mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 19:19:32 +03:00
b2255edcc0
This patch adds a new top-level vdev type called dRAID, which stands
for Distributed parity RAID. This pool configuration allows all dRAID
vdevs to participate when rebuilding to a distributed hot spare device.
This can substantially reduce the total time required to restore full
parity to pool with a failed device.
A dRAID pool can be created using the new top-level `draid` type.
Like `raidz`, the desired redundancy is specified after the type:
`draid[1,2,3]`. No additional information is required to create the
pool and reasonable default values will be chosen based on the number
of child vdevs in the dRAID vdev.
zpool create <pool> draid[1,2,3] <vdevs...>
Unlike raidz, additional optional dRAID configuration values can be
provided as part of the draid type as colon separated values. This
allows administrators to fully specify a layout for either performance
or capacity reasons. The supported options include:
zpool create <pool> \
draid[<parity>][:<data>d][:<children>c][:<spares>s] \
<vdevs...>
- draid[parity] - Parity level (default 1)
- draid[:<data>d] - Data devices per group (default 8)
- draid[:<children>c] - Expected number of child vdevs
- draid[:<spares>s] - Distributed hot spares (default 0)
Abbreviated example `zpool status` output for a 68 disk dRAID pool
with two distributed spares using special allocation classes.
```
pool: tank
state: ONLINE
config:
NAME STATE READ WRITE CKSUM
slag7 ONLINE 0 0 0
draid2:8d:68c:2s-0 ONLINE 0 0 0
L0 ONLINE 0 0 0
L1 ONLINE 0 0 0
...
U25 ONLINE 0 0 0
U26 ONLINE 0 0 0
spare-53 ONLINE 0 0 0
U27 ONLINE 0 0 0
draid2-0-0 ONLINE 0 0 0
U28 ONLINE 0 0 0
U29 ONLINE 0 0 0
...
U42 ONLINE 0 0 0
U43 ONLINE 0 0 0
special
mirror-1 ONLINE 0 0 0
L5 ONLINE 0 0 0
U5 ONLINE 0 0 0
mirror-2 ONLINE 0 0 0
L6 ONLINE 0 0 0
U6 ONLINE 0 0 0
spares
draid2-0-0 INUSE currently in use
draid2-0-1 AVAIL
```
When adding test coverage for the new dRAID vdev type the following
options were added to the ztest command. These options are leverages
by zloop.sh to test a wide range of dRAID configurations.
-K draid|raidz|random - kind of RAID to test
-D <value> - dRAID data drives per group
-S <value> - dRAID distributed hot spares
-R <value> - RAID parity (raidz or dRAID)
The zpool_create, zpool_import, redundancy, replacement and fault
test groups have all been updated provide test coverage for the
dRAID feature.
Co-authored-by: Isaac Huang <he.huang@intel.com>
Co-authored-by: Mark Maybee <mmaybee@cray.com>
Co-authored-by: Don Brady <don.brady@delphix.com>
Co-authored-by: Matthew Ahrens <mahrens@delphix.com>
Co-authored-by: Brian Behlendorf <behlendorf1@llnl.gov>
Reviewed-by: Mark Maybee <mmaybee@cray.com>
Reviewed-by: Matt Ahrens <matt@delphix.com>
Reviewed-by: Tony Hutter <hutter2@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #10102
124 lines
2.6 KiB
C
124 lines
2.6 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 http://www.opensolaris.org/os/licensing.
|
|
* See the License for the specific language governing permissions
|
|
* and limitations under the License.
|
|
*
|
|
* When distributing Covered Code, include this CDDL HEADER in each
|
|
* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
|
|
* If applicable, add the following below this CDDL HEADER, with the
|
|
* fields enclosed by brackets "[]" replaced with your own identifying
|
|
* information: Portions Copyright [yyyy] [name of copyright owner]
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
/*
|
|
* Copyright (C) 2016 Gvozden Nešković. All rights reserved.
|
|
*/
|
|
|
|
#ifndef RAIDZ_TEST_H
|
|
#define RAIDZ_TEST_H
|
|
|
|
#include <sys/spa.h>
|
|
|
|
static const char *raidz_impl_names[] = {
|
|
"original",
|
|
"scalar",
|
|
"sse2",
|
|
"ssse3",
|
|
"avx2",
|
|
"avx512f",
|
|
"avx512bw",
|
|
"aarch64_neon",
|
|
"aarch64_neonx2",
|
|
"powerpc_altivec",
|
|
NULL
|
|
};
|
|
|
|
typedef struct raidz_test_opts {
|
|
size_t rto_ashift;
|
|
uint64_t rto_offset;
|
|
size_t rto_dcols;
|
|
size_t rto_dsize;
|
|
size_t 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 = 0,
|
|
.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 D_ALL 0
|
|
#define D_INFO 1
|
|
#define D_DEBUG 2
|
|
|
|
#define LOG(lvl, a...) \
|
|
{ \
|
|
if (rto_opts.rto_v >= lvl) \
|
|
(void) fprintf(stdout, a); \
|
|
} \
|
|
|
|
#define LOG_OPT(lvl, opt, a...) \
|
|
{ \
|
|
if (opt->rto_v >= lvl) \
|
|
(void) fprintf(stdout, a); \
|
|
} \
|
|
|
|
#define ERR(a...) (void) fprintf(stderr, a)
|
|
|
|
|
|
#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);
|
|
|
|
struct raidz_map *vdev_raidz_map_alloc_expanded(abd_t *, uint64_t, uint64_t,
|
|
uint64_t, uint64_t, uint64_t, uint64_t, uint64_t);
|
|
|
|
#endif /* RAIDZ_TEST_H */
|