1
0
mirror of https://git.FreeBSD.org/src.git synced 2024-11-28 08:02:54 +00:00
freebsd/include/sys/vdev_indirect_mapping.h
Matthew Ahrens a1d477c24c OpenZFS 7614, 9064 - zfs device evacuation/removal
OpenZFS 7614 - zfs device evacuation/removal
OpenZFS 9064 - remove_mirror should wait for device removal to complete

This project allows top-level vdevs to be removed from the storage pool
with "zpool remove", reducing the total amount of storage in the pool.
This operation copies all allocated regions of the device to be removed
onto other devices, recording the mapping from old to new location.
After the removal is complete, read and free operations to the removed
(now "indirect") vdev must be remapped and performed at the new location
on disk.  The indirect mapping table is kept in memory whenever the pool
is loaded, so there is minimal performance overhead when doing operations
on the indirect vdev.

The size of the in-memory mapping table will be reduced when its entries
become "obsolete" because they are no longer used by any block pointers
in the pool.  An entry becomes obsolete when all the blocks that use
it are freed.  An entry can also become obsolete when all the snapshots
that reference it are deleted, and the block pointers that reference it
have been "remapped" in all filesystems/zvols (and clones).  Whenever an
indirect block is written, all the block pointers in it will be "remapped"
to their new (concrete) locations if possible.  This process can be
accelerated by using the "zfs remap" command to proactively rewrite all
indirect blocks that reference indirect (removed) vdevs.

Note that when a device is removed, we do not verify the checksum of
the data that is copied.  This makes the process much faster, but if it
were used on redundant vdevs (i.e. mirror or raidz vdevs), it would be
possible to copy the wrong data, when we have the correct data on e.g.
the other side of the mirror.

At the moment, only mirrors and simple top-level vdevs can be removed
and no removal is allowed if any of the top-level vdevs are raidz.

Porting Notes:

* Avoid zero-sized kmem_alloc() in vdev_compact_children().

    The device evacuation code adds a dependency that
    vdev_compact_children() be able to properly empty the vdev_child
    array by setting it to NULL and zeroing vdev_children.  Under Linux,
    kmem_alloc() and related functions return a sentinel pointer rather
    than NULL for zero-sized allocations.

* Remove comment regarding "mpt" driver where zfs_remove_max_segment
  is initialized to SPA_MAXBLOCKSIZE.

  Change zfs_condense_indirect_commit_entry_delay_ticks to
  zfs_condense_indirect_commit_entry_delay_ms for consistency with
  most other tunables in which delays are specified in ms.

* ZTS changes:

    Use set_tunable rather than mdb
    Use zpool sync as appropriate
    Use sync_pool instead of sync
    Kill jobs during test_removal_with_operation to allow unmount/export
    Don't add non-disk names such as "mirror" or "raidz" to $DISKS
    Use $TEST_BASE_DIR instead of /tmp
    Increase HZ from 100 to 1000 which is more common on Linux

    removal_multiple_indirection.ksh
        Reduce iterations in order to not time out on the code
        coverage builders.

    removal_resume_export:
        Functionally, the test case is correct but there exists a race
        where the kernel thread hasn't been fully started yet and is
        not visible.  Wait for up to 1 second for the removal thread
        to be started before giving up on it.  Also, increase the
        amount of data copied in order that the removal not finish
        before the export has a chance to fail.

* MMP compatibility, the concept of concrete versus non-concrete devices
  has slightly changed the semantics of vdev_writeable().  Update
  mmp_random_leaf_impl() accordingly.

* Updated dbuf_remap() to handle the org.zfsonlinux:large_dnode pool
  feature which is not supported by OpenZFS.

* Added support for new vdev removal tracepoints.

* Test cases removal_with_zdb and removal_condense_export have been
  intentionally disabled.  When run manually they pass as intended,
  but when running in the automated test environment they produce
  unreliable results on the latest Fedora release.

  They may work better once the upstream pool import refectoring is
  merged into ZoL at which point they will be re-enabled.

Authored by: Matthew Ahrens <mahrens@delphix.com>
Reviewed-by: Alex Reece <alex@delphix.com>
Reviewed-by: George Wilson <george.wilson@delphix.com>
Reviewed-by: John Kennedy <john.kennedy@delphix.com>
Reviewed-by: Prakash Surya <prakash.surya@delphix.com>
Reviewed by: Richard Laager <rlaager@wiktel.com>
Reviewed by: Tim Chase <tim@chase2k.com>
Reviewed by: Brian Behlendorf <behlendorf1@llnl.gov>
Approved by: Garrett D'Amore <garrett@damore.org>
Ported-by: Tim Chase <tim@chase2k.com>
Signed-off-by: Tim Chase <tim@chase2k.com>

OpenZFS-issue: https://www.illumos.org/issues/7614
OpenZFS-commit: https://github.com/openzfs/openzfs/commit/f539f1eb
Closes #6900
2018-04-14 12:16:17 -07:00

142 lines
4.4 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) 2015 by Delphix. All rights reserved.
*/
#ifndef _SYS_VDEV_INDIRECT_MAPPING_H
#define _SYS_VDEV_INDIRECT_MAPPING_H
#include <sys/dmu.h>
#include <sys/list.h>
#include <sys/spa.h>
#include <sys/space_map.h>
#ifdef __cplusplus
extern "C" {
#endif
typedef struct vdev_indirect_mapping_entry_phys {
/*
* Decode with DVA_MAPPING_* macros.
* Contains:
* the source offset (low 63 bits)
* the one-bit "mark", used for garbage collection (by zdb)
*/
uint64_t vimep_src;
/*
* Note: the DVA's asize is 24 bits, and can thus store ranges
* up to 8GB.
*/
dva_t vimep_dst;
} vdev_indirect_mapping_entry_phys_t;
#define DVA_MAPPING_GET_SRC_OFFSET(vimep) \
BF64_GET_SB((vimep)->vimep_src, 0, 63, SPA_MINBLOCKSHIFT, 0)
#define DVA_MAPPING_SET_SRC_OFFSET(vimep, x) \
BF64_SET_SB((vimep)->vimep_src, 0, 63, SPA_MINBLOCKSHIFT, 0, x)
typedef struct vdev_indirect_mapping_entry {
vdev_indirect_mapping_entry_phys_t vime_mapping;
uint32_t vime_obsolete_count;
list_node_t vime_node;
} vdev_indirect_mapping_entry_t;
/*
* This is stored in the bonus buffer of the mapping object, see comment of
* vdev_indirect_config for more details.
*/
typedef struct vdev_indirect_mapping_phys {
uint64_t vimp_max_offset;
uint64_t vimp_bytes_mapped;
uint64_t vimp_num_entries; /* number of v_i_m_entry_phys_t's */
/*
* For each entry in the mapping object, this object contains an
* entry representing the number of bytes of that mapping entry
* that were no longer in use by the pool at the time this indirect
* vdev was last condensed.
*/
uint64_t vimp_counts_object;
} vdev_indirect_mapping_phys_t;
#define VDEV_INDIRECT_MAPPING_SIZE_V0 (3 * sizeof (uint64_t))
typedef struct vdev_indirect_mapping {
uint64_t vim_object;
boolean_t vim_havecounts;
/*
* An ordered array of all mapping entries, sorted by source offset.
* Note that vim_entries is needed during a removal (and contains
* mappings that have been synced to disk so far) to handle frees
* from the removing device.
*/
vdev_indirect_mapping_entry_phys_t *vim_entries;
objset_t *vim_objset;
dmu_buf_t *vim_dbuf;
vdev_indirect_mapping_phys_t *vim_phys;
} vdev_indirect_mapping_t;
extern vdev_indirect_mapping_t *vdev_indirect_mapping_open(objset_t *os,
uint64_t object);
extern void vdev_indirect_mapping_close(vdev_indirect_mapping_t *vim);
extern uint64_t vdev_indirect_mapping_alloc(objset_t *os, dmu_tx_t *tx);
extern void vdev_indirect_mapping_free(objset_t *os, uint64_t obj,
dmu_tx_t *tx);
extern uint64_t vdev_indirect_mapping_num_entries(vdev_indirect_mapping_t *vim);
extern uint64_t vdev_indirect_mapping_max_offset(vdev_indirect_mapping_t *vim);
extern uint64_t vdev_indirect_mapping_object(vdev_indirect_mapping_t *vim);
extern uint64_t vdev_indirect_mapping_bytes_mapped(
vdev_indirect_mapping_t *vim);
extern uint64_t vdev_indirect_mapping_size(vdev_indirect_mapping_t *vim);
/*
* Writes the given list of vdev_indirect_mapping_entry_t to the mapping
* then updates internal state.
*/
extern void vdev_indirect_mapping_add_entries(vdev_indirect_mapping_t *vim,
list_t *vime_list, dmu_tx_t *tx);
extern vdev_indirect_mapping_entry_phys_t *
vdev_indirect_mapping_entry_for_offset(vdev_indirect_mapping_t *vim,
uint64_t offset);
extern vdev_indirect_mapping_entry_phys_t *
vdev_indirect_mapping_entry_for_offset_or_next(vdev_indirect_mapping_t *vim,
uint64_t offset);
extern uint32_t *vdev_indirect_mapping_load_obsolete_counts(
vdev_indirect_mapping_t *vim);
extern void vdev_indirect_mapping_load_obsolete_spacemap(
vdev_indirect_mapping_t *vim,
uint32_t *counts, space_map_t *obsolete_space_sm);
extern void vdev_indirect_mapping_increment_obsolete_count(
vdev_indirect_mapping_t *vim,
uint64_t offset, uint64_t asize, uint32_t *counts);
extern void vdev_indirect_mapping_free_obsolete_counts(
vdev_indirect_mapping_t *vim, uint32_t *counts);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_VDEV_INDIRECT_MAPPING_H */