a1d477c24c
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
189 lines
6.8 KiB
C
189 lines
6.8 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 (c) 2010, Oracle and/or its affiliates. All rights reserved.
|
|
* Copyright (c) 2012, 2017 by Delphix. All rights reserved.
|
|
* Copyright (c) 2017 Datto Inc.
|
|
*/
|
|
|
|
#ifndef _SYS_DSL_SCAN_H
|
|
#define _SYS_DSL_SCAN_H
|
|
|
|
#include <sys/zfs_context.h>
|
|
#include <sys/zio.h>
|
|
#include <sys/ddt.h>
|
|
#include <sys/bplist.h>
|
|
|
|
#ifdef __cplusplus
|
|
extern "C" {
|
|
#endif
|
|
|
|
struct objset;
|
|
struct dsl_dir;
|
|
struct dsl_dataset;
|
|
struct dsl_pool;
|
|
struct dmu_tx;
|
|
|
|
/*
|
|
* All members of this structure must be uint64_t, for byteswap
|
|
* purposes.
|
|
*/
|
|
typedef struct dsl_scan_phys {
|
|
uint64_t scn_func; /* pool_scan_func_t */
|
|
uint64_t scn_state; /* dsl_scan_state_t */
|
|
uint64_t scn_queue_obj;
|
|
uint64_t scn_min_txg;
|
|
uint64_t scn_max_txg;
|
|
uint64_t scn_cur_min_txg;
|
|
uint64_t scn_cur_max_txg;
|
|
uint64_t scn_start_time;
|
|
uint64_t scn_end_time;
|
|
uint64_t scn_to_examine; /* total bytes to be scanned */
|
|
uint64_t scn_examined; /* bytes scanned so far */
|
|
uint64_t scn_to_process;
|
|
uint64_t scn_processed;
|
|
uint64_t scn_errors; /* scan I/O error count */
|
|
uint64_t scn_ddt_class_max;
|
|
ddt_bookmark_t scn_ddt_bookmark;
|
|
zbookmark_phys_t scn_bookmark;
|
|
uint64_t scn_flags; /* dsl_scan_flags_t */
|
|
} dsl_scan_phys_t;
|
|
|
|
#define SCAN_PHYS_NUMINTS (sizeof (dsl_scan_phys_t) / sizeof (uint64_t))
|
|
|
|
typedef enum dsl_scan_flags {
|
|
DSF_VISIT_DS_AGAIN = 1<<0,
|
|
DSF_SCRUB_PAUSED = 1<<1,
|
|
} dsl_scan_flags_t;
|
|
|
|
#define DSL_SCAN_FLAGS_MASK (DSF_VISIT_DS_AGAIN)
|
|
|
|
/*
|
|
* Every pool will have one dsl_scan_t and this structure will contain
|
|
* in-memory information about the scan and a pointer to the on-disk
|
|
* representation (i.e. dsl_scan_phys_t). Most of the state of the scan
|
|
* is contained on-disk to allow the scan to resume in the event of a reboot
|
|
* or panic. This structure maintains information about the behavior of a
|
|
* running scan, some caching information, and how it should traverse the pool.
|
|
*
|
|
* The following members of this structure direct the behavior of the scan:
|
|
*
|
|
* scn_suspending - a scan that cannot be completed in a single txg or
|
|
* has exceeded its allotted time will need to suspend.
|
|
* When this flag is set the scanner will stop traversing
|
|
* the pool and write out the current state to disk.
|
|
*
|
|
* scn_restart_txg - directs the scanner to either restart or start a
|
|
* a scan at the specified txg value.
|
|
*
|
|
* scn_done_txg - when a scan completes its traversal it will set
|
|
* the completion txg to the next txg. This is necessary
|
|
* to ensure that any blocks that were freed during
|
|
* the scan but have not yet been processed (i.e deferred
|
|
* frees) are accounted for.
|
|
*
|
|
* This structure also maintains information about deferred frees which are
|
|
* a special kind of traversal. Deferred free can exist in either a bptree or
|
|
* a bpobj structure. The scn_is_bptree flag will indicate the type of
|
|
* deferred free that is in progress. If the deferred free is part of an
|
|
* asynchronous destroy then the scn_async_destroying flag will be set.
|
|
*/
|
|
typedef struct dsl_scan {
|
|
struct dsl_pool *scn_dp;
|
|
uint64_t scn_restart_txg;
|
|
uint64_t scn_done_txg;
|
|
uint64_t scn_sync_start_time;
|
|
uint64_t scn_issued_before_pass;
|
|
|
|
/* for freeing blocks */
|
|
boolean_t scn_is_bptree;
|
|
boolean_t scn_async_destroying;
|
|
boolean_t scn_async_stalled;
|
|
uint64_t scn_async_block_min_time_ms;
|
|
|
|
/* flags and stats for controlling scan state */
|
|
boolean_t scn_is_sorted; /* doing sequential scan */
|
|
boolean_t scn_clearing; /* scan is issuing sequential extents */
|
|
boolean_t scn_checkpointing; /* scan is issuing all queued extents */
|
|
boolean_t scn_suspending; /* scan is suspending until next txg */
|
|
uint64_t scn_last_checkpoint; /* time of last checkpoint */
|
|
|
|
/* members for thread synchronization */
|
|
zio_t *scn_zio_root; /* root zio for waiting on IO */
|
|
taskq_t *scn_taskq; /* task queue for issuing extents */
|
|
|
|
/* for controlling scan prefetch, protected by spa_scrub_lock */
|
|
boolean_t scn_prefetch_stop; /* prefetch should stop */
|
|
zbookmark_phys_t scn_prefetch_bookmark; /* prefetch start bookmark */
|
|
avl_tree_t scn_prefetch_queue; /* priority queue of prefetch IOs */
|
|
uint64_t scn_maxinflight_bytes; /* max bytes in flight for pool */
|
|
|
|
/* per txg statistics */
|
|
uint64_t scn_visited_this_txg; /* total bps visited this txg */
|
|
uint64_t scn_holes_this_txg;
|
|
uint64_t scn_lt_min_this_txg;
|
|
uint64_t scn_gt_max_this_txg;
|
|
uint64_t scn_ddt_contained_this_txg;
|
|
uint64_t scn_objsets_visited_this_txg;
|
|
uint64_t scn_avg_seg_size_this_txg;
|
|
uint64_t scn_segs_this_txg;
|
|
uint64_t scn_avg_zio_size_this_txg;
|
|
uint64_t scn_zios_this_txg;
|
|
|
|
/* members needed for syncing scan status to disk */
|
|
dsl_scan_phys_t scn_phys; /* on disk representation of scan */
|
|
dsl_scan_phys_t scn_phys_cached;
|
|
avl_tree_t scn_queue; /* queue of datasets to scan */
|
|
uint64_t scn_bytes_pending; /* outstanding data to issue */
|
|
} dsl_scan_t;
|
|
|
|
typedef struct dsl_scan_io_queue dsl_scan_io_queue_t;
|
|
|
|
void scan_init(void);
|
|
void scan_fini(void);
|
|
int dsl_scan_init(struct dsl_pool *dp, uint64_t txg);
|
|
void dsl_scan_fini(struct dsl_pool *dp);
|
|
void dsl_scan_sync(struct dsl_pool *, dmu_tx_t *);
|
|
int dsl_scan_cancel(struct dsl_pool *);
|
|
int dsl_scan(struct dsl_pool *, pool_scan_func_t);
|
|
boolean_t dsl_scan_scrubbing(const struct dsl_pool *dp);
|
|
int dsl_scrub_set_pause_resume(const struct dsl_pool *dp, pool_scrub_cmd_t cmd);
|
|
void dsl_resilver_restart(struct dsl_pool *, uint64_t txg);
|
|
boolean_t dsl_scan_resilvering(struct dsl_pool *dp);
|
|
boolean_t dsl_dataset_unstable(struct dsl_dataset *ds);
|
|
void dsl_scan_ddt_entry(dsl_scan_t *scn, enum zio_checksum checksum,
|
|
ddt_entry_t *dde, dmu_tx_t *tx);
|
|
void dsl_scan_ds_destroyed(struct dsl_dataset *ds, struct dmu_tx *tx);
|
|
void dsl_scan_ds_snapshotted(struct dsl_dataset *ds, struct dmu_tx *tx);
|
|
void dsl_scan_ds_clone_swapped(struct dsl_dataset *ds1, struct dsl_dataset *ds2,
|
|
struct dmu_tx *tx);
|
|
boolean_t dsl_scan_active(dsl_scan_t *scn);
|
|
boolean_t dsl_scan_is_paused_scrub(const dsl_scan_t *scn);
|
|
void dsl_scan_freed(spa_t *spa, const blkptr_t *bp);
|
|
void dsl_scan_io_queue_destroy(dsl_scan_io_queue_t *queue);
|
|
void dsl_scan_io_queue_vdev_xfer(vdev_t *svd, vdev_t *tvd);
|
|
|
|
#ifdef __cplusplus
|
|
}
|
|
#endif
|
|
|
|
#endif /* _SYS_DSL_SCAN_H */
|