zfs/include/sys/vdev.h

168 lines
5.8 KiB
C
Raw Normal View History

2008-11-20 20:01:55 +00:00
/*
* 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
*/
2008-11-20 20:01:55 +00:00
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2013 by Delphix. All rights reserved.
2008-11-20 20:01:55 +00:00
*/
#ifndef _SYS_VDEV_H
#define _SYS_VDEV_H
#include <sys/spa.h>
#include <sys/zio.h>
#include <sys/dmu.h>
#include <sys/space_map.h>
#include <sys/fs/zfs.h>
#ifdef __cplusplus
extern "C" {
#endif
2009-01-15 21:59:39 +00:00
typedef enum vdev_dtl_type {
DTL_MISSING, /* 0% replication: no copies of the data */
DTL_PARTIAL, /* less than 100% replication: some copies missing */
DTL_SCRUB, /* unable to fully repair during scrub/resilver */
DTL_OUTAGE, /* temporarily missing (used to attempt detach) */
DTL_TYPES
} vdev_dtl_type_t;
Add missing ZFS tunables This commit adds module options for all existing zfs tunables. Ideally the average user should never need to modify any of these values. However, in practice sometimes you do need to tweak these values for one reason or another. In those cases it's nice not to have to resort to rebuilding from source. All tunables are visable to modinfo and the list is as follows: $ modinfo module/zfs/zfs.ko filename: module/zfs/zfs.ko license: CDDL author: Sun Microsystems/Oracle, Lawrence Livermore National Laboratory description: ZFS srcversion: 8EAB1D71DACE05B5AA61567 depends: spl,znvpair,zcommon,zunicode,zavl vermagic: 2.6.32-131.0.5.el6.x86_64 SMP mod_unload modversions parm: zvol_major:Major number for zvol device (uint) parm: zvol_threads:Number of threads for zvol device (uint) parm: zio_injection_enabled:Enable fault injection (int) parm: zio_bulk_flags:Additional flags to pass to bulk buffers (int) parm: zio_delay_max:Max zio millisec delay before posting event (int) parm: zio_requeue_io_start_cut_in_line:Prioritize requeued I/O (bool) parm: zil_replay_disable:Disable intent logging replay (int) parm: zfs_nocacheflush:Disable cache flushes (bool) parm: zfs_read_chunk_size:Bytes to read per chunk (long) parm: zfs_vdev_max_pending:Max pending per-vdev I/Os (int) parm: zfs_vdev_min_pending:Min pending per-vdev I/Os (int) parm: zfs_vdev_aggregation_limit:Max vdev I/O aggregation size (int) parm: zfs_vdev_time_shift:Deadline time shift for vdev I/O (int) parm: zfs_vdev_ramp_rate:Exponential I/O issue ramp-up rate (int) parm: zfs_vdev_read_gap_limit:Aggregate read I/O over gap (int) parm: zfs_vdev_write_gap_limit:Aggregate write I/O over gap (int) parm: zfs_vdev_scheduler:I/O scheduler (charp) parm: zfs_vdev_cache_max:Inflate reads small than max (int) parm: zfs_vdev_cache_size:Total size of the per-disk cache (int) parm: zfs_vdev_cache_bshift:Shift size to inflate reads too (int) parm: zfs_scrub_limit:Max scrub/resilver I/O per leaf vdev (int) parm: zfs_recover:Set to attempt to recover from fatal errors (int) parm: spa_config_path:SPA config file (/etc/zfs/zpool.cache) (charp) parm: zfs_zevent_len_max:Max event queue length (int) parm: zfs_zevent_cols:Max event column width (int) parm: zfs_zevent_console:Log events to the console (int) parm: zfs_top_maxinflight:Max I/Os per top-level (int) parm: zfs_resilver_delay:Number of ticks to delay resilver (int) parm: zfs_scrub_delay:Number of ticks to delay scrub (int) parm: zfs_scan_idle:Idle window in clock ticks (int) parm: zfs_scan_min_time_ms:Min millisecs to scrub per txg (int) parm: zfs_free_min_time_ms:Min millisecs to free per txg (int) parm: zfs_resilver_min_time_ms:Min millisecs to resilver per txg (int) parm: zfs_no_scrub_io:Set to disable scrub I/O (bool) parm: zfs_no_scrub_prefetch:Set to disable scrub prefetching (bool) parm: zfs_txg_timeout:Max seconds worth of delta per txg (int) parm: zfs_no_write_throttle:Disable write throttling (int) parm: zfs_write_limit_shift:log2(fraction of memory) per txg (int) parm: zfs_txg_synctime_ms:Target milliseconds between tgx sync (int) parm: zfs_write_limit_min:Min tgx write limit (ulong) parm: zfs_write_limit_max:Max tgx write limit (ulong) parm: zfs_write_limit_inflated:Inflated tgx write limit (ulong) parm: zfs_write_limit_override:Override tgx write limit (ulong) parm: zfs_prefetch_disable:Disable all ZFS prefetching (int) parm: zfetch_max_streams:Max number of streams per zfetch (uint) parm: zfetch_min_sec_reap:Min time before stream reclaim (uint) parm: zfetch_block_cap:Max number of blocks to fetch at a time (uint) parm: zfetch_array_rd_sz:Number of bytes in a array_read (ulong) parm: zfs_pd_blks_max:Max number of blocks to prefetch (int) parm: zfs_dedup_prefetch:Enable prefetching dedup-ed blks (int) parm: zfs_arc_min:Min arc size (ulong) parm: zfs_arc_max:Max arc size (ulong) parm: zfs_arc_meta_limit:Meta limit for arc size (ulong) parm: zfs_arc_reduce_dnlc_percent:Meta reclaim percentage (int) parm: zfs_arc_grow_retry:Seconds before growing arc size (int) parm: zfs_arc_shrink_shift:log2(fraction of arc to reclaim) (int) parm: zfs_arc_p_min_shift:arc_c shift to calc min/max arc_p (int)
2011-05-03 22:09:28 +00:00
extern int zfs_nocacheflush;
2008-11-20 20:01:55 +00:00
extern int vdev_open(vdev_t *);
extern void vdev_open_children(vdev_t *);
extern int vdev_validate(vdev_t *, boolean_t);
2008-11-20 20:01:55 +00:00
extern void vdev_close(vdev_t *);
extern int vdev_create(vdev_t *, uint64_t txg, boolean_t isreplace);
extern void vdev_reopen(vdev_t *);
extern int vdev_validate_aux(vdev_t *vd);
extern zio_t *vdev_probe(vdev_t *vd, zio_t *pio);
2008-11-20 20:01:55 +00:00
extern boolean_t vdev_is_bootable(vdev_t *vd);
2008-11-20 20:01:55 +00:00
extern vdev_t *vdev_lookup_top(spa_t *spa, uint64_t vdev);
extern vdev_t *vdev_lookup_by_guid(vdev_t *vd, uint64_t guid);
extern int vdev_count_leaves(spa_t *spa);
2009-01-15 21:59:39 +00:00
extern void vdev_dtl_dirty(vdev_t *vd, vdev_dtl_type_t d,
uint64_t txg, uint64_t size);
extern boolean_t vdev_dtl_contains(vdev_t *vd, vdev_dtl_type_t d,
uint64_t txg, uint64_t size);
extern boolean_t vdev_dtl_empty(vdev_t *vd, vdev_dtl_type_t d);
2008-11-20 20:01:55 +00:00
extern void vdev_dtl_reassess(vdev_t *vd, uint64_t txg, uint64_t scrub_txg,
int scrub_done);
2009-01-15 21:59:39 +00:00
extern boolean_t vdev_dtl_required(vdev_t *vd);
extern boolean_t vdev_resilver_needed(vdev_t *vd,
uint64_t *minp, uint64_t *maxp);
2008-11-20 20:01:55 +00:00
extern void vdev_hold(vdev_t *);
extern void vdev_rele(vdev_t *);
2008-11-20 20:01:55 +00:00
extern int vdev_metaslab_init(vdev_t *vd, uint64_t txg);
extern void vdev_metaslab_fini(vdev_t *vd);
2009-07-02 22:44:48 +00:00
extern void vdev_metaslab_set_size(vdev_t *);
extern void vdev_expand(vdev_t *vd, uint64_t txg);
extern void vdev_split(vdev_t *vd);
extern void vdev_deadman(vdev_t *vd);
2008-11-20 20:01:55 +00:00
extern void vdev_get_stats(vdev_t *vd, vdev_stat_t *vs);
extern void vdev_clear_stats(vdev_t *vd);
extern void vdev_stat_update(zio_t *zio, uint64_t psize);
extern void vdev_scan_stat_init(vdev_t *vd);
2008-11-20 20:01:55 +00:00
extern void vdev_propagate_state(vdev_t *vd);
extern void vdev_set_state(vdev_t *vd, boolean_t isopen, vdev_state_t state,
vdev_aux_t aux);
extern void vdev_space_update(vdev_t *vd,
int64_t alloc_delta, int64_t defer_delta, int64_t space_delta);
2008-11-20 20:01:55 +00:00
extern uint64_t vdev_psize_to_asize(vdev_t *vd, uint64_t psize);
extern int vdev_fault(spa_t *spa, uint64_t guid, vdev_aux_t aux);
extern int vdev_degrade(spa_t *spa, uint64_t guid, vdev_aux_t aux);
2008-11-20 20:01:55 +00:00
extern int vdev_online(spa_t *spa, uint64_t guid, uint64_t flags,
vdev_state_t *);
extern int vdev_offline(spa_t *spa, uint64_t guid, uint64_t flags);
extern void vdev_clear(spa_t *spa, vdev_t *vd);
2008-11-20 20:01:55 +00:00
extern boolean_t vdev_is_dead(vdev_t *vd);
extern boolean_t vdev_readable(vdev_t *vd);
extern boolean_t vdev_writeable(vdev_t *vd);
extern boolean_t vdev_allocatable(vdev_t *vd);
extern boolean_t vdev_accessible(vdev_t *vd, zio_t *zio);
2008-11-20 20:01:55 +00:00
extern void vdev_cache_init(vdev_t *vd);
extern void vdev_cache_fini(vdev_t *vd);
extern boolean_t vdev_cache_read(zio_t *zio);
2008-11-20 20:01:55 +00:00
extern void vdev_cache_write(zio_t *zio);
extern void vdev_cache_purge(vdev_t *vd);
extern void vdev_queue_init(vdev_t *vd);
extern void vdev_queue_fini(vdev_t *vd);
extern zio_t *vdev_queue_io(zio_t *zio);
extern void vdev_queue_io_done(zio_t *zio);
FreeBSD r256956: Improve ZFS N-way mirror read performance by using load and locality information. The existing algorithm selects a preferred leaf vdev based on offset of the zio request modulo the number of members in the mirror. It assumes the devices are of equal performance and that spreading the requests randomly over both drives will be sufficient to saturate them. In practice this results in the leaf vdevs being under utilized. The new algorithm takes into the following additional factors: * Load of the vdevs (number outstanding I/O requests) * The locality of last queued I/O vs the new I/O request. Within the locality calculation additional knowledge about the underlying vdev is considered such as; is the device backing the vdev a rotating media device. This results in performance increases across the board as well as significant increases for predominantly streaming loads and for configurations which don't have evenly performing devices. The following are results from a setup with 3 Way Mirror with 2 x HD's and 1 x SSD from a basic test running multiple parrallel dd's. With pre-fetch disabled (vfs.zfs.prefetch_disable=1): == Stripe Balanced (default) == Read 15360MB using bs: 1048576, readers: 3, took 161 seconds @ 95 MB/s == Load Balanced (zfslinux) == Read 15360MB using bs: 1048576, readers: 3, took 297 seconds @ 51 MB/s == Load Balanced (locality freebsd) == Read 15360MB using bs: 1048576, readers: 3, took 54 seconds @ 284 MB/s With pre-fetch enabled (vfs.zfs.prefetch_disable=0): == Stripe Balanced (default) == Read 15360MB using bs: 1048576, readers: 3, took 91 seconds @ 168 MB/s == Load Balanced (zfslinux) == Read 15360MB using bs: 1048576, readers: 3, took 108 seconds @ 142 MB/s == Load Balanced (locality freebsd) == Read 15360MB using bs: 1048576, readers: 3, took 48 seconds @ 320 MB/s In addition to the performance changes the code was also restructured, with the help of Justin Gibbs, to provide a more logical flow which also ensures vdevs loads are only calculated from the set of valid candidates. The following additional sysctls where added to allow the administrator to tune the behaviour of the load algorithm: * vfs.zfs.vdev.mirror.rotating_inc * vfs.zfs.vdev.mirror.rotating_seek_inc * vfs.zfs.vdev.mirror.rotating_seek_offset * vfs.zfs.vdev.mirror.non_rotating_inc * vfs.zfs.vdev.mirror.non_rotating_seek_inc These changes where based on work started by the zfsonlinux developers: https://github.com/zfsonlinux/zfs/pull/1487 Reviewed by: gibbs, mav, will MFC after: 2 weeks Sponsored by: Multiplay References: https://github.com/freebsd/freebsd@5c7a6f5d https://github.com/freebsd/freebsd@31b7f68d https://github.com/freebsd/freebsd@e186f564 Performance Testing: https://github.com/zfsonlinux/zfs/pull/4334#issuecomment-189057141 Porting notes: - The tunables were adjusted to have ZoL-style names. - The code was modified to use ZoL's vd_nonrot. - Fixes were done to make cstyle.pl happy - Merge conflicts were handled manually - freebsd/freebsd@e186f564bc946f82c76e0b34c2f0370ed9aea022 by my collegue Andriy Gapon has been included. It applied perfectly, but added a cstyle regression. - This replaces 556011dbec2d10579819078559a77630fc559112 entirely. - A typo "IO'a" has been corrected to say "IO's" - Descriptions of new tunables were added to man/man5/zfs-module-parameters.5. Ported-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #4334
2016-02-13 01:47:22 +00:00
extern int vdev_queue_length(vdev_t *vd);
extern uint64_t vdev_queue_lastoffset(vdev_t *vd);
extern void vdev_queue_register_lastoffset(vdev_t *vd, zio_t *zio);
2008-11-20 20:01:55 +00:00
extern void vdev_config_dirty(vdev_t *vd);
extern void vdev_config_clean(vdev_t *vd);
extern int vdev_config_sync(vdev_t **svd, int svdcount, uint64_t txg);
2008-11-20 20:01:55 +00:00
extern void vdev_state_dirty(vdev_t *vd);
extern void vdev_state_clean(vdev_t *vd);
typedef enum vdev_config_flag {
VDEV_CONFIG_SPARE = 1 << 0,
VDEV_CONFIG_L2CACHE = 1 << 1,
VDEV_CONFIG_REMOVING = 1 << 2
} vdev_config_flag_t;
extern void vdev_top_config_generate(spa_t *spa, nvlist_t *config);
2008-11-20 20:01:55 +00:00
extern nvlist_t *vdev_config_generate(spa_t *spa, vdev_t *vd,
boolean_t getstats, vdev_config_flag_t flags);
2008-11-20 20:01:55 +00:00
/*
* Label routines
*/
struct uberblock;
extern uint64_t vdev_label_offset(uint64_t psize, int l, uint64_t offset);
extern int vdev_label_number(uint64_t psise, uint64_t offset);
extern nvlist_t *vdev_label_read_config(vdev_t *vd, uint64_t txg);
extern void vdev_uberblock_load(vdev_t *, struct uberblock *, nvlist_t **);
2008-11-20 20:01:55 +00:00
typedef enum {
VDEV_LABEL_CREATE, /* create/add a new device */
VDEV_LABEL_REPLACE, /* replace an existing device */
VDEV_LABEL_SPARE, /* add a new hot spare */
VDEV_LABEL_REMOVE, /* remove an existing device */
VDEV_LABEL_L2CACHE, /* add an L2ARC cache device */
VDEV_LABEL_SPLIT /* generating new label for split-off dev */
2008-11-20 20:01:55 +00:00
} vdev_labeltype_t;
extern int vdev_label_init(vdev_t *vd, uint64_t txg, vdev_labeltype_t reason);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_VDEV_H */