mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2025-10-26 18:05:04 +03:00
93cf20764a
4101 metaslab_debug should allow for fine-grained control
4102 space_maps should store more information about themselves
4103 space map object blocksize should be increased
4105 removing a mirrored log device results in a leaked object
4106 asynchronously load metaslab
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: Adam Leventhal <ahl@delphix.com>
Reviewed by: Sebastien Roy <seb@delphix.com>
Approved by: Garrett D'Amore <garrett@damore.org>
Prior to this patch, space_maps were preferred solely based on the
amount of free space left in each. Unfortunately, this heuristic didn't
contain any information about the make-up of that free space, which
meant we could keep preferring and loading a highly fragmented space map
that wouldn't actually have enough contiguous space to satisfy the
allocation; then unloading that space_map and repeating the process.
This change modifies the space_map's to store additional information
about the contiguous space in the space_map, so that we can use this
information to make a better decision about which space_map to load.
This requires reallocating all space_map objects to increase their
bonus buffer size sizes enough to fit the new metadata.
The above feature can be enabled via a new feature flag introduced by
this change: com.delphix:spacemap_histogram
In addition to the above, this patch allows the space_map block size to
be increase. Currently the block size is set to be 4K in size, which has
certain implications including the following:
* 4K sector devices will not see any compression benefit
* large space_maps require more metadata on-disk
* large space_maps require more time to load (typically random reads)
Now the space_map block size can adjust as needed up to the maximum size
set via the space_map_max_blksz variable.
A bug was fixed which resulted in potentially leaking an object when
removing a mirrored log device. The previous logic for vdev_remove() did
not deal with removing top-level vdevs that are interior vdevs (i.e.
mirror) correctly. The problem would occur when removing a mirrored log
device, and result in the DTL space map object being leaked; because
top-level vdevs don't have DTL space map objects associated with them.
References:
https://www.illumos.org/issues/4101
https://www.illumos.org/issues/4102
https://www.illumos.org/issues/4103
https://www.illumos.org/issues/4105
https://www.illumos.org/issues/4106
https://github.com/illumos/illumos-gate/commit/0713e23
Porting notes:
A handful of kmem_alloc() calls were converted to kmem_zalloc(). Also,
the KM_PUSHPAGE and TQ_PUSHPAGE flags were used as necessary.
Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Prakash Surya <surya1@llnl.gov>
Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov>
Closes #2488
96 lines
3.3 KiB
C
96 lines
3.3 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) 2013 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#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 *msp, uint64_t size);
|
|
boolean_t (*msop_fragmented)(metaslab_t *msp);
|
|
} metaslab_ops_t;
|
|
|
|
extern metaslab_ops_t *zfs_metaslab_ops;
|
|
|
|
metaslab_t *metaslab_init(metaslab_group_t *mg, uint64_t id,
|
|
uint64_t object, uint64_t txg);
|
|
void metaslab_fini(metaslab_t *msp);
|
|
|
|
void metaslab_load_wait(metaslab_t *msp);
|
|
int metaslab_load(metaslab_t *msp);
|
|
void metaslab_unload(metaslab_t *msp);
|
|
|
|
void metaslab_sync(metaslab_t *msp, uint64_t txg);
|
|
void metaslab_sync_done(metaslab_t *msp, uint64_t txg);
|
|
void metaslab_sync_reassess(metaslab_group_t *mg);
|
|
uint64_t metaslab_block_maxsize(metaslab_t *msp);
|
|
|
|
#define METASLAB_HINTBP_FAVOR 0x0
|
|
#define METASLAB_HINTBP_AVOID 0x1
|
|
#define METASLAB_GANG_HEADER 0x2
|
|
#define METASLAB_GANG_CHILD 0x4
|
|
#define METASLAB_GANG_AVOID 0x8
|
|
#define METASLAB_FASTWRITE 0x10
|
|
|
|
int metaslab_alloc(spa_t *spa, metaslab_class_t *mc, uint64_t psize,
|
|
blkptr_t *bp, int ncopies, uint64_t txg, blkptr_t *hintbp, int flags);
|
|
void metaslab_free(spa_t *spa, const blkptr_t *bp, uint64_t txg, boolean_t now);
|
|
int metaslab_claim(spa_t *spa, const blkptr_t *bp, uint64_t txg);
|
|
void metaslab_check_free(spa_t *spa, const blkptr_t *bp);
|
|
void metaslab_fastwrite_mark(spa_t *spa, const blkptr_t *bp);
|
|
void metaslab_fastwrite_unmark(spa_t *spa, const blkptr_t *bp);
|
|
|
|
metaslab_class_t *metaslab_class_create(spa_t *spa, metaslab_ops_t *ops);
|
|
void metaslab_class_destroy(metaslab_class_t *mc);
|
|
int metaslab_class_validate(metaslab_class_t *mc);
|
|
|
|
void metaslab_class_space_update(metaslab_class_t *mc,
|
|
int64_t alloc_delta, int64_t defer_delta,
|
|
int64_t space_delta, int64_t dspace_delta);
|
|
uint64_t metaslab_class_get_alloc(metaslab_class_t *mc);
|
|
uint64_t metaslab_class_get_space(metaslab_class_t *mc);
|
|
uint64_t metaslab_class_get_dspace(metaslab_class_t *mc);
|
|
uint64_t metaslab_class_get_deferred(metaslab_class_t *mc);
|
|
|
|
metaslab_group_t *metaslab_group_create(metaslab_class_t *mc, vdev_t *vd);
|
|
void metaslab_group_destroy(metaslab_group_t *mg);
|
|
void metaslab_group_activate(metaslab_group_t *mg);
|
|
void metaslab_group_passivate(metaslab_group_t *mg);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_METASLAB_H */
|