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
168 lines
4.3 KiB
C
168 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 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.
|
|
*/
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/spa.h>
|
|
#include <sys/vdev_impl.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/fs/zfs.h>
|
|
|
|
/*
|
|
* Virtual device vector for the pool's root vdev.
|
|
*/
|
|
|
|
static uint64_t
|
|
vdev_root_core_tvds(vdev_t *vd)
|
|
{
|
|
uint64_t tvds = 0;
|
|
|
|
for (uint64_t c = 0; c < vd->vdev_children; c++) {
|
|
vdev_t *cvd = vd->vdev_child[c];
|
|
|
|
if (!cvd->vdev_ishole && !cvd->vdev_islog &&
|
|
cvd->vdev_ops != &vdev_indirect_ops) {
|
|
tvds++;
|
|
}
|
|
}
|
|
|
|
return (tvds);
|
|
}
|
|
|
|
/*
|
|
* We should be able to tolerate one failure with absolutely no damage
|
|
* to our metadata. Two failures will take out space maps, a bunch of
|
|
* indirect block trees, meta dnodes, dnodes, etc. Probably not a happy
|
|
* place to live. When we get smarter, we can liberalize this policy.
|
|
* e.g. If we haven't lost two consecutive top-level vdevs, then we are
|
|
* probably fine. Adding bean counters during alloc/free can make this
|
|
* future guesswork more accurate.
|
|
*/
|
|
static boolean_t
|
|
too_many_errors(vdev_t *vd, uint64_t numerrors)
|
|
{
|
|
uint64_t tvds;
|
|
|
|
if (numerrors == 0)
|
|
return (B_FALSE);
|
|
|
|
tvds = vdev_root_core_tvds(vd);
|
|
ASSERT3U(numerrors, <=, tvds);
|
|
|
|
if (numerrors == tvds)
|
|
return (B_TRUE);
|
|
|
|
return (numerrors > spa_missing_tvds_allowed(vd->vdev_spa));
|
|
}
|
|
|
|
static int
|
|
vdev_root_open(vdev_t *vd, uint64_t *asize, uint64_t *max_asize,
|
|
uint64_t *ashift, uint64_t *pshift)
|
|
{
|
|
spa_t *spa = vd->vdev_spa;
|
|
int lasterror = 0;
|
|
int numerrors = 0;
|
|
|
|
if (vd->vdev_children == 0) {
|
|
vd->vdev_stat.vs_aux = VDEV_AUX_BAD_LABEL;
|
|
return (SET_ERROR(EINVAL));
|
|
}
|
|
|
|
vdev_open_children(vd);
|
|
|
|
for (int c = 0; c < vd->vdev_children; c++) {
|
|
vdev_t *cvd = vd->vdev_child[c];
|
|
|
|
if (cvd->vdev_open_error && !cvd->vdev_islog &&
|
|
cvd->vdev_ops != &vdev_indirect_ops) {
|
|
lasterror = cvd->vdev_open_error;
|
|
numerrors++;
|
|
}
|
|
}
|
|
|
|
if (spa_load_state(spa) != SPA_LOAD_NONE)
|
|
spa_set_missing_tvds(spa, numerrors);
|
|
|
|
if (too_many_errors(vd, numerrors)) {
|
|
vd->vdev_stat.vs_aux = VDEV_AUX_NO_REPLICAS;
|
|
return (lasterror);
|
|
}
|
|
|
|
*asize = 0;
|
|
*max_asize = 0;
|
|
*ashift = 0;
|
|
*pshift = 0;
|
|
|
|
return (0);
|
|
}
|
|
|
|
static void
|
|
vdev_root_close(vdev_t *vd)
|
|
{
|
|
for (int c = 0; c < vd->vdev_children; c++)
|
|
vdev_close(vd->vdev_child[c]);
|
|
}
|
|
|
|
static void
|
|
vdev_root_state_change(vdev_t *vd, int faulted, int degraded)
|
|
{
|
|
if (too_many_errors(vd, faulted)) {
|
|
vdev_set_state(vd, B_FALSE, VDEV_STATE_CANT_OPEN,
|
|
VDEV_AUX_NO_REPLICAS);
|
|
} else if (degraded || faulted) {
|
|
vdev_set_state(vd, B_FALSE, VDEV_STATE_DEGRADED, VDEV_AUX_NONE);
|
|
} else {
|
|
vdev_set_state(vd, B_FALSE, VDEV_STATE_HEALTHY, VDEV_AUX_NONE);
|
|
}
|
|
}
|
|
|
|
vdev_ops_t vdev_root_ops = {
|
|
.vdev_op_init = NULL,
|
|
.vdev_op_fini = NULL,
|
|
.vdev_op_open = vdev_root_open,
|
|
.vdev_op_close = vdev_root_close,
|
|
.vdev_op_asize = vdev_default_asize,
|
|
.vdev_op_min_asize = vdev_default_min_asize,
|
|
.vdev_op_min_alloc = NULL,
|
|
.vdev_op_io_start = NULL, /* not applicable to the root */
|
|
.vdev_op_io_done = NULL, /* not applicable to the root */
|
|
.vdev_op_state_change = vdev_root_state_change,
|
|
.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_ROOT, /* name of this vdev type */
|
|
.vdev_op_leaf = B_FALSE /* not a leaf vdev */
|
|
};
|