mirror_zfs/include/sys/space_map.h
Serapheim Dimitropoulos d2734cce68 OpenZFS 9166 - zfs storage pool checkpoint
Details about the motivation of this feature and its usage can
be found in this blogpost:

    https://sdimitro.github.io/post/zpool-checkpoint/

A lightning talk of this feature can be found here:
https://www.youtube.com/watch?v=fPQA8K40jAM

Implementation details can be found in big block comment of
spa_checkpoint.c

Side-changes that are relevant to this commit but not explained
elsewhere:

* renames members of "struct metaslab trees to be shorter without
  losing meaning

* space_map_{alloc,truncate}() accept a block size as a
  parameter. The reason is that in the current state all space
  maps that we allocate through the DMU use a global tunable
  (space_map_blksz) which defauls to 4KB. This is ok for metaslab
  space maps in terms of bandwirdth since they are scattered all
  over the disk. But for other space maps this default is probably
  not what we want. Examples are device removal's vdev_obsolete_sm
  or vdev_chedkpoint_sm from this review. Both of these have a
  1:1 relationship with each vdev and could benefit from a bigger
  block size.

Porting notes:

* The part of dsl_scan_sync() which handles async destroys has
  been moved into the new dsl_process_async_destroys() function.

* Remove "VERIFY(!(flags & FWRITE))" in "kernel.c" so zhack can write
  to block device backed pools.

* ZTS:
  * Fix get_txg() in zpool_sync_001_pos due to "checkpoint_txg".

  * Don't use large dd block sizes on /dev/urandom under Linux in
    checkpoint_capacity.

  * Adopt Delphix-OS's setting of 4 (spa_asize_inflation =
    SPA_DVAS_PER_BP + 1) for the checkpoint_capacity test to speed
    its attempts to fill the pool

  * Create the base and nested pools with sync=disabled to speed up
    the "setup" phase.

  * Clear labels in test pool between checkpoint tests to avoid
    duplicate pool issues.

  * The import_rewind_device_replaced test has been marked as "known
    to fail" for the reasons listed in its DISCLAIMER.

  * New module parameters:

      zfs_spa_discard_memory_limit,
      zfs_remove_max_bytes_pause (not documented - debugging only)
      vdev_max_ms_count (formerly metaslabs_per_vdev)
      vdev_min_ms_count

Authored by: Serapheim Dimitropoulos <serapheim.dimitro@delphix.com>
Reviewed by: Matthew Ahrens <mahrens@delphix.com>
Reviewed by: John Kennedy <john.kennedy@delphix.com>
Reviewed by: Dan Kimmel <dan.kimmel@delphix.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Richard Lowe <richlowe@richlowe.net>
Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Tim Chase <tim@chase2k.com>

OpenZFS-issue: https://illumos.org/issues/9166
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/7159fdb8
Closes #7570
2018-06-26 10:07:42 -07:00

174 lines
5.8 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) 2012, 2017 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 {
uint64_t smp_object; /* on-disk space map object */
uint64_t smp_objsize; /* size of the object */
int64_t smp_alloc; /* space allocated from the map */
uint64_t smp_pad[5]; /* reserved */
/*
* 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)
*/
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 */
uint64_t sm_length; /* synced length */
int64_t sm_alloc; /* synced space allocated */
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
*
* 1 3 10 50
* ,---+--------+------------+---------------------------------.
* | 1 | action | syncpass | txg (lower bits) |
* `---+--------+------------+---------------------------------'
* 63 62 60 59 50 49 0
*
*
* non-debug entry
*
* 1 47 1 15
* ,-----------------------------------------------------------.
* | 0 | offset (sm_shift units) | type | run |
* `-----------------------------------------------------------'
* 63 62 17 16 15 0
*/
/* All this stuff takes and returns bytes */
#define SM_RUN_DECODE(x) (BF64_DECODE(x, 0, 15) + 1)
#define SM_RUN_ENCODE(x) BF64_ENCODE((x) - 1, 0, 15)
#define SM_TYPE_DECODE(x) BF64_DECODE(x, 15, 1)
#define SM_TYPE_ENCODE(x) BF64_ENCODE(x, 15, 1)
#define SM_OFFSET_DECODE(x) BF64_DECODE(x, 16, 47)
#define SM_OFFSET_ENCODE(x) BF64_ENCODE(x, 16, 47)
#define SM_DEBUG_DECODE(x) BF64_DECODE(x, 63, 1)
#define SM_DEBUG_ENCODE(x) BF64_ENCODE(x, 63, 1)
#define SM_DEBUG_ACTION_DECODE(x) BF64_DECODE(x, 60, 3)
#define SM_DEBUG_ACTION_ENCODE(x) BF64_ENCODE(x, 60, 3)
#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_RUN_MAX SM_RUN_DECODE(~0ULL)
typedef enum {
SM_ALLOC,
SM_FREE
} maptype_t;
typedef int (*sm_cb_t)(maptype_t type, uint64_t offset, uint64_t size,
void *arg);
int space_map_load(space_map_t *sm, range_tree_t *rt, maptype_t maptype);
int space_map_iterate(space_map_t *sm, 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);
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);
void space_map_update(space_map_t *sm);
uint64_t space_map_object(space_map_t *sm);
uint64_t space_map_allocated(space_map_t *sm);
uint64_t space_map_length(space_map_t *sm);
void space_map_write(space_map_t *sm, range_tree_t *rt, maptype_t maptype,
dmu_tx_t *tx);
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);
int64_t space_map_alloc_delta(space_map_t *sm);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_SPACE_MAP_H */