *str = NULL;
2008-11-20 20:01:55 +00:00
char buf[128];
/*
* Ignore those source types that the user has chosen to ignore.
*/
if ((sourcetype & cbp->cb_sources) == 0)
return;
if (cbp->cb_first)
zprop_print_headers(cbp, cbp->cb_type);
for (i = 0; i < ZFS_GET_NCOLS; i++) {
2008-11-20 20:01:55 +00:00
switch (cbp->cb_columns[i]) {
case GET_COL_NAME:
str = name;
break;
case GET_COL_PROPERTY:
str = propname;
break;
case GET_COL_VALUE:
str = value;
break;
case GET_COL_SOURCE:
switch (sourcetype) {
case ZPROP_SRC_NONE:
str = "-";
break;
case ZPROP_SRC_DEFAULT:
str = "default";
break;
case ZPROP_SRC_LOCAL:
str = "local";
break;
case ZPROP_SRC_TEMPORARY:
str = "temporary";
break;
case ZPROP_SRC_INHERITED:
(void) snprintf(buf, sizeof (buf),
"inherited from %s", source);
str = buf;
break;
case ZPROP_SRC_RECEIVED:
str = "received";
break;
default:
str = NULL;
assert(!"unhandled zprop_source_t");
2008-11-20 20:01:55 +00:00
}
break;
case GET_COL_RECVD:
str = (recvd_value == NULL ? "-" : recvd_value);
break;
2008-11-20 20:01:55 +00:00
default:
continue;
}
if (i == (ZFS_GET_NCOLS - 1) ||
cbp->cb_columns[i + 1] == GET_COL_NONE)
2008-11-20 20:01:55 +00:00
(void) printf("%s", str);
else if (cbp->cb_scripted)
(void) printf("%s\t", str);
else
(void) printf("%-*s ",
cbp->cb_colwidths[cbp->cb_columns[i]],
str);
}
(void) printf("\n");
}
/*
* Given a numeric suffix, convert the value into a number of bits that the
* resulting value must be shifted.
*/
static int
str2shift(libzfs_handle_t *hdl, const char *buf)
{
const char *ends = "BKMGTPEZ";
int i;
if (buf[0] == '\0')
return (0);
for (i = 0; i < strlen(ends); i++) {
if (toupper(buf[0]) == ends[i])
break;
}
if (i == strlen(ends)) {
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"invalid numeric suffix '%s'"), buf);
2008-11-20 20:01:55 +00:00
return (-1);
}
/*
* Allow 'G' = 'GB' = 'GiB', case-insensitively.
* However, 'BB' and 'BiB' are disallowed.
2008-11-20 20:01:55 +00:00
*/
if (buf[1] == '\0' ||
(toupper(buf[0]) != 'B' &&
((toupper(buf[1]) == 'B' && buf[2] == '\0') ||
(toupper(buf[1]) == 'I' && toupper(buf[2]) == 'B' &&
buf[3] == '\0'))))
return (10 * i);
2008-11-20 20:01:55 +00:00
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"invalid numeric suffix '%s'"), buf);
2008-11-20 20:01:55 +00:00
return (-1);
}
/*
* Convert a string of the form '100G' into a real number. Used when setting
* properties or creating a volume. 'buf' is used to place an extended error
* message for the caller to use.
*/
int
zfs_nicestrtonum(libzfs_handle_t *hdl, const char *value, uint64_t *num)
{
char *end;
int shift;
*num = 0;
/* Check to see if this looks like a number. */
if ((value[0] < '0' || value[0] > '9') && value[0] != '.') {
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"bad numeric value '%s'"), value);
return (-1);
}
/* Rely on strtoull() to process the numeric portion. */
2008-11-20 20:01:55 +00:00
errno = 0;
2009-02-18 20:51:31 +00:00
*num = strtoull(value, &end, 10);
2008-11-20 20:01:55 +00:00
/*
* Check for ERANGE, which indicates that the value is too large to fit
* in a 64-bit value.
*/
if (errno == ERANGE) {
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"numeric value is too large"));
return (-1);
}
/*
* If we have a decimal value, then do the computation with floating
* point arithmetic. Otherwise, use standard arithmetic.
*/
if (*end == '.') {
double fval = strtod(value, &end);
if ((shift = str2shift(hdl, end)) == -1)
return (-1);
fval *= pow(2, shift);
/*
* UINT64_MAX is not exactly representable as a double.
* The closest representation is UINT64_MAX + 1, so we
* use a >= comparison instead of > for the bounds check.
*/
if (fval >= (double)UINT64_MAX) {
2008-11-20 20:01:55 +00:00
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"numeric value is too large"));
return (-1);
}
*num = (uint64_t)fval;
} else {
if ((shift = str2shift(hdl, end)) == -1)
return (-1);
/* Check for overflow */
if (shift >= 64 || (*num << shift) >> shift != *num) {
if (hdl)
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"numeric value is too large"));
return (-1);
}
*num <<= shift;
}
return (0);
}
/*
* Given a propname=value nvpair to set, parse any numeric properties
* (index, boolean, etc) if they are specified as strings and add the
* resulting nvpair to the returned nvlist.
*
* At the DSL layer, all properties are either 64-bit numbers or strings.
* We want the user to be able to ignore this fact and specify properties
* as native values (numbers, for example) or as strings (to simplify
* command line utilities). This also handles converting index types
* (compression, checksum, etc) from strings to their on-disk index.
*/
int
zprop_parse_value(libzfs_handle_t *hdl, nvpair_t *elem, int prop,
zfs_type_t type, nvlist_t *ret, char **svalp, uint64_t *ivalp,
const char *errbuf)
{
data_type_t datatype = nvpair_type(elem);
zprop_type_t proptype;
const char *propname;
char *value;
boolean_t isnone = B_FALSE;
boolean_t isauto = B_FALSE;
int err = 0;
2008-11-20 20:01:55 +00:00
if (type == ZFS_TYPE_POOL) {
proptype = zpool_prop_get_type(prop);
propname = zpool_prop_to_name(prop);
} else {
proptype = zfs_prop_get_type(prop);
propname = zfs_prop_to_name(prop);
}
/*
* Convert any properties to the internal DSL value types.
*/
*svalp = NULL;
*ivalp = 0;
switch (proptype) {
case PROP_TYPE_STRING:
if (datatype != DATA_TYPE_STRING) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' must be a string"), nvpair_name(elem));
goto error;
}
err = nvpair_value_string(elem, svalp);
if (err != 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' is invalid"), nvpair_name(elem));
goto error;
}
2008-11-20 20:01:55 +00:00
if (strlen(*svalp) >= ZFS_MAXPROPLEN) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' is too long"), nvpair_name(elem));
goto error;
}
break;
case PROP_TYPE_NUMBER:
if (datatype == DATA_TYPE_STRING) {
(void) nvpair_value_string(elem, &value);
if (strcmp(value, "none") == 0) {
isnone = B_TRUE;
} else if (strcmp(value, "auto") == 0) {
isauto = B_TRUE;
} else if (zfs_nicestrtonum(hdl, value, ivalp) != 0) {
2008-11-20 20:01:55 +00:00
goto error;
}
} else if (datatype == DATA_TYPE_UINT64) {
(void) nvpair_value_uint64(elem, ivalp);
} else {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' must be a number"), nvpair_name(elem));
goto error;
}
/*
* Quota special: force 'none' and don't allow 0.
*/
if ((type & ZFS_TYPE_DATASET) && *ivalp == 0 && !isnone &&
(prop == ZFS_PROP_QUOTA || prop == ZFS_PROP_REFQUOTA)) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"use 'none' to disable quota/refquota"));
goto error;
}
/*
* Special handling for "*_limit=none". In this case it's not
* 0 but UINT64_MAX.
*/
if ((type & ZFS_TYPE_DATASET) && isnone &&
(prop == ZFS_PROP_FILESYSTEM_LIMIT ||
prop == ZFS_PROP_SNAPSHOT_LIMIT)) {
*ivalp = UINT64_MAX;
}
/*
* Special handling for setting 'refreservation' to 'auto'. Use
* UINT64_MAX to tell the caller to use zfs_fix_auto_resv().
* 'auto' is only allowed on volumes.
*/
if (isauto) {
switch (prop) {
case ZFS_PROP_REFRESERVATION:
if ((type & ZFS_TYPE_VOLUME) == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s=auto' only allowed on "
"volumes"), nvpair_name(elem));
goto error;
}
*ivalp = UINT64_MAX;
break;
default:
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'auto' is invalid value for '%s'"),
nvpair_name(elem));
goto error;
}
}
2008-11-20 20:01:55 +00:00
break;
case PROP_TYPE_INDEX:
if (datatype != DATA_TYPE_STRING) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' must be a string"), nvpair_name(elem));
goto error;
}
(void) nvpair_value_string(elem, &value);
if (zprop_string_to_index(prop, value, ivalp, type) != 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"'%s' must be one of '%s'"), propname,
zprop_values(prop, type));
goto error;
}
break;
default:
abort();
}
/*
* Add the result to our return set of properties.
*/
if (*svalp != NULL) {
if (nvlist_add_string(ret, propname, *svalp) != 0) {
(void) no_memory(hdl);
return (-1);
}
} else {
if (nvlist_add_uint64(ret, propname, *ivalp) != 0) {
(void) no_memory(hdl);
return (-1);
}
}
return (0);
error:
(void) zfs_error(hdl, EZFS_BADPROP, errbuf);
return (-1);
}
static int
addlist(libzfs_handle_t *hdl, char *propname, zprop_list_t **listp,
zfs_type_t type)
{
int prop;
zprop_list_t *entry;
prop = zprop_name_to_prop(propname, type);
if (prop != ZPROP_INVAL && !zprop_valid_for_type(prop, type, B_FALSE))
prop = ZPROP_INVAL;
/*
* When no property table entry can be found, return failure if
* this is a pool property or if this isn't a user-defined
* dataset property,
*/
if (prop == ZPROP_INVAL && ((type == ZFS_TYPE_POOL &&
!zpool_prop_feature(propname) &&
!zpool_prop_unsupported(propname)) ||
(type == ZFS_TYPE_DATASET && !zfs_prop_user(propname) &&
!zfs_prop_userquota(propname) && !zfs_prop_written(propname)))) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"invalid property '%s'"), propname);
return (zfs_error(hdl, EZFS_BADPROP,
dgettext(TEXT_DOMAIN, "bad property list")));
}
if ((entry = zfs_alloc(hdl, sizeof (zprop_list_t))) == NULL)
return (-1);
entry->pl_prop = prop;
if (prop == ZPROP_INVAL) {
if ((entry->pl_user_prop = zfs_strdup(hdl, propname)) ==
NULL) {
free(entry);
return (-1);
}
entry->pl_width = strlen(propname);
} else {
entry->pl_width = zprop_width(prop, &entry->pl_fixed,
type);
}
*listp = entry;
return (0);
}
2008-11-20 20:01:55 +00:00
/*
* Given a comma-separated list of properties, construct a property list
* containing both user-defined and native properties. This function will
* return a NULL list if 'all' is specified, which can later be expanded
* by zprop_expand_list().
*/
int
zprop_get_list(libzfs_handle_t *hdl, char *props, zprop_list_t **listp,
zfs_type_t type)
{
*listp = NULL;
/*
* If 'all' is specified, return a NULL list.
*/
if (strcmp(props, "all") == 0)
return (0);
/*
* If no props were specified, return an error.
*/
if (props[0] == '\0') {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"no properties specified"));
return (zfs_error(hdl, EZFS_BADPROP, dgettext(TEXT_DOMAIN,
"bad property list")));
}
/*
* It would be nice to use getsubopt() here, but the inclusion of column
* aliases makes this more effort than it's worth.
*/
while (*props != '\0') {
size_t len;
char *p;
char c;
if ((p = strchr(props, ',')) == NULL) {
len = strlen(props);
p = props + len;
2008-11-20 20:01:55 +00:00
} else {
len = p - props;
2008-11-20 20:01:55 +00:00
}
/*
* Check for empty options.
*/
if (len == 0) {
zfs_error_aux(hdl, dgettext(TEXT_DOMAIN,
"empty property name"));
return (zfs_error(hdl, EZFS_BADPROP,
dgettext(TEXT_DOMAIN, "bad property list")));
}
/*
* Check all regular property names.
*/
c = props[len];
props[len] = '\0';
if (strcmp(props, "space") == 0) {
static char *spaceprops[] = {
"name", "avail", "used", "usedbysnapshots",
"usedbydataset", "usedbyrefreservation",
"usedbychildren", NULL
};
int i;
for (i = 0; spaceprops[i]; i++) {
if (addlist(hdl, spaceprops[i], listp, type))
return (-1);
listp = &(*listp)->pl_next;
2008-11-20 20:01:55 +00:00
}
} else {
if (addlist(hdl, props, listp, type))
return (-1);
listp = &(*listp)->pl_next;
2008-11-20 20:01:55 +00:00
}
props = p;
2008-11-20 20:01:55 +00:00
if (c == ',')
props++;
2008-11-20 20:01:55 +00:00
}
return (0);
}
void
zprop_free_list(zprop_list_t *pl)
{
zprop_list_t *next;
while (pl != NULL) {
next = pl->pl_next;
free(pl->pl_user_prop);
free(pl);
pl = next;
}
}
typedef struct expand_data {
zprop_list_t **last;
libzfs_handle_t *hdl;
zfs_type_t type;
} expand_data_t;
static int
2008-11-20 20:01:55 +00:00
zprop_expand_list_cb(int prop, void *cb)
{
zprop_list_t *entry;
expand_data_t *edp = cb;
if ((entry = zfs_alloc(edp->hdl, sizeof (zprop_list_t))) == NULL)
return (ZPROP_INVAL);
entry->pl_prop = prop;
entry->pl_width = zprop_width(prop, &entry->pl_fixed, edp->type);
entry->pl_all = B_TRUE;
*(edp->last) = entry;
edp->last = &entry->pl_next;
return (ZPROP_CONT);
}
int
zprop_expand_list(libzfs_handle_t *hdl, zprop_list_t **plp, zfs_type_t type)
{
zprop_list_t *entry;
zprop_list_t **last;
expand_data_t exp;
if (*plp == NULL) {
/*
* If this is the very first time we've been called for an 'all'
* specification, expand the list to include all native
* properties.
*/
last = plp;
exp.last = last;
exp.hdl = hdl;
exp.type = type;
if (zprop_iter_common(zprop_expand_list_cb, &exp, B_FALSE,
B_FALSE, type) == ZPROP_INVAL)
return (-1);
/*
* Add 'name' to the beginning of the list, which is handled
* specially.
*/
if ((entry = zfs_alloc(hdl, sizeof (zprop_list_t))) == NULL)
return (-1);
entry->pl_prop = (type == ZFS_TYPE_POOL) ? ZPOOL_PROP_NAME :
ZFS_PROP_NAME;
entry->pl_width = zprop_width(entry->pl_prop,
&entry->pl_fixed, type);
entry->pl_all = B_TRUE;
entry->pl_next = *plp;
*plp = entry;
}
return (0);
}
int
zprop_iter(zprop_func func, void *cb, boolean_t show_all, boolean_t ordered,
zfs_type_t type)
{
return (zprop_iter_common(func, cb, show_all, ordered, type));
}
/*
* Fill given version buffer with zfs userland version
*/
void
zfs_version_userland(char *version, int len)
{
(void) strlcpy(version, ZFS_META_ALIAS, len);
}
/*
* Prints both zfs userland and kernel versions
* Returns 0 on success, and -1 on error (with errno set)
*/
int
zfs_version_print(void)
{
char zver_userland[128];
char zver_kernel[128];
zfs_version_userland(zver_userland, sizeof (zver_userland));
(void) printf("%s\n", zver_userland);
if (zfs_version_kernel(zver_kernel, sizeof (zver_kernel)) == -1) {
fprintf(stderr, "zfs_version_kernel() failed: %s\n",
strerror(errno));
return (-1);
}
(void) printf("zfs-kmod-%s\n", zver_kernel);
return (0);
}
/*
* Return 1 if the user requested ANSI color output, and our terminal supports
* it. Return 0 for no color.
*/
static int
use_color(void)
{
static int use_color = -1;
char *term;
/*
* Optimization:
*
* For each zpool invocation, we do a single check to see if we should
* be using color or not, and cache that value for the lifetime of the
* the zpool command. That makes it cheap to call use_color() when
* we're printing with color. We assume that the settings are not going
* to change during the invocation of a zpool command (the user isn't
* going to change the ZFS_COLOR value while zpool is running, for
* example).
*/
if (use_color != -1) {
/*
* We've already figured out if we should be using color or
* not. Return the cached value.
*/
return (use_color);
}
term = getenv("TERM");
/*
* The user sets the ZFS_COLOR env var set to enable zpool ANSI color
* output. However if NO_COLOR is set (https://no-color.org/) then
* don't use it. Also, don't use color if terminal doesn't support
* it.
*/
if (libzfs_envvar_is_set("ZFS_COLOR") &&
!libzfs_envvar_is_set("NO_COLOR") &&
isatty(STDOUT_FILENO) && term && strcmp("dumb", term) != 0 &&
strcmp("unknown", term) != 0) {
/* Color supported */
use_color = 1;
} else {
use_color = 0;
}
return (use_color);
}
/*
* color_start() and color_end() are used for when you want to colorize a block
* of text. For example:
*
* color_start(ANSI_RED_FG)
* printf("hello");
* printf("world");
* color_end();
*/
void
color_start(char *color)
{
if (use_color())
printf("%s", color);
}
void
color_end(void)
{
if (use_color())
printf(ANSI_RESET);
}
/* printf() with a color. If color is NULL, then do a normal printf. */
int
printf_color(char *color, char *format, ...)
{
va_list aptr;
int rc;
if (color)
color_start(color);
va_start(aptr, format);
rc = vprintf(format, aptr);
va_end(aptr);
if (color)
color_end();
return (rc);
}