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
102 lines
3.4 KiB
C
102 lines
3.4 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) 2018, Intel Corporation.
|
|
* Copyright (c) 2020 by Lawrence Livermore National Security, LLC.
|
|
*/
|
|
|
|
#ifndef _SYS_VDEV_REBUILD_H
|
|
#define _SYS_VDEV_REBUILD_H
|
|
|
|
#include <sys/spa.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
/*
|
|
* Number of entries in the physical vdev_rebuild_phys structure. This
|
|
* state is stored per top-level as VDEV_ZAP_TOP_VDEV_REBUILD_PHYS.
|
|
*/
|
|
#define REBUILD_PHYS_ENTRIES 12
|
|
|
|
/*
|
|
* On-disk rebuild configuration and state. When adding new fields they
|
|
* must be added to the end of the structure.
|
|
*/
|
|
typedef struct vdev_rebuild_phys {
|
|
uint64_t vrp_rebuild_state; /* vdev_rebuild_state_t */
|
|
uint64_t vrp_last_offset; /* last rebuilt offset */
|
|
uint64_t vrp_min_txg; /* minimum missing txg */
|
|
uint64_t vrp_max_txg; /* maximum missing txg */
|
|
uint64_t vrp_start_time; /* start time */
|
|
uint64_t vrp_end_time; /* end time */
|
|
uint64_t vrp_scan_time_ms; /* total run time in ms */
|
|
uint64_t vrp_bytes_scanned; /* alloc bytes scanned */
|
|
uint64_t vrp_bytes_issued; /* read bytes rebuilt */
|
|
uint64_t vrp_bytes_rebuilt; /* rebuilt bytes */
|
|
uint64_t vrp_bytes_est; /* total bytes to scan */
|
|
uint64_t vrp_errors; /* errors during rebuild */
|
|
} vdev_rebuild_phys_t;
|
|
|
|
/*
|
|
* The vdev_rebuild_t describes the current state and how a top-level vdev
|
|
* should be rebuilt. The core elements are the top-vdev, the metaslab being
|
|
* rebuilt, range tree containing the allocted extents and the on-disk state.
|
|
*/
|
|
typedef struct vdev_rebuild {
|
|
vdev_t *vr_top_vdev; /* top-level vdev to rebuild */
|
|
metaslab_t *vr_scan_msp; /* scanning disabled metaslab */
|
|
range_tree_t *vr_scan_tree; /* scan ranges (in metaslab) */
|
|
kmutex_t vr_io_lock; /* inflight IO lock */
|
|
kcondvar_t vr_io_cv; /* inflight IO cv */
|
|
|
|
/* In-core state and progress */
|
|
uint64_t vr_scan_offset[TXG_SIZE];
|
|
uint64_t vr_prev_scan_time_ms; /* any previous scan time */
|
|
uint64_t vr_bytes_inflight_max; /* maximum bytes inflight */
|
|
uint64_t vr_bytes_inflight; /* current bytes inflight */
|
|
|
|
/* Per-rebuild pass statistics for calculating bandwidth */
|
|
uint64_t vr_pass_start_time;
|
|
uint64_t vr_pass_bytes_scanned;
|
|
uint64_t vr_pass_bytes_issued;
|
|
|
|
/* On-disk state updated by vdev_rebuild_zap_update_sync() */
|
|
vdev_rebuild_phys_t vr_rebuild_phys;
|
|
} vdev_rebuild_t;
|
|
|
|
boolean_t vdev_rebuild_active(vdev_t *);
|
|
|
|
int vdev_rebuild_load(vdev_t *);
|
|
void vdev_rebuild(vdev_t *);
|
|
void vdev_rebuild_stop_wait(vdev_t *);
|
|
void vdev_rebuild_stop_all(spa_t *);
|
|
void vdev_rebuild_restart(spa_t *);
|
|
void vdev_rebuild_clear_sync(void *, dmu_tx_t *);
|
|
int vdev_rebuild_get_stats(vdev_t *, vdev_rebuild_stat_t *);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_VDEV_REBUILD_H */
|