mirror_zfs/include/sys/dsl_synctask.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

125 lines
3.9 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 (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
* Copyright (c) 2012, 2017 by Delphix. All rights reserved.
*/
#ifndef _SYS_DSL_SYNCTASK_H
#define _SYS_DSL_SYNCTASK_H
#include <sys/txg.h>
#include <sys/zfs_context.h>
#ifdef __cplusplus
extern "C" {
#endif
struct dsl_pool;
typedef int (dsl_checkfunc_t)(void *, dmu_tx_t *);
typedef void (dsl_syncfunc_t)(void *, dmu_tx_t *);
typedef enum zfs_space_check {
/*
* Normal space check: if there is less than 3.2% free space,
* the operation will fail. Operations which are logically
* creating things should use this (e.g. "zfs create", "zfs snapshot").
* User writes (via the ZPL / ZVOL) also fail at this point.
*/
ZFS_SPACE_CHECK_NORMAL,
/*
* Space check allows use of half the slop space. If there
* is less than 1.6% free space, the operation will fail. Most
* operations should use this (e.g. "zfs set", "zfs rename"),
* because we want them to succeed even after user writes are failing,
* so that they can be used as part of the space recovery process.
*/
ZFS_SPACE_CHECK_RESERVED,
/*
* Space check allows use of three quarters of the slop space.
* If there is less than 0.8% free space, the operation will
* fail.
*/
ZFS_SPACE_CHECK_EXTRA_RESERVED,
/*
* In all cases "zfs destroy" is expected to result in an net
* reduction of space, except one. When the pool has a
* checkpoint, space freed by "zfs destroy" will not actually
* free anything internally. Thus, it starts failing after
* three quarters of the slop space is exceeded.
*/
ZFS_SPACE_CHECK_DESTROY = ZFS_SPACE_CHECK_EXTRA_RESERVED,
/*
* A channel program can run a "zfs destroy" as part of its
* script and therefore has the same space_check policy when
* being evaluated.
*/
ZFS_SPACE_CHECK_ZCP_EVAL = ZFS_SPACE_CHECK_DESTROY,
/*
* No space check is performed. This level of space check should
* be used cautiously as operations that use it can even run when
* 0.8% capacity is left for use. In this scenario, if there is a
* checkpoint, async destroys are suspended and any kind of freeing
* can potentially add space instead of freeing it.
*
* See also the comments above spa_slop_shift.
*/
ZFS_SPACE_CHECK_NONE,
ZFS_SPACE_CHECK_DISCARD_CHECKPOINT = ZFS_SPACE_CHECK_NONE,
} zfs_space_check_t;
typedef struct dsl_sync_task {
txg_node_t dst_node;
struct dsl_pool *dst_pool;
uint64_t dst_txg;
int dst_space;
zfs_space_check_t dst_space_check;
dsl_checkfunc_t *dst_checkfunc;
dsl_syncfunc_t *dst_syncfunc;
void *dst_arg;
int dst_error;
boolean_t dst_nowaiter;
} dsl_sync_task_t;
void dsl_sync_task_sync(dsl_sync_task_t *, dmu_tx_t *);
int dsl_sync_task(const char *, dsl_checkfunc_t *,
dsl_syncfunc_t *, void *, int, zfs_space_check_t);
void dsl_sync_task_nowait(struct dsl_pool *, dsl_syncfunc_t *,
void *, int, zfs_space_check_t, dmu_tx_t *);
int dsl_early_sync_task(const char *, dsl_checkfunc_t *,
dsl_syncfunc_t *, void *, int, zfs_space_check_t);
void dsl_early_sync_task_nowait(struct dsl_pool *, dsl_syncfunc_t *,
void *, int, zfs_space_check_t, dmu_tx_t *);
#ifdef __cplusplus
}
#endif
#endif /* _SYS_DSL_SYNCTASK_H */