mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-17 10:01:01 +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
123 lines
2.5 KiB
C
123 lines
2.5 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) 2016 Gvozden Nešković. All rights reserved.
|
|
*/
|
|
|
|
#ifndef RAIDZ_TEST_H
|
|
#define RAIDZ_TEST_H
|
|
|
|
#include <sys/spa.h>
|
|
|
|
static const char *const raidz_impl_names[] = {
|
|
"original",
|
|
"scalar",
|
|
"sse2",
|
|
"ssse3",
|
|
"avx2",
|
|
"avx512f",
|
|
"avx512bw",
|
|
"aarch64_neon",
|
|
"aarch64_neonx2",
|
|
"powerpc_altivec",
|
|
NULL
|
|
};
|
|
|
|
enum raidz_verbosity {
|
|
D_ALL,
|
|
D_INFO,
|
|
D_DEBUG,
|
|
};
|
|
|
|
typedef struct raidz_test_opts {
|
|
size_t rto_ashift;
|
|
uint64_t rto_offset;
|
|
size_t rto_dcols;
|
|
size_t rto_dsize;
|
|
enum raidz_verbosity rto_v;
|
|
size_t rto_sweep;
|
|
size_t rto_sweep_timeout;
|
|
size_t rto_benchmark;
|
|
size_t rto_expand;
|
|
uint64_t rto_expand_offset;
|
|
size_t rto_sanity;
|
|
size_t rto_gdb;
|
|
|
|
/* non-user options */
|
|
boolean_t rto_should_stop;
|
|
|
|
zio_t *zio_golden;
|
|
raidz_map_t *rm_golden;
|
|
} raidz_test_opts_t;
|
|
|
|
static const raidz_test_opts_t rto_opts_defaults = {
|
|
.rto_ashift = 9,
|
|
.rto_offset = 1ULL << 0,
|
|
.rto_dcols = 8,
|
|
.rto_dsize = 1<<19,
|
|
.rto_v = D_ALL,
|
|
.rto_sweep = 0,
|
|
.rto_benchmark = 0,
|
|
.rto_expand = 0,
|
|
.rto_expand_offset = -1ULL,
|
|
.rto_sanity = 0,
|
|
.rto_gdb = 0,
|
|
.rto_should_stop = B_FALSE
|
|
};
|
|
|
|
extern raidz_test_opts_t rto_opts;
|
|
|
|
static inline size_t ilog2(size_t a)
|
|
{
|
|
return (a > 1 ? 1 + ilog2(a >> 1) : 0);
|
|
}
|
|
|
|
|
|
#define LOG(lvl, ...) \
|
|
{ \
|
|
if (rto_opts.rto_v >= lvl) \
|
|
(void) fprintf(stdout, __VA_ARGS__); \
|
|
} \
|
|
|
|
#define LOG_OPT(lvl, opt, ...) \
|
|
{ \
|
|
if (opt->rto_v >= lvl) \
|
|
(void) fprintf(stdout, __VA_ARGS__); \
|
|
} \
|
|
|
|
#define ERR(...) (void) fprintf(stderr, __VA_ARGS__)
|
|
|
|
|
|
#define DBLSEP "================\n"
|
|
#define SEP "----------------\n"
|
|
|
|
|
|
#define raidz_alloc(size) abd_alloc(size, B_FALSE)
|
|
#define raidz_free(p, size) abd_free(p)
|
|
|
|
|
|
void init_zio_abd(zio_t *zio);
|
|
|
|
void run_raidz_benchmark(void);
|
|
|
|
#endif /* RAIDZ_TEST_H */
|