mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-12-26 19:19:32 +03:00
1b939560be
UNMAP/TRIM support is a frequently-requested feature to help prevent performance from degrading on SSDs and on various other SAN-like storage back-ends. By issuing UNMAP/TRIM commands for sectors which are no longer allocated the underlying device can often more efficiently manage itself. This TRIM implementation is modeled on the `zpool initialize` feature which writes a pattern to all unallocated space in the pool. The new `zpool trim` command uses the same vdev_xlate() code to calculate what sectors are unallocated, the same per- vdev TRIM thread model and locking, and the same basic CLI for a consistent user experience. The core difference is that instead of writing a pattern it will issue UNMAP/TRIM commands for those extents. The zio pipeline was updated to accommodate this by adding a new ZIO_TYPE_TRIM type and associated spa taskq. This new type makes is straight forward to add the platform specific TRIM/UNMAP calls to vdev_disk.c and vdev_file.c. These new ZIO_TYPE_TRIM zios are handled largely the same way as ZIO_TYPE_READs or ZIO_TYPE_WRITEs. This makes it possible to largely avoid changing the pipieline, one exception is that TRIM zio's may exceed the 16M block size limit since they contain no data. In addition to the manual `zpool trim` command, a background automatic TRIM was added and is controlled by the 'autotrim' property. It relies on the exact same infrastructure as the manual TRIM. However, instead of relying on the extents in a metaslab's ms_allocatable range tree, a ms_trim tree is kept per metaslab. When 'autotrim=on', ranges added back to the ms_allocatable tree are also added to the ms_free tree. The ms_free tree is then periodically consumed by an autotrim thread which systematically walks a top level vdev's metaslabs. Since the automatic TRIM will skip ranges it considers too small there is value in occasionally running a full `zpool trim`. This may occur when the freed blocks are small and not enough time was allowed to aggregate them. An automatic TRIM and a manual `zpool trim` may be run concurrently, in which case the automatic TRIM will yield to the manual TRIM. Reviewed-by: Jorgen Lundman <lundman@lundman.net> Reviewed-by: Tim Chase <tim@chase2k.com> Reviewed-by: Matt Ahrens <mahrens@delphix.com> Reviewed-by: George Wilson <george.wilson@delphix.com> Reviewed-by: Serapheim Dimitropoulos <serapheim@delphix.com> Contributions-by: Saso Kiselkov <saso.kiselkov@nexenta.com> Contributions-by: Tim Chase <tim@chase2k.com> Contributions-by: Chunwei Chen <tuxoko@gmail.com> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #8419 Closes #598
131 lines
4.7 KiB
C
131 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 (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
|
|
* Copyright (c) 2011, 2018 by Delphix. All rights reserved.
|
|
* Copyright (c) 2017, Intel Corporation.
|
|
*/
|
|
|
|
#ifndef _SYS_METASLAB_H
|
|
#define _SYS_METASLAB_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/space_map.h>
|
|
#include <sys/txg.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/avl.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
|
|
typedef struct metaslab_ops {
|
|
uint64_t (*msop_alloc)(metaslab_t *, uint64_t);
|
|
} metaslab_ops_t;
|
|
|
|
|
|
extern metaslab_ops_t *zfs_metaslab_ops;
|
|
|
|
int metaslab_init(metaslab_group_t *, uint64_t, uint64_t, uint64_t,
|
|
metaslab_t **);
|
|
void metaslab_fini(metaslab_t *);
|
|
|
|
int metaslab_load(metaslab_t *);
|
|
void metaslab_unload(metaslab_t *);
|
|
|
|
uint64_t metaslab_allocated_space(metaslab_t *);
|
|
|
|
void metaslab_sync(metaslab_t *, uint64_t);
|
|
void metaslab_sync_done(metaslab_t *, uint64_t);
|
|
void metaslab_sync_reassess(metaslab_group_t *);
|
|
uint64_t metaslab_block_maxsize(metaslab_t *);
|
|
|
|
/*
|
|
* metaslab alloc flags
|
|
*/
|
|
#define METASLAB_HINTBP_FAVOR 0x0
|
|
#define METASLAB_HINTBP_AVOID 0x1
|
|
#define METASLAB_GANG_HEADER 0x2
|
|
#define METASLAB_GANG_CHILD 0x4
|
|
#define METASLAB_ASYNC_ALLOC 0x8
|
|
#define METASLAB_DONT_THROTTLE 0x10
|
|
#define METASLAB_MUST_RESERVE 0x20
|
|
#define METASLAB_FASTWRITE 0x40
|
|
|
|
int metaslab_alloc(spa_t *, metaslab_class_t *, uint64_t,
|
|
blkptr_t *, int, uint64_t, blkptr_t *, int, zio_alloc_list_t *, zio_t *,
|
|
int);
|
|
int metaslab_alloc_dva(spa_t *, metaslab_class_t *, uint64_t,
|
|
dva_t *, int, dva_t *, uint64_t, int, zio_alloc_list_t *, int);
|
|
void metaslab_free(spa_t *, const blkptr_t *, uint64_t, boolean_t);
|
|
void metaslab_free_concrete(vdev_t *, uint64_t, uint64_t, boolean_t);
|
|
void metaslab_free_dva(spa_t *, const dva_t *, boolean_t);
|
|
void metaslab_free_impl_cb(uint64_t, vdev_t *, uint64_t, uint64_t, void *);
|
|
void metaslab_unalloc_dva(spa_t *, const dva_t *, uint64_t);
|
|
int metaslab_claim(spa_t *, const blkptr_t *, uint64_t);
|
|
int metaslab_claim_impl(vdev_t *, uint64_t, uint64_t, uint64_t);
|
|
void metaslab_check_free(spa_t *, const blkptr_t *);
|
|
void metaslab_fastwrite_mark(spa_t *, const blkptr_t *);
|
|
void metaslab_fastwrite_unmark(spa_t *, const blkptr_t *);
|
|
|
|
void metaslab_alloc_trace_init(void);
|
|
void metaslab_alloc_trace_fini(void);
|
|
void metaslab_trace_init(zio_alloc_list_t *);
|
|
void metaslab_trace_fini(zio_alloc_list_t *);
|
|
|
|
metaslab_class_t *metaslab_class_create(spa_t *, metaslab_ops_t *);
|
|
void metaslab_class_destroy(metaslab_class_t *);
|
|
int metaslab_class_validate(metaslab_class_t *);
|
|
void metaslab_class_histogram_verify(metaslab_class_t *);
|
|
uint64_t metaslab_class_fragmentation(metaslab_class_t *);
|
|
uint64_t metaslab_class_expandable_space(metaslab_class_t *);
|
|
boolean_t metaslab_class_throttle_reserve(metaslab_class_t *, int, int,
|
|
zio_t *, int);
|
|
void metaslab_class_throttle_unreserve(metaslab_class_t *, int, int, zio_t *);
|
|
|
|
uint64_t metaslab_class_get_alloc(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_space(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_dspace(metaslab_class_t *);
|
|
uint64_t metaslab_class_get_deferred(metaslab_class_t *);
|
|
|
|
metaslab_group_t *metaslab_group_create(metaslab_class_t *, vdev_t *, int);
|
|
void metaslab_group_destroy(metaslab_group_t *);
|
|
void metaslab_group_activate(metaslab_group_t *);
|
|
void metaslab_group_passivate(metaslab_group_t *);
|
|
boolean_t metaslab_group_initialized(metaslab_group_t *);
|
|
uint64_t metaslab_group_get_space(metaslab_group_t *);
|
|
void metaslab_group_histogram_verify(metaslab_group_t *);
|
|
uint64_t metaslab_group_fragmentation(metaslab_group_t *);
|
|
void metaslab_group_histogram_remove(metaslab_group_t *, metaslab_t *);
|
|
void metaslab_group_alloc_decrement(spa_t *, uint64_t, void *, int, int,
|
|
boolean_t);
|
|
void metaslab_group_alloc_verify(spa_t *, const blkptr_t *, void *, int);
|
|
void metaslab_recalculate_weight_and_sort(metaslab_t *);
|
|
void metaslab_disable(metaslab_t *);
|
|
void metaslab_enable(metaslab_t *, boolean_t);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_METASLAB_H */
|