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
155 lines
4.7 KiB
C
155 lines
4.7 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, 2017 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_TXG_H
|
|
#define _SYS_TXG_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/zfs_context.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define TXG_CONCURRENT_STATES 3 /* open, quiescing, syncing */
|
|
#define TXG_SIZE 4 /* next power of 2 */
|
|
#define TXG_MASK (TXG_SIZE - 1) /* mask for size */
|
|
#define TXG_INITIAL TXG_SIZE /* initial txg */
|
|
#define TXG_IDX (txg & TXG_MASK)
|
|
#define TXG_UNKNOWN 0
|
|
|
|
/* Number of txgs worth of frees we defer adding to in-core spacemaps */
|
|
#define TXG_DEFER_SIZE 2
|
|
|
|
typedef struct tx_cpu tx_cpu_t;
|
|
|
|
typedef struct txg_handle {
|
|
tx_cpu_t *th_cpu;
|
|
uint64_t th_txg;
|
|
} txg_handle_t;
|
|
|
|
typedef struct txg_node {
|
|
struct txg_node *tn_next[TXG_SIZE];
|
|
uint8_t tn_member[TXG_SIZE];
|
|
} txg_node_t;
|
|
|
|
typedef struct txg_list {
|
|
kmutex_t tl_lock;
|
|
size_t tl_offset;
|
|
spa_t *tl_spa;
|
|
txg_node_t *tl_head[TXG_SIZE];
|
|
} txg_list_t;
|
|
|
|
struct dsl_pool;
|
|
|
|
extern void txg_init(struct dsl_pool *dp, uint64_t txg);
|
|
extern void txg_fini(struct dsl_pool *dp);
|
|
extern void txg_sync_start(struct dsl_pool *dp);
|
|
extern void txg_sync_stop(struct dsl_pool *dp);
|
|
extern uint64_t txg_hold_open(struct dsl_pool *dp, txg_handle_t *txghp);
|
|
extern void txg_rele_to_quiesce(txg_handle_t *txghp);
|
|
extern void txg_rele_to_sync(txg_handle_t *txghp);
|
|
extern void txg_register_callbacks(txg_handle_t *txghp, list_t *tx_callbacks);
|
|
|
|
extern void txg_delay(struct dsl_pool *dp, uint64_t txg, hrtime_t delta,
|
|
hrtime_t resolution);
|
|
extern void txg_kick(struct dsl_pool *dp);
|
|
|
|
/*
|
|
* Wait until the given transaction group has finished syncing.
|
|
* Try to make this happen as soon as possible (eg. kick off any
|
|
* necessary syncs immediately). If txg==0, wait for the currently open
|
|
* txg to finish syncing.
|
|
*/
|
|
extern void txg_wait_synced(struct dsl_pool *dp, uint64_t txg);
|
|
|
|
/*
|
|
* Wait as above. Returns true if the thread was signaled while waiting.
|
|
*/
|
|
extern boolean_t txg_wait_synced_sig(struct dsl_pool *dp, uint64_t txg);
|
|
|
|
/*
|
|
* Wait until the given transaction group, or one after it, is
|
|
* the open transaction group. Try to make this happen as soon
|
|
* as possible (eg. kick off any necessary syncs immediately) when
|
|
* should_quiesce is set. If txg == 0, wait for the next open txg.
|
|
*/
|
|
extern void txg_wait_open(struct dsl_pool *dp, uint64_t txg,
|
|
boolean_t should_quiesce);
|
|
|
|
/*
|
|
* Returns TRUE if we are "backed up" waiting for the syncing
|
|
* transaction to complete; otherwise returns FALSE.
|
|
*/
|
|
extern boolean_t txg_stalled(struct dsl_pool *dp);
|
|
|
|
/* returns TRUE if someone is waiting for the next txg to sync */
|
|
extern boolean_t txg_sync_waiting(struct dsl_pool *dp);
|
|
|
|
extern void txg_verify(spa_t *spa, uint64_t txg);
|
|
|
|
/*
|
|
* Wait for pending commit callbacks of already-synced transactions to finish
|
|
* processing.
|
|
*/
|
|
extern void txg_wait_callbacks(struct dsl_pool *dp);
|
|
|
|
/*
|
|
* Per-txg object lists.
|
|
*/
|
|
|
|
#define TXG_CLEAN(txg) ((txg) - 1)
|
|
|
|
extern void txg_list_create(txg_list_t *tl, spa_t *spa, size_t offset);
|
|
extern void txg_list_destroy(txg_list_t *tl);
|
|
extern boolean_t txg_list_empty(txg_list_t *tl, uint64_t txg);
|
|
extern boolean_t txg_all_lists_empty(txg_list_t *tl);
|
|
extern boolean_t txg_list_add(txg_list_t *tl, void *p, uint64_t txg);
|
|
extern boolean_t txg_list_add_tail(txg_list_t *tl, void *p, uint64_t txg);
|
|
extern void *txg_list_remove(txg_list_t *tl, uint64_t txg);
|
|
extern void *txg_list_remove_this(txg_list_t *tl, void *p, uint64_t txg);
|
|
extern boolean_t txg_list_member(txg_list_t *tl, void *p, uint64_t txg);
|
|
extern void *txg_list_head(txg_list_t *tl, uint64_t txg);
|
|
extern void *txg_list_next(txg_list_t *tl, void *p, uint64_t txg);
|
|
|
|
/* Global tuning */
|
|
extern int zfs_txg_timeout;
|
|
|
|
|
|
#ifdef ZFS_DEBUG
|
|
#define TXG_VERIFY(spa, txg) txg_verify(spa, txg)
|
|
#else
|
|
#define TXG_VERIFY(spa, txg)
|
|
#endif
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_TXG_H */
|