spa_misc.c revision f0ba89be159095fb15265a5e1cd79e09e5e44ef9
/*
* 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
* 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 2010 Sun Microsystems, Inc. All rights reserved.
* Use is subject to license terms.
*/
#include <sys/zfs_context.h>
#include <sys/spa_impl.h>
#include <sys/zio_checksum.h>
#include <sys/zio_compress.h>
#include <sys/vdev_impl.h>
#include <sys/metaslab.h>
#include <sys/uberblock_impl.h>
#include <sys/dsl_pool.h>
#include <sys/dsl_prop.h>
#include <sys/metaslab_impl.h>
#include "zfs_prop.h"
/*
* SPA locking
*
* There are four basic locks for managing spa_t structures:
*
* spa_namespace_lock (global mutex)
*
* This lock must be acquired to do any of the following:
*
* - Lookup a spa_t by name
* - Add or remove a spa_t from the namespace
* - Increase spa_refcount from non-zero
* - Check if spa_refcount is zero
* - Rename a spa_t
*
* It does not need to handle recursion. A create or destroy may
* reference objects (files or zvols) in other pools, but by
* definition they must have an existing reference, and will never need
* to lookup a spa_t by name.
*
* spa_refcount (per-spa refcount_t protected by mutex)
*
* This reference count keep track of any active users of the spa_t. The
* spa_t cannot be destroyed or freed while this is non-zero. Internally,
* the refcount is never really 'zero' - opening a pool implicitly keeps
* some references in the DMU. Internally we check against spa_minref, but
*
* spa_config_lock[] (per-spa array of rwlocks)
*
* This protects the spa_t from config changes, and must be held in
* the following circumstances:
*
* - RW_READER to perform I/O to the spa
* - RW_WRITER to change the vdev config
*
* The locking order is fairly straightforward:
*
* spa_namespace_lock -> spa_refcount
*
* The namespace lock must be acquired to increase the refcount from 0
* or to check if it is zero.
*
* spa_refcount -> spa_config_lock[]
*
* There must be at least one valid reference on the spa_t to acquire
* the config lock.
*
* spa_namespace_lock -> spa_config_lock[]
*
* The namespace lock must always be taken before the config lock.
*
*
* The spa_namespace_lock can be acquired directly and is globally visible.
*
* The namespace is manipulated using the following functions, all of which
* require the spa_namespace_lock to be held.
*
* spa_lookup() Lookup a spa_t by name.
*
* spa_add() Create a new spa_t in the namespace.
*
* spa_remove() Remove a spa_t from the namespace. This also
* frees up any memory associated with the spa_t.
*
* spa_next() Returns the next spa_t in the system, or the
* first if NULL is passed.
*
* spa_evict_all() Shutdown and remove all spa_t structures in
* the system.
*
*
* The spa_refcount is manipulated using the following functions:
*
* spa_open_ref() Adds a reference to the given spa_t. Must be
* called with spa_namespace_lock held if the
* refcount is currently zero.
*
* spa_close() Remove a reference from the spa_t. This will
* not free the spa_t or remove it from the
* namespace. No locking is required.
*
* spa_refcount_zero() Returns true if the refcount is currently
* zero. Must be called with spa_namespace_lock
* held.
*
* The spa_config_lock[] is an array of rwlocks, ordered as follows:
* SCL_CONFIG > SCL_STATE > SCL_ALLOC > SCL_ZIO > SCL_FREE > SCL_VDEV.
* spa_config_lock[] is manipulated with spa_config_{enter,exit,held}().
*
* To read the configuration, it suffices to hold one of these locks as reader.
* To modify the configuration, you must hold all locks as writer. To modify
* you must hold SCL_STATE and SCL_ZIO as writer.
*
* We use these distinct config locks to avoid recursive lock entry.
* For example, spa_sync() (which holds SCL_CONFIG as reader) induces
* block allocations (SCL_ALLOC), which may require reading space maps
* from disk (dmu_read() -> zio_read() -> SCL_ZIO).
*
* The spa config locks cannot be normal rwlocks because we need the
* ability to hand off ownership. For example, SCL_ZIO is acquired
* by the issuing thread and later released by an interrupt thread.
* They do, however, obey the usual write-wanted semantics to prevent
* writer (i.e. system administrator) starvation.
*
* The lock acquisition rules are as follows:
*
* SCL_CONFIG
* Protects changes to the vdev tree topology, such as vdev
* (spa_config_dirty_list) and the set of spares and l2arc devices.
*
* SCL_STATE
* Protects changes to pool state and vdev state, such as vdev
* (spa_state_dirty_list) and global pool state (spa_state).
*
* SCL_ALLOC
* Protects changes to metaslab groups and classes.
* Held as reader by metaslab_alloc() and metaslab_claim().
*
* SCL_ZIO
* Held by bp-level zios (those which have no io_vd upon entry)
* to prevent changes to the vdev tree. The bp-level zio implicitly
* protects all of its vdev child zios, which do not hold SCL_ZIO.
*
* SCL_FREE
* Protects changes to metaslab groups and classes.
* Held as reader by metaslab_free(). SCL_FREE is distinct from
* SCL_ALLOC, and lower than SCL_ZIO, so that we can safely free
* blocks in zio_done() while another i/o that holds either
* SCL_ALLOC or SCL_ZIO is waiting for this i/o to complete.
*
* SCL_VDEV
* Held as reader to prevent changes to the vdev tree during trivial
* inquiries such as bp_get_dsize(). SCL_VDEV is distinct from the
* other locks, and lower than all of them, to ensure that it's safe
* to acquire regardless of caller context.
*
* In addition, the following rules apply:
*
* (a) spa_props_lock protects pool properties, spa_config and spa_config_list.
* The lock ordering is SCL_CONFIG > spa_props_lock.
*
* (b) I/O operations on leaf vdevs. For any zio operation that takes
* an explicit vdev_t argument -- such as zio_ioctl(), zio_read_phys(),
* or zio_write_phys() -- the caller must ensure that the config cannot
* cannot change in the interim, and that the vdev cannot be reopened.
* SCL_STATE as reader suffices for both.
*
* The vdev configuration is protected by spa_vdev_enter() / spa_vdev_exit().
*
* spa_vdev_enter() Acquire the namespace lock and the config lock
* for writing.
*
* spa_vdev_exit() Release the config lock, wait for all I/O
* to complete, sync the updated configs to the
* cache, and release the namespace lock.
*
* vdev state is protected by spa_vdev_state_enter() / spa_vdev_state_exit().
* Like spa_vdev_enter/exit, these are convenience wrappers -- the actual
* locking is, always, based on spa_namespace_lock and spa_config_lock[].
*
* spa_rename() is also implemented within this file since is requires
* manipulation of the namespace.
*/
static avl_tree_t spa_namespace_avl;
static kcondvar_t spa_namespace_cv;
static int spa_active_count;
static kmutex_t spa_spare_lock;
static avl_tree_t spa_spare_avl;
static kmutex_t spa_l2cache_lock;
static avl_tree_t spa_l2cache_avl;
int spa_mode_global;
#ifdef ZFS_DEBUG
/* Everything except dprintf is on by default in debug builds */
int zfs_flags = ~ZFS_DEBUG_DPRINTF;
#else
int zfs_flags = 0;
#endif
/*
* zfs_recover can be set to nonzero to attempt to recover from
* otherwise-fatal errors, typically caused by on-disk corruption. When
* set, calls to zfs_panic_recover() will turn into warning messages.
*/
int zfs_recover = 0;
/*
* ==========================================================================
* SPA config locking
* ==========================================================================
*/
static void
{
for (int i = 0; i < SCL_LOCKS; i++) {
scl->scl_write_wanted = 0;
}
}
static void
{
for (int i = 0; i < SCL_LOCKS; i++) {
}
}
int
{
for (int i = 0; i < SCL_LOCKS; i++) {
if (!(locks & (1 << i)))
continue;
return (0);
}
} else {
return (0);
}
}
}
return (1);
}
void
{
int wlocks_held = 0;
for (int i = 0; i < SCL_LOCKS; i++) {
wlocks_held |= (1 << i);
if (!(locks & (1 << i)))
continue;
}
} else {
scl->scl_write_wanted++;
scl->scl_write_wanted--;
}
}
}
}
void
{
for (int i = SCL_LOCKS - 1; i >= 0; i--) {
if (!(locks & (1 << i)))
continue;
}
}
}
int
{
int locks_held = 0;
for (int i = 0; i < SCL_LOCKS; i++) {
if (!(locks & (1 << i)))
continue;
locks_held |= 1 << i;
}
return (locks_held);
}
/*
* ==========================================================================
* SPA namespace functions
* ==========================================================================
*/
/*
* Lookup the named spa_t in the AVL tree. The spa_namespace_lock must be held.
* Returns NULL if no matching spa_t is found.
*/
spa_t *
spa_lookup(const char *name)
{
char c;
char *cp;
/*
* If it's a full dataset name, figure out the pool name and
* just use that.
*/
if (cp) {
c = *cp;
*cp = '\0';
}
if (cp)
*cp = c;
return (spa);
}
/*
* Create an uninitialized spa_t with the given name. Requires
* spa_namespace_lock. The caller must ensure that the spa_t doesn't already
* exist by calling spa_lookup() first.
*/
spa_t *
{
for (int t = 0; t < TXG_SIZE; t++)
/*
* Set the alternate root, if there is one.
*/
if (altroot) {
}
/*
* Every pool starts with the default cachefile
*/
return (spa);
}
/*
* Removes a spa_t from the namespace, freeing up any memory used. Requires
* spa_namespace_lock. This is called only after the spa_t has been closed and
* deactivated.
*/
void
{
}
}
for (int t = 0; t < TXG_SIZE; t++)
}
/*
* Given a pool, return the next pool in the namespace, or NULL if there is
* none. If 'prev' is NULL, return the first pool.
*/
spa_t *
{
if (prev)
else
return (avl_first(&spa_namespace_avl));
}
/*
* ==========================================================================
* SPA refcount functions
* ==========================================================================
*/
/*
* Add a reference to the given spa_t. Must have at least one reference, or
* have the namespace lock held.
*/
void
{
}
/*
* Remove a reference to the given spa_t. Must have at least one reference, or
* have the namespace lock held.
*/
void
{
}
/*
* Check to see if the spa refcount is zero. Must be called with
* spa_namespace_lock held. We really compare against spa_minref, which is the
* number of references acquired when opening a pool
*/
{
}
/*
* ==========================================================================
* SPA spare and l2cache tracking
* ==========================================================================
*/
/*
* Hot spares and cache devices are tracked using the same code below,
* for 'auxiliary' devices.
*/
typedef struct spa_aux {
int aux_count;
} spa_aux_t;
static int
spa_aux_compare(const void *a, const void *b)
{
return (-1);
return (1);
else
return (0);
}
void
{
} else {
}
}
void
{
}
}
{
if (pool) {
if (found)
else
}
if (refcnt) {
if (found)
else
*refcnt = 0;
}
}
void
{
}
/*
* Spares are tracked globally due to the following constraints:
*
* - A spare may be part of multiple pools.
* - A spare may be added to a pool even if it's actively in use within
* another pool.
* - A spare in use in any pool can only be the source of a replacement if
* the target is a spare in the same pool.
*
* We keep track of all spares on the system through the use of a reference
* counted AVL tree. When a vdev is added as a spare, or used as a replacement
* spare, then we bump the reference count in the AVL tree. In addition, we set
* the 'vdev_isspare' member to indicate that the device is a spare (active or
* inactive). When a spare is made active (used to replace a device in the
* pool), we also keep track of which pool its been made a part of.
*
* The 'spa_spare_lock' protects the AVL tree. These functions are normally
* called under the spa_namespace lock as part of vdev reconfiguration. The
* separate spare lock exists for the status query path, which does not need to
* be completely consistent with respect to other vdev configuration changes.
*/
static int
spa_spare_compare(const void *a, const void *b)
{
return (spa_aux_compare(a, b));
}
void
{
}
void
{
}
{
return (found);
}
void
{
}
/*
* Level 2 ARC devices are tracked globally for the same reasons as spares.
* Cache devices currently only support one pool per cache device, and so
* for these devices the aux reference count is currently unused beyond 1.
*/
static int
spa_l2cache_compare(const void *a, const void *b)
{
return (spa_aux_compare(a, b));
}
void
{
}
void
{
}
{
return (found);
}
void
{
}
/*
* ==========================================================================
* SPA vdev locking
* ==========================================================================
*/
/*
* Lock the given spa_t for the purpose of adding or removing a vdev.
* Grabs the global spa_namespace_lock plus the spa config lock for writing.
* It returns the next transaction group for the spa_t.
*/
{
return (spa_vdev_config_enter(spa));
}
/*
* Internal implementation for spa_vdev_enter(). Used when a vdev
* operation requires multiple syncs (i.e. removing a device) while
* keeping the spa_namespace_lock held.
*/
{
}
/*
* Used in combination with spa_vdev_config_enter() to allow the syncing
* of multiple transactions without releasing the spa_namespace_lock.
*/
void
{
int config_changed = B_FALSE;
/*
* Reassess the DTLs.
*/
/*
* If the config changed, notify the scrub thread that it must restart.
*/
}
/*
* Verify the metaslab classes.
*/
/*
* Panic the system if the specified tag requires it. This
* is useful for ensuring that configurations are updated
* transactionally.
*/
/*
* Note: this txg_wait_synced() is important because it ensures
* that there won't be more than one config change per txg.
* This allows us to use the txg as the generation number.
*/
if (error == 0)
}
/*
* If the config changed, update the config cache.
*/
if (config_changed)
}
/*
* Unlock the spa_t after adding or removing a vdev. Besides undoing the
* locking of spa_vdev_enter(), we also want make sure the transactions have
* synced to disk, and then update the global configuration cache with the new
* information.
*/
int
{
return (error);
}
/*
* Lock the given spa_t for the purpose of changing vdev state.
*/
void
{
}
int
{
0, 0, B_FALSE);
}
/*
* If anything changed, wait for it to sync. This ensures that,
* from the system administrator's perspective, zpool(1M) commands
* are synchronous. This is important for things like zpool offline:
* when the command completes, you expect no further I/O from ZFS.
*/
return (error);
}
/*
* ==========================================================================
* Miscellaneous functions
* ==========================================================================
*/
/*
* Rename a spa_t.
*/
int
{
int err;
/*
* Lookup the spa_t and grab the config lock for writing. We need to
* actually open the pool so that we can sync out the necessary labels.
* It's OK to call spa_open() with the namespace lock held because we
* allow recursive calls for other reasons.
*/
return (err);
}
/*
* Sync all labels to disk with the new names by marking the root vdev
* dirty and waiting for it to sync. It will pick up the new pool name
* during the sync.
*/
/*
* Sync the updated config cache.
*/
return (0);
}
/*
* Determine whether a pool with given pool_guid exists. If device_guid is
* non-zero, determine whether the pool exists *and* contains a device with the
* specified device_guid.
*/
{
avl_tree_t *t = &spa_namespace_avl;
continue;
continue;
if (device_guid == 0)
break;
device_guid) != NULL)
break;
/*
* Check any devices we may be in the process of adding.
*/
if (spa->spa_pending_vdev) {
device_guid) != NULL)
break;
}
}
}
}
char *
spa_strdup(const char *s)
{
char *new;
return (new);
}
void
spa_strfree(char *s)
{
}
{
uint64_t r;
(void) random_get_pseudo_bytes((void *)&r, sizeof (uint64_t));
return (r % range);
}
{
} else {
}
return (guid);
}
void
{
}
}
void
{
uint64_t freeze_txg = 0;
}
if (freeze_txg != 0)
}
void
zfs_panic_recover(const char *fmt, ...)
{
}
/*
* ==========================================================================
* Accessor functions
* ==========================================================================
*/
{
return (spa->spa_async_suspended);
}
{
return (spa->spa_dsl_pool);
}
blkptr_t *
{
}
void
{
}
void
{
buf[0] = '\0';
else
}
int
{
return (spa->spa_sync_pass);
}
char *
{
}
{
/*
* If we fail to parse the config during spa_load(), we can go through
* the error path (which posts an ereport) and end up here with no root
* vdev. We stash the original pool guid in 'spa_load_guid' to handle
* this case.
*/
else
return (spa->spa_load_guid);
}
{
}
{
return (spa->spa_first_txg);
}
{
return (spa->spa_syncing_txg);
}
{
}
{
return (spa->spa_load_state);
}
{
return (spa->spa_freeze_txg);
}
/* ARGSUSED */
{
/*
* The worst case is single-sector max-parity RAID-Z blocks, in which
* case the space requirement is exactly (VDEV_RAIDZ_MAXPARITY + 1)
* times the size; so just assume that. Add to this the fact that
* we can have up to 3 DVAs per bp, and one more factor of 2 because
* the block may be dittoed with up to 3 DVAs by ddt_sync().
*/
}
{
return (spa->spa_dspace);
}
void
{
}
/*
* Return the failure mode that has been set to this pool. The default
*/
{
return (spa->spa_failmode);
}
{
return (spa->spa_suspended);
}
{
}
{
return (spa->spa_deflate);
}
{
return (spa->spa_normal_class);
}
{
return (spa->spa_log_class);
}
int
{
/*
* As of SPA_VERSION == SPA_VERSION_DITTO_BLOCKS, we are able to
* handle BPs with more than one DVA allocated. Set our max
* replication level accordingly.
*/
return (1);
}
{
}
return (dsize);
}
{
for (int d = 0; d < SPA_DVAS_PER_BP; d++)
return (dsize);
}
{
for (int d = 0; d < SPA_DVAS_PER_BP; d++)
return (dsize);
}
/*
* ==========================================================================
* Initialization and Termination
* ==========================================================================
*/
static int
{
int s;
if (s > 0)
return (1);
if (s < 0)
return (-1);
return (0);
}
int
spa_busy(void)
{
return (spa_active_count);
}
void
{
}
void
{
unique_init();
zio_init();
dmu_init();
zil_init();
l2arc_start();
}
void
spa_fini(void)
{
l2arc_stop();
zil_fini();
dmu_fini();
zio_fini();
unique_fini();
}
/*
* Return whether this pool has slogs. No locking needed.
* It's not a problem if the wrong answer is returned as it's only for
* performance and not correctness
*/
{
}
{
return (spa->spa_log_state);
}
void
{
}
{
return (spa->spa_is_root);
}
{
}
int
{
}
{
return (spa->spa_bootfs);
}
{
return (spa->spa_delegation);
}
objset_t *
{
return (spa->spa_meta_objset);
}
enum zio_checksum
{
return (spa->spa_dedup_checksum);
}