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
97 lines
3.1 KiB
C
97 lines
3.1 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 2009 Sun Microsystems, Inc. All rights reserved.
|
|
* Use is subject to license terms.
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2013 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_RANGE_TREE_H
|
|
#define _SYS_RANGE_TREE_H
|
|
|
|
#include <sys/avl.h>
|
|
#include <sys/dmu.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
#define RANGE_TREE_HISTOGRAM_SIZE 64
|
|
|
|
typedef struct range_tree_ops range_tree_ops_t;
|
|
|
|
typedef struct range_tree {
|
|
avl_tree_t rt_root; /* offset-ordered segment AVL tree */
|
|
uint64_t rt_space; /* sum of all segments in the map */
|
|
range_tree_ops_t *rt_ops;
|
|
void *rt_arg;
|
|
|
|
/*
|
|
* The rt_histogram maintains a histogram of ranges. Each bucket,
|
|
* rt_histogram[i], contains the number of ranges whose size is:
|
|
* 2^i <= size of range in bytes < 2^(i+1)
|
|
*/
|
|
uint64_t rt_histogram[RANGE_TREE_HISTOGRAM_SIZE];
|
|
kmutex_t *rt_lock; /* pointer to lock that protects map */
|
|
} range_tree_t;
|
|
|
|
typedef struct range_seg {
|
|
avl_node_t rs_node; /* AVL node */
|
|
avl_node_t rs_pp_node; /* AVL picker-private node */
|
|
uint64_t rs_start; /* starting offset of this segment */
|
|
uint64_t rs_end; /* ending offset (non-inclusive) */
|
|
} range_seg_t;
|
|
|
|
struct range_tree_ops {
|
|
void (*rtop_create)(range_tree_t *rt, void *arg);
|
|
void (*rtop_destroy)(range_tree_t *rt, void *arg);
|
|
void (*rtop_add)(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void (*rtop_remove)(range_tree_t *rt, range_seg_t *rs, void *arg);
|
|
void (*rtop_vacate)(range_tree_t *rt, void *arg);
|
|
};
|
|
|
|
typedef void range_tree_func_t(void *arg, uint64_t start, uint64_t size);
|
|
|
|
void range_tree_init(void);
|
|
void range_tree_fini(void);
|
|
range_tree_t *range_tree_create(range_tree_ops_t *ops, void *arg, kmutex_t *lp);
|
|
void range_tree_destroy(range_tree_t *rt);
|
|
boolean_t range_tree_contains(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
uint64_t range_tree_space(range_tree_t *rt);
|
|
void range_tree_verify(range_tree_t *rt, uint64_t start, uint64_t size);
|
|
void range_tree_swap(range_tree_t **rtsrc, range_tree_t **rtdst);
|
|
void range_tree_stat_verify(range_tree_t *rt);
|
|
|
|
void range_tree_add(void *arg, uint64_t start, uint64_t size);
|
|
void range_tree_remove(void *arg, uint64_t start, uint64_t size);
|
|
|
|
void range_tree_vacate(range_tree_t *rt, range_tree_func_t *func, void *arg);
|
|
void range_tree_walk(range_tree_t *rt, range_tree_func_t *func, void *arg);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_RANGE_TREE_H */
|