mirror of
https://git.proxmox.com/git/mirror_zfs.git
synced 2024-11-18 18:31:00 +03:00
d2734cce68
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
97 lines
2.6 KiB
C
97 lines
2.6 KiB
C
/*
|
|
* CDDL HEADER START
|
|
*
|
|
* This file and its contents are supplied under the terms of the
|
|
* Common Development and Distribution License ("CDDL"), version 1.0.
|
|
* You may only use this file in accordance with the terms of version
|
|
* 1.0 of the CDDL.
|
|
*
|
|
* A full copy of the text of the CDDL should have accompanied this
|
|
* source. A copy of the CDDL is also available via the Internet at
|
|
* http://www.illumos.org/license/CDDL.
|
|
*
|
|
* CDDL HEADER END
|
|
*/
|
|
|
|
/*
|
|
* Copyright (c) 2014, 2017 by Delphix. All rights reserved.
|
|
*/
|
|
|
|
#ifndef _SYS_VDEV_REMOVAL_H
|
|
#define _SYS_VDEV_REMOVAL_H
|
|
|
|
#include <sys/spa.h>
|
|
#include <sys/bpobj.h>
|
|
#include <sys/vdev_indirect_mapping.h>
|
|
#include <sys/vdev_indirect_births.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
typedef struct spa_vdev_removal {
|
|
uint64_t svr_vdev_id;
|
|
uint64_t svr_max_offset_to_sync[TXG_SIZE];
|
|
/* Thread performing a vdev removal. */
|
|
kthread_t *svr_thread;
|
|
/* Segments left to copy from the current metaslab. */
|
|
range_tree_t *svr_allocd_segs;
|
|
kmutex_t svr_lock;
|
|
kcondvar_t svr_cv;
|
|
boolean_t svr_thread_exit;
|
|
|
|
/*
|
|
* New mappings to write out each txg.
|
|
*/
|
|
list_t svr_new_segments[TXG_SIZE];
|
|
|
|
/*
|
|
* Ranges that were freed while a mapping was in flight. This is
|
|
* a subset of the ranges covered by vdev_im_new_segments.
|
|
*/
|
|
range_tree_t *svr_frees[TXG_SIZE];
|
|
|
|
/*
|
|
* Number of bytes which we have finished our work for
|
|
* in each txg. This could be data copied (which will be part of
|
|
* the mappings in vdev_im_new_segments), or data freed before
|
|
* we got around to copying it.
|
|
*/
|
|
uint64_t svr_bytes_done[TXG_SIZE];
|
|
|
|
/* List of leaf zap objects to be unlinked */
|
|
nvlist_t *svr_zaplist;
|
|
} spa_vdev_removal_t;
|
|
|
|
typedef struct spa_condensing_indirect {
|
|
/*
|
|
* New mappings to write out each txg.
|
|
*/
|
|
list_t sci_new_mapping_entries[TXG_SIZE];
|
|
|
|
vdev_indirect_mapping_t *sci_new_mapping;
|
|
} spa_condensing_indirect_t;
|
|
|
|
extern int spa_remove_init(spa_t *);
|
|
extern void spa_restart_removal(spa_t *);
|
|
extern int spa_condense_init(spa_t *);
|
|
extern void spa_condense_fini(spa_t *);
|
|
extern void spa_start_indirect_condensing_thread(spa_t *);
|
|
extern void spa_vdev_condense_suspend(spa_t *);
|
|
extern int spa_vdev_remove(spa_t *, uint64_t, boolean_t);
|
|
extern void free_from_removing_vdev(vdev_t *, uint64_t, uint64_t);
|
|
extern int spa_removal_get_stats(spa_t *, pool_removal_stat_t *);
|
|
extern void svr_sync(spa_t *spa, dmu_tx_t *tx);
|
|
extern void spa_vdev_remove_suspend(spa_t *);
|
|
extern int spa_vdev_remove_cancel(spa_t *);
|
|
extern void spa_vdev_removal_destroy(spa_vdev_removal_t *svr);
|
|
|
|
extern int vdev_removal_max_span;
|
|
extern int zfs_remove_max_segment;
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_VDEV_REMOVAL_H */
|