mirror_zfs/include/sys/dsl_scan.h

188 lines
6.8 KiB
C
Raw Normal View History

/*
* 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, 2014 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;
Add erratum for issue #2094 ZoL commit 1421c89 unintentionally changed the disk format in a forward- compatible, but not backward compatible way. This was accomplished by adding an entry to zbookmark_t, which is included in a couple of on-disk structures. That lead to the creation of pools with incorrect dsl_scan_phys_t objects that could only be imported by versions of ZoL containing that commit. Such pools cannot be imported by other versions of ZFS or past versions of ZoL. The additional field has been removed by the previous commit. However, affected pools must be imported and scrubbed using a version of ZoL with this commit applied. This will return the pools to a state in which they may be imported by other implementations. The 'zpool import' or 'zpool status' command can be used to determine if a pool is impacted. A message similar to one of the following means your pool must be scrubbed to restore compatibility. $ zpool import pool: zol-0.6.2-173 id: 1165955789558693437 state: ONLINE status: Errata #1 detected. action: The pool can be imported using its name or numeric identifier, however there is a compatibility issue which should be corrected by running 'zpool scrub' see: http://zfsonlinux.org/msg/ZFS-8000-ER config: ... $ zpool status pool: zol-0.6.2-173 state: ONLINE scan: pool compatibility issue detected. see: https://github.com/zfsonlinux/zfs/issues/2094 action: To correct the issue run 'zpool scrub'. config: ... If there was an async destroy in progress 'zpool import' will prevent the pool from being imported. Further advice on how to proceed will be provided by the error message as follows. $ zpool import pool: zol-0.6.2-173 id: 1165955789558693437 state: ONLINE status: Errata #2 detected. action: The pool can not be imported with this version of ZFS due to an active asynchronous destroy. Revert to an earlier version and allow the destroy to complete before updating. see: http://zfsonlinux.org/msg/ZFS-8000-ER config: ... Pools affected by the damaged dsl_scan_phys_t can be detected prior to an upgrade by running the following command as root: zdb -dddd poolname 1 | grep -P '^\t\tscan = ' | sed -e 's;scan = ;;' | wc -w Note that `poolname` must be replaced with the name of the pool you wish to check. A value of 25 indicates the dsl_scan_phys_t has been damaged. A value of 24 indicates that the dsl_scan_phys_t is normal. A value of 0 indicates that there has never been a scrub run on the pool. The regression caused by the change to zbookmark_t never made it into a tagged release, Gentoo backports, Ubuntu, Debian, Fedora, or EPEL stable respositorys. Only those using the HEAD version directly from Github after the 0.6.2 but before the 0.6.3 tag are affected. This patch does have one limitation that should be mentioned. It will not detect errata #2 on a pool unless errata #1 is also present. It expected this will not be a significant problem because pools impacted by errata #2 have a high probably of being impacted by errata #1. End users can ensure they do no hit this unlikely case by waiting for all asynchronous destroy operations to complete before updating ZoL. The presence of any background destroys on any imported pools can be checked by running `zpool get freeing` as root. This will display a non-zero value for any pool with an active asynchronous destroy. Lastly, it is expected that no user data has been lost as a result of this erratum. Original-patch-by: Tim Chase <tim@chase2k.com> Reworked-by: Brian Behlendorf <behlendorf1@llnl.gov> Signed-off-by: Tim Chase <tim@chase2k.com> Signed-off-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Issue #2094
2014-02-21 08:28:33 +04:00
#define DSL_SCAN_FLAGS_MASK (DSF_VISIT_DS_AGAIN)
Illumos #3956, #3957, #3958, #3959, #3960, #3961, #3962 3956 ::vdev -r should work with pipelines 3957 ztest should update the cachefile before killing itself 3958 multiple scans can lead to partial resilvering 3959 ddt entries are not always resilvered 3960 dsl_scan can skip over dedup-ed blocks if physical birth != logical birth 3961 freed gang blocks are not resilvered and can cause pool to suspend 3962 ztest should print out zfs debug buffer before exiting Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <ahl@delphix.com> Approved by: Richard Lowe <richlowe@richlowe.net> References: https://www.illumos.org/issues/3956 https://www.illumos.org/issues/3957 https://www.illumos.org/issues/3958 https://www.illumos.org/issues/3959 https://www.illumos.org/issues/3960 https://www.illumos.org/issues/3961 https://www.illumos.org/issues/3962 illumos/illumos-gate@b4952e17e8858d3225793b28788278de9fe6038d Ported-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Porting notes: 1. zfs_dbgmsg_print() is only used in userland. Since we do not have mdb on Linux, it does not make sense to make it available in the kernel. This means that a build failure will occur if any future kernel patch depends on it. However, that is unlikely given that this functionality was added to support zdb. 2. zfs_dbgmsg_print() is only invoked for -VVV or greater log levels. This preserves the existing behavior of minimal noise when running with -V, and -VV. 3. In vdev_config_generate() the call to nvlist_alloc() was not changed to fnvlist_alloc() because we must pass KM_PUSHPAGE in the txg_sync context.
2013-08-08 00:16:22 +04:00
/*
* 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.
Illumos #3956, #3957, #3958, #3959, #3960, #3961, #3962 3956 ::vdev -r should work with pipelines 3957 ztest should update the cachefile before killing itself 3958 multiple scans can lead to partial resilvering 3959 ddt entries are not always resilvered 3960 dsl_scan can skip over dedup-ed blocks if physical birth != logical birth 3961 freed gang blocks are not resilvered and can cause pool to suspend 3962 ztest should print out zfs debug buffer before exiting Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <ahl@delphix.com> Approved by: Richard Lowe <richlowe@richlowe.net> References: https://www.illumos.org/issues/3956 https://www.illumos.org/issues/3957 https://www.illumos.org/issues/3958 https://www.illumos.org/issues/3959 https://www.illumos.org/issues/3960 https://www.illumos.org/issues/3961 https://www.illumos.org/issues/3962 illumos/illumos-gate@b4952e17e8858d3225793b28788278de9fe6038d Ported-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Porting notes: 1. zfs_dbgmsg_print() is only used in userland. Since we do not have mdb on Linux, it does not make sense to make it available in the kernel. This means that a build failure will occur if any future kernel patch depends on it. However, that is unlikely given that this functionality was added to support zdb. 2. zfs_dbgmsg_print() is only invoked for -VVV or greater log levels. This preserves the existing behavior of minimal noise when running with -V, and -VV. 3. In vdev_config_generate() the call to nvlist_alloc() was not changed to fnvlist_alloc() because we must pass KM_PUSHPAGE in the txg_sync context.
2013-08-08 00:16:22 +04:00
* 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;
Illumos #3956, #3957, #3958, #3959, #3960, #3961, #3962 3956 ::vdev -r should work with pipelines 3957 ztest should update the cachefile before killing itself 3958 multiple scans can lead to partial resilvering 3959 ddt entries are not always resilvered 3960 dsl_scan can skip over dedup-ed blocks if physical birth != logical birth 3961 freed gang blocks are not resilvered and can cause pool to suspend 3962 ztest should print out zfs debug buffer before exiting Reviewed by: Matthew Ahrens <mahrens@delphix.com> Reviewed by: Adam Leventhal <ahl@delphix.com> Approved by: Richard Lowe <richlowe@richlowe.net> References: https://www.illumos.org/issues/3956 https://www.illumos.org/issues/3957 https://www.illumos.org/issues/3958 https://www.illumos.org/issues/3959 https://www.illumos.org/issues/3960 https://www.illumos.org/issues/3961 https://www.illumos.org/issues/3962 illumos/illumos-gate@b4952e17e8858d3225793b28788278de9fe6038d Ported-by: Richard Yao <ryao@gentoo.org> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Porting notes: 1. zfs_dbgmsg_print() is only used in userland. Since we do not have mdb on Linux, it does not make sense to make it available in the kernel. This means that a build failure will occur if any future kernel patch depends on it. However, that is unlikely given that this functionality was added to support zdb. 2. zfs_dbgmsg_print() is only invoked for -VVV or greater log levels. This preserves the existing behavior of minimal noise when running with -V, and -VV. 3. In vdev_config_generate() the call to nvlist_alloc() was not changed to fnvlist_alloc() because we must pass KM_PUSHPAGE in the txg_sync context.
2013-08-08 00:16:22 +04:00
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;
/* 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 */