* 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.
+ * or https://opensource.org/licenses/CDDL-1.0.
* See the License for the specific language governing permissions
* and limitations under the License.
*
*/
/*
* Copyright (c) 2005, 2010, Oracle and/or its affiliates. All rights reserved.
- * Copyright (c) 2011, 2017 by Delphix. All rights reserved.
+ * Copyright (c) 2011, 2019 by Delphix. All rights reserved.
* Copyright 2015 Nexenta Systems, Inc. All rights reserved.
* Copyright (c) 2014 Spectra Logic Corporation, All rights reserved.
* Copyright 2013 Saso Kiselkov. All rights reserved.
* Copyright (c) 2017 Datto Inc.
+ * Copyright (c) 2017, Intel Corporation.
+ * Copyright (c) 2019, loli10K <ezomori.nozomu@gmail.com>. All rights reserved.
+ * Copyright (c) 2023, Klara Inc.
*/
#include <sys/zfs_context.h>
+#include <sys/zfs_chksum.h>
#include <sys/spa_impl.h>
#include <sys/zio.h>
#include <sys/zio_checksum.h>
#include <sys/zap.h>
#include <sys/zil.h>
#include <sys/vdev_impl.h>
+#include <sys/vdev_initialize.h>
+#include <sys/vdev_trim.h>
#include <sys/vdev_file.h>
#include <sys/vdev_raidz.h>
#include <sys/metaslab.h>
#include <sys/fs/zfs.h>
#include <sys/metaslab_impl.h>
#include <sys/arc.h>
+#include <sys/brt.h>
#include <sys/ddt.h>
#include <sys/kstat.h>
#include "zfs_prop.h"
+#include <sys/btree.h>
#include <sys/zfeature.h>
-#include "qat.h"
+#include <sys/qat.h>
+#include <sys/zstd/zstd.h>
/*
* SPA locking
*
- * There are four basic locks for managing spa_t structures:
+ * There are three basic locks for managing spa_t structures:
*
* spa_namespace_lock (global mutex)
*
* 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)
+ * spa_refcount (per-spa zfs_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,
* 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 it requires
- * manipulation of the namespace.
*/
static avl_tree_t spa_namespace_avl;
kmutex_t spa_namespace_lock;
static kcondvar_t spa_namespace_cv;
-int spa_max_replication_override = SPA_DVAS_PER_BP;
+static const int spa_max_replication_override = SPA_DVAS_PER_BP;
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;
-kmem_cache_t *spa_buffer_pool;
-int spa_mode_global;
+spa_mode_t spa_mode_global = SPA_MODE_UNINIT;
#ifdef ZFS_DEBUG
/*
* has not completed in zfs_deadman_synctime_ms is considered "hung" resulting
* in one of three behaviors controlled by zfs_deadman_failmode.
*/
-unsigned long zfs_deadman_synctime_ms = 600000ULL;
+uint64_t zfs_deadman_synctime_ms = 600000UL; /* 10 min. */
/*
* This value controls the maximum amount of time zio_wait() will block for an
* outstanding IO. By default this is 300 seconds at which point the "hung"
* behavior will be applied as described for zfs_deadman_synctime_ms.
*/
-unsigned long zfs_deadman_ziotime_ms = 300000ULL;
+uint64_t zfs_deadman_ziotime_ms = 300000UL; /* 5 min. */
/*
* Check time in milliseconds. This defines the frequency at which we check
* for hung I/O.
*/
-unsigned long zfs_deadman_checktime_ms = 60000ULL;
+uint64_t zfs_deadman_checktime_ms = 60000UL; /* 1 min. */
/*
* By default the deadman is enabled.
*/
-int zfs_deadman_enabled = 1;
+int zfs_deadman_enabled = B_TRUE;
/*
* Controls the behavior of the deadman when it detects a "hung" I/O.
* continue - Attempt to recover from a "hung" I/O
* panic - Panic the system
*/
-char *zfs_deadman_failmode = "wait";
+const char *zfs_deadman_failmode = "wait";
/*
* The worst case is single-sector max-parity RAID-Z blocks, in which
* the worst case is:
* (VDEV_RAIDZ_MAXPARITY + 1) * SPA_DVAS_PER_BP * 2 == 24
*/
-int spa_asize_inflation = 24;
+uint_t spa_asize_inflation = 24;
/*
* Normally, we don't allow the last 3.2% (1/(2^spa_slop_shift)) of space in
- * the pool to be consumed. This ensures that we don't run the pool
- * completely out of space, due to unaccounted changes (e.g. to the MOS).
- * It also limits the worst-case time to allocate space. If we have
- * less than this amount of free space, most ZPL operations (e.g. write,
- * create) will return ENOSPC.
+ * the pool to be consumed (bounded by spa_max_slop). This ensures that we
+ * don't run the pool completely out of space, due to unaccounted changes (e.g.
+ * to the MOS). It also limits the worst-case time to allocate space. If we
+ * have less than this amount of free space, most ZPL operations (e.g. write,
+ * create) will return ENOSPC. The ZIL metaslabs (spa_embedded_log_class) are
+ * also part of this 3.2% of space which can't be consumed by normal writes;
+ * the slop space "proper" (spa_get_slop_space()) is decreased by the embedded
+ * log space.
*
* Certain operations (e.g. file removal, most administrative actions) can
* use half the slop space. They will only return ENOSPC if less than half
* These are the operations that call dsl_pool_adjustedsize() with the netfree
* argument set to TRUE.
*
+ * Operations that are almost guaranteed to free up space in the absence of
+ * a pool checkpoint can use up to three quarters of the slop space
+ * (e.g zfs destroy).
+ *
* A very restricted set of operations are always permitted, regardless of
* the amount of free space. These are the operations that call
- * dsl_sync_task(ZFS_SPACE_CHECK_NONE), e.g. "zfs destroy". If these
- * operations result in a net increase in the amount of space used,
- * it is possible to run the pool completely out of space, causing it to
- * be permanently read-only.
+ * dsl_sync_task(ZFS_SPACE_CHECK_NONE). If these operations result in a net
+ * increase in the amount of space used, it is possible to run the pool
+ * completely out of space, causing it to be permanently read-only.
*
* Note that on very small pools, the slop space will be larger than
* 3.2%, in an effort to have it be at least spa_min_slop (128MB),
* but we never allow it to be more than half the pool size.
*
+ * Further, on very large pools, the slop space will be smaller than
+ * 3.2%, to avoid reserving much more space than we actually need; bounded
+ * by spa_max_slop (128GB).
+ *
* See also the comments in zfs_space_check_t.
*/
-int spa_slop_shift = 5;
-uint64_t spa_min_slop = 128 * 1024 * 1024;
+uint_t spa_slop_shift = 5;
+static const uint64_t spa_min_slop = 128ULL * 1024 * 1024;
+static const uint64_t spa_max_slop = 128ULL * 1024 * 1024 * 1024;
+
+/*
+ * Number of allocators to use, per spa instance
+ */
+static int spa_num_allocators = 4;
+
+/*
+ * Spa active allocator.
+ * Valid values are zfs_active_allocator=<dynamic|cursor|new-dynamic>.
+ */
+const char *zfs_active_allocator = "dynamic";
+
+void
+spa_load_failed(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+ char buf[256];
+
+ va_start(adx, fmt);
+ (void) vsnprintf(buf, sizeof (buf), fmt, adx);
+ va_end(adx);
+
+ zfs_dbgmsg("spa_load(%s, config %s): FAILED: %s", spa->spa_name,
+ spa->spa_trust_config ? "trusted" : "untrusted", buf);
+}
+
+void
+spa_load_note(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+ char buf[256];
+
+ va_start(adx, fmt);
+ (void) vsnprintf(buf, sizeof (buf), fmt, adx);
+ va_end(adx);
+
+ zfs_dbgmsg("spa_load(%s, config %s): %s", spa->spa_name,
+ spa->spa_trust_config ? "trusted" : "untrusted", buf);
+
+ spa_import_progress_set_notes_nolog(spa, "%s", buf);
+}
+
+/*
+ * By default dedup and user data indirects land in the special class
+ */
+static int zfs_ddt_data_is_special = B_TRUE;
+static int zfs_user_indirect_is_special = B_TRUE;
+
+/*
+ * The percentage of special class final space reserved for metadata only.
+ * Once we allocate 100 - zfs_special_class_metadata_reserve_pct we only
+ * let metadata into the class.
+ */
+static uint_t zfs_special_class_metadata_reserve_pct = 25;
/*
* ==========================================================================
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_init(&scl->scl_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&scl->scl_cv, NULL, CV_DEFAULT, NULL);
- refcount_create_untracked(&scl->scl_count);
scl->scl_writer = NULL;
scl->scl_write_wanted = 0;
+ scl->scl_count = 0;
}
}
spa_config_lock_t *scl = &spa->spa_config_lock[i];
mutex_destroy(&scl->scl_lock);
cv_destroy(&scl->scl_cv);
- refcount_destroy(&scl->scl_count);
ASSERT(scl->scl_writer == NULL);
ASSERT(scl->scl_write_wanted == 0);
+ ASSERT(scl->scl_count == 0);
}
}
int
-spa_config_tryenter(spa_t *spa, int locks, void *tag, krw_t rw)
+spa_config_tryenter(spa_t *spa, int locks, const void *tag, krw_t rw)
{
for (int i = 0; i < SCL_LOCKS; i++) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
}
} else {
ASSERT(scl->scl_writer != curthread);
- if (!refcount_is_zero(&scl->scl_count)) {
+ if (scl->scl_count != 0) {
mutex_exit(&scl->scl_lock);
spa_config_exit(spa, locks & ((1 << i) - 1),
tag);
}
scl->scl_writer = curthread;
}
- (void) refcount_add(&scl->scl_count, tag);
+ scl->scl_count++;
mutex_exit(&scl->scl_lock);
}
return (1);
}
-void
-spa_config_enter(spa_t *spa, int locks, void *tag, krw_t rw)
+static void
+spa_config_enter_impl(spa_t *spa, int locks, const void *tag, krw_t rw,
+ int mmp_flag)
{
+ (void) tag;
int wlocks_held = 0;
ASSERT3U(SCL_LOCKS, <, sizeof (wlocks_held) * NBBY);
continue;
mutex_enter(&scl->scl_lock);
if (rw == RW_READER) {
- while (scl->scl_writer || scl->scl_write_wanted) {
+ while (scl->scl_writer ||
+ (!mmp_flag && scl->scl_write_wanted)) {
cv_wait(&scl->scl_cv, &scl->scl_lock);
}
} else {
ASSERT(scl->scl_writer != curthread);
- while (!refcount_is_zero(&scl->scl_count)) {
+ while (scl->scl_count != 0) {
scl->scl_write_wanted++;
cv_wait(&scl->scl_cv, &scl->scl_lock);
scl->scl_write_wanted--;
}
scl->scl_writer = curthread;
}
- (void) refcount_add(&scl->scl_count, tag);
+ scl->scl_count++;
mutex_exit(&scl->scl_lock);
}
ASSERT3U(wlocks_held, <=, locks);
}
void
-spa_config_exit(spa_t *spa, int locks, void *tag)
+spa_config_enter(spa_t *spa, int locks, const void *tag, krw_t rw)
+{
+ spa_config_enter_impl(spa, locks, tag, rw, 0);
+}
+
+/*
+ * The spa_config_enter_mmp() allows the mmp thread to cut in front of
+ * outstanding write lock requests. This is needed since the mmp updates are
+ * time sensitive and failure to service them promptly will result in a
+ * suspended pool. This pool suspension has been seen in practice when there is
+ * a single disk in a pool that is responding slowly and presumably about to
+ * fail.
+ */
+
+void
+spa_config_enter_mmp(spa_t *spa, int locks, const void *tag, krw_t rw)
{
+ spa_config_enter_impl(spa, locks, tag, rw, 1);
+}
+
+void
+spa_config_exit(spa_t *spa, int locks, const void *tag)
+{
+ (void) tag;
for (int i = SCL_LOCKS - 1; i >= 0; i--) {
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
mutex_enter(&scl->scl_lock);
- ASSERT(!refcount_is_zero(&scl->scl_count));
- if (refcount_remove(&scl->scl_count, tag) == 0) {
+ ASSERT(scl->scl_count > 0);
+ if (--scl->scl_count == 0) {
ASSERT(scl->scl_writer == NULL ||
scl->scl_writer == curthread);
scl->scl_writer = NULL; /* OK in either case */
spa_config_lock_t *scl = &spa->spa_config_lock[i];
if (!(locks & (1 << i)))
continue;
- if ((rw == RW_READER && !refcount_is_zero(&scl->scl_count)) ||
+ if ((rw == RW_READER && scl->scl_count != 0) ||
(rw == RW_WRITER && scl->scl_writer == curthread))
locks_held |= 1 << i;
}
zfs_dbgmsg("slow spa_sync: started %llu seconds ago, calls %llu",
(gethrtime() - spa->spa_sync_starttime) / NANOSEC,
- ++spa->spa_deadman_calls);
+ (u_longlong_t)++spa->spa_deadman_calls);
if (zfs_deadman_enabled)
vdev_deadman(spa->spa_root_vdev, FTAG);
MSEC_TO_TICK(zfs_deadman_checktime_ms));
}
+static int
+spa_log_sm_sort_by_txg(const void *va, const void *vb)
+{
+ const spa_log_sm_t *a = va;
+ const spa_log_sm_t *b = vb;
+
+ return (TREE_CMP(a->sls_txg, b->sls_txg));
+}
+
/*
* Create an uninitialized spa_t with the given name. Requires
* spa_namespace_lock. The caller must ensure that the spa_t doesn't already
mutex_init(&spa->spa_suspend_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa->spa_vdev_top_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa->spa_feat_stats_lock, NULL, MUTEX_DEFAULT, NULL);
- mutex_init(&spa->spa_alloc_lock, NULL, MUTEX_DEFAULT, NULL);
+ mutex_init(&spa->spa_flushed_ms_lock, NULL, MUTEX_DEFAULT, NULL);
+ mutex_init(&spa->spa_activities_lock, NULL, MUTEX_DEFAULT, NULL);
cv_init(&spa->spa_async_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_evicting_os_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_proc_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_scrub_io_cv, NULL, CV_DEFAULT, NULL);
cv_init(&spa->spa_suspend_cv, NULL, CV_DEFAULT, NULL);
+ cv_init(&spa->spa_activities_cv, NULL, CV_DEFAULT, NULL);
+ cv_init(&spa->spa_waiters_cv, NULL, CV_DEFAULT, NULL);
for (int t = 0; t < TXG_SIZE; t++)
bplist_create(&spa->spa_free_bplist[t]);
spa->spa_load_max_txg = UINT64_MAX;
spa->spa_proc = &p0;
spa->spa_proc_state = SPA_PROC_NONE;
+ spa->spa_trust_config = B_TRUE;
+ spa->spa_hostid = zone_get_hostid(NULL);
spa->spa_deadman_synctime = MSEC2NSEC(zfs_deadman_synctime_ms);
spa->spa_deadman_ziotime = MSEC2NSEC(zfs_deadman_ziotime_ms);
spa_set_deadman_failmode(spa, zfs_deadman_failmode);
+ spa_set_allocator(spa, zfs_active_allocator);
- refcount_create(&spa->spa_refcount);
+ zfs_refcount_create(&spa->spa_refcount);
spa_config_lock_init(spa);
spa_stats_init(spa);
if (altroot)
spa->spa_root = spa_strdup(altroot);
- avl_create(&spa->spa_alloc_tree, zio_bookmark_compare,
- sizeof (zio_t), offsetof(zio_t, io_alloc_node));
+ /* Do not allow more allocators than CPUs. */
+ spa->spa_alloc_count = MIN(MAX(spa_num_allocators, 1), boot_ncpus);
+
+ spa->spa_allocs = kmem_zalloc(spa->spa_alloc_count *
+ sizeof (spa_alloc_t), KM_SLEEP);
+ for (int i = 0; i < spa->spa_alloc_count; i++) {
+ mutex_init(&spa->spa_allocs[i].spaa_lock, NULL, MUTEX_DEFAULT,
+ NULL);
+ avl_create(&spa->spa_allocs[i].spaa_tree, zio_bookmark_compare,
+ sizeof (zio_t), offsetof(zio_t, io_queue_node.a));
+ }
+
+ avl_create(&spa->spa_metaslabs_by_flushed, metaslab_sort_by_flushed,
+ sizeof (metaslab_t), offsetof(metaslab_t, ms_spa_txg_node));
+ avl_create(&spa->spa_sm_logs_by_txg, spa_log_sm_sort_by_txg,
+ sizeof (spa_log_sm_t), offsetof(spa_log_sm_t, sls_node));
+ list_create(&spa->spa_log_summary, sizeof (log_summary_entry_t),
+ offsetof(log_summary_entry_t, lse_node));
/*
* Every pool starts with the default cachefile
spa->spa_min_ashift = INT_MAX;
spa->spa_max_ashift = 0;
+ spa->spa_min_alloc = INT_MAX;
+ spa->spa_gcd_alloc = INT_MAX;
/* Reset cached value */
spa->spa_dedup_dspace = ~0ULL;
spa->spa_feat_refcount_cache[i] = SPA_FEATURE_DISABLED;
}
+ list_create(&spa->spa_leaf_list, sizeof (vdev_t),
+ offsetof(vdev_t, vdev_leaf_node));
+
return (spa);
}
spa_config_dirent_t *dp;
ASSERT(MUTEX_HELD(&spa_namespace_lock));
- ASSERT(spa->spa_state == POOL_STATE_UNINITIALIZED);
- ASSERT3U(refcount_count(&spa->spa_refcount), ==, 0);
+ ASSERT(spa_state(spa) == POOL_STATE_UNINITIALIZED);
+ ASSERT3U(zfs_refcount_count(&spa->spa_refcount), ==, 0);
+ ASSERT0(spa->spa_waiters);
nvlist_free(spa->spa_config_splitting);
if (spa->spa_root)
spa_strfree(spa->spa_root);
- while ((dp = list_head(&spa->spa_config_list)) != NULL) {
- list_remove(&spa->spa_config_list, dp);
+ while ((dp = list_remove_head(&spa->spa_config_list)) != NULL) {
if (dp->scd_path != NULL)
spa_strfree(dp->scd_path);
kmem_free(dp, sizeof (spa_config_dirent_t));
}
- avl_destroy(&spa->spa_alloc_tree);
+ for (int i = 0; i < spa->spa_alloc_count; i++) {
+ avl_destroy(&spa->spa_allocs[i].spaa_tree);
+ mutex_destroy(&spa->spa_allocs[i].spaa_lock);
+ }
+ kmem_free(spa->spa_allocs, spa->spa_alloc_count *
+ sizeof (spa_alloc_t));
+
+ avl_destroy(&spa->spa_metaslabs_by_flushed);
+ avl_destroy(&spa->spa_sm_logs_by_txg);
+ list_destroy(&spa->spa_log_summary);
list_destroy(&spa->spa_config_list);
+ list_destroy(&spa->spa_leaf_list);
nvlist_free(spa->spa_label_features);
nvlist_free(spa->spa_load_info);
nvlist_free(spa->spa_feat_stats);
spa_config_set(spa, NULL);
- refcount_destroy(&spa->spa_refcount);
+ zfs_refcount_destroy(&spa->spa_refcount);
spa_stats_destroy(spa);
spa_config_lock_destroy(spa);
cv_destroy(&spa->spa_proc_cv);
cv_destroy(&spa->spa_scrub_io_cv);
cv_destroy(&spa->spa_suspend_cv);
+ cv_destroy(&spa->spa_activities_cv);
+ cv_destroy(&spa->spa_waiters_cv);
- mutex_destroy(&spa->spa_alloc_lock);
+ mutex_destroy(&spa->spa_flushed_ms_lock);
mutex_destroy(&spa->spa_async_lock);
mutex_destroy(&spa->spa_errlist_lock);
mutex_destroy(&spa->spa_errlog_lock);
mutex_destroy(&spa->spa_suspend_lock);
mutex_destroy(&spa->spa_vdev_top_lock);
mutex_destroy(&spa->spa_feat_stats_lock);
+ mutex_destroy(&spa->spa_activities_lock);
kmem_free(spa, sizeof (spa_t));
}
* have the namespace lock held.
*/
void
-spa_open_ref(spa_t *spa, void *tag)
+spa_open_ref(spa_t *spa, const void *tag)
{
- ASSERT(refcount_count(&spa->spa_refcount) >= spa->spa_minref ||
+ ASSERT(zfs_refcount_count(&spa->spa_refcount) >= spa->spa_minref ||
MUTEX_HELD(&spa_namespace_lock));
- (void) refcount_add(&spa->spa_refcount, tag);
+ (void) zfs_refcount_add(&spa->spa_refcount, tag);
}
/*
* have the namespace lock held.
*/
void
-spa_close(spa_t *spa, void *tag)
+spa_close(spa_t *spa, const void *tag)
{
- ASSERT(refcount_count(&spa->spa_refcount) > spa->spa_minref ||
+ ASSERT(zfs_refcount_count(&spa->spa_refcount) > spa->spa_minref ||
MUTEX_HELD(&spa_namespace_lock));
- (void) refcount_remove(&spa->spa_refcount, tag);
+ (void) zfs_refcount_remove(&spa->spa_refcount, tag);
}
/*
* so the asserts in spa_close() do not apply.
*/
void
-spa_async_close(spa_t *spa, void *tag)
+spa_async_close(spa_t *spa, const void *tag)
{
- (void) refcount_remove(&spa->spa_refcount, tag);
+ (void) zfs_refcount_remove(&spa->spa_refcount, tag);
}
/*
{
ASSERT(MUTEX_HELD(&spa_namespace_lock));
- return (refcount_count(&spa->spa_refcount) == spa->spa_minref);
+ return (zfs_refcount_count(&spa->spa_refcount) == spa->spa_minref);
}
/*
const spa_aux_t *sa = (const spa_aux_t *)a;
const spa_aux_t *sb = (const spa_aux_t *)b;
- return (AVL_CMP(sa->aux_guid, sb->aux_guid));
+ return (TREE_CMP(sa->aux_guid, sb->aux_guid));
}
-void
+static void
spa_aux_add(vdev_t *vd, avl_tree_t *avl)
{
avl_index_t where;
}
}
-void
+static void
spa_aux_remove(vdev_t *vd, avl_tree_t *avl)
{
spa_aux_t search;
}
}
-boolean_t
+static boolean_t
spa_aux_exists(uint64_t guid, uint64_t *pool, int *refcnt, avl_tree_t *avl)
{
spa_aux_t search, *found;
return (found != NULL);
}
-void
+static void
spa_aux_activate(vdev_t *vd, avl_tree_t *avl)
{
spa_aux_t search, *found;
/*
* 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
+ * - 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
+ * - 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
{
mutex_enter(&spa->spa_vdev_top_lock);
mutex_enter(&spa_namespace_lock);
+
+ vdev_autotrim_stop_all(spa);
+
+ return (spa_vdev_config_enter(spa));
+}
+
+/*
+ * The same as spa_vdev_enter() above but additionally takes the guid of
+ * the vdev being detached. When there is a rebuild in process it will be
+ * suspended while the vdev tree is modified then resumed by spa_vdev_exit().
+ * The rebuild is canceled if only a single child remains after the detach.
+ */
+uint64_t
+spa_vdev_detach_enter(spa_t *spa, uint64_t guid)
+{
+ mutex_enter(&spa->spa_vdev_top_lock);
+ mutex_enter(&spa_namespace_lock);
+
+ vdev_autotrim_stop_all(spa);
+
+ if (guid != 0) {
+ vdev_t *vd = spa_lookup_by_guid(spa, guid, B_FALSE);
+ if (vd) {
+ vdev_rebuild_stop_wait(vd->vdev_top);
+ }
+ }
+
return (spa_vdev_config_enter(spa));
}
* of multiple transactions without releasing the spa_namespace_lock.
*/
void
-spa_vdev_config_exit(spa_t *spa, vdev_t *vd, uint64_t txg, int error, char *tag)
+spa_vdev_config_exit(spa_t *spa, vdev_t *vd, uint64_t txg, int error,
+ const char *tag)
{
ASSERT(MUTEX_HELD(&spa_namespace_lock));
/*
* Reassess the DTLs.
*/
- vdev_dtl_reassess(spa->spa_root_vdev, 0, 0, B_FALSE);
+ vdev_dtl_reassess(spa->spa_root_vdev, 0, 0, B_FALSE, B_FALSE);
if (error == 0 && !list_is_empty(&spa->spa_config_dirty_list)) {
config_changed = B_TRUE;
*/
ASSERT(metaslab_class_validate(spa_normal_class(spa)) == 0);
ASSERT(metaslab_class_validate(spa_log_class(spa)) == 0);
+ ASSERT(metaslab_class_validate(spa_embedded_log_class(spa)) == 0);
+ ASSERT(metaslab_class_validate(spa_special_class(spa)) == 0);
+ ASSERT(metaslab_class_validate(spa_dedup_class(spa)) == 0);
spa_config_exit(spa, SCL_ALL, spa);
if (vd != NULL) {
ASSERT(!vd->vdev_detached || vd->vdev_dtl_sm == NULL);
- spa_config_enter(spa, SCL_ALL, spa, RW_WRITER);
+ if (vd->vdev_ops->vdev_op_leaf) {
+ mutex_enter(&vd->vdev_initialize_lock);
+ vdev_initialize_stop(vd, VDEV_INITIALIZE_CANCELED,
+ NULL);
+ mutex_exit(&vd->vdev_initialize_lock);
+
+ mutex_enter(&vd->vdev_trim_lock);
+ vdev_trim_stop(vd, VDEV_TRIM_CANCELED, NULL);
+ mutex_exit(&vd->vdev_trim_lock);
+ }
+
+ /*
+ * The vdev may be both a leaf and top-level device.
+ */
+ vdev_autotrim_stop_wait(vd);
+
+ spa_config_enter(spa, SCL_STATE_ALL, spa, RW_WRITER);
vdev_free(vd);
- spa_config_exit(spa, SCL_ALL, spa);
+ spa_config_exit(spa, SCL_STATE_ALL, spa);
}
/*
* If the config changed, update the config cache.
*/
if (config_changed)
- spa_write_cachefile(spa, B_FALSE, B_TRUE);
+ spa_write_cachefile(spa, B_FALSE, B_TRUE, B_TRUE);
}
/*
int
spa_vdev_exit(spa_t *spa, vdev_t *vd, uint64_t txg, int error)
{
+ vdev_autotrim_restart(spa);
+ vdev_rebuild_restart(spa);
+
spa_vdev_config_exit(spa, vd, txg, error, FTAG);
mutex_exit(&spa_namespace_lock);
mutex_exit(&spa->spa_vdev_top_lock);
}
if (vd != NULL || error == 0)
- vdev_dtl_reassess(vdev_top, 0, 0, B_FALSE);
+ vdev_dtl_reassess(vdev_top, 0, 0, B_FALSE, B_FALSE);
if (vd != NULL) {
if (vd != spa->spa_root_vdev)
/*
* If anything changed, wait for it to sync. This ensures that,
- * from the system administrator's perspective, zpool(1M) commands
+ * from the system administrator's perspective, zpool(8) commands
* are synchronous. This is important for things like zpool offline:
* when the command completes, you expect no further I/O from ZFS.
*/
*/
if (config_changed) {
mutex_enter(&spa_namespace_lock);
- spa_write_cachefile(spa, B_FALSE, B_TRUE);
+ spa_write_cachefile(spa, B_FALSE, B_TRUE, B_FALSE);
mutex_exit(&spa_namespace_lock);
}
vdev_config_dirty(spa->spa_root_vdev);
}
-/*
- * Rename a spa_t.
- */
-int
-spa_rename(const char *name, const char *newname)
-{
- spa_t *spa;
- 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.
- */
- mutex_enter(&spa_namespace_lock);
- if ((err = spa_open(name, &spa, FTAG)) != 0) {
- mutex_exit(&spa_namespace_lock);
- return (err);
- }
-
- spa_config_enter(spa, SCL_ALL, FTAG, RW_WRITER);
-
- avl_remove(&spa_namespace_avl, spa);
- (void) strlcpy(spa->spa_name, newname, sizeof (spa->spa_name));
- avl_add(&spa_namespace_avl, spa);
-
- /*
- * 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.
- */
- vdev_config_dirty(spa->spa_root_vdev);
-
- spa_config_exit(spa, SCL_ALL, FTAG);
-
- txg_wait_synced(spa->spa_dsl_pool, 0);
-
- /*
- * Sync the updated config cache.
- */
- spa_write_cachefile(spa, B_FALSE, B_TRUE);
-
- spa_close(spa, FTAG);
-
- mutex_exit(&spa_namespace_lock);
-
- return (0);
-}
-
/*
* Return the spa_t associated with given pool_guid, if it exists. If
* device_guid is non-zero, determine whether the pool exists *and* contains
len = strlen(s);
new = kmem_alloc(len + 1, KM_SLEEP);
- bcopy(s, new, len);
- new[len] = '\0';
+ memcpy(new, s, len + 1);
return (new);
}
kmem_free(s, strlen(s) + 1);
}
-uint64_t
-spa_get_random(uint64_t range)
-{
- uint64_t r;
-
- ASSERT(range != 0);
-
- if (range == 1)
- return (0);
-
- (void) random_get_pseudo_bytes((void *)&r, sizeof (uint64_t));
-
- return (r % range);
-}
-
uint64_t
spa_generate_guid(spa_t *spa)
{
- uint64_t guid = spa_get_random(-1ULL);
+ uint64_t guid;
if (spa != NULL) {
- while (guid == 0 || spa_guid_exists(spa_guid(spa), guid))
- guid = spa_get_random(-1ULL);
+ do {
+ (void) random_get_pseudo_bytes((void *)&guid,
+ sizeof (guid));
+ } while (guid == 0 || spa_guid_exists(spa_guid(spa), guid));
} else {
- while (guid == 0 || spa_guid_exists(guid, 0))
- guid = spa_get_random(-1ULL);
+ do {
+ (void) random_get_pseudo_bytes((void *)&guid,
+ sizeof (guid));
+ } while (guid == 0 || spa_guid_exists(guid, 0));
}
return (guid);
snprintf_blkptr(char *buf, size_t buflen, const blkptr_t *bp)
{
char type[256];
- char *checksum = NULL;
- char *compress = NULL;
+ const char *checksum = NULL;
+ const char *compress = NULL;
if (bp != NULL) {
if (BP_GET_TYPE(bp) & DMU_OT_NEWTYPE) {
compress = zio_compress_table[BP_GET_COMPRESS(bp)].ci_name;
}
- SNPRINTF_BLKPTR(snprintf, ' ', buf, buflen, bp, type, checksum,
+ SNPRINTF_BLKPTR(kmem_scnprintf, ' ', buf, buflen, bp, type, checksum,
compress);
}
return (val);
}
+void
+spa_activate_allocation_classes(spa_t *spa, dmu_tx_t *tx)
+{
+ /*
+ * We bump the feature refcount for each special vdev added to the pool
+ */
+ ASSERT(spa_feature_is_enabled(spa, SPA_FEATURE_ALLOCATION_CLASSES));
+ spa_feature_incr(spa, SPA_FEATURE_ALLOCATION_CLASSES, tx);
+}
+
/*
* ==========================================================================
* Accessor functions
if (spa->spa_root == NULL)
buf[0] = '\0';
else
- (void) strncpy(buf, spa->spa_root, buflen);
+ (void) strlcpy(buf, spa->spa_root, buflen);
}
-int
+uint32_t
spa_sync_pass(spa_t *spa)
{
return (spa->spa_sync_pass);
}
/*
- * Return the amount of slop space in bytes. It is 1/32 of the pool (3.2%),
- * or at least 128MB, unless that would cause it to be more than half the
- * pool size.
- *
- * See the comment above spa_slop_shift for details.
+ * Return the amount of slop space in bytes. It is typically 1/32 of the pool
+ * (3.2%), minus the embedded log space. On very small pools, it may be
+ * slightly larger than this. On very large pools, it will be capped to
+ * the value of spa_max_slop. The embedded log space is not included in
+ * spa_dspace. By subtracting it, the usable space (per "zfs list") is a
+ * constant 97% of the total space, regardless of metaslab size (assuming the
+ * default spa_slop_shift=5 and a non-tiny pool).
+ *
+ * See the comment above spa_slop_shift for more details.
*/
uint64_t
spa_get_slop_space(spa_t *spa)
{
- uint64_t space = spa_get_dspace(spa);
- return (MAX(space >> spa_slop_shift, MIN(space >> 1, spa_min_slop)));
+ uint64_t space = 0;
+ uint64_t slop = 0;
+
+ /*
+ * Make sure spa_dedup_dspace has been set.
+ */
+ if (spa->spa_dedup_dspace == ~0ULL)
+ spa_update_dspace(spa);
+
+ /*
+ * spa_get_dspace() includes the space only logically "used" by
+ * deduplicated data, so since it's not useful to reserve more
+ * space with more deduplicated data, we subtract that out here.
+ */
+ space = spa_get_dspace(spa) - spa->spa_dedup_dspace;
+ slop = MIN(space >> spa_slop_shift, spa_max_slop);
+
+ /*
+ * Subtract the embedded log space, but no more than half the (3.2%)
+ * unusable space. Note, the "no more than half" is only relevant if
+ * zfs_embedded_slog_min_ms >> spa_slop_shift < 2, which is not true by
+ * default.
+ */
+ uint64_t embedded_log =
+ metaslab_class_get_dspace(spa_embedded_log_class(spa));
+ slop -= MIN(embedded_log, slop >> 1);
+
+ /*
+ * Slop space should be at least spa_min_slop, but no more than half
+ * the entire pool.
+ */
+ slop = MAX(slop, MIN(space >> 1, spa_min_slop));
+ return (slop);
}
uint64_t
return (spa->spa_dspace);
}
+uint64_t
+spa_get_checkpoint_space(spa_t *spa)
+{
+ return (spa->spa_checkpoint_info.sci_dspace);
+}
+
void
spa_update_dspace(spa_t *spa)
{
spa->spa_dspace = metaslab_class_get_dspace(spa_normal_class(spa)) +
- ddt_get_dedup_dspace(spa);
- if (spa->spa_vdev_removal != NULL) {
+ ddt_get_dedup_dspace(spa) + brt_get_dspace(spa);
+ if (spa->spa_nonallocating_dspace > 0) {
/*
- * We can't allocate from the removing device, so
- * subtract its size. This prevents the DMU/DSL from
- * filling up the (now smaller) pool while we are in the
- * middle of removing the device.
+ * Subtract the space provided by all non-allocating vdevs that
+ * contribute to dspace. If a file is overwritten, its old
+ * blocks are freed and new blocks are allocated. If there are
+ * no snapshots of the file, the available space should remain
+ * the same. The old blocks could be freed from the
+ * non-allocating vdev, but the new blocks must be allocated on
+ * other (allocating) vdevs. By reserving the entire size of
+ * the non-allocating vdevs (including allocated space), we
+ * ensure that there will be enough space on the allocating
+ * vdevs for this file overwrite to succeed.
*
* Note that the DMU/DSL doesn't actually know or care
* how much space is allocated (it does its own tracking
* of how much space has been logically used). So it
* doesn't matter that the data we are moving may be
- * allocated twice (on the old device and the new
- * device).
+ * allocated twice (on the old device and the new device).
*/
- spa_config_enter(spa, SCL_VDEV, FTAG, RW_READER);
- vdev_t *vd =
- vdev_lookup_top(spa, spa->spa_vdev_removal->svr_vdev_id);
- spa->spa_dspace -= spa_deflate(spa) ?
- vd->vdev_stat.vs_dspace : vd->vdev_stat.vs_space;
- spa_config_exit(spa, SCL_VDEV, FTAG);
+ ASSERT3U(spa->spa_dspace, >=, spa->spa_nonallocating_dspace);
+ spa->spa_dspace -= spa->spa_nonallocating_dspace;
}
}
return (spa->spa_log_class);
}
+metaslab_class_t *
+spa_embedded_log_class(spa_t *spa)
+{
+ return (spa->spa_embedded_log_class);
+}
+
+metaslab_class_t *
+spa_special_class(spa_t *spa)
+{
+ return (spa->spa_special_class);
+}
+
+metaslab_class_t *
+spa_dedup_class(spa_t *spa)
+{
+ return (spa->spa_dedup_class);
+}
+
+/*
+ * Locate an appropriate allocation class
+ */
+metaslab_class_t *
+spa_preferred_class(spa_t *spa, uint64_t size, dmu_object_type_t objtype,
+ uint_t level, uint_t special_smallblk)
+{
+ /*
+ * ZIL allocations determine their class in zio_alloc_zil().
+ */
+ ASSERT(objtype != DMU_OT_INTENT_LOG);
+
+ boolean_t has_special_class = spa->spa_special_class->mc_groups != 0;
+
+ if (DMU_OT_IS_DDT(objtype)) {
+ if (spa->spa_dedup_class->mc_groups != 0)
+ return (spa_dedup_class(spa));
+ else if (has_special_class && zfs_ddt_data_is_special)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ /* Indirect blocks for user data can land in special if allowed */
+ if (level > 0 && (DMU_OT_IS_FILE(objtype) || objtype == DMU_OT_ZVOL)) {
+ if (has_special_class && zfs_user_indirect_is_special)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ if (DMU_OT_IS_METADATA(objtype) || level > 0) {
+ if (has_special_class)
+ return (spa_special_class(spa));
+ else
+ return (spa_normal_class(spa));
+ }
+
+ /*
+ * Allow small file blocks in special class in some cases (like
+ * for the dRAID vdev feature). But always leave a reserve of
+ * zfs_special_class_metadata_reserve_pct exclusively for metadata.
+ */
+ if (DMU_OT_IS_FILE(objtype) &&
+ has_special_class && size <= special_smallblk) {
+ metaslab_class_t *special = spa_special_class(spa);
+ uint64_t alloc = metaslab_class_get_alloc(special);
+ uint64_t space = metaslab_class_get_space(special);
+ uint64_t limit =
+ (space * (100 - zfs_special_class_metadata_reserve_pct))
+ / 100;
+
+ if (alloc < limit)
+ return (special);
+ }
+
+ return (spa_normal_class(spa));
+}
+
void
spa_evicting_os_register(spa_t *spa, objset_t *os)
{
return (spa->spa_deadman_synctime);
}
+spa_autotrim_t
+spa_get_autotrim(spa_t *spa)
+{
+ return (spa->spa_autotrim);
+}
+
uint64_t
spa_deadman_ziotime(spa_t *spa)
{
spa->spa_deadman_failmode = ZIO_FAILURE_MODE_WAIT;
}
+void
+spa_set_deadman_ziotime(hrtime_t ns)
+{
+ spa_t *spa = NULL;
+
+ if (spa_mode_global != SPA_MODE_UNINIT) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa->spa_deadman_ziotime = ns;
+ mutex_exit(&spa_namespace_lock);
+ }
+}
+
+void
+spa_set_deadman_synctime(hrtime_t ns)
+{
+ spa_t *spa = NULL;
+
+ if (spa_mode_global != SPA_MODE_UNINIT) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa->spa_deadman_synctime = ns;
+ mutex_exit(&spa_namespace_lock);
+ }
+}
+
uint64_t
dva_get_dsize_sync(spa_t *spa, const dva_t *dva)
{
return (dsize);
}
+uint64_t
+spa_dirty_data(spa_t *spa)
+{
+ return (spa->spa_dsl_pool->dp_dirty_total);
+}
+
+/*
+ * ==========================================================================
+ * SPA Import Progress Routines
+ * ==========================================================================
+ */
+
+typedef struct spa_import_progress {
+ uint64_t pool_guid; /* unique id for updates */
+ char *pool_name;
+ spa_load_state_t spa_load_state;
+ char *spa_load_notes;
+ uint64_t mmp_sec_remaining; /* MMP activity check */
+ uint64_t spa_load_max_txg; /* rewind txg */
+ procfs_list_node_t smh_node;
+} spa_import_progress_t;
+
+spa_history_list_t *spa_import_progress_list = NULL;
+
+static int
+spa_import_progress_show_header(struct seq_file *f)
+{
+ seq_printf(f, "%-20s %-14s %-14s %-12s %-16s %s\n", "pool_guid",
+ "load_state", "multihost_secs", "max_txg",
+ "pool_name", "notes");
+ return (0);
+}
+
+static int
+spa_import_progress_show(struct seq_file *f, void *data)
+{
+ spa_import_progress_t *sip = (spa_import_progress_t *)data;
+
+ seq_printf(f, "%-20llu %-14llu %-14llu %-12llu %-16s %s\n",
+ (u_longlong_t)sip->pool_guid, (u_longlong_t)sip->spa_load_state,
+ (u_longlong_t)sip->mmp_sec_remaining,
+ (u_longlong_t)sip->spa_load_max_txg,
+ (sip->pool_name ? sip->pool_name : "-"),
+ (sip->spa_load_notes ? sip->spa_load_notes : "-"));
+
+ return (0);
+}
+
+/* Remove oldest elements from list until there are no more than 'size' left */
+static void
+spa_import_progress_truncate(spa_history_list_t *shl, unsigned int size)
+{
+ spa_import_progress_t *sip;
+ while (shl->size > size) {
+ sip = list_remove_head(&shl->procfs_list.pl_list);
+ if (sip->pool_name)
+ spa_strfree(sip->pool_name);
+ if (sip->spa_load_notes)
+ kmem_strfree(sip->spa_load_notes);
+ kmem_free(sip, sizeof (spa_import_progress_t));
+ shl->size--;
+ }
+
+ IMPLY(size == 0, list_is_empty(&shl->procfs_list.pl_list));
+}
+
+static void
+spa_import_progress_init(void)
+{
+ spa_import_progress_list = kmem_zalloc(sizeof (spa_history_list_t),
+ KM_SLEEP);
+
+ spa_import_progress_list->size = 0;
+
+ spa_import_progress_list->procfs_list.pl_private =
+ spa_import_progress_list;
+
+ procfs_list_install("zfs",
+ NULL,
+ "import_progress",
+ 0644,
+ &spa_import_progress_list->procfs_list,
+ spa_import_progress_show,
+ spa_import_progress_show_header,
+ NULL,
+ offsetof(spa_import_progress_t, smh_node));
+}
+
+static void
+spa_import_progress_destroy(void)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ procfs_list_uninstall(&shl->procfs_list);
+ spa_import_progress_truncate(shl, 0);
+ procfs_list_destroy(&shl->procfs_list);
+ kmem_free(shl, sizeof (spa_history_list_t));
+}
+
+int
+spa_import_progress_set_state(uint64_t pool_guid,
+ spa_load_state_t load_state)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+ int error = ENOENT;
+
+ if (shl->size == 0)
+ return (0);
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+ sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+ if (sip->pool_guid == pool_guid) {
+ sip->spa_load_state = load_state;
+ if (sip->spa_load_notes != NULL) {
+ kmem_strfree(sip->spa_load_notes);
+ sip->spa_load_notes = NULL;
+ }
+ error = 0;
+ break;
+ }
+ }
+ mutex_exit(&shl->procfs_list.pl_lock);
+
+ return (error);
+}
+
+static void
+spa_import_progress_set_notes_impl(spa_t *spa, boolean_t log_dbgmsg,
+ const char *fmt, va_list adx)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+ uint64_t pool_guid = spa_guid(spa);
+
+ if (shl->size == 0)
+ return;
+
+ char *notes = kmem_vasprintf(fmt, adx);
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+ sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+ if (sip->pool_guid == pool_guid) {
+ if (sip->spa_load_notes != NULL) {
+ kmem_strfree(sip->spa_load_notes);
+ sip->spa_load_notes = NULL;
+ }
+ sip->spa_load_notes = notes;
+ if (log_dbgmsg)
+ zfs_dbgmsg("'%s' %s", sip->pool_name, notes);
+ notes = NULL;
+ break;
+ }
+ }
+ mutex_exit(&shl->procfs_list.pl_lock);
+ if (notes != NULL)
+ kmem_strfree(notes);
+}
+
+void
+spa_import_progress_set_notes(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+
+ va_start(adx, fmt);
+ spa_import_progress_set_notes_impl(spa, B_TRUE, fmt, adx);
+ va_end(adx);
+}
+
+void
+spa_import_progress_set_notes_nolog(spa_t *spa, const char *fmt, ...)
+{
+ va_list adx;
+
+ va_start(adx, fmt);
+ spa_import_progress_set_notes_impl(spa, B_FALSE, fmt, adx);
+ va_end(adx);
+}
+
+int
+spa_import_progress_set_max_txg(uint64_t pool_guid, uint64_t load_max_txg)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+ int error = ENOENT;
+
+ if (shl->size == 0)
+ return (0);
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+ sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+ if (sip->pool_guid == pool_guid) {
+ sip->spa_load_max_txg = load_max_txg;
+ error = 0;
+ break;
+ }
+ }
+ mutex_exit(&shl->procfs_list.pl_lock);
+
+ return (error);
+}
+
+int
+spa_import_progress_set_mmp_check(uint64_t pool_guid,
+ uint64_t mmp_sec_remaining)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+ int error = ENOENT;
+
+ if (shl->size == 0)
+ return (0);
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+ sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+ if (sip->pool_guid == pool_guid) {
+ sip->mmp_sec_remaining = mmp_sec_remaining;
+ error = 0;
+ break;
+ }
+ }
+ mutex_exit(&shl->procfs_list.pl_lock);
+
+ return (error);
+}
+
+/*
+ * A new import is in progress, add an entry.
+ */
+void
+spa_import_progress_add(spa_t *spa)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+ const char *poolname = NULL;
+
+ sip = kmem_zalloc(sizeof (spa_import_progress_t), KM_SLEEP);
+ sip->pool_guid = spa_guid(spa);
+
+ (void) nvlist_lookup_string(spa->spa_config, ZPOOL_CONFIG_POOL_NAME,
+ &poolname);
+ if (poolname == NULL)
+ poolname = spa_name(spa);
+ sip->pool_name = spa_strdup(poolname);
+ sip->spa_load_state = spa_load_state(spa);
+ sip->spa_load_notes = NULL;
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ procfs_list_add(&shl->procfs_list, sip);
+ shl->size++;
+ mutex_exit(&shl->procfs_list.pl_lock);
+}
+
+void
+spa_import_progress_remove(uint64_t pool_guid)
+{
+ spa_history_list_t *shl = spa_import_progress_list;
+ spa_import_progress_t *sip;
+
+ mutex_enter(&shl->procfs_list.pl_lock);
+ for (sip = list_tail(&shl->procfs_list.pl_list); sip != NULL;
+ sip = list_prev(&shl->procfs_list.pl_list, sip)) {
+ if (sip->pool_guid == pool_guid) {
+ if (sip->pool_name)
+ spa_strfree(sip->pool_name);
+ if (sip->spa_load_notes)
+ spa_strfree(sip->spa_load_notes);
+ list_remove(&shl->procfs_list.pl_list, sip);
+ shl->size--;
+ kmem_free(sip, sizeof (spa_import_progress_t));
+ break;
+ }
+ }
+ mutex_exit(&shl->procfs_list.pl_lock);
+}
+
/*
* ==========================================================================
* Initialization and Termination
s = strcmp(s1->spa_name, s2->spa_name);
- return (AVL_ISIGN(s));
+ return (TREE_ISIGN(s));
}
void
}
void
-spa_init(int mode)
+spa_init(spa_mode_t mode)
{
mutex_init(&spa_namespace_lock, NULL, MUTEX_DEFAULT, NULL);
mutex_init(&spa_spare_lock, NULL, MUTEX_DEFAULT, NULL);
spa_mode_global = mode;
#ifndef _KERNEL
- if (spa_mode_global != FREAD && dprintf_find_string("watch")) {
+ if (spa_mode_global != SPA_MODE_READ && dprintf_find_string("watch")) {
struct sigaction sa;
sa.sa_flags = SA_SIGINFO;
#endif
fm_init();
- refcount_init();
+ zfs_refcount_init();
unique_init();
- range_tree_init();
- metaslab_alloc_trace_init();
+ zfs_btree_init();
+ metaslab_stat_init();
+ brt_init();
ddt_init();
zio_init();
dmu_init();
zil_init();
- vdev_cache_stat_init();
vdev_mirror_stat_init();
vdev_raidz_math_init();
vdev_file_init();
zfs_prop_init();
+ chksum_init();
zpool_prop_init();
zpool_feature_init();
spa_config_load();
+ vdev_prop_init();
l2arc_start();
scan_init();
qat_init();
+ spa_import_progress_init();
}
void
spa_evict_all();
vdev_file_fini();
- vdev_cache_stat_fini();
vdev_mirror_stat_fini();
vdev_raidz_math_fini();
+ chksum_fini();
zil_fini();
dmu_fini();
zio_fini();
ddt_fini();
- metaslab_alloc_trace_fini();
- range_tree_fini();
+ brt_fini();
+ metaslab_stat_fini();
+ zfs_btree_fini();
unique_fini();
- refcount_fini();
+ zfs_refcount_fini();
fm_fini();
scan_fini();
qat_fini();
+ spa_import_progress_destroy();
avl_destroy(&spa_namespace_avl);
avl_destroy(&spa_spare_avl);
}
/*
- * Return whether this pool has slogs. No locking needed.
+ * Return whether this pool has a dedicated slog device. No locking needed.
* It's not a problem if the wrong answer is returned as it's only for
- * performance and not correctness
+ * performance and not correctness.
*/
boolean_t
spa_has_slogs(spa_t *spa)
{
- return (spa->spa_log_class->mc_rotor != NULL);
+ return (spa->spa_log_class->mc_groups != 0);
}
spa_log_state_t
boolean_t
spa_writeable(spa_t *spa)
{
- return (!!(spa->spa_mode & FWRITE));
+ return (!!(spa->spa_mode & SPA_MODE_WRITE) && spa->spa_trust_config);
}
/*
boolean_t
spa_has_pending_synctask(spa_t *spa)
{
- return (!txg_all_lists_empty(&spa->spa_dsl_pool->dp_sync_tasks));
+ return (!txg_all_lists_empty(&spa->spa_dsl_pool->dp_sync_tasks) ||
+ !txg_all_lists_empty(&spa->spa_dsl_pool->dp_early_sync_tasks));
}
-int
+spa_mode_t
spa_mode(spa_t *spa)
{
return (spa->spa_mode);
spa->spa_scan_pass_scrub_pause = spa->spa_scan_pass_start;
else
spa->spa_scan_pass_scrub_pause = 0;
+
+ if (dsl_errorscrub_is_paused(spa->spa_dsl_pool->dp_scan))
+ spa->spa_scan_pass_errorscrub_pause = spa->spa_scan_pass_start;
+ else
+ spa->spa_scan_pass_errorscrub_pause = 0;
+
spa->spa_scan_pass_scrub_spent_paused = 0;
spa->spa_scan_pass_exam = 0;
spa->spa_scan_pass_issued = 0;
- vdev_scan_stat_init(spa->spa_root_vdev);
+
+ // error scrub stats
+ spa->spa_scan_pass_errorscrub_spent_paused = 0;
}
/*
{
dsl_scan_t *scn = spa->spa_dsl_pool ? spa->spa_dsl_pool->dp_scan : NULL;
- if (scn == NULL || scn->scn_phys.scn_func == POOL_SCAN_NONE)
+ if (scn == NULL || (scn->scn_phys.scn_func == POOL_SCAN_NONE &&
+ scn->errorscrub_phys.dep_func == POOL_SCAN_NONE))
return (SET_ERROR(ENOENT));
- bzero(ps, sizeof (pool_scan_stat_t));
+
+ memset(ps, 0, sizeof (pool_scan_stat_t));
/* data stored on disk */
ps->pss_func = scn->scn_phys.scn_func;
ps->pss_end_time = scn->scn_phys.scn_end_time;
ps->pss_to_examine = scn->scn_phys.scn_to_examine;
ps->pss_examined = scn->scn_phys.scn_examined;
- ps->pss_to_process = scn->scn_phys.scn_to_process;
+ ps->pss_skipped = scn->scn_phys.scn_skipped;
ps->pss_processed = scn->scn_phys.scn_processed;
ps->pss_errors = scn->scn_phys.scn_errors;
ps->pss_issued =
scn->scn_issued_before_pass + spa->spa_scan_pass_issued;
+ /* error scrub data stored on disk */
+ ps->pss_error_scrub_func = scn->errorscrub_phys.dep_func;
+ ps->pss_error_scrub_state = scn->errorscrub_phys.dep_state;
+ ps->pss_error_scrub_start = scn->errorscrub_phys.dep_start_time;
+ ps->pss_error_scrub_end = scn->errorscrub_phys.dep_end_time;
+ ps->pss_error_scrub_examined = scn->errorscrub_phys.dep_examined;
+ ps->pss_error_scrub_to_be_examined =
+ scn->errorscrub_phys.dep_to_examine;
+
+ /* error scrub data not stored on disk */
+ ps->pss_pass_error_scrub_pause = spa->spa_scan_pass_errorscrub_pause;
+
return (0);
}
return (spa->spa_multihost ? B_TRUE : B_FALSE);
}
-unsigned long
-spa_get_hostid(void)
+uint32_t
+spa_get_hostid(spa_t *spa)
+{
+ return (spa->spa_hostid);
+}
+
+boolean_t
+spa_trust_config(spa_t *spa)
+{
+ return (spa->spa_trust_config);
+}
+
+uint64_t
+spa_missing_tvds_allowed(spa_t *spa)
+{
+ return (spa->spa_missing_tvds_allowed);
+}
+
+space_map_t *
+spa_syncing_log_sm(spa_t *spa)
+{
+ return (spa->spa_syncing_log_sm);
+}
+
+void
+spa_set_missing_tvds(spa_t *spa, uint64_t missing)
+{
+ spa->spa_missing_tvds = missing;
+}
+
+/*
+ * Return the pool state string ("ONLINE", "DEGRADED", "SUSPENDED", etc).
+ */
+const char *
+spa_state_to_name(spa_t *spa)
{
- unsigned long myhostid;
+ ASSERT3P(spa, !=, NULL);
-#ifdef _KERNEL
- myhostid = zone_get_hostid(NULL);
-#else /* _KERNEL */
/*
- * We're emulating the system's hostid in userland, so
- * we can't use zone_get_hostid().
+ * it is possible for the spa to exist, without root vdev
+ * as the spa transitions during import/export
*/
- (void) ddi_strtoul(hw_serial, NULL, 10, &myhostid);
-#endif /* _KERNEL */
+ vdev_t *rvd = spa->spa_root_vdev;
+ if (rvd == NULL) {
+ return ("TRANSITIONING");
+ }
+ vdev_state_t state = rvd->vdev_state;
+ vdev_aux_t aux = rvd->vdev_stat.vs_aux;
- return (myhostid);
+ if (spa_suspended(spa))
+ return ("SUSPENDED");
+
+ switch (state) {
+ case VDEV_STATE_CLOSED:
+ case VDEV_STATE_OFFLINE:
+ return ("OFFLINE");
+ case VDEV_STATE_REMOVED:
+ return ("REMOVED");
+ case VDEV_STATE_CANT_OPEN:
+ if (aux == VDEV_AUX_CORRUPT_DATA || aux == VDEV_AUX_BAD_LOG)
+ return ("FAULTED");
+ else if (aux == VDEV_AUX_SPLIT_POOL)
+ return ("SPLIT");
+ else
+ return ("UNAVAIL");
+ case VDEV_STATE_FAULTED:
+ return ("FAULTED");
+ case VDEV_STATE_DEGRADED:
+ return ("DEGRADED");
+ case VDEV_STATE_HEALTHY:
+ return ("ONLINE");
+ default:
+ break;
+ }
+
+ return ("UNKNOWN");
}
-#if defined(_KERNEL) && defined(HAVE_SPL)
+boolean_t
+spa_top_vdevs_spacemap_addressable(spa_t *spa)
+{
+ vdev_t *rvd = spa->spa_root_vdev;
+ for (uint64_t c = 0; c < rvd->vdev_children; c++) {
+ if (!vdev_is_spacemap_addressable(rvd->vdev_child[c]))
+ return (B_FALSE);
+ }
+ return (B_TRUE);
+}
-#include <linux/mod_compat.h>
+boolean_t
+spa_has_checkpoint(spa_t *spa)
+{
+ return (spa->spa_checkpoint_txg != 0);
+}
-static int
-param_set_deadman_failmode(const char *val, zfs_kernel_param_t *kp)
+boolean_t
+spa_importing_readonly_checkpoint(spa_t *spa)
+{
+ return ((spa->spa_import_flags & ZFS_IMPORT_CHECKPOINT) &&
+ spa->spa_mode == SPA_MODE_READ);
+}
+
+uint64_t
+spa_min_claim_txg(spa_t *spa)
+{
+ uint64_t checkpoint_txg = spa->spa_uberblock.ub_checkpoint_txg;
+
+ if (checkpoint_txg != 0)
+ return (checkpoint_txg + 1);
+
+ return (spa->spa_first_txg);
+}
+
+/*
+ * If there is a checkpoint, async destroys may consume more space from
+ * the pool instead of freeing it. In an attempt to save the pool from
+ * getting suspended when it is about to run out of space, we stop
+ * processing async destroys.
+ */
+boolean_t
+spa_suspend_async_destroy(spa_t *spa)
+{
+ dsl_pool_t *dp = spa_get_dsl(spa);
+
+ uint64_t unreserved = dsl_pool_unreserved_space(dp,
+ ZFS_SPACE_CHECK_EXTRA_RESERVED);
+ uint64_t used = dsl_dir_phys(dp->dp_root_dir)->dd_used_bytes;
+ uint64_t avail = (unreserved > used) ? (unreserved - used) : 0;
+
+ if (spa_has_checkpoint(spa) && avail == 0)
+ return (B_TRUE);
+
+ return (B_FALSE);
+}
+
+#if defined(_KERNEL)
+
+int
+param_set_deadman_failmode_common(const char *val)
{
spa_t *spa = NULL;
char *p;
if (val == NULL)
- return (SET_ERROR(-EINVAL));
+ return (SET_ERROR(EINVAL));
if ((p = strchr(val, '\n')) != NULL)
*p = '\0';
if (strcmp(val, "wait") != 0 && strcmp(val, "continue") != 0 &&
strcmp(val, "panic"))
- return (SET_ERROR(-EINVAL));
+ return (SET_ERROR(EINVAL));
- mutex_enter(&spa_namespace_lock);
- while ((spa = spa_next(spa)) != NULL)
- spa_set_deadman_failmode(spa, val);
- mutex_exit(&spa_namespace_lock);
+ if (spa_mode_global != SPA_MODE_UNINIT) {
+ mutex_enter(&spa_namespace_lock);
+ while ((spa = spa_next(spa)) != NULL)
+ spa_set_deadman_failmode(spa, val);
+ mutex_exit(&spa_namespace_lock);
+ }
- return (param_set_charp(val, kp));
+ return (0);
}
+#endif
/* Namespace manipulation */
EXPORT_SYMBOL(spa_lookup);
EXPORT_SYMBOL(spa_deflate);
EXPORT_SYMBOL(spa_normal_class);
EXPORT_SYMBOL(spa_log_class);
+EXPORT_SYMBOL(spa_special_class);
+EXPORT_SYMBOL(spa_preferred_class);
EXPORT_SYMBOL(spa_max_replication);
EXPORT_SYMBOL(spa_prev_software_version);
EXPORT_SYMBOL(spa_get_failmode);
EXPORT_SYMBOL(spa_maxdnodesize);
/* Miscellaneous support routines */
-EXPORT_SYMBOL(spa_rename);
EXPORT_SYMBOL(spa_guid_exists);
EXPORT_SYMBOL(spa_strdup);
EXPORT_SYMBOL(spa_strfree);
-EXPORT_SYMBOL(spa_get_random);
EXPORT_SYMBOL(spa_generate_guid);
EXPORT_SYMBOL(snprintf_blkptr);
EXPORT_SYMBOL(spa_freeze);
EXPORT_SYMBOL(spa_writeable);
EXPORT_SYMBOL(spa_mode);
EXPORT_SYMBOL(spa_namespace_lock);
+EXPORT_SYMBOL(spa_trust_config);
+EXPORT_SYMBOL(spa_missing_tvds_allowed);
+EXPORT_SYMBOL(spa_set_missing_tvds);
+EXPORT_SYMBOL(spa_state_to_name);
+EXPORT_SYMBOL(spa_importing_readonly_checkpoint);
+EXPORT_SYMBOL(spa_min_claim_txg);
+EXPORT_SYMBOL(spa_suspend_async_destroy);
+EXPORT_SYMBOL(spa_has_checkpoint);
+EXPORT_SYMBOL(spa_top_vdevs_spacemap_addressable);
+
+ZFS_MODULE_PARAM(zfs, zfs_, flags, UINT, ZMOD_RW,
+ "Set additional debugging flags");
+
+ZFS_MODULE_PARAM(zfs, zfs_, recover, INT, ZMOD_RW,
+ "Set to attempt to recover from fatal errors");
+
+ZFS_MODULE_PARAM(zfs, zfs_, free_leak_on_eio, INT, ZMOD_RW,
+ "Set to ignore IO errors during free and permanently leak the space");
-/* BEGIN CSTYLED */
-module_param(zfs_flags, uint, 0644);
-MODULE_PARM_DESC(zfs_flags, "Set additional debugging flags");
+ZFS_MODULE_PARAM(zfs_deadman, zfs_deadman_, checktime_ms, U64, ZMOD_RW,
+ "Dead I/O check interval in milliseconds");
-module_param(zfs_recover, int, 0644);
-MODULE_PARM_DESC(zfs_recover, "Set to attempt to recover from fatal errors");
+ZFS_MODULE_PARAM(zfs_deadman, zfs_deadman_, enabled, INT, ZMOD_RW,
+ "Enable deadman timer");
-module_param(zfs_free_leak_on_eio, int, 0644);
-MODULE_PARM_DESC(zfs_free_leak_on_eio,
- "Set to ignore IO errors during free and permanently leak the space");
-
-module_param(zfs_deadman_synctime_ms, ulong, 0644);
-MODULE_PARM_DESC(zfs_deadman_synctime_ms,
- "Pool sync expiration time in milliseconds");
+ZFS_MODULE_PARAM(zfs_spa, spa_, asize_inflation, UINT, ZMOD_RW,
+ "SPA size estimate multiplication factor");
-module_param(zfs_deadman_ziotime_ms, ulong, 0644);
-MODULE_PARM_DESC(zfs_deadman_ziotime_ms,
- "IO expiration time in milliseconds");
+ZFS_MODULE_PARAM(zfs, zfs_, ddt_data_is_special, INT, ZMOD_RW,
+ "Place DDT data into the special class");
-module_param(zfs_deadman_checktime_ms, ulong, 0644);
-MODULE_PARM_DESC(zfs_deadman_checktime_ms,
- "Dead I/O check interval in milliseconds");
+ZFS_MODULE_PARAM(zfs, zfs_, user_indirect_is_special, INT, ZMOD_RW,
+ "Place user data indirect blocks into the special class");
-module_param(zfs_deadman_enabled, int, 0644);
-MODULE_PARM_DESC(zfs_deadman_enabled, "Enable deadman timer");
+/* BEGIN CSTYLED */
+ZFS_MODULE_PARAM_CALL(zfs_deadman, zfs_deadman_, failmode,
+ param_set_deadman_failmode, param_get_charp, ZMOD_RW,
+ "Failmode for deadman timer");
-module_param_call(zfs_deadman_failmode, param_set_deadman_failmode,
- param_get_charp, &zfs_deadman_failmode, 0644);
-MODULE_PARM_DESC(zfs_deadman_failmode, "Failmode for deadman timer");
+ZFS_MODULE_PARAM_CALL(zfs_deadman, zfs_deadman_, synctime_ms,
+ param_set_deadman_synctime, spl_param_get_u64, ZMOD_RW,
+ "Pool sync expiration time in milliseconds");
-module_param(spa_asize_inflation, int, 0644);
-MODULE_PARM_DESC(spa_asize_inflation,
- "SPA size estimate multiplication factor");
+ZFS_MODULE_PARAM_CALL(zfs_deadman, zfs_deadman_, ziotime_ms,
+ param_set_deadman_ziotime, spl_param_get_u64, ZMOD_RW,
+ "IO expiration time in milliseconds");
-module_param(spa_slop_shift, int, 0644);
-MODULE_PARM_DESC(spa_slop_shift, "Reserved free space in pool");
+ZFS_MODULE_PARAM(zfs, zfs_, special_class_metadata_reserve_pct, UINT, ZMOD_RW,
+ "Small file blocks in special vdevs depends on this much "
+ "free space available");
/* END CSTYLED */
-#endif
+
+ZFS_MODULE_PARAM_CALL(zfs_spa, spa_, slop_shift, param_set_slop_shift,
+ param_get_uint, ZMOD_RW, "Reserved free space in pool");
+
+ZFS_MODULE_PARAM(zfs, spa_, num_allocators, INT, ZMOD_RW,
+ "Number of allocators per spa, capped by ncpus");
projects / mirror_zfs.git / blobdiff