[mirror_zfs.git] / include / sys / space_map.h

/*
 * 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 https://opensource.org/licenses/CDDL-1.0.
 * 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) 2012, 2019 by Delphix. All rights reserved.
 */

#ifndef _SYS_SPACE_MAP_H
#define	_SYS_SPACE_MAP_H

#include <sys/avl.h>
#include <sys/range_tree.h>
#include <sys/dmu.h>

#ifdef	__cplusplus
extern "C" {
#endif

/*
 * The size of the space map object has increased to include a histogram.
 * The SPACE_MAP_SIZE_V0 designates the original size and is used to
 * maintain backward compatibility.
 */
#define	SPACE_MAP_SIZE_V0	(3 * sizeof (uint64_t))
#define	SPACE_MAP_HISTOGRAM_SIZE	32

/*
 * The space_map_phys is the on-disk representation of the space map.
 * Consumers of space maps should never reference any of the members of this
 * structure directly. These members may only be updated in syncing context.
 *
 * Note the smp_object is no longer used but remains in the structure
 * for backward compatibility.
 */
typedef struct space_map_phys {
	/* object number: not needed but kept for backwards compatibility */
	uint64_t	smp_object;

	/* length of the object in bytes */
	uint64_t	smp_length;

	/* space allocated from the map */
	int64_t		smp_alloc;

	/* reserved */
	uint64_t	smp_pad[5];

	/*
	 * The smp_histogram maintains a histogram of free regions. Each
	 * bucket, smp_histogram[i], contains the number of free regions
	 * whose size is:
	 * 2^(i+sm_shift) <= size of free region in bytes < 2^(i+sm_shift+1)
	 *
	 * Note that, if log space map feature is enabled, histograms of
	 * space maps that belong to metaslabs will take into account any
	 * unflushed changes for their metaslabs, even though the actual
	 * space map doesn't have entries for these changes.
	 */
	uint64_t	smp_histogram[SPACE_MAP_HISTOGRAM_SIZE];
} space_map_phys_t;

/*
 * The space map object defines a region of space, its size, how much is
 * allocated, and the on-disk object that stores this information.
 * Consumers of space maps may only access the members of this structure.
 *
 * Note: the space_map may not be accessed concurrently; consumers
 * must provide external locking if required.
 */
typedef struct space_map {
	uint64_t	sm_start;	/* start of map */
	uint64_t	sm_size;	/* size of map */
	uint8_t		sm_shift;	/* unit shift */
	objset_t	*sm_os;		/* objset for this map */
	uint64_t	sm_object;	/* object id for this map */
	uint32_t	sm_blksz;	/* block size for space map */
	dmu_buf_t	*sm_dbuf;	/* space_map_phys_t dbuf */
	space_map_phys_t *sm_phys;	/* on-disk space map */
} space_map_t;

/*
 * debug entry
 *
 *     2     2        10                     50
 *  +-----+-----+------------+----------------------------------+
 *  | 1 0 | act |  syncpass  |        txg (lower bits)          |
 *  +-----+-----+------------+----------------------------------+
 *   63 62 61 60 59        50 49                                0
 *
 *
 * one-word entry
 *
 *    1               47                   1           15
 *  +-----------------------------------------------------------+
 *  | 0 |   offset (sm_shift units)    | type |       run       |
 *  +-----------------------------------------------------------+
 *   63  62                          16   15   14               0
 *
 *
 * two-word entry
 *
 *     2     2               36                      24
 *  +-----+-----+---------------------------+-------------------+
 *  | 1 1 | pad |            run            |       vdev        |
 *  +-----+-----+---------------------------+-------------------+
 *   63 62 61 60 59                       24 23                 0
 *
 *     1                            63
 *  +------+----------------------------------------------------+
 *  | type |                      offset                        |
 *  +------+----------------------------------------------------+
 *     63   62                                                  0
 *
 * Note that a two-word entry will not straddle a block boundary.
 * If necessary, the last word of a block will be padded with a
 * debug entry (with act = syncpass = txg = 0).
 */

typedef enum {
	SM_ALLOC,
	SM_FREE
} maptype_t;

typedef struct space_map_entry {
	maptype_t sme_type;
	uint32_t sme_vdev;	/* max is 2^24-1; SM_NO_VDEVID if not present */
	uint64_t sme_offset;	/* max is 2^63-1; units of sm_shift */
	uint64_t sme_run;	/* max is 2^36; units of sm_shift */

	/*
	 * The following fields are not part of the actual space map entry
	 * on-disk and they are populated with the values from the debug
	 * entry most recently visited starting from the beginning to the
	 * end of the space map.
	 */
	uint64_t sme_txg;
	uint64_t sme_sync_pass;
} space_map_entry_t;

#define	SM_NO_VDEVID	(1 << SPA_VDEVBITS)

/* one-word entry constants */
#define	SM_DEBUG_PREFIX	2
#define	SM_OFFSET_BITS	47
#define	SM_RUN_BITS	15

/* two-word entry constants */
#define	SM2_PREFIX	3
#define	SM2_OFFSET_BITS	63
#define	SM2_RUN_BITS	36

#define	SM_PREFIX_DECODE(x)	BF64_DECODE(x, 62, 2)
#define	SM_PREFIX_ENCODE(x)	BF64_ENCODE(x, 62, 2)

#define	SM_DEBUG_ACTION_DECODE(x)	BF64_DECODE(x, 60, 2)
#define	SM_DEBUG_ACTION_ENCODE(x)	BF64_ENCODE(x, 60, 2)
#define	SM_DEBUG_SYNCPASS_DECODE(x)	BF64_DECODE(x, 50, 10)
#define	SM_DEBUG_SYNCPASS_ENCODE(x)	BF64_ENCODE(x, 50, 10)
#define	SM_DEBUG_TXG_DECODE(x)		BF64_DECODE(x, 0, 50)
#define	SM_DEBUG_TXG_ENCODE(x)		BF64_ENCODE(x, 0, 50)

#define	SM_OFFSET_DECODE(x)	BF64_DECODE(x, 16, SM_OFFSET_BITS)
#define	SM_OFFSET_ENCODE(x)	BF64_ENCODE(x, 16, SM_OFFSET_BITS)
#define	SM_TYPE_DECODE(x)	BF64_DECODE(x, 15, 1)
#define	SM_TYPE_ENCODE(x)	BF64_ENCODE(x, 15, 1)
#define	SM_RUN_DECODE(x)	(BF64_DECODE(x, 0, SM_RUN_BITS) + 1)
#define	SM_RUN_ENCODE(x)	BF64_ENCODE((x) - 1, 0, SM_RUN_BITS)
#define	SM_RUN_MAX		SM_RUN_DECODE(~0ULL)
#define	SM_OFFSET_MAX		SM_OFFSET_DECODE(~0ULL)

#define	SM2_RUN_DECODE(x)	(BF64_DECODE(x, SPA_VDEVBITS, SM2_RUN_BITS) + 1)
#define	SM2_RUN_ENCODE(x)	BF64_ENCODE((x) - 1, SPA_VDEVBITS, SM2_RUN_BITS)
#define	SM2_VDEV_DECODE(x)	BF64_DECODE(x, 0, SPA_VDEVBITS)
#define	SM2_VDEV_ENCODE(x)	BF64_ENCODE(x, 0, SPA_VDEVBITS)
#define	SM2_TYPE_DECODE(x)	BF64_DECODE(x, SM2_OFFSET_BITS, 1)
#define	SM2_TYPE_ENCODE(x)	BF64_ENCODE(x, SM2_OFFSET_BITS, 1)
#define	SM2_OFFSET_DECODE(x)	BF64_DECODE(x, 0, SM2_OFFSET_BITS)
#define	SM2_OFFSET_ENCODE(x)	BF64_ENCODE(x, 0, SM2_OFFSET_BITS)
#define	SM2_RUN_MAX		SM2_RUN_DECODE(~0ULL)
#define	SM2_OFFSET_MAX		SM2_OFFSET_DECODE(~0ULL)

boolean_t sm_entry_is_debug(uint64_t e);
boolean_t sm_entry_is_single_word(uint64_t e);
boolean_t sm_entry_is_double_word(uint64_t e);

typedef int (*sm_cb_t)(space_map_entry_t *sme, void *arg);

int space_map_load(space_map_t *sm, range_tree_t *rt, maptype_t maptype);
int space_map_load_length(space_map_t *sm, range_tree_t *rt, maptype_t maptype,
    uint64_t length);
int space_map_iterate(space_map_t *sm, uint64_t length,
    sm_cb_t callback, void *arg);
int space_map_incremental_destroy(space_map_t *sm, sm_cb_t callback, void *arg,
    dmu_tx_t *tx);

boolean_t space_map_histogram_verify(space_map_t *sm, range_tree_t *rt);
void space_map_histogram_clear(space_map_t *sm);
void space_map_histogram_add(space_map_t *sm, range_tree_t *rt,
    dmu_tx_t *tx);

uint64_t space_map_object(space_map_t *sm);
int64_t space_map_allocated(space_map_t *sm);
uint64_t space_map_length(space_map_t *sm);
uint64_t space_map_entries(space_map_t *sm, range_tree_t *rt);
uint64_t space_map_nblocks(space_map_t *sm);

void space_map_write(space_map_t *sm, range_tree_t *rt, maptype_t maptype,
    uint64_t vdev_id, dmu_tx_t *tx);
uint64_t space_map_estimate_optimal_size(space_map_t *sm, range_tree_t *rt,
    uint64_t vdev_id);
void space_map_truncate(space_map_t *sm, int blocksize, dmu_tx_t *tx);
uint64_t space_map_alloc(objset_t *os, int blocksize, dmu_tx_t *tx);
void space_map_free(space_map_t *sm, dmu_tx_t *tx);
void space_map_free_obj(objset_t *os, uint64_t smobj, dmu_tx_t *tx);

int space_map_open(space_map_t **smp, objset_t *os, uint64_t object,
    uint64_t start, uint64_t size, uint8_t shift);
void space_map_close(space_map_t *sm);

#ifdef	__cplusplus
}
#endif

#endif	/* _SYS_SPACE_MAP_H */
Commit	Line	Data
34dc7c2f BB	1	/*
	2	* CDDL HEADER START
	3	*
	4	* The contents of this file are subject to the terms of the
	5	* Common Development and Distribution License (the "License").
	6	* You may not use this file except in compliance with the License.
	7	*
	8	* You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
1d3ba0bf	9	* or https://opensource.org/licenses/CDDL-1.0.
34dc7c2f BB	10	* See the License for the specific language governing permissions
	11	* and limitations under the License.
	12	*
	13	* When distributing Covered Code, include this CDDL HEADER in each
	14	* file and include the License file at usr/src/OPENSOLARIS.LICENSE.
	15	* If applicable, add the following below this CDDL HEADER, with the
	16	* fields enclosed by brackets "[]" replaced with your own identifying
	17	* information: Portions Copyright [yyyy] [name of copyright owner]
	18	*
	19	* CDDL HEADER END
	20	*/
	21	/*
9babb374	22	* Copyright 2009 Sun Microsystems, Inc. All rights reserved.
34dc7c2f BB	23	* Use is subject to license terms.
	24	*/
	25
55d85d5a	26	/*
93e28d66	27	* Copyright (c) 2012, 2019 by Delphix. All rights reserved.
55d85d5a GW	28	*/
55d85d5a GW	29
34dc7c2f BB	30	#ifndef _SYS_SPACE_MAP_H
	31	#define _SYS_SPACE_MAP_H
	32
34dc7c2f	33	#include <sys/avl.h>
93cf2076	34	#include <sys/range_tree.h>
34dc7c2f BB	35	#include <sys/dmu.h>
	36
	37	#ifdef __cplusplus
	38	extern "C" {
	39	#endif
	40
93cf2076 GW	41	/*
	42	* The size of the space map object has increased to include a histogram.
	43	* The SPACE_MAP_SIZE_V0 designates the original size and is used to
	44	* maintain backward compatibility.
	45	*/
	46	#define SPACE_MAP_SIZE_V0 (3 * sizeof (uint64_t))
f3a7f661	47	#define SPACE_MAP_HISTOGRAM_SIZE 32
93cf2076 GW	48
	49	/*
	50	* The space_map_phys is the on-disk representation of the space map.
	51	* Consumers of space maps should never reference any of the members of this
	52	* structure directly. These members may only be updated in syncing context.
	53	*
	54	* Note the smp_object is no longer used but remains in the structure
	55	* for backward compatibility.
	56	*/
	57	typedef struct space_map_phys {
425d3237 SD	58	/* object number: not needed but kept for backwards compatibility */
	59	uint64_t smp_object;
	60
	61	/* length of the object in bytes */
	62	uint64_t smp_length;
	63
	64	/* space allocated from the map */
	65	int64_t smp_alloc;
	66
	67	/* reserved */
	68	uint64_t smp_pad[5];
93cf2076 GW	69
	70	/*
	71	* The smp_histogram maintains a histogram of free regions. Each
	72	* bucket, smp_histogram[i], contains the number of free regions
	73	* whose size is:
	74	* 2^(i+sm_shift) <= size of free region in bytes < 2^(i+sm_shift+1)
93e28d66 SD	75	*
	76	* Note that, if log space map feature is enabled, histograms of
	77	* space maps that belong to metaslabs will take into account any
	78	* unflushed changes for their metaslabs, even though the actual
	79	* space map doesn't have entries for these changes.
93cf2076	80	*/
f3a7f661	81	uint64_t smp_histogram[SPACE_MAP_HISTOGRAM_SIZE];
93cf2076	82	} space_map_phys_t;
34dc7c2f	83
93cf2076 GW	84	/*
	85	* The space map object defines a region of space, its size, how much is
	86	* allocated, and the on-disk object that stores this information.
	87	* Consumers of space maps may only access the members of this structure.
a1d477c2 MA	88	*
	89	* Note: the space_map may not be accessed concurrently; consumers
	90	* must provide external locking if required.
93cf2076	91	*/
34dc7c2f	92	typedef struct space_map {
34dc7c2f BB	93	uint64_t sm_start; /* start of map */
	94	uint64_t sm_size; /* size of map */
	95	uint8_t sm_shift; /* unit shift */
93cf2076 GW	96	objset_t sm_os; / objset for this map */
	97	uint64_t sm_object; /* object id for this map */
	98	uint32_t sm_blksz; /* block size for space map */
	99	dmu_buf_t sm_dbuf; / space_map_phys_t dbuf */
	100	space_map_phys_t sm_phys; / on-disk space map */
34dc7c2f BB	101	} space_map_t;
34dc7c2f BB	102
34dc7c2f BB	103	/*
	104	* debug entry
	105	*
4d044c4c SD	106	* 2 2 10 50
	107	* +-----+-----+------------+----------------------------------+
	108	* \| 1 0 \| act \| syncpass \| txg (lower bits) \|
	109	* +-----+-----+------------+----------------------------------+
	110	* 63 62 61 60 59 50 49 0
34dc7c2f BB	111	*
34dc7c2f BB	112	*
4d044c4c	113	* one-word entry
34dc7c2f BB	114	*
34dc7c2f BB	115	* 1 47 1 15
4d044c4c	116	* +-----------------------------------------------------------+
34dc7c2f	117	* \| 0 \| offset (sm_shift units) \| type \| run \|
4d044c4c SD	118	* +-----------------------------------------------------------+
	119	* 63 62 16 15 14 0
	120	*
	121	*
	122	* two-word entry
	123	*
	124	* 2 2 36 24
	125	* +-----+-----+---------------------------+-------------------+
	126	* \| 1 1 \| pad \| run \| vdev \|
	127	* +-----+-----+---------------------------+-------------------+
	128	* 63 62 61 60 59 24 23 0
	129	*
	130	* 1 63
	131	* +------+----------------------------------------------------+
	132	* \| type \| offset \|
	133	* +------+----------------------------------------------------+
	134	* 63 62 0
	135	*
	136	* Note that a two-word entry will not straddle a block boundary.
	137	* If necessary, the last word of a block will be padded with a
	138	* debug entry (with act = syncpass = txg = 0).
34dc7c2f BB	139	*/
34dc7c2f BB	140
4d044c4c SD	141	typedef enum {
	142	SM_ALLOC,
	143	SM_FREE
	144	} maptype_t;
	145
	146	typedef struct space_map_entry {
	147	maptype_t sme_type;
	148	uint32_t sme_vdev; /* max is 2^24-1; SM_NO_VDEVID if not present */
	149	uint64_t sme_offset; /* max is 2^63-1; units of sm_shift */
	150	uint64_t sme_run; /* max is 2^36; units of sm_shift */
6774931d MA	151
	152	/*
	153	* The following fields are not part of the actual space map entry
	154	* on-disk and they are populated with the values from the debug
	155	* entry most recently visited starting from the beginning to the
	156	* end of the space map.
	157	*/
	158	uint64_t sme_txg;
	159	uint64_t sme_sync_pass;
4d044c4c SD	160	} space_map_entry_t;
	161
	162	#define SM_NO_VDEVID (1 << SPA_VDEVBITS)
34dc7c2f	163
4d044c4c SD	164	/* one-word entry constants */
	165	#define SM_DEBUG_PREFIX 2
	166	#define SM_OFFSET_BITS 47
	167	#define SM_RUN_BITS 15
34dc7c2f	168
4d044c4c SD	169	/* two-word entry constants */
	170	#define SM2_PREFIX 3
	171	#define SM2_OFFSET_BITS 63
	172	#define SM2_RUN_BITS 36
	173
	174	#define SM_PREFIX_DECODE(x) BF64_DECODE(x, 62, 2)
	175	#define SM_PREFIX_ENCODE(x) BF64_ENCODE(x, 62, 2)
	176
	177	#define SM_DEBUG_ACTION_DECODE(x) BF64_DECODE(x, 60, 2)
	178	#define SM_DEBUG_ACTION_ENCODE(x) BF64_ENCODE(x, 60, 2)
34dc7c2f BB	179	#define SM_DEBUG_SYNCPASS_DECODE(x) BF64_DECODE(x, 50, 10)
34dc7c2f BB	180	#define SM_DEBUG_SYNCPASS_ENCODE(x) BF64_ENCODE(x, 50, 10)
34dc7c2f BB	181	#define SM_DEBUG_TXG_DECODE(x) BF64_DECODE(x, 0, 50)
	182	#define SM_DEBUG_TXG_ENCODE(x) BF64_ENCODE(x, 0, 50)
	183
4d044c4c SD	184	#define SM_OFFSET_DECODE(x) BF64_DECODE(x, 16, SM_OFFSET_BITS)
	185	#define SM_OFFSET_ENCODE(x) BF64_ENCODE(x, 16, SM_OFFSET_BITS)
	186	#define SM_TYPE_DECODE(x) BF64_DECODE(x, 15, 1)
	187	#define SM_TYPE_ENCODE(x) BF64_ENCODE(x, 15, 1)
	188	#define SM_RUN_DECODE(x) (BF64_DECODE(x, 0, SM_RUN_BITS) + 1)
	189	#define SM_RUN_ENCODE(x) BF64_ENCODE((x) - 1, 0, SM_RUN_BITS)
	190	#define SM_RUN_MAX SM_RUN_DECODE(~0ULL)
	191	#define SM_OFFSET_MAX SM_OFFSET_DECODE(~0ULL)
	192
	193	#define SM2_RUN_DECODE(x) (BF64_DECODE(x, SPA_VDEVBITS, SM2_RUN_BITS) + 1)
	194	#define SM2_RUN_ENCODE(x) BF64_ENCODE((x) - 1, SPA_VDEVBITS, SM2_RUN_BITS)
	195	#define SM2_VDEV_DECODE(x) BF64_DECODE(x, 0, SPA_VDEVBITS)
	196	#define SM2_VDEV_ENCODE(x) BF64_ENCODE(x, 0, SPA_VDEVBITS)
	197	#define SM2_TYPE_DECODE(x) BF64_DECODE(x, SM2_OFFSET_BITS, 1)
	198	#define SM2_TYPE_ENCODE(x) BF64_ENCODE(x, SM2_OFFSET_BITS, 1)
	199	#define SM2_OFFSET_DECODE(x) BF64_DECODE(x, 0, SM2_OFFSET_BITS)
	200	#define SM2_OFFSET_ENCODE(x) BF64_ENCODE(x, 0, SM2_OFFSET_BITS)
	201	#define SM2_RUN_MAX SM2_RUN_DECODE(~0ULL)
	202	#define SM2_OFFSET_MAX SM2_OFFSET_DECODE(~0ULL)
	203
	204	boolean_t sm_entry_is_debug(uint64_t e);
	205	boolean_t sm_entry_is_single_word(uint64_t e);
	206	boolean_t sm_entry_is_double_word(uint64_t e);
	207
	208	typedef int (sm_cb_t)(space_map_entry_t sme, void *arg);
a1d477c2	209
93cf2076	210	int space_map_load(space_map_t sm, range_tree_t rt, maptype_t maptype);
425d3237 SD	211	int space_map_load_length(space_map_t sm, range_tree_t rt, maptype_t maptype,
	212	uint64_t length);
	213	int space_map_iterate(space_map_t *sm, uint64_t length,
	214	sm_cb_t callback, void *arg);
d2734cce SD	215	int space_map_incremental_destroy(space_map_t sm, sm_cb_t callback, void arg,
d2734cce SD	216	dmu_tx_t *tx);
93cf2076	217
928e8ad4	218	boolean_t space_map_histogram_verify(space_map_t sm, range_tree_t rt);
93cf2076 GW	219	void space_map_histogram_clear(space_map_t *sm);
	220	void space_map_histogram_add(space_map_t sm, range_tree_t rt,
	221	dmu_tx_t *tx);
	222
93cf2076	223	uint64_t space_map_object(space_map_t *sm);
425d3237	224	int64_t space_map_allocated(space_map_t *sm);
93cf2076	225	uint64_t space_map_length(space_map_t *sm);
93e28d66 SD	226	uint64_t space_map_entries(space_map_t sm, range_tree_t rt);
93e28d66 SD	227	uint64_t space_map_nblocks(space_map_t *sm);
93cf2076 GW	228
93cf2076 GW	229	void space_map_write(space_map_t sm, range_tree_t rt, maptype_t maptype,
4d044c4c SD	230	uint64_t vdev_id, dmu_tx_t *tx);
	231	uint64_t space_map_estimate_optimal_size(space_map_t sm, range_tree_t rt,
	232	uint64_t vdev_id);
d2734cce SD	233	void space_map_truncate(space_map_t sm, int blocksize, dmu_tx_t tx);
d2734cce SD	234	uint64_t space_map_alloc(objset_t os, int blocksize, dmu_tx_t tx);
93cf2076	235	void space_map_free(space_map_t sm, dmu_tx_t tx);
a1d477c2	236	void space_map_free_obj(objset_t os, uint64_t smobj, dmu_tx_t tx);
93cf2076 GW	237
93cf2076 GW	238	int space_map_open(space_map_t *smp, objset_t os, uint64_t object,
a1d477c2	239	uint64_t start, uint64_t size, uint8_t shift);
93cf2076 GW	240	void space_map_close(space_map_t *sm);
93cf2076 GW	241
34dc7c2f BB	242	#ifdef __cplusplus
	243	}
	244	#endif
	245
	246	#endif /* _SYS_SPACE_MAP_H */