mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-27 11:29:36 +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
132 lines
3.7 KiB
C
132 lines
3.7 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 2010 Sun Microsystems, Inc. All rights reserved.
|
|
* Use is subject to license terms.
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2012, 2016 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
/*
|
|
* The 'missing' vdev is a special vdev type used only during import. It
|
|
* signifies a placeholder in the root vdev for some vdev that we know is
|
|
* missing. We pass it down to the kernel to allow the rest of the
|
|
* configuration to parsed and an attempt made to open all available devices.
|
|
* Because its GUID is always 0, we know that the guid sum will mismatch and we
|
|
* won't be able to open the pool anyway.
|
|
*/
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/vdev_impl.h>
|
|
#include <sys/fs/zfs.h>
|
|
#include <sys/zio.h>
|
|
|
|
/* ARGSUSED */
|
|
static int
|
|
vdev_missing_open(vdev_t *vd, uint64_t *psize, uint64_t *max_psize,
|
|
uint64_t *ashift, uint64_t *pshift)
|
|
{
|
|
/*
|
|
* Really this should just fail. But then the root vdev will be in the
|
|
* faulted state with VDEV_AUX_NO_REPLICAS, when what we really want is
|
|
* VDEV_AUX_BAD_GUID_SUM. So we pretend to succeed, knowing that we
|
|
* will fail the GUID sum check before ever trying to open the pool.
|
|
*/
|
|
*psize = 0;
|
|
*max_psize = 0;
|
|
*ashift = 0;
|
|
*pshift = 0;
|
|
return (0);
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_close(vdev_t *vd)
|
|
{
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_io_start(zio_t *zio)
|
|
{
|
|
zio->io_error = SET_ERROR(ENOTSUP);
|
|
zio_execute(zio);
|
|
}
|
|
|
|
/* ARGSUSED */
|
|
static void
|
|
vdev_missing_io_done(zio_t *zio)
|
|
{
|
|
}
|
|
|
|
vdev_ops_t vdev_missing_ops = {
|
|
.vdev_op_init = NULL,
|
|
.vdev_op_fini = NULL,
|
|
.vdev_op_open = vdev_missing_open,
|
|
.vdev_op_close = vdev_missing_close,
|
|
.vdev_op_asize = vdev_default_asize,
|
|
.vdev_op_min_asize = vdev_default_min_asize,
|
|
.vdev_op_min_alloc = NULL,
|
|
.vdev_op_io_start = vdev_missing_io_start,
|
|
.vdev_op_io_done = vdev_missing_io_done,
|
|
.vdev_op_state_change = NULL,
|
|
.vdev_op_need_resilver = NULL,
|
|
.vdev_op_hold = NULL,
|
|
.vdev_op_rele = NULL,
|
|
.vdev_op_remap = NULL,
|
|
.vdev_op_xlate = NULL,
|
|
.vdev_op_rebuild_asize = NULL,
|
|
.vdev_op_metaslab_init = NULL,
|
|
.vdev_op_config_generate = NULL,
|
|
.vdev_op_nparity = NULL,
|
|
.vdev_op_ndisks = NULL,
|
|
.vdev_op_type = VDEV_TYPE_MISSING, /* name of this vdev type */
|
|
.vdev_op_leaf = B_TRUE /* leaf vdev */
|
|
};
|
|
|
|
vdev_ops_t vdev_hole_ops = {
|
|
.vdev_op_init = NULL,
|
|
.vdev_op_fini = NULL,
|
|
.vdev_op_open = vdev_missing_open,
|
|
.vdev_op_close = vdev_missing_close,
|
|
.vdev_op_asize = vdev_default_asize,
|
|
.vdev_op_min_asize = vdev_default_min_asize,
|
|
.vdev_op_min_alloc = NULL,
|
|
.vdev_op_io_start = vdev_missing_io_start,
|
|
.vdev_op_io_done = vdev_missing_io_done,
|
|
.vdev_op_state_change = NULL,
|
|
.vdev_op_need_resilver = NULL,
|
|
.vdev_op_hold = NULL,
|
|
.vdev_op_rele = NULL,
|
|
.vdev_op_remap = NULL,
|
|
.vdev_op_xlate = NULL,
|
|
.vdev_op_rebuild_asize = NULL,
|
|
.vdev_op_metaslab_init = NULL,
|
|
.vdev_op_config_generate = NULL,
|
|
.vdev_op_nparity = NULL,
|
|
.vdev_op_ndisks = NULL,
|
|
.vdev_op_type = VDEV_TYPE_HOLE, /* name of this vdev type */
|
|
.vdev_op_leaf = B_TRUE /* leaf vdev */
|
|
};
|