mirror_zfs/include/sys/vdev_draid.h

111 lines
3.4 KiB
C
Raw Normal View History

Distributed Spare (dRAID) Feature 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
2020-11-14 00:51:51 +03:00
/*
* 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, Intel Corporation.
* Copyright (c) 2020 by Lawrence Livermore National Security, LLC.
*/
#ifndef _SYS_VDEV_DRAID_H
#define _SYS_VDEV_DRAID_H
#include <sys/types.h>
#include <sys/abd.h>
#include <sys/nvpair.h>
#include <sys/zio.h>
#include <sys/vdev_impl.h>
#include <sys/vdev_raidz_impl.h>
#include <sys/vdev.h>
#ifdef __cplusplus
extern "C" {
#endif
/*
* Constants required to generate and use dRAID permutations.
*/
#define VDEV_DRAID_SEED 0xd7a1d5eed
#define VDEV_DRAID_MAX_MAPS 254
#define VDEV_DRAID_ROWSHIFT SPA_MAXBLOCKSHIFT
#define VDEV_DRAID_ROWHEIGHT (1ULL << VDEV_DRAID_ROWSHIFT)
#define VDEV_DRAID_REFLOW_RESERVE (2 * VDEV_DRAID_ROWHEIGHT)
/*
* dRAID permutation map.
*/
typedef struct draid_map {
uint64_t dm_children; /* # of permuation columns */
uint64_t dm_nperms; /* # of permutation rows */
uint64_t dm_seed; /* dRAID map seed */
uint64_t dm_checksum; /* Checksum of generated map */
uint8_t *dm_perms; /* base permutation array */
} draid_map_t;
/*
* dRAID configuration.
*/
typedef struct vdev_draid_config {
/*
* Values read from the dRAID nvlist configuration.
*/
uint64_t vdc_ndata; /* # of data devices in group */
uint64_t vdc_nparity; /* # of parity devices in group */
uint64_t vdc_nspares; /* # of distributed spares */
uint64_t vdc_children; /* # of children */
uint64_t vdc_ngroups; /* # groups per slice */
/*
* Immutable derived constants.
*/
uint8_t *vdc_perms; /* permutation array */
uint64_t vdc_nperms; /* # of permutations */
uint64_t vdc_groupwidth; /* = data + parity */
uint64_t vdc_ndisks; /* = children - spares */
uint64_t vdc_groupsz; /* = groupwidth * DRAID_ROWSIZE */
uint64_t vdc_devslicesz; /* = (groupsz * groups) / ndisks */
} vdev_draid_config_t;
/*
* Functions for handling dRAID permutation maps.
*/
extern uint64_t vdev_draid_rand(uint64_t *);
extern int vdev_draid_lookup_map(uint64_t, const draid_map_t **);
extern int vdev_draid_generate_perms(const draid_map_t *, uint8_t **);
/*
* General dRAID support functions.
*/
extern boolean_t vdev_draid_readable(vdev_t *, uint64_t);
extern boolean_t vdev_draid_missing(vdev_t *, uint64_t, uint64_t, uint64_t);
extern uint64_t vdev_draid_asize_to_psize(vdev_t *, uint64_t);
extern void vdev_draid_map_alloc_empty(zio_t *, struct raidz_row *);
extern nvlist_t *vdev_draid_read_config_spare(vdev_t *);
/* Functions for dRAID distributed spares. */
extern vdev_t *vdev_draid_spare_get_child(vdev_t *, uint64_t);
extern vdev_t *vdev_draid_spare_get_parent(vdev_t *);
extern int vdev_draid_spare_create(nvlist_t *, vdev_t *, uint64_t *, uint64_t);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_VDEV_DRAID_H */