mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 03:09:34 +03:00
5caeef02fa
This feature allows disks to be added one at a time to a RAID-Z group, expanding its capacity incrementally. This feature is especially useful for small pools (typically with only one RAID-Z group), where there isn't sufficient hardware to add capacity by adding a whole new RAID-Z group (typically doubling the number of disks). == Initiating expansion == A new device (disk) can be attached to an existing RAIDZ vdev, by running `zpool attach POOL raidzP-N NEW_DEVICE`, e.g. `zpool attach tank raidz2-0 sda`. The new device will become part of the RAIDZ group. A "raidz expansion" will be initiated, and the new device will contribute additional space to the RAIDZ group once the expansion completes. The `feature@raidz_expansion` on-disk feature flag must be `enabled` to initiate an expansion, and it remains `active` for the life of the pool. In other words, pools with expanded RAIDZ vdevs can not be imported by older releases of the ZFS software. == During expansion == The expansion entails reading all allocated space from existing disks in the RAIDZ group, and rewriting it to the new disks in the RAIDZ group (including the newly added device). The expansion progress can be monitored with `zpool status`. Data redundancy is maintained during (and after) the expansion. If a disk fails while the expansion is in progress, the expansion pauses until the health of the RAIDZ vdev is restored (e.g. by replacing the failed disk and waiting for reconstruction to complete). The pool remains accessible during expansion. Following a reboot or export/import, the expansion resumes where it left off. == After expansion == When the expansion completes, the additional space is available for use, and is reflected in the `available` zfs property (as seen in `zfs list`, `df`, etc). Expansion does not change the number of failures that can be tolerated without data loss (e.g. a RAIDZ2 is still a RAIDZ2 even after expansion). A RAIDZ vdev can be expanded multiple times. After the expansion completes, old blocks remain with their old data-to-parity ratio (e.g. 5-wide RAIDZ2, has 3 data to 2 parity), but distributed among the larger set of disks. New blocks will be written with the new data-to-parity ratio (e.g. a 5-wide RAIDZ2 which has been expanded once to 6-wide, has 4 data to 2 parity). However, the RAIDZ vdev's "assumed parity ratio" does not change, so slightly less space than is expected may be reported for newly-written blocks, according to `zfs list`, `df`, `ls -s`, and similar tools. Sponsored-by: The FreeBSD Foundation Sponsored-by: iXsystems, Inc. Sponsored-by: vStack Reviewed-by: Brian Behlendorf <behlendorf1@llnl.gov> Reviewed-by: Mark Maybee <mark.maybee@delphix.com> Authored-by: Matthew Ahrens <mahrens@delphix.com> Contributions-by: Fedor Uporov <fuporov.vstack@gmail.com> Contributions-by: Stuart Maybee <stuart.maybee@comcast.net> Contributions-by: Thorsten Behrens <tbehrens@outlook.com> Contributions-by: Fmstrat <nospam@nowsci.com> Contributions-by: Don Brady <dev.fs.zfs@gmail.com> Signed-off-by: Don Brady <dev.fs.zfs@gmail.com> Closes #15022
143 lines
4.3 KiB
C
143 lines
4.3 KiB
C
/*
|
|
* 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 https://opensource.org/licenses/CDDL-1.0.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2011, 2018 by Delphix. All rights reserved.
|
|
* Copyright (c) 2013 by Saso Kiselkov. All rights reserved.
|
|
* Copyright (c) 2013, Joyent, Inc. All rights reserved.
|
|
* Copyright (c) 2017, Intel Corporation.
|
|
*/
|
|
|
|
#ifndef _ZFEATURE_COMMON_H
|
|
#define _ZFEATURE_COMMON_H extern __attribute__((visibility("default")))
|
|
|
|
#include <sys/fs/zfs.h>
|
|
#include <sys/inttypes.h>
|
|
#include <sys/types.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
struct zfeature_info;
|
|
|
|
typedef enum spa_feature {
|
|
SPA_FEATURE_NONE = -1,
|
|
SPA_FEATURE_ASYNC_DESTROY,
|
|
SPA_FEATURE_EMPTY_BPOBJ,
|
|
SPA_FEATURE_LZ4_COMPRESS,
|
|
SPA_FEATURE_MULTI_VDEV_CRASH_DUMP,
|
|
SPA_FEATURE_SPACEMAP_HISTOGRAM,
|
|
SPA_FEATURE_ENABLED_TXG,
|
|
SPA_FEATURE_HOLE_BIRTH,
|
|
SPA_FEATURE_EXTENSIBLE_DATASET,
|
|
SPA_FEATURE_EMBEDDED_DATA,
|
|
SPA_FEATURE_BOOKMARKS,
|
|
SPA_FEATURE_FS_SS_LIMIT,
|
|
SPA_FEATURE_LARGE_BLOCKS,
|
|
SPA_FEATURE_LARGE_DNODE,
|
|
SPA_FEATURE_SHA512,
|
|
SPA_FEATURE_SKEIN,
|
|
SPA_FEATURE_EDONR,
|
|
SPA_FEATURE_USEROBJ_ACCOUNTING,
|
|
SPA_FEATURE_ENCRYPTION,
|
|
SPA_FEATURE_PROJECT_QUOTA,
|
|
SPA_FEATURE_DEVICE_REMOVAL,
|
|
SPA_FEATURE_OBSOLETE_COUNTS,
|
|
SPA_FEATURE_POOL_CHECKPOINT,
|
|
SPA_FEATURE_SPACEMAP_V2,
|
|
SPA_FEATURE_ALLOCATION_CLASSES,
|
|
SPA_FEATURE_RESILVER_DEFER,
|
|
SPA_FEATURE_BOOKMARK_V2,
|
|
SPA_FEATURE_REDACTION_BOOKMARKS,
|
|
SPA_FEATURE_REDACTED_DATASETS,
|
|
SPA_FEATURE_BOOKMARK_WRITTEN,
|
|
SPA_FEATURE_LOG_SPACEMAP,
|
|
SPA_FEATURE_LIVELIST,
|
|
SPA_FEATURE_DEVICE_REBUILD,
|
|
SPA_FEATURE_ZSTD_COMPRESS,
|
|
SPA_FEATURE_DRAID,
|
|
SPA_FEATURE_ZILSAXATTR,
|
|
SPA_FEATURE_HEAD_ERRLOG,
|
|
SPA_FEATURE_BLAKE3,
|
|
SPA_FEATURE_BLOCK_CLONING,
|
|
SPA_FEATURE_AVZ_V2,
|
|
SPA_FEATURE_REDACTION_LIST_SPILL,
|
|
SPA_FEATURE_RAIDZ_EXPANSION,
|
|
SPA_FEATURES
|
|
} spa_feature_t;
|
|
|
|
#define SPA_FEATURE_DISABLED (-1ULL)
|
|
|
|
typedef enum zfeature_flags {
|
|
/* Can open pool readonly even if this feature is not supported. */
|
|
ZFEATURE_FLAG_READONLY_COMPAT = (1 << 0),
|
|
/*
|
|
* Is this feature necessary to load the pool? i.e. do we need this
|
|
* feature to read the full feature list out of the MOS?
|
|
*/
|
|
ZFEATURE_FLAG_MOS = (1 << 1),
|
|
/* Activate this feature at the same time it is enabled. */
|
|
ZFEATURE_FLAG_ACTIVATE_ON_ENABLE = (1 << 2),
|
|
/* Each dataset has a field set if it has ever used this feature. */
|
|
ZFEATURE_FLAG_PER_DATASET = (1 << 3)
|
|
} zfeature_flags_t;
|
|
|
|
typedef enum zfeature_type {
|
|
ZFEATURE_TYPE_BOOLEAN,
|
|
ZFEATURE_TYPE_UINT64_ARRAY,
|
|
ZFEATURE_NUM_TYPES
|
|
} zfeature_type_t;
|
|
|
|
typedef struct zfeature_info {
|
|
spa_feature_t fi_feature;
|
|
const char *fi_uname; /* User-facing feature name */
|
|
const char *fi_guid; /* On-disk feature identifier */
|
|
const char *fi_desc; /* Feature description */
|
|
zfeature_flags_t fi_flags;
|
|
boolean_t fi_zfs_mod_supported; /* supported by running zfs module */
|
|
zfeature_type_t fi_type; /* Only relevant for PER_DATASET features */
|
|
/* array of dependencies, terminated by SPA_FEATURE_NONE */
|
|
const spa_feature_t *fi_depends;
|
|
} zfeature_info_t;
|
|
|
|
typedef int (zfeature_func_t)(zfeature_info_t *, void *);
|
|
|
|
#define ZFS_FEATURE_DEBUG
|
|
|
|
_ZFEATURE_COMMON_H zfeature_info_t spa_feature_table[SPA_FEATURES];
|
|
_ZFEATURE_COMMON_H boolean_t zfeature_checks_disable;
|
|
|
|
_ZFEATURE_COMMON_H boolean_t zfeature_is_valid_guid(const char *);
|
|
|
|
_ZFEATURE_COMMON_H boolean_t zfeature_is_supported(const char *);
|
|
_ZFEATURE_COMMON_H int zfeature_lookup_guid(const char *, spa_feature_t *);
|
|
_ZFEATURE_COMMON_H int zfeature_lookup_name(const char *, spa_feature_t *);
|
|
_ZFEATURE_COMMON_H boolean_t zfeature_depends_on(spa_feature_t, spa_feature_t);
|
|
|
|
_ZFEATURE_COMMON_H void zpool_feature_init(void);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _ZFEATURE_COMMON_H */
|